Unit testing and results.
\r\n\t[2] J. V. Moloney, A. C. Newell. Nonlinear Optics. Westview Press, Oxford, 2004.
\r\n\t[3] M. Kauranen, A. V. Zayats. Nonlinear Plasmonics. Nature Photonics, vol. 6, 2012, pp. 737-748.
\r\n\t[4] P. Dombi, Z. Pápa, J. Vogelsang et al. Strong-field nano-optics. Reviews of Modern Physics, vol. 92, 2020, pp. 025003-1 – 025003-66.
\r\n\t[5] N. C. Panoiu, W. E. I. Sha, D.Y. Lei, G.-C. Li. Nonlinear optics in plasmonic nanostructures. Journal of Optics, 20, 2018, pp. 1-36.
\r\n\t[6] A. Krasnok, A. Alu. Active nanophotonics. Proceedings of IEEE, vol. 108, 2020, pp. 628-654.
\r\n\t[7] M. Lapine, I.V. Shadrivov, Yu. S. Kivshar. Colloquium: Nonlinear metamaterials. Reviews of Modern Physics, vol. 86, 2014, pp. 1093-1123.
\r\n\t[8] Iam Choon Khoo. Nonlinear optics, active plasmonics and metamaterials with liquid crystals. Progress in Quantum Electronics, vol. 38, 2014, pp. 77- 117.
\r\n\t
Given the recent development of self-driving cars by companies such as Tesla, Google and others, it was of interest to attempt to replicate this on a smaller scale, by implementing a similar method on a small electronic toy car. An issue many developers in this industry are having is the issue of leaving the device connected to a wide area network (WAN) all the time, leaving the vehicles vulnerable to not only hacking but also vulnerable to being unable to make decisions in out-of-reach places such as the countryside where a WAN may not be available or only available intermittently. The decision was made to attempt the replication on a small scale, using a closed network with the computations occurring within the vehicle, as opposed to externally. The study was viewed as a proof of concept to test the possibility and feasibility, which could help lead research on full-scale self-driving cars and potentially also enhance the toy industry.
\nThis study mainly focuses on a proof-of-concept implementation of artificial neural networks (ANNs) to classify road sign images in a real-time scenario integrated with relevant image processing techniques. The study includes how the processed data outputted by ANN models is translated into defined movements of the car and whether it is suitably efficient to follow a track.
\nNeural networks are often used for image processing. Once the network is trained and the weighting values/structure is stored, all that would be required on future runs of the program would be to load these stored values/designs for the trained network for it to have the ability to run correctly. This means that once the network is trained, real-time image classification and thus prediction of the movement become very efficient. This is a beneficial method for a project of this sort, as the car is driving in real time and thus computations must be made in real time.
\nThe overall objective was to allow the vehicle to drive autonomously around an unknown track with little to no error, utilising collision avoidance.
\nThis project is a proof-of-concept study to demonstrate how existing ANN state-of-the-art knowledge and related theory can be used for developing an autonomous toy vehicle and letting it to operate without the need to use external computations. It has been adopted as a research problem, which means it has resulted from a lack of current evidence into the subject matter, and thus this project is an attempt at proving that such a concept is not only theoretically feasible but actually possible.
\nThe system is comprised of three subsystems: an input unit (sensors, camera), the processing unit (Raspberry Pi) and an output unit (L293D motor controller connected to Raspberry Pi).
\nThe input required two front-placed ultrasonic sensors both at a 15° left and right angle from the vehicle’s direct line of sight. This is mainly used to ensure no objects are within a certain distance from the front of the vehicle (this prevents collisions) and a Pi Camera which is used to stream video data. This data is used in the processing subsystem by the neural network to calculate the direction and recognise the track and stop signs. Both peripherals are constantly sending data to the Raspberry Pi.
\nHC-SR04 sensors, raspiCam and L293D chip were the best hardware options of obvious choice—because they are all the most commonly used [1, 2] supported and documented hardware in the Raspberry Pi.
\nThe processing unit handles multiple tasks such as dealing with input data, scaling down and applying necessary imaging filters to the data received from the camera, calculating distances based on data received from the ultrasonic sensors to be used for object detection, controlling the motors via L293D chip, utilising a neural network to process the data from the camera to recognise the track ahead and further recognise on-track stop signs and assigning a corresponding movement instruction based on this data.
\nThe output unit consists mainly of the hardware which is wired to the Pi such as the motor controller and the motors themselves, both of which are controlled by the Pi.
\nThis report follows a structure where I outline the research into my theory, the design process of the vehicle itself including the neural network, implementation and finally testing processes involved in proving this as a concept.
\nA variety of libraries/application programming interfaces (APIs) were required to implement the hardware in C++:
\nWiringPi: “WiringPi is a PIN based GPIO access library written in C for the BCM2835 used in the Raspberry Pi. It is released under the GNU LGPLv3 licence and is usable from C, C++ and RTB (BASIC) as well as many other languages with suitable wrappers” [3]. WiringPi allows the user to apply and change power levels to the peripheral devices which are installed [4]. This results in a lot smoother code interface which avoids system calls to use the hardware, in particular, the use of the “softPwm” function which allows easy and convenient power on/off capabilities which will be necessary for sending “pulses” of power to the ultrasonic sensors.
\nlibv4l (Video 4Linux): “libv4l is a collection of libraries which adds a thin abstraction layer on top of video 4linux2 devices. The purpose of this (thin) layer is to make it easy for application writers to support a wide variety of devices without having to write separate code for different devices in the same class.” [5]. The libv4l library will allow the Pi Camera to be recognised as an external camera through the Pi, which allows extra functionalities on image processing and avoids the need of a system call through the C++ code to use it.
\nPIGPIO: “pigpio is a library for the Raspberry which allows control of the General-Purpose Input Outputs (GPIO). pigpio works on all versions of the Pi.” [3].
\nThese three libraries would allow me to use the camera through the Pi, control the motors’ directions and send the relevant pulses to the ultrasonic sensors to calculate a distance regarding object detection.
\nThe image stream from the camera is a 60 FPS video stream in 1920 × 1080 resolution. This obviously is too big to be fed into any kind of machine learning algorithm and would require huge amounts of processing, which, given the relatively low computational power of a Raspberry Pi, would not be efficient enough to give the car the ability to work in real time.
\nTo combat this, a variety of image processing techniques can be applied. For example, the image would need to be scaled down to 10x10 which still is of high enough resolution to recognise lines but is more computable.
\nAn interesting article regarding image processing by Rosebrock showed a very useful image processing process which would be very beneficial for my type of project called canny edge processing:
“Step 1: Smooth the image using a Gaussian filter to remove high frequency noise.
Step 2: Compute the gradient intensity representations of the image.
Step 3: Apply non-maximum suppression to remove “false” responses to edge detection.
Step 4: Apply thresholding using a lower and upper boundary on the gradient values.
Step 5: Track edges using hysteresis by suppressing weak edges that are not connected to strong edges” [6].
The following results are presented in Figure 1.
\nAn overview of canny edge detections [6].
It appeared to work quite well, with adaptable options regarding the strength of the effect. It was decided an automatic level should be applied for ease of use. It is clear that this is easily adaptable for the issue of recognising two lines either side of the vehicle and would (assuming a plain background) solve the problem very efficiently.
\nThis reduction in noise on the image would also help with real-time processing and stop the issue of anomalous results which would cause the vehicle to potentially go off-track.
\nThis is a generalised diagram of how these types of devices usually run.
\nMachine learning algorithms are often used in self-driving cars due to their advanced capabilities to be adapted for use in image processing. The most popular form of machine learning algorithm is known to be artificial neural networks, which are very good, in that a NN can be trained methodically for nearly every given circumstance imaginable. It can be highly adaptable in terms of size/computing power required and can be designed in any given way relevant to the user’s needs. To do this, calculation and specification of the number of nodes in each layer need to accurately produce the required outputs (Figure 2).
\nAutonomous car system overview.
In a NN, the connections between each node have a “weighting” value which is applied to the data which passed through it; these values are determined through training via the use of “training data” and then stored in a final version which is called the “model”. The model can then be used with unseen data in real time to produce an accurate output; this is called “testing” via the use of “test data”. Adapting these values to be correct for all input circumstances is known as the aforementioned “training”; this can be done through a variety of different methods, one of which is backpropagation. When training is complete, the weighting values can be stored, and thus further usage of the NN from then on will only require loading these stored values to make it run correctly (provided no changes have been made to the design of the NN) [7]. This means that once the network is trained, prediction of the movement becomes very fast. This is beneficial especially for real-time computation projects, as computation is done at a very efficient rate.
\nThe middle (hidden) layers of the neural network are used to recognise patterns, such as in this case, the edges of the track, which are conceived from the input data. The output layer interprets these patterns to generate a probability for each output being true. These probabilities are then interpreted to determine whether to turn left/right or stay straight and go forwards or backwards.
\nBy installing a Raspberry Pi, camera and ultrasonic sensors, the aim was to give the Raspberry Pi capabilities of driving the car through a written piece of software which is be run using C/C++. The intention was to create, within this, a form of artificial intelligence called a neural network. The neural network acts as the “brain” of the device and after extensive training can be used for image processing/classification of real-time camera data in order to aid the computation of real-time decisions on which movement instruction the car should follow during the movement step. This allows the device to drive autonomously and thus be adaptable to different situations. It does this by recognising two white lines either side of the vehicle, known as the “track” which the car should stay between.
\nConsidered to be the first “self-driving remote-controlled (RC) car” design was done in 2015 by “Team Pegasus”, a team of graduates from the Gothenburg University. They used Arduino and Raspberry Pi to build a robot car, integrated with a remote-controlled software application running on an Android device [8]. Team Pegasus is the first creator of an Android-powered RC car using similar computation methods; however, they used an external server which was connected to the mobile device to perform the computing process.
\nThe only other similar project found was done by Zheng Wang using Python and utilising a NN to process the images. Again, this used an external server connected to the Pi network to do the computing. This was a very small-scale device but worked very well. Wang also utilised OpenCV—an open source computer vision library which has a large variety of functionalities. Wang’s device was able to follow lines, recognise objects and stop signs [9]. The only real weakness of this was its inability to do on-board computation.
\nThese projects both used very large-scale NN to do the computation efficiently; thus, both were required to use an external server to do the computation. This was a problem as the device can only be used indoors with a suitable connection to the server. Despite the large-scale network, it could only be implemented on a small-scale track to ensure there was always an adequate connection to the server.
\nMachine learning is one of the main forms of artificial intelligence; it is an area concerned with how machines can learn to recognise patterns in data and thus enable them to predict future outcomes based on previous patterns. It is a branch of artificial intelligence which often interlaces with a wide variety of mathematic functions and pattern recognition techniques [10]. Some methods of machine learning include decision trees, K-nearest neighbours (KNN) and the most famous ANNs.
\nAn artificial neural network is a system that is designed to replicate the connections from the synapses within the human brain and their associated learning processes. The human brain consists of many neurons (cells) which all can process information independently. Within these cells are three main parts, the cell body, which contains the nucleus, the “dendrites” which receive information and a long axon connected to other cell’s dendrites for outputting information. Information passed between neurons in the brain through the dendrites is in a form similar to that of an electrical signal. When the signal level is of a required value (which will be set within the individual nucleus), the neuron will activate, and information will be sent along its axon to other neurons [11]. This can be applied to a piece of written software to replicate this process for any modelling and problem-solving purposes.
\nAnother similarity that can be achieved through an ANN is processing information via interconnected nodes using simple signals, each link between nodes has its own numerical “weight” when coded, and this is the primary means of learning, which is achieved by altering these “weight values” towards an optimum value to gain a connection with a high success rate.
\nANNs are code-based representation of a biological neural network; they are incredibly adaptable and have a variety of different structures/training techniques which can be used to adapt the network based on the most efficient design to solve the problem in hand. NN applications are mainly used for data mining purposes; however, they are also adaptable for use for many other computational problems. One example of this is using a particular model of NN, renown as multilayer perceptron (MLP), for image recognition to note and recognise the difference between things such as handwriting styles, animal types, facial recognition and many others.
\nThere are two types of learning strategies available to the training of neural networks:
Supervised learning: within this the concept of a “teacher” is present, and its role is to compare the network output with the correct output and make “adjustments” if necessary. One of the most well-known examples is “backpropagation” algorithm, which is a gradient-based approach minimising the error level between the output and the desired results [11]. This is highly effective when your training data is of a high quality and well labelled. However, it runs risks in terms of performance should you have any anomalies within your training set that you are unaware of.
Unsupervised learning: within this there is no concept of a “teacher”, and thus the network learns by examining the input data over multiple iterations until any inherent properties are discovered [12]. This is much more effective over a longer period of time and can be very efficient when done correctly.
The learning process of ANNs is also known as the process of “training”, where a set of test values or a “training set” is passed through the ANN and its output values are compared to those which are expected and then the values are altered accordingly for the next iterative trial. To compare this to the human NN, the ANN’s nodes are trained to fire in response to a particular input of bits/pattern. Each input will have its own value or according weight, and this will be calculated by multiplying the value by its assigned weight. If the sum of all these inputs equals a greater value than the activation threshold, the neuron will activate; this is the same as in ANN’s. Once these values are accurate for many cases, should the same pattern of input be placed into the ANN, its associated output will be given. This is a typical process of machine learning. If in non-training mode, the ANN will process the bits as normal and usually and if training was sufficient, the NN should still produce the correct output in the end.
\nFor this project, supervised learning was used as we had an abundance of very high-level training data to work with, all of which was already labelled.
\nMultilayer perceptrons (also known as backpropagation neural network) are a type of neural network. As seen in Figure 3, they consist of a feedforward network structure including one or more hidden layers and a non-linear activation function (e.g. sigmoid) and utilise a supervised learning approach to training using a method called “backpropagation”. MLPs are the most commonly used form of ANNs since they have a very flexible form—meaning they are adaptable to many different circumstances and problems [13].
\nBackpropagation neural network with one hidden layer [14].
The feedforward structure was the first released structure for a neural networks and is also the simplest form. It originates with an X amount of input nodes, in which each receives one value. The number of input nodes is always equal to the size of one individual element in the data set. For example, when using an MLP for image processing, if the image is 20 × 20 pixels, there would need to be 400 input neurons to account for each pixel. This helps to determine the size of the network, and because of this all data being fed into the network must be of the same size.
\nAs these values go through the network in the same method as in a NN, an input pattern from the data set is passed through the input layer, and each value proceeds to propagate through the layers of the network with the weights being applied to the value until the output values are produced. Typically, the output values are a set of probabilities for each output option to be true.
\nWhen this process is occurring during the iterations through the training set, the set of output values is compared to the expected output set, and a set of error values is calculated for how much of an error each node contributes to the overall error. This error calculation occurs across all layers in the network due to the simple fact that inevitably all layers and their respective nodes contribute a small amount to the overall error. To combat this the error calculation occurs through each layer, and each input value to determine the amount connection has contributed to the overall error. This is then used in the backpropagation function to alter the weights accordingly.
\nTraining the model is the most crucial part of the process. Firstly, the weighting values are all initialized with random numbers between −1 and +1. Then the training set or “training data” is imported.
\nNext begins the recursive process which, each time, presents one piece of training data to the network, which propagates through the network, and an output is produced. This output is then compared to the labelled output of the training data. Following this comparison, the training algorithm propagates backwards through the network, known as “backpropagation”, and alters the weighting values accordingly. This is repeated a finite amount of times specified by the person running the training model, until it is completed and the values are stable.
\nBackpropagation algorithm is a supervised learning technique which is applied to train neural networks. It works by propagating the error backwards through the network and internally altering the weight values between each node to try to improve the quality of output by minimising the error in the next runs. This is done in the “training” phase where the network is shown a “training set” which consists of a series of data and the correct output per data item is attached. This is then fed through the network, and backpropagation alters the weights to make it work for all data types and their corresponding outputs.
\nBackpropagation works by receiving the error value for each node, as calculated in the feedforward propagation, and utilises these error values while propagating through the network to adjust the node weightings positively or negatively in accordance with the error values per node.
\nThis is explained in more detail [11] with “Once the error signal for each node has been determined, the errors are then used by the nodes to update the values for each connection weight until the network converges to a state that allows all the training patterns to be encoded. The Backpropagation algorithm looks for the minimum value of the error function in weight space using a technique called the delta rule or gradient descent. The weights that minimise the error function are then considered to be a solution to the learning problem” [11].
\nThe standard pseudocode for training a neural network using backpropagation method which can be adapted to any language is as follows (Figure 4):
\nTraining a neural network using a backpropagation algorithm [15].
While training the network to understand data, it is very important not to over-train or under-train the network, as both have problems associated.
\nUnder-training can occur when the network does not have enough hidden layers/nodes within these layers to accurately represent the complexities of the problem accurately. The result of this is that the network is not of a sufficient size to recognise patterns effectively and will consequently under-fit the data pattern.
\nOver-training can be caused by a network that is overly complex—meaning that it follows the major pattern exactly and when confronted with other data, may not produce results that are within the average range of the training data. Networks with too many hidden nodes will tend to over-fit the data pattern [16].
\nThis can be combatted by designing an adequate network structure prior to training and ensuring the rate/iterations of backpropagation are not too low or too high, thus creating a network that creates good solutions to new data problems.
\nMachine learning is a vast field of artificial intelligence, which includes many learning and modelling approaches. Another algorithm which could be an alternative solution to this problem is to implement the K-nearest-neighbour search algorithm, which is one of the most known unsupervised learning algorithms used for data clustering and classification. This is explained briefly in [17] as “Nearest neighbour search is an optimization technique for finding closest points in metric spaces. Specifically, given a set of n reference points R and query point q, both in the same metric space V” [17].
\nThis would allow a training set similar to that of a neural network; however, here, they are all stored alongside their relevant move instruction. In larger data sets, this could be very beneficial, as there would be a large training set to compare to; however, with such a simple task as this, autonomous car application, it could be considered “overkill” as the potential for undertraining is too high. Furthermore, in safety-critical situations such as a car driving, a “best guess” kind of algorithm may not return the best results; should an anomaly arise, it could have serious repercussions.
\nThere are two commonly used C/C++ libraries which support machine learning, FANN and OpenCV. The decision was made to use OpenCV due to the fact that it is much more well-documented and has a tutorial part of their documentation which is considered to be very helpful. Furthermore, neither FANN’s documentation nor the library itself has been modified since 2007, which deems it potentially outdated for newer versions of C++ [18].
\nThe developed system carries a variety of performance constraints. The Raspberry Pi does not have high processing capabilities, and thus the network needed to be efficient enough for the device to get at least five MLP runs per second in order to run smoothly. The amount of time between calculations will directly affect the quality of the cars’ driving ability. This study is however merely a proof of concept, and thus a high processing power is not necessary to prove the concept works.
\nA further performance constraint would be in relation to the quality of the driving of the vehicle, for example, it could be very jittery when driving or be quite smooth—this is all proportionate to the amount of computations the neural network can do per second. If the computation power of the Pi means that this is quite slow, naturally, the vehicle will not be 100% accurate in staying between the lines, whereas if it can be developed to work efficiently, this may be less of a problem and the vehicle will drive more “smoothly”.
\nA solution’s quality could be measured in terms of the number of errors/stops the vehicle makes in a given time frame, and the lower this value is, the more efficient the device is.
\nBelow is the design of the hardware side of the system, excluding the external camera; we used two motors to control drive and steering and two HC-SR04 ultrasonic distance sensors to ensure for obstacle detection (Figure 5).
\nSystem design architecture of hardware.
Implementation of the hardware can be a challenge without the correct equipment. Following the initial designs, in the prototyping stage, a breadboard was used (see above) to manually switch wires and avoid soldering until the circuit was fully working. However, breadboards are not a long-term solution, and the wires will begin to fall out of the sockets, so at the point that a working circuit is created, it should be noted down in a form such as this (Figure 6).
\nHardware circuit, sensors and motor controller.
This then allows the creation of a long-term solution: a custom printed circuit board (PCB) soldering is required to do this, but it is much more secure and thus more reliable, especially in projects which experience a high level of movement. PCB designs usually represent the following (Figure 7).
\nFinal PCB design of the hardware.
A more modular layout is required for a project of this sort, because it is designed to be totally mobile and adaptable to different circumstances. Consequently, a Scalextric-type (modular) approach with around 6 corners and 10 straight pieces would be a good idea.
\nThe turning circle of the car required a large space, and the size of an A2 paper was chosen to make a modular-type design of which various sheets could contain different directions which led to the following two possibilities:
\nDue to the nature of the testing environment/demonstration environment—a floor—a decision was made to determine the track would have to blend into the background on which the track was being set, in case of the unlikely event when the track went off course. It was viewed, while considering the “canny edge detection” in Figure 8, that the white background may interfere with the surrounding environment and the image preprocessing would essentially and completely alter the image, so it is viewed that the black background would be more suitable for the environment the vehicle will be in (Figure 9).
\nWhite background with black lines.
Black background with white lines.
The following decisions were made:
The images are scaled down from 1024x720 to 10x10 to add efficiency to the network as the larger the image, the larger is the network; 100 bits was an efficient base level for the number of nodes in the input layer.
The neural network should have five layers, to account for a steady rate of drop off in the number of nodes per layer, inevitably aiming to end up with three outputs.
Given the objective was to achieve 5 FPS while the vehicle was driving and the length of the test track was around 25 m, we determined at a steady speed of 2.5 km/h; the vehicle would undergo around 300 frames per iteration. This was then used to calculate that at a high level, while taking into account the possibility of overtraining and undertraining, the training set should be around 50x the size of the data it would be handling, taking into account duplicate images around corners and other variables, so a training set of ~15,000 images were collected manually and labelled accordingly.
The MLP topology for this project is as follows (Figure 10):
\nSystem topology.
The first layer is the input layer—this has 100 nodes to represent the 100 values in the one-dimensional array the live image is converted to. Each one of these nodes represents 1 pixel in the 10x10 image.
\nThe second, third and fourth layers have 50, 25 and 12 nodes, respectively; these are known as hidden layers, and these sizes are calculated automatically.
\nThe fifth layer which happens to be the output layer has three nodes, which all correspond to the steering control instructions:
Output 0: FORWARDS | LEFT
Output 1: FORWARDS | RIGHT
Output 2: FORWARD ONLY
The training images are taken by a small script on the Pi which allows a photo to be taken every X seconds. This was set to 0.8. The image resizing and image filters were added and then implemented; while this was running, the car was moved round the track allowing for multiple angles and directions. All of these photos were then stored on the Pi.
\nFrom that set of photos, manual collation was required to store each picture in its corresponding class folder, in this case, one of 0, 1, or 2.
\nOnce these images had been correctly stored, another part of the program could read them from their containing class folder and compute the following to store them in an XML file named Train_data.xml.
\nThis data is all then stored in Training_data.xml. The same process occurs again for generating/gathering of training data.
\nThis process occurs to convert the real-time image into a format that is suitable for a neural network’s input Layer (Figure 11).
\nThe process of generating training and test data sets.
The image is filtered using the image processing techniques (black and white, Gaussian blur, canny edge detection) in order to make the image as simple as possible and have only the lines as a defining feature; this means there is less chance of errors in recognising and classifying the image via the NN.
\nThe images are scaled down to 10x10 in order to make an efficient and enough neural network; the larger the image, the larger the size of the neural network will need to be, which is directly proportionate to the efficiency/iterations per second of the image classifying loop that the device can perform. Thus, a smaller image resolution was chosen in order to make the device as efficient as possible.
\nFirstly, the filtered image is retrieved from the live stream from the camera and reshaped row by row to create a 1x100 image and converted to a one-dimensional array of 100 values ranging from 0 to 255 to represent each pixel of the image by each particular element of the array. The one-dimensional array is then directly fed into the neural network as the correct input format. Provided this process occurs on each data item, it can then be fed into the network for training, testing and prediction purposes.
\nTraining the network is done via the Train() function within OpenCV. Prior to calling this, the associated parameters have to be set. The process of doing this is relatively simple due to the helpful documentation provided in the OpenCV source codes and thus drastically reduces the amount of code required to show this.
\nFirstly, all values from training data set need to be loaded and added to the stack in their respective math formats (Figure 12).
\nLoading the data from XML file.
Following this, the network needs to be defined and its topology declared (Figure 13).
\nDeclaring the network and assigning its topology.
Next, the relevant network parameters need to be set.
\nFirstly, the activation function must be set, due to the fact that this network is a Multilayer-perceptron, the chosen activation function is sigmoid (Figure 14).
\nSet the activation function to sigmoid.
Next, setting the training method and training criteria, a backpropagation rate of 0.0001 for 50,000 iterations was chosen, the higher level of iterations will make the weighting more secure and could be potentially viewed as “over-training”; however, in the given circumstance of a real-time application, the network has to be as accurate as possible. The rate of backpropagation ratio being set to 0.0001 is the standard rate which is used by the majority of users (Figure 15).
\nSet training method and training criteria.
Following this, all that is required is to call the TRAIN function from the CV library, to run the training algorithm with the above specified topology, parameters and data (Figure 16).
\nTrain model.
Prediction is used in the testing process and the self-driving process. Prediction is the processing of unknown data in order to categorise the class of the image it is being given.
\nIn the case of testing, this is used to compare the network’s output to the correct output in order to calculate the accuracy of the network.
\nIn the self-driving process, the unknown data (camera image and sensor date) is fed into the neural network via prediction to determine the classification of the image. The value returned is used to determine the current state of the track in front of the vehicle, and this is the direction the car should move in.
\nIn the real-time processing part of the project, the real-time image has the aforementioned image preprocessing functions applied to it, to transform it from a fully coloured image into a one-dimensional array of binary values, to match the input layer of the MLP.
\nPrediction works by receiving this correctly formatted array and passing it to the input layer. This is then fed through the network (which has been fully loaded from the NNVALUES.XML file).
\nFollowing this, the network will produce an array of float values, representing the probability of the image belonging to that class. So, in this case it will produce an array of three float values, representing the probability the image which belongs to each of those classified outputs (0, 1, 2).
\nThe highest value in this array is recorded, and its location in the array (0, 1, 2) defines which class the image is most likely to belong to.
\nThis highest value location is then fed into a switch statement which implements a move instruction based on the value.
\nPrior to the calling of the AutoDrive function, the following criteria must be met in order for it to work fully:
\nAll hardware devices must be fully installed and working.
\nTraining and testing data must be created and stored.
\nTraining must be called to train the network and save it once trained.
\nTesting of the network must prove a high accuracy level of the network.
\nThe track must be ready to use.
\nAll of this is however done by the administrator to initialise the system prior to demonstration.
\nFollowing this, the device can be placed onto the track and will drive around it, utilising object detection and NN prediction in order to make informed decisions on which directions to drive.
\nIt can begin the self-driving Loop in which it will continue driving until the process is halted. This loop will continue to iterate, driving the car in the desired direction based on the current image of the track in front of it, which will change each iteration.
\nUnit testing is the testing for the initial components and all basic instructions in the system. These are developed from the basic implementation of the system (Table 1).
\nTest | \nTest criteria | \nWhere | \nQualifier | \nPass | \n
---|---|---|---|---|
1 | \nDoes front motor turn right? | \nTestMotors() | \nVisual | \nYes | \n
2 | \nDoes front motor turn left? | \nTestMotors() | \nVisual | \nYes | \n
3 | \nDoes rear motor go forward? | \nTestMotors() | \nVisual | \nYes | \n
4 | \nDoes rear motor go forwards and front motor go left? | \nTestMotors() | \nVisual | \nYes | \n
5 | \nDoes rear motor go forwards and front motor go right? | \nTestMotors() | \nVisual | \nYes | \n
6 | \nDoes sensor A function halt when object is within 15 cm? | \nTestSensors() | \nVisual | \nYes | \n
7 | \nDoes sensor B function halt when object is within 15 cm? | \nTestSensors() | \nVisual | \nYes | \n
8 | \nSensor A distance of 15 cm shown when object is 15 cm away | \nDistanceSenseA() | \nVisual | \nYes | \n
9 | \nSensor A distance of 50 cm shown when object is 50 cm away | \nDistanceSenseA() | \nVisual | \nYes | \n
10 | \nSensor B distance of 15 cm shown when object is 15 cm away | \nDistanceSenseB() | \nVisual | \nYes | \n
11 | \nSensor B distance of 50 cm shown when object is 50 cm away | \nDistanceSenseB() | \nVisual | \nYes | \n
Unit testing and results.
Integration testing is testing to see if the more advanced functionalities of the system are comprised from the design process (Table 2).
\nTest | \nTest criteria | \nWhere | \nQualifier | \nPass | \n
---|---|---|---|---|
12 | \nDoes canny edge filter apply to image stream from camera? | \nTestCamera() | \nVisual | \nYes | \n
13 | \nDoes camera image become scaled down to 10x10 resolution? | \nTestCamera() | \nVisual | \nYes | \n
14 | \nCan image stream from camera be converted to black and white? | \nTestCamera() | \nVisual | \nYes | \n
15 | \nCan image stream from camera be saved/loaded? | \nTestCamera() | \nVisual | \nYes | \n
16 | \nCan image stream from camera be reshaped from 10x10 to 1x100? | \nTestCamera() | \nVisual | \nYes | \n
17 | \nCan image be converted to a 1D array of values [0–255]? | \nTestCamera() | \nVisual | \nYes | \n
18 | \nCan a saved image be loaded? | \nAutoDrive() | \nVisual | \nYes | \n
19 | \nCan a set of images and their classes (read from folder name) be stored as a training data set? | \nReadScanStore() | \nVisual | \nYes | \n
20 | \nCan training data be stored in an XML file? | \nReadScanStore() | \nVisual | \nYes | \n
21 | \nCan a MLP be defined and created based on its topology? | \nTrainNetwork() | \nVisual | \nYes | \n
22 | \nCan a trained MLP be stored once trained to an XML file? | \nTrainNetwork() | \nVisual | \nYes | \n
23 | \nCan a trained MLP be loaded from an XML file? | \nTestNetwork() | \nVisual | \nYes | \n
24 | \nCan a training data set be used to train an MLP? | \nTrainNetwork() | \nVisual | \nYes | \n
25 | \nIs backpropagation the algorithm used to train the MLP? | \nTrainNetwork() | \nVisual | \nYes | \n
26 | \nDoes test data allow user to define accuracy of a trained MLP? | \nTestNetwork() | \nVisual | \nYes | \n
27 | \nDoes OpenCV’s backpropagation algorithm work? | \nTestNetwork() | \nVisual | \nYes | \n
28 | \nAre weight values stored of trained MLP not all the same? | \nTestNetwork() | \nVisual | \nYes | \n
29 | \nDoes NN/MLP allow prediction with current image? | \nAutoDrive() | \nVisual | \nYes | \n
30 | \nCalculate most likely output via neural network (prediction) | \nAutoDrive() | \nVisual | \nYes | \n
Integration testing and results.
The system testing is the tests of the overall system. These are defined by the research section to determine what is needed from the system for the user (Table 3).
\nTest | \nTest criteria | \nWhere | \nQualifier | \nPass | \n
---|---|---|---|---|
31 | \nUser menu option: testing for camera | \nSysMenu() | \nVisual | \nYes | \n
32 | \nUser menu option: testing for MLP accuracy | \nSysMenu() | \nVisual | \nYes | \n
33 | \nIs user menu easy to use? | \nSysMenu() | \nVisual | \nYes | \n
34 | \nUser menu option: testing for motors | \nSysMenu() | \nVisual | \nYes | \n
35 | \nUser menu option: testing for ultrasonic sensors | \nSysMenu() | \nVisual | \nYes | \n
36 | \nDoes the vehicle stay still if there is an object within 15 cm of the front of it? | \nAutoDrive() | \nVisual | \nYes | \n
37 | \nDoes the vehicle stay between the two lines needed to drive? | \nAutoDrive() | \nVisual | \nYes | \n
38 | \nDoes the vehicle successfully drive one loop around the track? | \nAutoDrive() | \nVisual | \nYes | \n
System testing and results.
These tests are used to qualitatively test the self-driving capabilities of the car and measure how smoothly it runs.
\nThese are measured visually during demonstration and thus are only considered to be an opinion as opposed to a solid pass/fail scheme (Table 4).
\nTest | \nTest criteria | \nWhere | \nQualifier | \nScore | \n
---|---|---|---|---|
41 | \nScore out of 10 for smoothness of drive when following a straight line | \nAutoDrive() | \nVisual opinion | \n9 | \n
42 | \nScore out of 10 for smoothness of drive when going around a corner | \nAutoDrive() | \nVisual opinion | \n6 | \n
43 | \nScore out of 10 for smoothness of driving when following an entire track | \nAutoDrive() | \nVisual opinion | \n7 | \n
Acceptance test and results.
Overall the project has achieved what it was required to do; it is fully able to drive around the track to a suitable level of accuracy. The chosen libraries were suitable for the project and provided well-documented functions regarding all aspects required to enable the vehicle to do the tasks that it had to perform.
\nIn my opinion, the best feature of the vehicle is the custom-made circuit board, which required a great deal of time and effort to design and build. Once this occurred, everything from the operational hardware point of view went very smoothly.
\nThe system passed all of the required tests. However, there was not enough time to implement some of the “would like to” aspects of the MoSCoW requirement analysis, but as discussed below, there is potential for further development.
\nThe main aims were to verify:
\nCan the vehicle recognise a track via NN and camera data?
\nCan the vehicle follow the track?
\nCan the vehicle control the car motors?
\nCan the vehicle utilise collision avoidance via ultrasonic sensors?
\nCan the vehicle recognise and stop at stop signs for a certain amount of time?
\nFollowing the test phase, the vehicle has shown the capabilities required to pass the first four out of five aims.
\nThe vehicle fully utilises the neural network to accurately classify the real-time image to decide upon and then implement a movement instruction. This allows the vehicle to follow the track given any set layout and follow it until the procedure is manually stopped. A variety of obstacles have been placed in front of the vehicle during operation, and when this occurs, the ultrasonic sensors recognise it, and the vehicle stops within the specified distance in order to avoid collision. The vehicle remains stationary until the obstacle moves away or is removed from its path. If the obstacle is moved around incrementally, it will “follow” the object staying at a minimum of the specified distance away. This is a very useful functionality for potential additions to the project which is to have the vehicle following other moving vehicles or staying a specified distance away from the obstacle should it be moving.
\nHowever, the stop sign detection capability was not implemented due to time constraints. To do this a Haar cascade qualifier must be used; this is an entirely different machine learning algorithm and thus would have to be implemented alongside the neural network. This naturally would have added many further functionalities. This was placed into the “would like to have this requirement later to develop the system design further” section of the MoSCoW analysis of the requirements because not only would this further implementation be time-consuming but finding small-scale stop signs that would be adequate for this task proved to be challenging and thus was not achieved in time.
\nIn relation to the MoSCoW analysis, “all of the must have”, “should have” and “could have” related requirements were fully met to a good standard.
\nFurther developments may be made as specified to cover the “would like to” aspect of the requirements.
\nImplementing a backpropagation algorithm manually as opposed to relying on the one provided from OpenCV, this would be desirable as it has the potential to be developed in a manner that may be more efficient for the problem at hand than just a generic algorithm.
\nA possible improvement would also be integrating the capability of designing, recognising and acting upon stop signs via a Haar cascade qualifier. This would be a further development to the device which could allow it to have more functionality and thus be more applicable to real-world projects.
\nAnother adaptation which would have been interesting to implement would be using a K-nearest neighbour algorithm for the machine learning part of the project. This could be used to compare the results from this to that of the neural network, to see which is more accurate. However, as aforementioned this was not implemented currently because of the much larger data set that would be required to train it.
\nThe only final improvement which could be made to the system would be to improve the mathematical functions applied to the ultrasonic distance sensors, which will be discussed below. These are currently only accurate at reading distances up to 50 cm using a simple mathematic function which for the present problem is acceptable, but future adaptations to the device may require more accuracy and thus more advanced mathematics to allow it to be accurate up to 5 m.
\nHardware design encountered a variety of problems with the circuitry of the vehicle which connected the external components to the Pi. Using a breadboard to connect all the components was not viable in the long term, and testing proved that as the car rattled, wires would come free as they were not fixed in place.
\nThis was fixed by having a permanent version of the circuit made and soldered in the workshops at the university, producing a finished product seen in Figure 7. This took a while to be perfect, and because of this, other tasks had to be put on hold pending the new board design. The new board completely solved the problem and provided both stability and much greater longevity to the product.
\nThe software design process also had problems along the way which required solving.
\nThe ultrasonic sensors in front of the vehicle required advanced mathematical formulae to be accurate at all distances, which would take time to complete, whereas using much a simpler formula would only mean they were accurate up to 50 cm as opposed to 5 m. This in the end was chosen as the vehicle only needs to be able to stop within 50 cm of an object, and anything beyond that distance cannot be considered an object in the vehicle’s path. A useful add-on to develop the device further would be to utilise this functionality correctly for all distances. However, for the purpose of the current project, it was not viewed as critical.
\nOverall, the track design was a good choice. The black background stops the edges of the paper from being seen as different to the colour of the dark floor, meaning only the edges of the track (white lines) are seen as fully qualified edges by the edge detector. The only issue with the track is that the corners can be viewed by some as “too tight” and thus the vehicle sometimes struggles to stay completely between the lines while turning through them. However, this is not a major issue as overall the vehicle remains between the lines for the majority of the driving cases, and if it does go out of the lines, it will self-correct.
\nObstacle detection works perfectly, allowing the vehicle to stop moving if anything is within 15 cm in front of it. This is exactly what was stated in the system requirements.
\nImage recognition correctly classifies the images based on the direction they are qualified under, with a score of 114/114 on the test data.
\nOverall, I feel that this was a successful project, in that it demonstrates a clear proof of concept that the computations required for autonomous cars do not have to be performed externally but may be done within the vehicle itself. The effect of this will be to make it much more versatile and adaptable for different environments and requirements. Another benefit of increased capacity and functionality within the vehicle would be to make it less vulnerable to external access, such as hacking, which could have implications for the vehicle, its user and others.
\nThe limitations imposed by the scale of the vehicle used in this work will affect the physical space available to house the computing hardware to that which will fit within the vehicle. This will have consequences for the functionalities the car is able to effectively demonstrate when using such small-scale computational devices.
\nI would like to thank my supervisor Dr. Mehmet Aydin, professor of enterprise system module, for being available throughout the entire process of this project and having an in-depth knowledge of all the software techniques and development techniques required to complete this task.
\nI would also like to thank Dr. Larry Bull, professor of artificial intelligence, for his help in the general structure of the neural network and advice regarding the training data.
\nThis project was chosen because it is considered to be very complex and the use of neural networks to process images is a study that is always improving. Furthermore, this project was chosen as a proof of concept for autonomous vehicles, which are constantly in development for future real-world applications. This means it is an area where this theory may be beneficial for further research by others.
\nMy intention was to improve this by scaling down the size of the neural network, making the device more portable and thus more realistic. This can be done by allowing the computations to be done on the Pi itself, making the device more mobile. It was concluded that this could potentially come at the cost of performance as trying to do computations of a large-scale neural network on a Raspberry Pi will be near impossible. As a result of this, the network needed to be scaled down, meaning much smaller images being passed, and the FPS rate will also need to be reduced to around 5–10 FPS. This is sufficient, considering the project is only a proof of concept.
\nIntechOpen is the first native scientific publisher of Open Access books, with more than 116,000 authors worldwide, ranging from globally-renowned Nobel Prize winners to up-and-coming researchers at the cutting edge of scientific discovery. Established in Europe with the new headquarters based in London, and with plans for international growth, IntechOpen is the leading publisher of Open Access scientific books. The values of our business are based on the same ones that any scientist applies to their research -- we have created a culture of respect, collegiality and collaboration within an atmosphere that’s relaxed, friendly and progressive.
",metaTitle:"Social Media Community Manager and Marketing Assistant",metaDescription:"We are looking to add further talent to our team in The Shard office in London with a full-time Marketing and Communications Specialist position. The candidate will bring with them a creative and enthusiastic mindset, high level problem-solving skills, the latest marketing and social media platforms skills and strong involvement in community-best practices to engage with researchers and scholars online. The ideal candidate will be a dynamic, forward thinking, approachable team player, able to communicate with all in the global, growing company, with an ability to understand and build a rapport within the research community.",metaKeywords:null,canonicalURL:null,contentRaw:'[{"type":"htmlEditorComponent","content":"We are looking to add further talent to our team in The Shard office in London with a full-time Social Media Community Manager and Marketing Assistant position. The candidate will bring with them a creative and enthusiastic mindset, high level problem-solving skills, the latest marketing and social media platforms skills and strong involvement in community-best practices to engage with researchers and scholars online. The ideal candidate wll be a dynamic, forward thinking, approachable team player, able to communicate with all in the global, growing company, with an ability to understand and build a rapport within the research community.
\\n\\nThe Social Media Community Manager and Marketing Assistant will report to the Senior Marketing Manager. They will work alongside the Marketing and Corporate Communications team, supporting the preparation of all marketing programs, assisting in the development of scientific marketing and communication deliverables, and creating content for social media outlets, as well as managing international social communities.
\\n\\nResponsibilities:
\\n\\nEssential Skills:
\\n\\nDesired Skills:
\\n\\nWhat makes IntechOpen a great place to work?
\\n\\nIntechOpen is a global, dynamic and fast-growing company offering excellent opportunities to develop. We are a young and vibrant company where great people do great work. We offer a creative, dedicated, committed, passionate, and above all, fun environment where you can work, travel, meet world-renowned researchers and grow your career and experience.
\\n\\nTo apply, please email a copy of your CV and covering letter to hogan@intechopen.com stating your salary expectations.
\\n\\nNote: This full-time position will have an immediate start. In your cover letter, please indicate when you might be available for a block of two hours. As part of the interview process, all candidates that make it to the second phase will participate in a writing exercise.
\\n\\n*IntechOpen is an Equal Opportunities Employer consistent with its obligations under the law and does not discriminate against any employee or applicant on the basis of disability, gender, age, colour, national origin, race, religion, sexual orientation, war veteran status, or any classification protected by state, or local law.
\\n"}]'},components:[{type:"htmlEditorComponent",content:'We are looking to add further talent to our team in The Shard office in London with a full-time Social Media Community Manager and Marketing Assistant position. The candidate will bring with them a creative and enthusiastic mindset, high level problem-solving skills, the latest marketing and social media platforms skills and strong involvement in community-best practices to engage with researchers and scholars online. The ideal candidate wll be a dynamic, forward thinking, approachable team player, able to communicate with all in the global, growing company, with an ability to understand and build a rapport within the research community.
\n\nThe Social Media Community Manager and Marketing Assistant will report to the Senior Marketing Manager. They will work alongside the Marketing and Corporate Communications team, supporting the preparation of all marketing programs, assisting in the development of scientific marketing and communication deliverables, and creating content for social media outlets, as well as managing international social communities.
\n\nResponsibilities:
\n\nEssential Skills:
\n\nDesired Skills:
\n\nWhat makes IntechOpen a great place to work?
\n\nIntechOpen is a global, dynamic and fast-growing company offering excellent opportunities to develop. We are a young and vibrant company where great people do great work. We offer a creative, dedicated, committed, passionate, and above all, fun environment where you can work, travel, meet world-renowned researchers and grow your career and experience.
\n\nTo apply, please email a copy of your CV and covering letter to hogan@intechopen.com stating your salary expectations.
\n\nNote: This full-time position will have an immediate start. In your cover letter, please indicate when you might be available for a block of two hours. As part of the interview process, all candidates that make it to the second phase will participate in a writing exercise.
\n\n*IntechOpen is an Equal Opportunities Employer consistent with its obligations under the law and does not discriminate against any employee or applicant on the basis of disability, gender, age, colour, national origin, race, religion, sexual orientation, war veteran status, or any classification protected by state, or local law.
\n'}]},successStories:{items:[]},authorsAndEditors:{filterParams:{sort:"featured,name"},profiles:[{id:"6700",title:"Dr.",name:"Abbass A.",middleName:null,surname:"Hashim",slug:"abbass-a.-hashim",fullName:"Abbass A. Hashim",position:null,profilePictureURL:"https://mts.intechopen.com/storage/users/6700/images/1864_n.jpg",biography:"Currently I am carrying out research in several areas of interest, mainly covering work on chemical and bio-sensors, semiconductor thin film device fabrication and characterisation.\nAt the moment I have very strong interest in radiation environmental pollution and bacteriology treatment. The teams of researchers are working very hard to bring novel results in this field. I am also a member of the team in charge for the supervision of Ph.D. students in the fields of development of silicon based planar waveguide sensor devices, study of inelastic electron tunnelling in planar tunnelling nanostructures for sensing applications and development of organotellurium(IV) compounds for semiconductor applications. I am a specialist in data analysis techniques and nanosurface structure. I have served as the editor for many books, been a member of the editorial board in science journals, have published many papers and hold many patents.",institutionString:null,institution:{name:"Sheffield Hallam University",country:{name:"United Kingdom"}}},{id:"54525",title:"Prof.",name:"Abdul Latif",middleName:null,surname:"Ahmad",slug:"abdul-latif-ahmad",fullName:"Abdul Latif Ahmad",position:null,profilePictureURL:"//cdnintech.com/web/frontend/www/assets/author.svg",biography:null,institutionString:null,institution:null},{id:"20567",title:"Prof.",name:"Ado",middleName:null,surname:"Jorio",slug:"ado-jorio",fullName:"Ado Jorio",position:null,profilePictureURL:"//cdnintech.com/web/frontend/www/assets/author.svg",biography:null,institutionString:null,institution:{name:"Universidade Federal de Minas Gerais",country:{name:"Brazil"}}},{id:"47940",title:"Dr.",name:"Alberto",middleName:null,surname:"Mantovani",slug:"alberto-mantovani",fullName:"Alberto Mantovani",position:null,profilePictureURL:"//cdnintech.com/web/frontend/www/assets/author.svg",biography:null,institutionString:null,institution:null},{id:"12392",title:"Mr.",name:"Alex",middleName:null,surname:"Lazinica",slug:"alex-lazinica",fullName:"Alex Lazinica",position:null,profilePictureURL:"https://mts.intechopen.com/storage/users/12392/images/7282_n.png",biography:"Alex Lazinica is the founder and CEO of IntechOpen. After obtaining a Master's degree in Mechanical Engineering, he continued his PhD studies in Robotics at the Vienna University of Technology. Here he worked as a robotic researcher with the university's Intelligent Manufacturing Systems Group as well as a guest researcher at various European universities, including the Swiss Federal Institute of Technology Lausanne (EPFL). During this time he published more than 20 scientific papers, gave presentations, served as a reviewer for major robotic journals and conferences and most importantly he co-founded and built the International Journal of Advanced Robotic Systems- world's first Open Access journal in the field of robotics. Starting this journal was a pivotal point in his career, since it was a pathway to founding IntechOpen - Open Access publisher focused on addressing academic researchers needs. Alex is a personification of IntechOpen key values being trusted, open and entrepreneurial. Today his focus is on defining the growth and development strategy for the company.",institutionString:null,institution:{name:"TU Wien",country:{name:"Austria"}}},{id:"19816",title:"Prof.",name:"Alexander",middleName:null,surname:"Kokorin",slug:"alexander-kokorin",fullName:"Alexander Kokorin",position:null,profilePictureURL:"https://mts.intechopen.com/storage/users/19816/images/1607_n.jpg",biography:"Alexander I. Kokorin: born: 1947, Moscow; DSc., PhD; Principal Research Fellow (Research Professor) of Department of Kinetics and Catalysis, N. Semenov Institute of Chemical Physics, Russian Academy of Sciences, Moscow.\r\nArea of research interests: physical chemistry of complex-organized molecular and nanosized systems, including polymer-metal complexes; the surface of doped oxide semiconductors. He is an expert in structural, absorptive, catalytic and photocatalytic properties, in structural organization and dynamic features of ionic liquids, in magnetic interactions between paramagnetic centers. The author or co-author of 3 books, over 200 articles and reviews in scientific journals and books. He is an actual member of the International EPR/ESR Society, European Society on Quantum Solar Energy Conversion, Moscow House of Scientists, of the Board of Moscow Physical Society.",institutionString:null,institution:{name:"Semenov Institute of Chemical Physics",country:{name:"Russia"}}},{id:"62389",title:"PhD.",name:"Ali Demir",middleName:null,surname:"Sezer",slug:"ali-demir-sezer",fullName:"Ali Demir Sezer",position:null,profilePictureURL:"https://mts.intechopen.com/storage/users/62389/images/3413_n.jpg",biography:"Dr. Ali Demir Sezer has a Ph.D. from Pharmaceutical Biotechnology at the Faculty of Pharmacy, University of Marmara (Turkey). He is the member of many Pharmaceutical Associations and acts as a reviewer of scientific journals and European projects under different research areas such as: drug delivery systems, nanotechnology and pharmaceutical biotechnology. Dr. Sezer is the author of many scientific publications in peer-reviewed journals and poster communications. Focus of his research activity is drug delivery, physico-chemical characterization and biological evaluation of biopolymers micro and nanoparticles as modified drug delivery system, and colloidal drug carriers (liposomes, nanoparticles etc.).",institutionString:null,institution:{name:"Marmara University",country:{name:"Turkey"}}},{id:"61051",title:"Prof.",name:"Andrea",middleName:null,surname:"Natale",slug:"andrea-natale",fullName:"Andrea Natale",position:null,profilePictureURL:"//cdnintech.com/web/frontend/www/assets/author.svg",biography:null,institutionString:null,institution:null},{id:"100762",title:"Prof.",name:"Andrea",middleName:null,surname:"Natale",slug:"andrea-natale",fullName:"Andrea Natale",position:null,profilePictureURL:"//cdnintech.com/web/frontend/www/assets/author.svg",biography:null,institutionString:null,institution:{name:"St David's Medical Center",country:{name:"United States of America"}}},{id:"107416",title:"Dr.",name:"Andrea",middleName:null,surname:"Natale",slug:"andrea-natale",fullName:"Andrea Natale",position:null,profilePictureURL:"//cdnintech.com/web/frontend/www/assets/author.svg",biography:null,institutionString:null,institution:{name:"Texas Cardiac Arrhythmia",country:{name:"United States of America"}}},{id:"64434",title:"Dr.",name:"Angkoon",middleName:null,surname:"Phinyomark",slug:"angkoon-phinyomark",fullName:"Angkoon Phinyomark",position:null,profilePictureURL:"https://mts.intechopen.com/storage/users/64434/images/2619_n.jpg",biography:"My name is Angkoon Phinyomark. I received a B.Eng. degree in Computer Engineering with First Class Honors in 2008 from Prince of Songkla University, Songkhla, Thailand, where I received a Ph.D. degree in Electrical Engineering. My research interests are primarily in the area of biomedical signal processing and classification notably EMG (electromyography signal), EOG (electrooculography signal), and EEG (electroencephalography signal), image analysis notably breast cancer analysis and optical coherence tomography, and rehabilitation engineering. I became a student member of IEEE in 2008. During October 2011-March 2012, I had worked at School of Computer Science and Electronic Engineering, University of Essex, Colchester, Essex, United Kingdom. In addition, during a B.Eng. I had been a visiting research student at Faculty of Computer Science, University of Murcia, Murcia, Spain for three months.\n\nI have published over 40 papers during 5 years in refereed journals, books, and conference proceedings in the areas of electro-physiological signals processing and classification, notably EMG and EOG signals, fractal analysis, wavelet analysis, texture analysis, feature extraction and machine learning algorithms, and assistive and rehabilitative devices. I have several computer programming language certificates, i.e. Sun Certified Programmer for the Java 2 Platform 1.4 (SCJP), Microsoft Certified Professional Developer, Web Developer (MCPD), Microsoft Certified Technology Specialist, .NET Framework 2.0 Web (MCTS). I am a Reviewer for several refereed journals and international conferences, such as IEEE Transactions on Biomedical Engineering, IEEE Transactions on Industrial Electronics, Optic Letters, Measurement Science Review, and also a member of the International Advisory Committee for 2012 IEEE Business Engineering and Industrial Applications and 2012 IEEE Symposium on Business, Engineering and Industrial Applications.",institutionString:null,institution:{name:"Joseph Fourier University",country:{name:"France"}}},{id:"55578",title:"Dr.",name:"Antonio",middleName:null,surname:"Jurado-Navas",slug:"antonio-jurado-navas",fullName:"Antonio Jurado-Navas",position:null,profilePictureURL:"https://mts.intechopen.com/storage/users/55578/images/4574_n.png",biography:"Antonio Jurado-Navas received the M.S. degree (2002) and the Ph.D. degree (2009) in Telecommunication Engineering, both from the University of Málaga (Spain). He first worked as a consultant at Vodafone-Spain. From 2004 to 2011, he was a Research Assistant with the Communications Engineering Department at the University of Málaga. In 2011, he became an Assistant Professor in the same department. From 2012 to 2015, he was with Ericsson Spain, where he was working on geo-location\ntools for third generation mobile networks. Since 2015, he is a Marie-Curie fellow at the Denmark Technical University. His current research interests include the areas of mobile communication systems and channel modeling in addition to atmospheric optical communications, adaptive optics and statistics",institutionString:null,institution:{name:"University of Malaga",country:{name:"Spain"}}}],filtersByRegion:[{group:"region",caption:"North America",value:1,count:5766},{group:"region",caption:"Middle and South America",value:2,count:5228},{group:"region",caption:"Africa",value:3,count:1717},{group:"region",caption:"Asia",value:4,count:10370},{group:"region",caption:"Australia and Oceania",value:5,count:897},{group:"region",caption:"Europe",value:6,count:15791}],offset:12,limit:12,total:118192},chapterEmbeded:{data:{}},editorApplication:{success:null,errors:{}},ofsBooks:{filterParams:{topicId:"178"},books:[],filtersByTopic:[{group:"topic",caption:"Agricultural and Biological Sciences",value:5,count:16},{group:"topic",caption:"Biochemistry, Genetics and Molecular Biology",value:6,count:4},{group:"topic",caption:"Business, Management and Economics",value:7,count:2},{group:"topic",caption:"Chemistry",value:8,count:8},{group:"topic",caption:"Computer and Information Science",value:9,count:6},{group:"topic",caption:"Earth and Planetary Sciences",value:10,count:7},{group:"topic",caption:"Engineering",value:11,count:19},{group:"topic",caption:"Environmental Sciences",value:12,count:2},{group:"topic",caption:"Immunology and Microbiology",value:13,count:3},{group:"topic",caption:"Materials Science",value:14,count:5},{group:"topic",caption:"Mathematics",value:15,count:1},{group:"topic",caption:"Medicine",value:16,count:24},{group:"topic",caption:"Neuroscience",value:18,count:2},{group:"topic",caption:"Pharmacology, Toxicology and Pharmaceutical Science",value:19,count:3},{group:"topic",caption:"Physics",value:20,count:3},{group:"topic",caption:"Psychology",value:21,count:4},{group:"topic",caption:"Robotics",value:22,count:1},{group:"topic",caption:"Social Sciences",value:23,count:3},{group:"topic",caption:"Technology",value:24,count:1},{group:"topic",caption:"Veterinary Medicine and Science",value:25,count:1}],offset:12,limit:12,total:0},popularBooks:{featuredBooks:[{type:"book",id:"9385",title:"Renewable Energy",subtitle:"Technologies and Applications",isOpenForSubmission:!1,hash:"a6b446d19166f17f313008e6c056f3d8",slug:"renewable-energy-technologies-and-applications",bookSignature:"Tolga Taner, Archana Tiwari and Taha Selim Ustun",coverURL:"https://cdn.intechopen.com/books/images_new/9385.jpg",editors:[{id:"197240",title:"Associate Prof.",name:"Tolga",middleName:null,surname:"Taner",slug:"tolga-taner",fullName:"Tolga Taner"}],equalEditorOne:{id:"186791",title:"Dr.",name:"Archana",middleName:null,surname:"Tiwari",slug:"archana-tiwari",fullName:"Archana Tiwari",profilePictureURL:"https://mts.intechopen.com/storage/users/186791/images/system/186791.jpg",biography:"Dr. Archana Tiwari is Associate Professor at Amity University, India. Her research interests include renewable sources of energy from microalgae and further utilizing the residual biomass for the generation of value-added products, bioremediation through microalgae and microbial consortium, antioxidative enzymes and stress, and nutraceuticals from microalgae. She has been working on algal biotechnology for the last two decades. She has published her research in many international journals and has authored many books and chapters with renowned publishing houses. She has also delivered talks as an invited speaker at many national and international conferences. Dr. Tiwari is the recipient of several awards including Researcher of the Year and Distinguished Scientist.",institutionString:"Amity University",position:null,outsideEditionCount:0,totalCites:0,totalAuthoredChapters:"3",totalChapterViews:"0",totalEditedBooks:"1",institution:{name:"Amity University",institutionURL:null,country:{name:"India"}}},equalEditorTwo:{id:"197609",title:"Prof.",name:"Taha Selim",middleName:null,surname:"Ustun",slug:"taha-selim-ustun",fullName:"Taha Selim Ustun",profilePictureURL:"https://mts.intechopen.com/storage/users/197609/images/system/197609.jpeg",biography:"Dr. Taha Selim Ustun received a Ph.D. in Electrical Engineering from Victoria University, Melbourne, Australia. He is a researcher with the Fukushima Renewable Energy Institute, AIST (FREA), where he leads the Smart Grid Cybersecurity Laboratory. Prior to that, he was a faculty member with the School of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA. His current research interests include power systems protection, communication in power networks, distributed generation, microgrids, electric vehicle integration, and cybersecurity in smart grids. He serves on the editorial boards of IEEE Access, IEEE Transactions on Industrial Informatics, Energies, Electronics, Electricity, World Electric Vehicle and Information journals. Dr. Ustun is a member of the IEEE 2004 and 2800, IEC Renewable Energy Management WG 8, and IEC TC 57 WG17. He has been invited to run specialist courses in Africa, India, and China. He has delivered talks for the Qatar Foundation, the World Energy Council, the Waterloo Global Science Initiative, and the European Union Energy Initiative (EUEI). His research has attracted funding from prestigious programs in Japan, Australia, the European Union, and North America.",institutionString:"Fukushima Renewable Energy Institute, AIST (FREA)",position:null,outsideEditionCount:0,totalCites:0,totalAuthoredChapters:"1",totalChapterViews:"0",totalEditedBooks:"0",institution:{name:"National Institute of Advanced Industrial Science and Technology",institutionURL:null,country:{name:"Japan"}}},equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"10065",title:"Wavelet Theory",subtitle:null,isOpenForSubmission:!1,hash:"d8868e332169597ba2182d9b004d60de",slug:"wavelet-theory",bookSignature:"Somayeh Mohammady",coverURL:"https://cdn.intechopen.com/books/images_new/10065.jpg",editors:[{id:"109280",title:"Dr.",name:"Somayeh",middleName:null,surname:"Mohammady",slug:"somayeh-mohammady",fullName:"Somayeh Mohammady"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"9644",title:"Glaciers and the Polar Environment",subtitle:null,isOpenForSubmission:!1,hash:"e8cfdc161794e3753ced54e6ff30873b",slug:"glaciers-and-the-polar-environment",bookSignature:"Masaki Kanao, Danilo Godone and Niccolò Dematteis",coverURL:"https://cdn.intechopen.com/books/images_new/9644.jpg",editors:[{id:"51959",title:"Dr.",name:"Masaki",middleName:null,surname:"Kanao",slug:"masaki-kanao",fullName:"Masaki Kanao"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"8985",title:"Natural Resources Management and Biological Sciences",subtitle:null,isOpenForSubmission:!1,hash:"5c2e219a6c021a40b5a20c041dea88c4",slug:"natural-resources-management-and-biological-sciences",bookSignature:"Edward R. Rhodes and Humood Naser",coverURL:"https://cdn.intechopen.com/books/images_new/8985.jpg",editors:[{id:"280886",title:"Prof.",name:"Edward R",middleName:null,surname:"Rhodes",slug:"edward-r-rhodes",fullName:"Edward R Rhodes"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"9671",title:"Macrophages",subtitle:null,isOpenForSubmission:!1,hash:"03b00fdc5f24b71d1ecdfd75076bfde6",slug:"macrophages",bookSignature:"Hridayesh Prakash",coverURL:"https://cdn.intechopen.com/books/images_new/9671.jpg",editors:[{id:"287184",title:"Dr.",name:"Hridayesh",middleName:null,surname:"Prakash",slug:"hridayesh-prakash",fullName:"Hridayesh Prakash"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"9313",title:"Clay Science and Technology",subtitle:null,isOpenForSubmission:!1,hash:"6fa7e70396ff10620e032bb6cfa6fb72",slug:"clay-science-and-technology",bookSignature:"Gustavo Morari Do Nascimento",coverURL:"https://cdn.intechopen.com/books/images_new/9313.jpg",editors:[{id:"7153",title:"Prof.",name:"Gustavo",middleName:null,surname:"Morari Do Nascimento",slug:"gustavo-morari-do-nascimento",fullName:"Gustavo Morari Do Nascimento"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"9888",title:"Nuclear Power Plants",subtitle:"The Processes from the Cradle to the Grave",isOpenForSubmission:!1,hash:"c2c8773e586f62155ab8221ebb72a849",slug:"nuclear-power-plants-the-processes-from-the-cradle-to-the-grave",bookSignature:"Nasser Awwad",coverURL:"https://cdn.intechopen.com/books/images_new/9888.jpg",editors:[{id:"145209",title:"Prof.",name:"Nasser",middleName:"S",surname:"Awwad",slug:"nasser-awwad",fullName:"Nasser Awwad"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"9027",title:"Human Blood Group Systems and Haemoglobinopathies",subtitle:null,isOpenForSubmission:!1,hash:"d00d8e40b11cfb2547d1122866531c7e",slug:"human-blood-group-systems-and-haemoglobinopathies",bookSignature:"Osaro Erhabor and Anjana Munshi",coverURL:"https://cdn.intechopen.com/books/images_new/9027.jpg",editors:[{id:"35140",title:null,name:"Osaro",middleName:null,surname:"Erhabor",slug:"osaro-erhabor",fullName:"Osaro Erhabor"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"7841",title:"New Insights Into Metabolic Syndrome",subtitle:null,isOpenForSubmission:!1,hash:"ef5accfac9772b9e2c9eff884f085510",slug:"new-insights-into-metabolic-syndrome",bookSignature:"Akikazu Takada",coverURL:"https://cdn.intechopen.com/books/images_new/7841.jpg",editors:[{id:"248459",title:"Dr.",name:"Akikazu",middleName:null,surname:"Takada",slug:"akikazu-takada",fullName:"Akikazu Takada"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"8558",title:"Aerodynamics",subtitle:null,isOpenForSubmission:!1,hash:"db7263fc198dfb539073ba0260a7f1aa",slug:"aerodynamics",bookSignature:"Mofid Gorji-Bandpy and Aly-Mousaad Aly",coverURL:"https://cdn.intechopen.com/books/images_new/8558.jpg",editors:[{id:"35542",title:"Prof.",name:"Mofid",middleName:null,surname:"Gorji-Bandpy",slug:"mofid-gorji-bandpy",fullName:"Mofid Gorji-Bandpy"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"7847",title:"Medical Toxicology",subtitle:null,isOpenForSubmission:!1,hash:"db9b65bea093de17a0855a1b27046247",slug:"medical-toxicology",bookSignature:"Pınar Erkekoglu and Tomohisa Ogawa",coverURL:"https://cdn.intechopen.com/books/images_new/7847.jpg",editors:[{id:"109978",title:"Prof.",name:"Pınar",middleName:null,surname:"Erkekoglu",slug:"pinar-erkekoglu",fullName:"Pınar Erkekoglu"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"10432",title:"Casting Processes and Modelling of Metallic Materials",subtitle:null,isOpenForSubmission:!1,hash:"2c5c9df938666bf5d1797727db203a6d",slug:"casting-processes-and-modelling-of-metallic-materials",bookSignature:"Zakaria Abdallah and Nada Aldoumani",coverURL:"https://cdn.intechopen.com/books/images_new/10432.jpg",editors:[{id:"201670",title:"Dr.",name:"Zak",middleName:null,surname:"Abdallah",slug:"zak-abdallah",fullName:"Zak Abdallah"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}}],offset:12,limit:12,total:5240},hotBookTopics:{hotBooks:[],offset:0,limit:12,total:null},publish:{},publishingProposal:{success:null,errors:{}},books:{featuredBooks:[{type:"book",id:"10065",title:"Wavelet Theory",subtitle:null,isOpenForSubmission:!1,hash:"d8868e332169597ba2182d9b004d60de",slug:"wavelet-theory",bookSignature:"Somayeh Mohammady",coverURL:"https://cdn.intechopen.com/books/images_new/10065.jpg",editors:[{id:"109280",title:"Dr.",name:"Somayeh",middleName:null,surname:"Mohammady",slug:"somayeh-mohammady",fullName:"Somayeh Mohammady"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"9644",title:"Glaciers and the Polar Environment",subtitle:null,isOpenForSubmission:!1,hash:"e8cfdc161794e3753ced54e6ff30873b",slug:"glaciers-and-the-polar-environment",bookSignature:"Masaki Kanao, Danilo Godone and Niccolò Dematteis",coverURL:"https://cdn.intechopen.com/books/images_new/9644.jpg",editors:[{id:"51959",title:"Dr.",name:"Masaki",middleName:null,surname:"Kanao",slug:"masaki-kanao",fullName:"Masaki Kanao"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"9385",title:"Renewable Energy",subtitle:"Technologies and Applications",isOpenForSubmission:!1,hash:"a6b446d19166f17f313008e6c056f3d8",slug:"renewable-energy-technologies-and-applications",bookSignature:"Tolga Taner, Archana Tiwari and Taha Selim Ustun",coverURL:"https://cdn.intechopen.com/books/images_new/9385.jpg",editors:[{id:"197240",title:"Associate Prof.",name:"Tolga",middleName:null,surname:"Taner",slug:"tolga-taner",fullName:"Tolga Taner"}],equalEditorOne:{id:"186791",title:"Dr.",name:"Archana",middleName:null,surname:"Tiwari",slug:"archana-tiwari",fullName:"Archana Tiwari",profilePictureURL:"https://mts.intechopen.com/storage/users/186791/images/system/186791.jpg",biography:"Dr. Archana Tiwari is Associate Professor at Amity University, India. Her research interests include renewable sources of energy from microalgae and further utilizing the residual biomass for the generation of value-added products, bioremediation through microalgae and microbial consortium, antioxidative enzymes and stress, and nutraceuticals from microalgae. She has been working on algal biotechnology for the last two decades. She has published her research in many international journals and has authored many books and chapters with renowned publishing houses. She has also delivered talks as an invited speaker at many national and international conferences. Dr. Tiwari is the recipient of several awards including Researcher of the Year and Distinguished Scientist.",institutionString:"Amity University",position:null,outsideEditionCount:0,totalCites:0,totalAuthoredChapters:"3",totalChapterViews:"0",totalEditedBooks:"1",institution:{name:"Amity University",institutionURL:null,country:{name:"India"}}},equalEditorTwo:{id:"197609",title:"Prof.",name:"Taha Selim",middleName:null,surname:"Ustun",slug:"taha-selim-ustun",fullName:"Taha Selim Ustun",profilePictureURL:"https://mts.intechopen.com/storage/users/197609/images/system/197609.jpeg",biography:"Dr. Taha Selim Ustun received a Ph.D. in Electrical Engineering from Victoria University, Melbourne, Australia. He is a researcher with the Fukushima Renewable Energy Institute, AIST (FREA), where he leads the Smart Grid Cybersecurity Laboratory. Prior to that, he was a faculty member with the School of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA. His current research interests include power systems protection, communication in power networks, distributed generation, microgrids, electric vehicle integration, and cybersecurity in smart grids. He serves on the editorial boards of IEEE Access, IEEE Transactions on Industrial Informatics, Energies, Electronics, Electricity, World Electric Vehicle and Information journals. Dr. Ustun is a member of the IEEE 2004 and 2800, IEC Renewable Energy Management WG 8, and IEC TC 57 WG17. He has been invited to run specialist courses in Africa, India, and China. He has delivered talks for the Qatar Foundation, the World Energy Council, the Waterloo Global Science Initiative, and the European Union Energy Initiative (EUEI). His research has attracted funding from prestigious programs in Japan, Australia, the European Union, and North America.",institutionString:"Fukushima Renewable Energy Institute, AIST (FREA)",position:null,outsideEditionCount:0,totalCites:0,totalAuthoredChapters:"1",totalChapterViews:"0",totalEditedBooks:"0",institution:{name:"National Institute of Advanced Industrial Science and Technology",institutionURL:null,country:{name:"Japan"}}},equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"8985",title:"Natural Resources Management and Biological Sciences",subtitle:null,isOpenForSubmission:!1,hash:"5c2e219a6c021a40b5a20c041dea88c4",slug:"natural-resources-management-and-biological-sciences",bookSignature:"Edward R. Rhodes and Humood Naser",coverURL:"https://cdn.intechopen.com/books/images_new/8985.jpg",editors:[{id:"280886",title:"Prof.",name:"Edward R",middleName:null,surname:"Rhodes",slug:"edward-r-rhodes",fullName:"Edward R Rhodes"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"9671",title:"Macrophages",subtitle:null,isOpenForSubmission:!1,hash:"03b00fdc5f24b71d1ecdfd75076bfde6",slug:"macrophages",bookSignature:"Hridayesh Prakash",coverURL:"https://cdn.intechopen.com/books/images_new/9671.jpg",editors:[{id:"287184",title:"Dr.",name:"Hridayesh",middleName:null,surname:"Prakash",slug:"hridayesh-prakash",fullName:"Hridayesh Prakash"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"9313",title:"Clay Science and Technology",subtitle:null,isOpenForSubmission:!1,hash:"6fa7e70396ff10620e032bb6cfa6fb72",slug:"clay-science-and-technology",bookSignature:"Gustavo Morari Do Nascimento",coverURL:"https://cdn.intechopen.com/books/images_new/9313.jpg",editors:[{id:"7153",title:"Prof.",name:"Gustavo",middleName:null,surname:"Morari Do Nascimento",slug:"gustavo-morari-do-nascimento",fullName:"Gustavo Morari Do Nascimento"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"9888",title:"Nuclear Power Plants",subtitle:"The Processes from the Cradle to the Grave",isOpenForSubmission:!1,hash:"c2c8773e586f62155ab8221ebb72a849",slug:"nuclear-power-plants-the-processes-from-the-cradle-to-the-grave",bookSignature:"Nasser Awwad",coverURL:"https://cdn.intechopen.com/books/images_new/9888.jpg",editors:[{id:"145209",title:"Prof.",name:"Nasser",middleName:"S",surname:"Awwad",slug:"nasser-awwad",fullName:"Nasser Awwad"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"9027",title:"Human Blood Group Systems and Haemoglobinopathies",subtitle:null,isOpenForSubmission:!1,hash:"d00d8e40b11cfb2547d1122866531c7e",slug:"human-blood-group-systems-and-haemoglobinopathies",bookSignature:"Osaro Erhabor and Anjana Munshi",coverURL:"https://cdn.intechopen.com/books/images_new/9027.jpg",editors:[{id:"35140",title:null,name:"Osaro",middleName:null,surname:"Erhabor",slug:"osaro-erhabor",fullName:"Osaro Erhabor"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"10432",title:"Casting Processes and Modelling of Metallic Materials",subtitle:null,isOpenForSubmission:!1,hash:"2c5c9df938666bf5d1797727db203a6d",slug:"casting-processes-and-modelling-of-metallic-materials",bookSignature:"Zakaria Abdallah and Nada Aldoumani",coverURL:"https://cdn.intechopen.com/books/images_new/10432.jpg",editors:[{id:"201670",title:"Dr.",name:"Zak",middleName:null,surname:"Abdallah",slug:"zak-abdallah",fullName:"Zak Abdallah"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}},{type:"book",id:"7841",title:"New Insights Into Metabolic Syndrome",subtitle:null,isOpenForSubmission:!1,hash:"ef5accfac9772b9e2c9eff884f085510",slug:"new-insights-into-metabolic-syndrome",bookSignature:"Akikazu Takada",coverURL:"https://cdn.intechopen.com/books/images_new/7841.jpg",editors:[{id:"248459",title:"Dr.",name:"Akikazu",middleName:null,surname:"Takada",slug:"akikazu-takada",fullName:"Akikazu Takada"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}}],latestBooks:[{type:"book",id:"9243",title:"Coastal Environments",subtitle:null,isOpenForSubmission:!1,hash:"8e05e5f631e935eef366980f2e28295d",slug:"coastal-environments",bookSignature:"Yuanzhi Zhang and X. San Liang",coverURL:"https://cdn.intechopen.com/books/images_new/9243.jpg",editedByType:"Edited by",editors:[{id:"77597",title:"Prof.",name:"Yuanzhi",middleName:null,surname:"Zhang",slug:"yuanzhi-zhang",fullName:"Yuanzhi Zhang"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"10020",title:"Operations Management",subtitle:"Emerging Trend in the Digital Era",isOpenForSubmission:!1,hash:"526f0dbdc7e4d85b82ce8383ab894b4c",slug:"operations-management-emerging-trend-in-the-digital-era",bookSignature:"Antonella Petrillo, Fabio De Felice, Germano Lambert-Torres and Erik Bonaldi",coverURL:"https://cdn.intechopen.com/books/images_new/10020.jpg",editedByType:"Edited by",editors:[{id:"181603",title:"Dr.",name:"Antonella",middleName:null,surname:"Petrillo",slug:"antonella-petrillo",fullName:"Antonella Petrillo"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"9521",title:"Antimicrobial Resistance",subtitle:"A One Health Perspective",isOpenForSubmission:!1,hash:"30949e78832e1afba5606634b52056ab",slug:"antimicrobial-resistance-a-one-health-perspective",bookSignature:"Mihai Mareș, Swee Hua Erin Lim, Kok-Song Lai and Romeo-Teodor Cristina",coverURL:"https://cdn.intechopen.com/books/images_new/9521.jpg",editedByType:"Edited by",editors:[{id:"88785",title:"Prof.",name:"Mihai",middleName:null,surname:"Mares",slug:"mihai-mares",fullName:"Mihai Mares"}],equalEditorOne:{id:"190224",title:"Dr.",name:"Swee Hua Erin",middleName:null,surname:"Lim",slug:"swee-hua-erin-lim",fullName:"Swee Hua Erin Lim",profilePictureURL:"https://mts.intechopen.com/storage/users/190224/images/system/190224.png",biography:"Dr. Erin Lim is presently working as an Assistant Professor in the Division of Health Sciences, Abu Dhabi Women\\'s College, Higher Colleges of Technology in Abu Dhabi, United Arab Emirates and is affiliated as an Associate Professor to Perdana University-Royal College of Surgeons in Ireland, Selangor, Malaysia. She obtained her Ph.D. from Universiti Putra Malaysia in 2010 with a National Science Fellowship awarded from the Ministry of Science, Technology and Innovation Malaysia and has been actively involved in research ever since. Her main research interests include analysis of carriage and transmission of multidrug resistant bacteria in non-conventional settings, besides an interest in natural products for antimicrobial testing. She is heavily involved in the elucidation of mechanisms of reversal of resistance in bacteria in addition to investigating the immunological analyses of diseases, development of vaccination and treatment models in animals. She hopes her work will support the discovery of therapeutics in the clinical setting and assist in the combat against the burden of antibiotic resistance.",institutionString:"Abu Dhabi Women’s College",position:null,outsideEditionCount:0,totalCites:0,totalAuthoredChapters:"3",totalChapterViews:"0",totalEditedBooks:"0",institution:{name:"Perdana University",institutionURL:null,country:{name:"Malaysia"}}},equalEditorTwo:{id:"221544",title:"Dr.",name:"Kok-Song",middleName:null,surname:"Lai",slug:"kok-song-lai",fullName:"Kok-Song Lai",profilePictureURL:"https://mts.intechopen.com/storage/users/221544/images/system/221544.jpeg",biography:"Dr. Lai Kok Song is an Assistant Professor in the Division of Health Sciences, Abu Dhabi Women\\'s College, Higher Colleges of Technology in Abu Dhabi, United Arab Emirates. He obtained his Ph.D. in Biological Sciences from Nara Institute of Science and Technology, Japan in 2012. Prior to his academic appointment, Dr. Lai worked as a Senior Scientist at the Ministry of Science, Technology and Innovation, Malaysia. His current research areas include antimicrobial resistance and plant-pathogen interaction. His particular interest lies in the study of the antimicrobial mechanism via membrane disruption of essential oils against multi-drug resistance bacteria through various biochemical, molecular and proteomic approaches. Ultimately, he hopes to uncover and determine novel biomarkers related to antibiotic resistance that can be developed into new therapeutic strategies.",institutionString:"Higher Colleges of Technology",position:null,outsideEditionCount:0,totalCites:0,totalAuthoredChapters:"8",totalChapterViews:"0",totalEditedBooks:"0",institution:{name:"Higher Colleges of Technology",institutionURL:null,country:{name:"United Arab Emirates"}}},equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"9560",title:"Creativity",subtitle:"A Force to Innovation",isOpenForSubmission:!1,hash:"58f740bc17807d5d88d647c525857b11",slug:"creativity-a-force-to-innovation",bookSignature:"Pooja Jain",coverURL:"https://cdn.intechopen.com/books/images_new/9560.jpg",editedByType:"Edited by",editors:[{id:"316765",title:"Dr.",name:"Pooja",middleName:null,surname:"Jain",slug:"pooja-jain",fullName:"Pooja Jain"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"9669",title:"Recent Advances in Rice Research",subtitle:null,isOpenForSubmission:!1,hash:"12b06cc73e89af1e104399321cc16a75",slug:"recent-advances-in-rice-research",bookSignature:"Mahmood-ur- Rahman Ansari",coverURL:"https://cdn.intechopen.com/books/images_new/9669.jpg",editedByType:"Edited by",editors:[{id:"185476",title:"Dr.",name:"Mahmood-Ur-",middleName:null,surname:"Rahman Ansari",slug:"mahmood-ur-rahman-ansari",fullName:"Mahmood-Ur- Rahman Ansari"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"10192",title:"Background and Management of Muscular Atrophy",subtitle:null,isOpenForSubmission:!1,hash:"eca24028d89912b5efea56e179dff089",slug:"background-and-management-of-muscular-atrophy",bookSignature:"Julianna Cseri",coverURL:"https://cdn.intechopen.com/books/images_new/10192.jpg",editedByType:"Edited by",editors:[{id:"135579",title:"Dr.",name:"Julianna",middleName:null,surname:"Cseri",slug:"julianna-cseri",fullName:"Julianna Cseri"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"9550",title:"Entrepreneurship",subtitle:"Contemporary Issues",isOpenForSubmission:!1,hash:"9b4ac1ee5b743abf6f88495452b1e5e7",slug:"entrepreneurship-contemporary-issues",bookSignature:"Mladen Turuk",coverURL:"https://cdn.intechopen.com/books/images_new/9550.jpg",editedByType:"Edited by",editors:[{id:"319755",title:"Prof.",name:"Mladen",middleName:null,surname:"Turuk",slug:"mladen-turuk",fullName:"Mladen Turuk"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"10065",title:"Wavelet Theory",subtitle:null,isOpenForSubmission:!1,hash:"d8868e332169597ba2182d9b004d60de",slug:"wavelet-theory",bookSignature:"Somayeh Mohammady",coverURL:"https://cdn.intechopen.com/books/images_new/10065.jpg",editedByType:"Edited by",editors:[{id:"109280",title:"Dr.",name:"Somayeh",middleName:null,surname:"Mohammady",slug:"somayeh-mohammady",fullName:"Somayeh Mohammady"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"9313",title:"Clay Science and Technology",subtitle:null,isOpenForSubmission:!1,hash:"6fa7e70396ff10620e032bb6cfa6fb72",slug:"clay-science-and-technology",bookSignature:"Gustavo Morari Do Nascimento",coverURL:"https://cdn.intechopen.com/books/images_new/9313.jpg",editedByType:"Edited by",editors:[{id:"7153",title:"Prof.",name:"Gustavo",middleName:null,surname:"Morari Do Nascimento",slug:"gustavo-morari-do-nascimento",fullName:"Gustavo Morari Do Nascimento"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"9888",title:"Nuclear Power Plants",subtitle:"The Processes from the Cradle to the Grave",isOpenForSubmission:!1,hash:"c2c8773e586f62155ab8221ebb72a849",slug:"nuclear-power-plants-the-processes-from-the-cradle-to-the-grave",bookSignature:"Nasser Awwad",coverURL:"https://cdn.intechopen.com/books/images_new/9888.jpg",editedByType:"Edited by",editors:[{id:"145209",title:"Prof.",name:"Nasser",middleName:"S",surname:"Awwad",slug:"nasser-awwad",fullName:"Nasser Awwad"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}}]},subject:{topic:{id:"54",title:"Human Genetics",slug:"human-genetics",parent:{title:"Biochemistry, Genetics and Molecular Biology",slug:"biochemistry-genetics-and-molecular-biology"},numberOfBooks:31,numberOfAuthorsAndEditors:1019,numberOfWosCitations:1067,numberOfCrossrefCitations:413,numberOfDimensionsCitations:1019,videoUrl:null,fallbackUrl:null,description:null},booksByTopicFilter:{topicSlug:"human-genetics",sort:"-publishedDate",limit:12,offset:0},booksByTopicCollection:[{type:"book",id:"8073",title:"Chromosomal Abnormalities",subtitle:null,isOpenForSubmission:!1,hash:"6a9d3c58434edf5e65f9849a6858edfe",slug:"chromosomal-abnormalities",bookSignature:"Tülay Aşkın Çelik and Subrata Dey",coverURL:"https://cdn.intechopen.com/books/images_new/8073.jpg",editedByType:"Edited by",editors:[{id:"74041",title:"Dr.",name:"Tulay",middleName:null,surname:"Askin Celik",slug:"tulay-askin-celik",fullName:"Tulay Askin Celik"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"6920",title:"Cytogenetics",subtitle:"Past, Present and Further Perspectives",isOpenForSubmission:!1,hash:"d72001eed508dfa72d9a68e1de28bb4b",slug:"cytogenetics-past-present-and-further-perspectives",bookSignature:"Marcelo Larramendy and Sonia Soloneski",coverURL:"https://cdn.intechopen.com/books/images_new/6920.jpg",editedByType:"Edited by",editors:[{id:"14764",title:"Dr.",name:"Marcelo L.",middleName:null,surname:"Larramendy",slug:"marcelo-l.-larramendy",fullName:"Marcelo L. Larramendy"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"6719",title:"Genetic Diversity and Disease Susceptibility",subtitle:null,isOpenForSubmission:!1,hash:"0c9919347cc7cb1dcbc245ce8684eee7",slug:"genetic-diversity-and-disease-susceptibility",bookSignature:"Yamin Liu",coverURL:"https://cdn.intechopen.com/books/images_new/6719.jpg",editedByType:"Edited by",editors:[{id:"201887",title:"Ph.D.",name:"Yamin",middleName:null,surname:"Liu",slug:"yamin-liu",fullName:"Yamin Liu"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"7204",title:"Gene Expression and Regulation in Mammalian Cells",subtitle:"Transcription Toward the Establishment of Novel Therapeutics",isOpenForSubmission:!1,hash:"10030057b2e2dee7d800ff27658c3a69",slug:"gene-expression-and-regulation-in-mammalian-cells-transcription-toward-the-establishment-of-novel-therapeutics",bookSignature:"Fumiaki Uchiumi",coverURL:"https://cdn.intechopen.com/books/images_new/7204.jpg",editedByType:"Edited by",editors:[{id:"47235",title:"Dr.",name:"Fumiaki",middleName:null,surname:"Uchiumi",slug:"fumiaki-uchiumi",fullName:"Fumiaki Uchiumi"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"6435",title:"Gene Expression and Regulation in Mammalian Cells",subtitle:"Transcription From General Aspects",isOpenForSubmission:!1,hash:"8573c44c537def5c800a0f6d4ed844d6",slug:"gene-expression-and-regulation-in-mammalian-cells-transcription-from-general-aspects",bookSignature:"Fumiaki Uchiumi",coverURL:"https://cdn.intechopen.com/books/images_new/6435.jpg",editedByType:"Edited by",editors:[{id:"47235",title:"Dr.",name:"Fumiaki",middleName:null,surname:"Uchiumi",slug:"fumiaki-uchiumi",fullName:"Fumiaki Uchiumi"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"5784",title:"Antibody Engineering",subtitle:null,isOpenForSubmission:!1,hash:"2c8c3e133140fbc7f563918285e7c3c2",slug:"antibody-engineering",bookSignature:"Thomas Böldicke",coverURL:"https://cdn.intechopen.com/books/images_new/5784.jpg",editedByType:"Edited by",editors:[{id:"176804",title:"Dr.",name:"Thomas",middleName:null,surname:"Böldicke",slug:"thomas-boldicke",fullName:"Thomas Böldicke"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"5986",title:"The Role of Matrix Metalloproteinase in Human Body Pathologies",subtitle:null,isOpenForSubmission:!1,hash:"ef3e8940d7f0b229028d6fb71b1e0927",slug:"the-role-of-matrix-metalloproteinase-in-human-body-pathologies",bookSignature:"Francesco Travascio",coverURL:"https://cdn.intechopen.com/books/images_new/5986.jpg",editedByType:"Edited by",editors:[{id:"172239",title:"Dr.",name:"Francesco",middleName:null,surname:"Travascio",slug:"francesco-travascio",fullName:"Francesco Travascio"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"5817",title:"Embryo Cleavage",subtitle:null,isOpenForSubmission:!1,hash:"11de486fcf8fe42d4359c65e71a8f1da",slug:"embryo-cleavage",bookSignature:"Bin Wu",coverURL:"https://cdn.intechopen.com/books/images_new/5817.jpg",editedByType:"Edited by",editors:[{id:"108807",title:"Ph.D.",name:"Bin",middleName:null,surname:"Wu",slug:"bin-wu",fullName:"Bin Wu"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"4588",title:"New Discoveries in Embryology",subtitle:null,isOpenForSubmission:!1,hash:"2d40aace9724b9c451a8d8168acd0169",slug:"new-discoveries-in-embryology",bookSignature:"Bin Wu",coverURL:"https://cdn.intechopen.com/books/images_new/4588.jpg",editedByType:"Edited by",editors:[{id:"108807",title:"Ph.D.",name:"Bin",middleName:null,surname:"Wu",slug:"bin-wu",fullName:"Bin Wu"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"4594",title:"胚胎移植新进展",subtitle:"Advances in Embryo Transfer",isOpenForSubmission:!1,hash:"32b738c0d0cbce7a61a3ea63b5d43ed0",slug:"advances-in-embryo-transfer-translation-chinese",bookSignature:"Bin Wu",coverURL:"https://cdn.intechopen.com/books/images_new/4594.jpg",editedByType:"Edited by",editors:[{id:"108807",title:"Ph.D.",name:"Bin",middleName:null,surname:"Wu",slug:"bin-wu",fullName:"Bin Wu"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"1907",title:"Reviews on Selected Topics of Telomere Biology",subtitle:null,isOpenForSubmission:!1,hash:"5f4f25ba706645403bab2aa721a0809b",slug:"reviews-on-selected-topics-of-telomere-biology",bookSignature:"Bibo Li",coverURL:"https://cdn.intechopen.com/books/images_new/1907.jpg",editedByType:"Edited by",editors:[{id:"109879",title:"Dr.",name:"Bibo",middleName:null,surname:"Li",slug:"bibo-li",fullName:"Bibo Li"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}},{type:"book",id:"2518",title:"Binding Protein",subtitle:null,isOpenForSubmission:!1,hash:"6e70c7a9b0007d8f78ae4f3effba9664",slug:"binding-protein",bookSignature:"Kotb Abdelmohsen",coverURL:"https://cdn.intechopen.com/books/images_new/2518.jpg",editedByType:"Edited by",editors:[{id:"144861",title:"Dr.",name:"Kotb",middleName:null,surname:"Abdelmohsen",slug:"kotb-abdelmohsen",fullName:"Kotb Abdelmohsen"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter",authoredCaption:"Edited by"}}],booksByTopicTotal:31,mostCitedChapters:[{id:"38236",doi:"10.5772/50129",title:"Extrinsic and Intrinsic Apoptosis Signal Pathway Review",slug:"extrinsic-and-intrinsic-apoptosis-signal-pathway-review",totalDownloads:10544,totalCrossrefCites:33,totalDimensionsCites:61,book:{slug:"apoptosis-and-medicine",title:"Apoptosis and Medicine",fullTitle:"Apoptosis and Medicine"},signatures:"Zhao Hongmei",authors:[{id:"146795",title:"Dr.",name:"Zhao",middleName:null,surname:"Hongmei",slug:"zhao-hongmei",fullName:"Zhao Hongmei"}]},{id:"35489",doi:"10.5772/37107",title:"MM-GB(PB)SA Calculations of Protein-Ligand Binding Free Energies",slug:"mm-gb-pb-sa-calculations-of-protein-ligand-binding-free-energies",totalDownloads:8040,totalCrossrefCites:9,totalDimensionsCites:45,book:{slug:"molecular-dynamics-studies-of-synthetic-and-biological-macromolecules",title:"Molecular Dynamics",fullTitle:"Molecular Dynamics - Studies of Synthetic and Biological Macromolecules"},signatures:"Joseph M. Hayes and Georgios Archontis",authors:[{id:"102666",title:"Dr.",name:"Joseph",middleName:"M.",surname:"Hayes",slug:"joseph-hayes",fullName:"Joseph Hayes"},{id:"111282",title:"Prof.",name:"Georgios",middleName:null,surname:"Archontis",slug:"georgios-archontis",fullName:"Georgios Archontis"}]},{id:"38806",doi:"10.5772/48277",title:"Bacterial Two-Component Systems: Structures and Signaling Mechanisms",slug:"bacterial-two-component-systems-structures-and-signaling-mechanisms",totalDownloads:4694,totalCrossrefCites:14,totalDimensionsCites:28,book:{slug:"protein-phosphorylation-in-human-health",title:"Protein Phosphorylation in Human Health",fullTitle:"Protein Phosphorylation in Human Health"},signatures:"Shuishu Wang",authors:[{id:"141519",title:"Dr.",name:"Shuishu",middleName:null,surname:"Wang",slug:"shuishu-wang",fullName:"Shuishu Wang"}]}],mostDownloadedChaptersLast30Days:[{id:"62578",title:"DNA Polymorphisms: DNA-Based Molecular Markers and Their Application in Medicine",slug:"dna-polymorphisms-dna-based-molecular-markers-and-their-application-in-medicine",totalDownloads:3132,totalCrossrefCites:3,totalDimensionsCites:4,book:{slug:"genetic-diversity-and-disease-susceptibility",title:"Genetic Diversity and Disease Susceptibility",fullTitle:"Genetic Diversity and Disease Susceptibility"},signatures:"Salwa Teama",authors:[{id:"249329",title:"Dr.",name:"Salwa",middleName:null,surname:"Teama",slug:"salwa-teama",fullName:"Salwa Teama"}]},{id:"59173",title:"Separation of Monoclonal Antibodies by Analytical Size Exclusion Chromatography",slug:"separation-of-monoclonal-antibodies-by-analytical-size-exclusion-chromatography",totalDownloads:2846,totalCrossrefCites:0,totalDimensionsCites:2,book:{slug:"antibody-engineering",title:"Antibody Engineering",fullTitle:"Antibody Engineering"},signatures:"Atis Chakrabarti",authors:[{id:"199389",title:"Ph.D.",name:"Atis",middleName:null,surname:"Chakrabarti",slug:"atis-chakrabarti",fullName:"Atis Chakrabarti"}]},{id:"56481",title:"Detailed Protocols for the Selection of Antiviral Human Antibodies from Combinatorial Immune Phage Display Libraries",slug:"detailed-protocols-for-the-selection-of-antiviral-human-antibodies-from-combinatorial-immune-phage-d",totalDownloads:1369,totalCrossrefCites:0,totalDimensionsCites:0,book:{slug:"antibody-engineering",title:"Antibody Engineering",fullTitle:"Antibody Engineering"},signatures:"Philipp Diebolder and Adalbert Krawczyk",authors:[{id:"198001",title:"Dr.",name:"Adalbert",middleName:null,surname:"Krawczyk",slug:"adalbert-krawczyk",fullName:"Adalbert Krawczyk"},{id:"198002",title:"Dr.",name:"Philipp",middleName:null,surname:"Diebolder",slug:"philipp-diebolder",fullName:"Philipp Diebolder"}]},{id:"38804",title:"The Prp4 Kinase: Its Substrates, Function and Regulation in Pre-mRNA Splicing",slug:"the-prp4-kinase-its-substrates-function-and-regulation-in-pre-mrna-splicing",totalDownloads:2303,totalCrossrefCites:2,totalDimensionsCites:7,book:{slug:"protein-phosphorylation-in-human-health",title:"Protein Phosphorylation in Human Health",fullTitle:"Protein Phosphorylation in Human Health"},signatures:"Martin Lützelberger and Norbert F. Käufer",authors:[{id:"141382",title:"Prof.",name:"Norbert",middleName:"F.",surname:"Käufer",slug:"norbert-kaufer",fullName:"Norbert Käufer"},{id:"144512",title:"Dr.",name:"Martin",middleName:null,surname:"Lützelberger",slug:"martin-lutzelberger",fullName:"Martin Lützelberger"}]},{id:"49200",title:"Human Embryology",slug:"human-embryology",totalDownloads:2688,totalCrossrefCites:2,totalDimensionsCites:3,book:{slug:"new-discoveries-in-embryology",title:"New Discoveries in Embryology",fullTitle:"New Discoveries in Embryology"},signatures:"Shigehito Yamada, Mark Hill and Tetsuya Takakuwa",authors:[{id:"49486",title:"Prof.",name:"Shigehito",middleName:null,surname:"Yamada",slug:"shigehito-yamada",fullName:"Shigehito Yamada"},{id:"90205",title:"Prof.",name:"Tetsuya",middleName:null,surname:"Takakuwa",slug:"tetsuya-takakuwa",fullName:"Tetsuya Takakuwa"},{id:"175453",title:"Dr.",name:"Mark",middleName:null,surname:"Hill",slug:"mark-hill",fullName:"Mark Hill"}]},{id:"58467",title:"Generation of Antibody Diversity",slug:"generation-of-antibody-diversity",totalDownloads:2024,totalCrossrefCites:1,totalDimensionsCites:1,book:{slug:"antibody-engineering",title:"Antibody Engineering",fullTitle:"Antibody Engineering"},signatures:"Oliver Backhaus",authors:[{id:"177685",title:"M.Sc.",name:"Oliver",middleName:null,surname:"Backhaus",slug:"oliver-backhaus",fullName:"Oliver Backhaus"}]},{id:"40892",title:"Control of Telomere Length in Drosophila",slug:"control-of-telomere-length-in-drosophila",totalDownloads:1455,totalCrossrefCites:3,totalDimensionsCites:5,book:{slug:"reviews-on-selected-topics-of-telomere-biology",title:"Reviews on Selected Topics of Telomere Biology",fullTitle:"Reviews on Selected Topics of Telomere Biology"},signatures:"Sergey Shpiz and Alla Kalmykova",authors:[{id:"115829",title:"Dr.",name:"Alla",middleName:null,surname:"Kalmykova",slug:"alla-kalmykova",fullName:"Alla Kalmykova"},{id:"117877",title:"Dr.",name:"Sergey",middleName:null,surname:"Shpiz",slug:"sergey-shpiz",fullName:"Sergey Shpiz"}]},{id:"39204",title:"Modulation of Gene Expression by RNA Binding Proteins: mRNA Stability and Translation",slug:"modulation-of-gene-expression-by-rna-binding-proteins-mrna-stability-and-translation",totalDownloads:4940,totalCrossrefCites:2,totalDimensionsCites:6,book:{slug:"binding-protein",title:"Binding Protein",fullTitle:"Binding Protein"},signatures:"Kotb Abdelmohsen",authors:[{id:"144861",title:"Dr.",name:"Kotb",middleName:null,surname:"Abdelmohsen",slug:"kotb-abdelmohsen",fullName:"Kotb Abdelmohsen"}]},{id:"19303",title:"Archaeal DNA Repair Nucleases",slug:"archaeal-dna-repair-nucleases",totalDownloads:2322,totalCrossrefCites:0,totalDimensionsCites:0,book:{slug:"dna-repair-on-the-pathways-to-fixing-dna-damage-and-errors",title:"DNA Repair",fullTitle:"DNA Repair - On the Pathways to Fixing DNA Damage and Errors"},signatures:"Roxanne Lestini, Christophe Creze, Didier Flament, Hannu Myllykallio and Ghislaine Henneke",authors:[{id:"44844",title:"Dr.",name:"Hannu",middleName:null,surname:"Myllykallio",slug:"hannu-myllykallio",fullName:"Hannu Myllykallio"},{id:"51718",title:"Dr.",name:"Ghislaine",middleName:null,surname:"Henneke",slug:"ghislaine-henneke",fullName:"Ghislaine Henneke"},{id:"57263",title:"Dr.",name:"Rosane",middleName:null,surname:"Lestini",slug:"rosane-lestini",fullName:"Rosane Lestini"},{id:"57264",title:"Dr.",name:"Christophe",middleName:null,surname:"Creze",slug:"christophe-creze",fullName:"Christophe Creze"},{id:"57265",title:"Dr.",name:"Didier",middleName:null,surname:"Flament",slug:"didier-flament",fullName:"Didier Flament"}]},{id:"38242",title:"Cell Death and Cancer, Novel Therapeutic Strategies",slug:"cell-death-and-cancer-novel-therapeutic-strategies",totalDownloads:3117,totalCrossrefCites:3,totalDimensionsCites:4,book:{slug:"apoptosis-and-medicine",title:"Apoptosis and Medicine",fullTitle:"Apoptosis and Medicine"},signatures:"Silvina Grasso, M. Piedad Menéndez-Gutiérrez, Estefanía Carrasco-García, Leticia Mayor-López, Elena Tristante, Lourdes Rocamora-Reverte, Ángeles Gómez-Martínez, Pilar García-Morales, José A. Ferragut, Miguel Saceda and Isabel Martínez-Lacaci",authors:[{id:"145739",title:"Dr.",name:"Isabel",middleName:null,surname:"Martinez-Lacaci",slug:"isabel-martinez-lacaci",fullName:"Isabel Martinez-Lacaci"}]}],onlineFirstChaptersFilter:{topicSlug:"human-genetics",limit:3,offset:0},onlineFirstChaptersCollection:[],onlineFirstChaptersTotal:0},preDownload:{success:null,errors:{}},aboutIntechopen:{},privacyPolicy:{},peerReviewing:{},howOpenAccessPublishingWithIntechopenWorks:{},sponsorshipBooks:{sponsorshipBooks:[{type:"book",id:"10176",title:"Microgrids and Local Energy Systems",subtitle:null,isOpenForSubmission:!0,hash:"c32b4a5351a88f263074b0d0ca813a9c",slug:null,bookSignature:"Prof. Nick Jenkins",coverURL:"https://cdn.intechopen.com/books/images_new/10176.jpg",editedByType:null,editors:[{id:"55219",title:"Prof.",name:"Nick",middleName:null,surname:"Jenkins",slug:"nick-jenkins",fullName:"Nick Jenkins"}],equalEditorOne:null,equalEditorTwo:null,equalEditorThree:null,productType:{id:"1",chapterContentType:"chapter"}}],offset:8,limit:8,total:1},route:{name:"profile.detail",path:"/profiles/317288/inka-janna-janssen",hash:"",query:{},params:{id:"317288",slug:"inka-janna-janssen"},fullPath:"/profiles/317288/inka-janna-janssen",meta:{},from:{name:null,path:"/",hash:"",query:{},params:{},fullPath:"/",meta:{}}}},function(){var e;(e=document.currentScript||document.scripts[document.scripts.length-1]).parentNode.removeChild(e)}()