Search

This paper focuses on the development of a Graphical User Interface (GUI) and Artificial Neural Network (ANN) for the prediction of photovoltaic (PV) power output. PV power is generated based on the time, location, and surrounding climate conditions. Therefore, solar power generation predictions using computational methods are needed since the changing weather, which will impact the output power will not generate according to its rating. The objectives of this research are to predict photovoltaic power output at Universiti Tun Hussein Onn Malaysia (UTHM), develop an ANN configuration that can perform the prediction of solar power generation, and design GUI system that can both perform the calculations of power generation and ANN. In order to test the efficiency and reliability, MATLAB software has been used to develop the GUI and ANN, and the output is compared with the proposed mathematical equations. The real data as input data was obtained from the PV solar panel located at GSEnergy Focus Group fertigation site. The GUI with user-friendly features and ANN have been successfully designed and developed which can perform daily prediction of solar power output. On top of that, the results have shown that the ANN predictions are more precise to the real data than the GUI. [ABSTRACT FROM AUTHOR]

Through the use of malware, particularly JavaScript, cybercriminals have turned online applications into one of their main targets for impersonation. Detection of such dangerous code in real-time, therefore, becomes crucial in order to prevent any harmful action. By categorizing the salient characteristics of the malicious code, this study suggests an effective technique for identifying malicious Java scripts that were previously unknown, employing an interceptor on the client side. By employing the wrapper approach for dimensionality reduction, a feature subset was generated. In this paper, we propose an approach for handling the malware detection task in imbalanced data situations. Our approach utilizes two main imbalanced solutions namely, Synthetic Minority Over Sampling Technique (SMOTE) and Tomek Links with the object of augmenting the data and then applying a Deep Neural Network (DNN) for classifying the scripts. The conducted experiments demonstrate the efficient performance of our approach and it achieves an accuracy of 94.00%. [ABSTRACT FROM AUTHOR]

The rapid increase in the number of medical image repositories nowadays has led to problems in managing and retrieving medical visual data. This has proved the necessity of Content-Based Image Retrieval (CBIR) with the aim of facilitating the investigation of such medical imagery. One of the most serious challenges that require special attention is the representational quality of the embeddings generated by the retrieval pipelines. These embeddings should include global and local features to obtain more useful information from the input data. To fill this gap, in this paper, we propose a CBIR framework that utilizes the power of deep neural networks to efficiently classify and fetch the most related medical images with respect to a query image. Our proposed model is based on combining Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs) and learns to capture both the locality and also the globality of high-level feature maps. Our method is trained to encode the images in the database and outputs a ranking list containing the most similar image to the least similar one to the query. To conduct our experiments, an intermodal dataset containing ten classes with five different modalities is used to train and assess the proposed framework. The results show an average classification accuracy of 95.32 % and a mean average precision of 0.61. Our proposed framework can be very effective in retrieving multimodal medical images with the images of different organs in the body. [ABSTRACT FROM AUTHOR]

Curse of dimensionality is one of the biggest challenges in classification problems. High dimensionality of problem increases classification rate and brings about classification error. Selecting an effective subset of features is an important point in analyzing correlation rate in classification issues. The main purpose of this paper is enhancing characters recognition and classification, creating quick and low-cost classes, and eventually recognizing Persian handwritten characters more accurately and faster. In this paper, to reduce feature dimensionality of datasets, a hybrid approach using artificial neural network, genetic algorithm and quantum genetic algorithm is proposed that can be used to distinguish Persian handwritten letters. Implementation results show that proposed algorithms are able to reduce number of features by 19% to 49%. They also show that recognition and classification accuracy of resulted subset of features has risen, by 7/31%, comparing to primitive dataset. [ABSTRACT FROM AUTHOR]

Designing nonlinear optimal controllers such as Minimum Variance Controller (MVC) has many difficulties. Main difficulties are 1) in order to design controller; the explicit relations between outputs and inputs must be executable. This relation is defined as implicitly in the nonlinear models; 2) learning controller is a high dimensional-multimodal optimization task and search space can be extremely rugged and has many local minima. In this paper, in order to overcome these disadvantages, the model-free optimal controller scheme is utilized. In a model-free controller, as the system model is not available, the gradient of the cost function cannot be executed. Instead, in this paper, a relation between gradient of the controller with gradient of the system model is derived by inverse lemma. The controller structure is selected to be neural network. Then, the gradient based PSO (GPSO) is proposed to be a learning controller. GPSO has both advantages of global searching and convergence properties. The application of the methodology to the empirical CSTR model indicates that this approach gives very credible estimates of the controller. The simulation results indicate that the proposed method can be more accurate than existing methods. [ABSTRACT FROM AUTHOR]

Automatic classification of electrocardiogram (ECG) arrhythmias is essential to timely and early diagnosis of conditions of the heart. In this paper, a new method for ECG arrhythmias classification using Wavelet Transform (WT) and neural networks (NN) is proposed. Here, we have used a discrete Wavelet Transform (DWT) for processing ECG recordings, and extracting some time-frequency features. In addition, we have combined the features extracted by DWT with ECG morphology and heartbeat interval features, to obtain our final set of features to be used for training a Multi-Layer Perceptron (MLP) neural network. The MLP Neural Network performs the classification task. In recent years, many algorithms have been proposed and discussed for arrhythmias detection. the results reported in them, have generally been limited to relatively small set of data patterns. In this paper 26 recordings of the MIT-BIH arrhythmias database have been used for training and testing our neural network based classifier. The simulation results of best structure show that the classification accuracy of the proposed method is 94.72% over 360 patterns using 26 files including normal and five arrhythmias. [ABSTRACT FROM AUTHOR]

Diabetes is the costliest gland disease in the world. Given the high rates of diabetic people, the necessity of reducing the costs of early re-hospitalization and increasing re-admissions within 30 days after discharge have drawn the attention of researchers and other health sector authorities to find ways to reduce potential and preventable hospital re-admissions. The objective of this paper is to estimate the risk of re-hospitalization of diabetic patients. In order to achieve this goal, the data were first pre-processed, and then, radial base function neural network combined with colonial competition optimization algorithm was used to estimate the risk of re-hospitalization of diabetic patients. Moreover, this risk was estimated using back propagation neural network algorithm and the radial base function neural network algorithm. The accuracy of the proposed method is 99.91. This method shows higher performance compared to radial base function neural network method and back propagation neural network without feature selection. [ABSTRACT FROM AUTHOR]

Rolling mill Industry is one of the most profitable industries in the world. Chatter phenomenon is one of the key issues in this industry. Chatter or rolling unwanted vibrations not only has an adverse effect on product quality, but also reduces considerably the efficiency with reduced rolling velocities of rolling lines. This paper is an attempt to simulate the phenomenon of Chatter more accurate than the previous performed simulations. In order to increase the production speed, it needs to avoid parameters which effect on the Chatter and varieties with the rolling lines condition. Actual values of these parameters were determined in the archives of the Mobarakeh two stand cold rolling mills and collected on the 210 case study of real chattering. To simulate the experiment, a neural network is trained and weights and bias values of the neural network with genetic optimization algorithm were used to get an optimal neural network which reduces bugs on the test data. So this model is capable to predict speed of Chatter threshold on rolling process of two stand cold rolling mill with the accuracy less than one percent. So it can be used in rolling process with the building intelligent recognition systems to prevent the creator conditions of the chatter frequency range. [ABSTRACT FROM AUTHOR]

This paper presents a computational study on the dynamic of nitric oxide (NO) in both the biological and artificial environments, by the analysis of important nitric oxide diffusion attributes. We apply the compartmental model of NO diffusion as a formal tool, using a computational neuroscience point of view. The main objective is the analyses of the emergence and dynamic of complex structures, essentially diffusion neighbourhood (DNB), in environments with volume transmission (VT). The study is performed by the observation of the NO diffusion attributes, the NO directionality (NOD), the average influence (AI) and the center of DNB (CDNB). We present a study of the influences and dependences with respect to associated features to the NO synthesis-diffusion process, and to the different environments where it spreads (non-isotropy and non-homogeneity). The paper is structured into three sets of experiences which cover the aforementioned aspects: influence of the NO synthesis process, isolated and multiple processes, influence of distance to the element where NO is synthesized, and influence of features of the diffusion environment. The developments have been performed in mono bi-and three-dimensional environments, with endothelial cell features. The study contributes the needed formalism to management the dynamic of NO in artificial and biological environments also to quantify the information representation capacity that a type of NO diffusion-based signaling presents and their implications in many other underlying neural mechanisms, such as neural recruitment, synchronization of computations between neurons and in the brain activity in general. [ABSTRACT FROM AUTHOR]

The direct force thrust control (DTFC) is linear type of the direct torque control (DTC) method. The advantages of DTFC method are structure simplicity, low dependency to motor parameters and no requirement to coordination transformations. In this paper this method is modified in order to eliminate the defects that include the switching frequency and exciting large ripples of force and flux. In previous works, the structure simplicity of DTC, rare calculations to reduce the force ripples and fixing switching frequency are disaffirmed. With regards to keeping DTC advantages, a new method is presented in this paper to eliminate the defects by the aid of neural network. Also, the precise non-linear behavior of PMLSM motor in DTC has been considered by using space vector modulation. Finally, the simulation results concluded by the submitted intelligent DTC-SVM method are more satisfactory than other methods. [ABSTRACT FROM AUTHOR]

This paper proposes a unified neural network controller in development of series active power filter. Three major power quality problems considered for this work are harmonics, sags, and interruptions, and dealing with all of them really needs effective unified algorithm which could adapt with variation of signals. Therefore, Levenberg-Marquardt (L-M) back propagation algorithm is introduced in this controller which helps the proposed controller to work properly with dynamic responses with appropriate achievement of convergence. Simulation results clearly show high performance of the proposed controller with series APF system. Its ability of adaptive estimating enhances the response time of the system to only one cycle. It performs well under various testing conditions with significant reduction of harmonics, correction of sags, and fast response to interruptions. [ABSTRACT FROM AUTHOR]

In this paper we present a nonlinear optimal control method based on approximating the solution of Hamilton-Jacobi-Bellman (HJB) equation. Value function is approximated as the output of Multilayer Perceptron Neural Network (MLPNN). Parameters of MLPNN are weights and biases of each layer that form structure of the proposed neural network. These parameters are unknown thus we apply an Adaptive Extended Kalman Filter to approximate unknown parameters. In so doing, the problem of solution of HJB equation is converted to estimation of MLPNN parameters. Also, convergence of the estimation error of MLPNN parameters is proven. Two examples have been brought to show the merits of the proposed approach and to compare the obtained results by applying the multilayer Perceptron and the Radial Basic Function Neural Network (RBFNN). [ABSTRACT FROM AUTHOR]

Rolling mill Industry is one of the most profitable industries in the world. Chatter phenomenon is one of the key issues in this industry. Chatter or rolling unwanted vibrations not only has an adverse effect on product quality, but also reduces considerably the efficiency with reduced rolling velocities of rolling lines. This paper is an attempt to simulate the phenomenon of Chatter more accurate than the previous performed simulations. In order to increase the production speed, it needs to avoid parameters which effect on the Chatter and varieties with the rolling lines condition. Actual values of these parameters were determined in the archives of the Mobarakeh two stand cold rolling mills and collected on the 210 case study of real chattering. To simulate the experiment, a neural network is trained and weights and bias values of the neural network with genetic optimization algorithm were used to get an optimal neural network which reduces bugs on the test data. So this model is capable to predict speed of Chatter threshold on rolling process of two stand cold rolling mill with the accuracy less than one percent. So it can be used in rolling process with the building intelligent recognition systems to prevent the creator conditions of the chatter frequency range. [ABSTRACT FROM AUTHOR]

Prostate cancer is one of the leading causes of death by cancer among men in the world. Ultrasonography is said to be the safest technique in medical imaging so it is used extensively in prostate cancer detection. On the other hand, determining of prostate's boundary in TRUS (Transrectal Ultrasound) images is very necessary in lots of treatment methods prostate cancer. So the first and essential step for computer aided diagnosis (CAD) is the automatic prostate segmentation that is an open problem yet. But the low SNR, presence of strong speckle noise, Weak edges and shadow artifacts in these kinds of images limit the effectiveness of classical segmentation schemes. The classical segmentation methods fail completely or require post processing step to remove invalid object boundaries in the segmentation results. This paper has proposed a fully automatic algorithm for prostate segmentation in TRUS images that overcomes the explained problems completely. The presented algorithm contains three main stages. First, morphological smoothing and stick's filter are used for noise removing. A neural network is employed in the second step to find a point in prostate region. Finally in the last step, the prostate boundaries are extracted by GVF active contour. Some experiments for the performance validity of the presented method, compared with the extracted prostate by the proposed algorithm with manually-delineated boundaries by radiologist. The results show that our method extracts prostate boundaries with mean square area error lower than 4.4%. [ABSTRACT FROM AUTHOR]

In this article the electrical parameters of the induction motor are estimated by measuring temperature of its components. This process consists of four sections: 1-Thermal resistance model 2- Electrical parameters 3- Electrical model and 4- Neural network which presents motor parameters and operational status compatible with corresponding learning data. In thermal resistance model, we use physical and geometrical properties of motor components to formulate thermal resistance of each component of the motor. In electrical model, electrical losses are calculated by electrical variables, by relationship between electrical losses and thermal resistance ,these modelesgives us corresponding temperatures as output. These temperatures were used for training network (temperatures as input data, stator current and maximum torque as target data) in the neural network. After measuring temperatures of the components and using them as inputs to neural network, the corresponding stator current and maximum torque (target data) are estimated. All the stator currents referred to this paper were validated by experimental measurements. [ABSTRACT FROM AUTHOR]

In this paper, an auto tuned load frequency controller based on Fuzzy Wavelet Neural Network (FWNN) and Shuffled Frog Leaping Algorithm (SFLA) is employed to damp the deviations of frequency and tie line power due to the load disturbances in a multi-area power system. Optimal tuning of the FWNN parameters is very important to improve the design performance and achieve a satisfactory level of robustness, for a particular operation. In this work, a new systematic tuning method is developed for designing the FWNN load frequency controller. For this, the error between the desired system output and output of control object is employed to tune the FWNN parameters. Tuning rule is accomplished based on SFLA approach by minimizing a combination of control error. To show the effectiveness of the proposed method, some numerical results are presented for a two area power system considering governor saturation and the results are compared to the obtained results by a classic PI controller and a fuzzy load frequency controller. Moreover, the robustness of the proposed method is tested against change of parameters. The simulation studies show that the designed controller by proposed method has a very desirable dynamic performance, better operation and improved system parameters such as settling time and step response rise time even when the system parameters change. [ABSTRACT FROM AUTHOR]

In this paper an approach is presented for edge detection of noisy images that have been degraded by impulsive noise. It uses Fuzzy Inference System (FIS) and Ant Colony Optimization (ACO). Starting with, using the FIS with 12 simple rules is to identify the noisy pixels in order to perform the filtering operation only for the noisy pixels. Probable edge pixels in 4 main directions for filtered image are detected using fuzzy rules and then ACO is applied by assigning a higher pheromone value for the probable edge pixels rather than other pixels so that the ant's movement toward edge pixels gets faster. Another factor is the influence of the heuristic information in the movement of any ant that is considered to be proportional to local change in intensity of each pixel in order to the possibility of movement of ants increased toward pixels that have more change in their local intensity. Finally, by using an intelligent thresholding technique which is provided by training a neural network, the edges from the final pheromone matrix are extracted. Experimental results are provided in order to demonstrate the superior performance of the proposed approach. [ABSTRACT FROM AUTHOR]

In this paper, a hybrid of Neural Network (NN) and Fast Traversal Filter (FTF) based controller in each area is used to determine the optimal parameters of Load Frequency Control (LFC) of a realistic two area power system. The two area power system is modeled considering the various non -linearities like governor dead band, generation rate constraint (GRC) and boiler dynamics. Input to the controller i.e. the error signal is divided into two parts- linear and non- linear. The linear part of the input signal is minimized by the FTF algorithm, whereas the non- linear part is minimized by the NN algorithm. The output of the controller is the sum of the outputs of NN and FTF networks. The proposed hybrid controller requires less number of samples for training of weights, thus making the system fast. This is highly desirable in power quality problems. The various components of power system are reduced to transfer functions and the system performance is analyzed for 1% step load perturbation in area1 with different controllersproportional and integral (PI), neural network (NN) and NN+FTF based controllers. The simulations demonstrate the fast and smooth performance of the power system with the proposed controller. Simulated results evince the superiority of the proposed hybrid controller. [ABSTRACT FROM AUTHOR]

The demand for RFID tags has recently increased due to the development of the RFID. Over the past decade, great efforts have been devoted to the design of RFID tags without chip inside. The concept of chipless RFID tags appears to be a promising solution for low cost item tagging because the cost of active RFID tag depends mainly on the chip used in them. This paper presents the progress of the chipless RFID tag and introduces major studies in this filed. Advantages and disadvantages of these methods are pointed out. [ABSTRACT FROM AUTHOR]

In this paper, investigation is carried out for the improvement of power system stability by utilizing auxiliary controls for controlling HVDC power flow. The current controller model and the line dynamics are considered in the stability analysis. Transient stability analysis is done on a multi-machine system, where, a neural network controller is developed to improve the stability of the power system and to improve the response time of the controller to the changing conditions in power system. The results show the application of the neural network controller in AC-DC power systems. [ABSTRACT FROM AUTHOR]

A biometric system provides automatic identification of an individual based on unique features or characteristics possessed by that person. Iris recognition is regarded as one of the most reliable and accurate available biometric systems. This paper proposes an efficient iris recognition system that employs a novel method to localize the iris region on the eye,s image based on approximating the iris radius using the pupil characteristics and cumulative sum based on gray change analysis to extract features from the normalized iris template. Fuzzy ARTMAP neural network is also applied to classify the iris codes. The results of simulations on a set of 756 eyes' images illustrated a fast, accurate and noise resistant personal identification system. The proposed system achieved zero false acceptance rate using 1800-bit binary iris codes and recognized all authorized users with 100% accuracy. [ABSTRACT FROM AUTHOR]

Accurate liver segmentation on Magnetic Resonance Images (MRI) is a challenging task especially at sites where surrounding tissues such as spleen and kidney have densities similar to that of the liver and lesions reside at the liver edges. The first and essential step for computer aided diagnosis (CAD) is the automatic liver segmentation that is still an open problem. Extensive research has been performed for liver segmentation; however it is still challenging to distinguish which algorithm produces more precise segmentation results to various medical images. In this paper, we have presented a new automatic system for liver segmentation in abdominal MRI images. Our method extracts liver regions based on several successive steps. The preprocessing stage is applied for image enhancement such as edge preserved and noise reduction. The proposed algorithm for liver segmentation is a combined algorithm which utilizes a contour algorithm with a Vector Field Convolution (VFC) field as its external force and perceptron neural network. By convolving the edge map generated from the image with the user-defined vector field kernel, VFC is calculated. We use trained neural networks to extract some features from liver region. The extracted features are used to find initial point for starting VFC algorithm. This system was applied to a series of test images to extract liver region. Experimental results showed the promise of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Active queue control aims to improve the overall communication network throughput, while providing lower delay and small packet loss rate. The basic idea is to actively trigger packet dropping (or marking provided by explicit congestion notification (ECN)) before buffer overflow. In this paper, two artificial neural networks (ANN)-based control schemes are proposed for adaptive queue control in TCP communication networks. The structure of these controllers is optimized using genetic algorithm (GA) and the output weights of ANNs are optimized using particle swarm optimization (PSO) algorithm. The controllers are radial bias function (RBF)-based, but to improve the robustness of RBF controller, an error-integral term is added to RBF equation in the second scheme. Experimental results show that GA- PSO-optimized improved RBF (I-RBF) model controls network congestion effectively in terms of link utilization with a low packet loss rate and outperforms Drop Tail, proportional-integral (PI), random exponential marking (REM), and adaptive random early detection (ARED) controllers. [ABSTRACT FROM AUTHOR]

Intrusion Detection System (IDS) deals with a very large amount of data that includes redundant and irrelevant features. Therefore, feature selection is a necessary data pre-processing step to design IDSs that are lightweight. In this paper, a novel feature selection method based on data mining techniques is proposed, which uses fuzzy association rules to obtain the optimum feature subset. In this research, the fuzzy ARTMAP neural network is used as the classifier to evaluate the goodness of the obtained feature subset. The effectiveness of proposed method is evaluated by experiments on KDD Cup99 dataset. According to the performance comparisons with some other machine learning methods that have used the same dataset, the proposed method is the most efficient on detection rate, false alarm rate and cost per example. [ABSTRACT FROM AUTHOR]

A brain computer interface (BCI) records the activation of the brain and classifies it into different classes. BCIs can be used by both severely motor disabled as well as healthy people to control devices. The study addresses the development and application of a novel medical technology to measure a patient's brain activity, translated it with intelligent software, and uses the translated signals to drive patient-specific effectors. In this work, the EEG pattern recognition approach is used based on brain computer interfaces for moving hands right and left. Electroencephalographic (EEG) signals produced by the brain were used as input to the proposed BCI system. There are two BCI approaches used in this paper; the offline BCI approach and the online BCI approach. In the offline approach, the Dataset of motor imagery EEG recordings is used, while in the online approach we used our own BCI system to capture EEG recordings. The practical online testing demonstrates the feasibility of using the proposed system with the ability of real-time processing, automatic analysis. The Principle Component Analysis (PCA) is used for both artifact removal and feature extraction. Wavelet Transformation is also developed to extract the important information from EEG recordings. The K-Nearest-Neighbor (KNN) and Neural Networks (NNs) classifiers were used to find out what the user wants. The results show that we can effectively classify two kinds of tasks based on both BCI approaches with best predictive accuracy of 99.2% for offline approach and 98 % for online approach when wavelet transform and Neural Networks used together. This gives an ideal solution for people with severe neuromuscular disorders, such as Amyotrophic Lateral Sclerosis (ALS) or spinal cord injury, people who are totally paralyzed, or "locked-in", help them to have a communication channel with others. [ABSTRACT FROM AUTHOR]

The increased use of nonlinear devices in the industry has resulted in the direct increase of harmonic distortion in power systems during these last years. Active filter systems are proposed to mitigate current harmonics generated by nonlinear loads. The conventional scheme based on a two-level voltage source inverter controlled by a hysteresis controller has several disadvantages and cannot be used for medium or high-power applications. To overcome these drawbacks and improve the APF performance, there's a great tendency to use multilevel inverters controlled by intelligent controllers. Three level (NPC) inverter is one of the most widely used topologies in various industrial applications such as machine drives and power factor compensators. On the other hand, artificial neural networks are under study and investigation in other power electronics applications. In order to gain the advantages of the three-level inverter and artificial neural networks and to reduce the complexity of classical control schemes, a new active power filter configuration controlled by two MLPNN (Multi-Layer Perceptron Neural Network) is proposed in this paper. The first ANN is used to replace the PWM current controller, and the second one to maintain a constant dc link voltage across the capacitors and compensate the inverter power losses. The performance of the global system, including power and control circuits is evaluated by Matlab-Simulink and SimPowerSystem Toolbox simulation. The obtained results confirm the effectiveness of the proposed control scheme. [ABSTRACT FROM AUTHOR]

Uncontrolled energization of large power transformers may result in magnetizing inrush current of high amplitude and switching over-voltages. The most effective method for the limitation of the switching over-voltages is controlled switching since the magnitudes of the produced transients are strongly dependent on the closing instants of the switch. We introduce a harmonic index that its minimum value is corresponding to the best-case switching time. Also, this paper presents an Artificial Neural Network (ANN)-based approach to estimate the optimum switching instants for real time applications. In the proposed ANN, second order Levenberg-Marquardt method is used to train the multilayer perceptron. ANN training is performed based on equivalent circuit parameters of the network. Thus, trained ANN is applicable to every studied system. To verify the effectiveness of the proposed index and accuracy of the ANN-based approach, two case studies are presented and demonstrated. [ABSTRACT FROM AUTHOR]

In this paper a license plate detection and recognition system for Iranian private cars is implemented. The proposed license plate localization algorithm is based on region elements analysis which works properly independent of distance (how far a vehicle is), rotation (angle between camera and vehicle), and contrast (being dirty, reflected, or deformed). In addition, more than one car may exist in the image. The proposed method extracts edges and then determines the candidate regions by applying window movement. The region elements analysis includes binarization, character analysis, character continuity analysis and character parallelism analysis. After detecting license plates, we estimate the rotation angle and try to compensate it. In order to identify a detected plate, every character should be recognized. For this purpose, we present 25 features and use them as the input to an artificial neural network classifier. The experimental results show that our proposed method achieves appropriate performance for both detection and recognition of the Iranian license plates. [ABSTRACT FROM AUTHOR]

The number of attacks in computer networks has grown extensively, and many new intrusive methods have been appeared. Intrusion detection is known as an effective method to secure the information and communication systems. In this paper, the performance of Elman and partial-connected dynamic neural network (PCDNN) architectures are investigated for misuse detection in computer networks. To select the most significant features, logistic regression is also used to rank the input features of mentioned neural networks (NNs) based on the Chi-square values for different selected subsets in this work. In addition, genetic algorithm (GA) is used as an optimization search scheme to determine the sub-optimal architecture of investigated NNs with selected input features. International knowledge discovery and data mining group (KDD) dataset is used for training and test of the mentioned models in this study. The features of KDD data are categorized as basic, content, time-based traffic, and host-based traffic features. Empirical results show that PCDNN with selected input features and categorized input connections offers better detection rate (DR) among the investigated models. The mentioned NN also performs better in terms of cost per example (CPE) when compared to other proposed models in this study. False alarm rate (FAR) of the PCDNN with selected input features and categorized input connections is better than other proposed models, as well. [ABSTRACT FROM AUTHOR]

This paper presents the comparative performance of neuro- Fuzzy controlled Voltage Source Converters (VSC) based Flexible AC Transmission System (FACTS) devices, such as Static Synchronous Series Compensator (SSSC), Static Synchronous Compensator (STATCOM), and Unified Power Flow Controller (UPFC) in terms of improvement in transient stability. In neuro-fuzzy control method the simplicity of fuzzy systems and the ability of training in neural networks have been combined. The training data set the parameters of membership functions in fuzzy controller. This Adaptive Network Fuzzy Inference System (ANFIS) can track the given input-output data in order to conform to the desired controller. The maximization of energy function of UPFC is used as an objective function to generate the training data. Proposed method is tested on a single machine infinitive bus system to confirm its performance through simulation. The results prove the noticeable influence of ANFIS controlled UPFC on increasing Critical Clearing Time (CCT) of system. [ABSTRACT FROM AUTHOR]

Knowledge embedded within artificial neural networks (ANNs) is distributed over the connections and weights of neurons. So, the user considers ANN as a black box system. There are many researches investigating the area of rule extraction by ANNs. In this paper, a dynamic cell structure (DCS) neural network and a modified version of LERX algorithm are used for rule extraction. On the other hand, intrusion detection system (IDS) is known as a critical technology to secure computer networks. So, the proposed algorithm is used to develop IDS and classify the patterns of intrusion. To compare the performance of the proposed system with other machine learning algorithms, multi-layer perceptron (MLP) with output weight optimization-hidden weight optimization (OWO-HWO) training algorithm is employed with selected inputs based on the results of a feature relevance analysis. Empirical results show the superior performance of the IDS based on rule extraction from DCS, in recognizing hard-detectable attack categories, e.g. userto- root (U2R) and also offering competitive false alarm rate (FAR). Although, MLP with 25 selected input features, instead of 41 standard features introduced by knowledge discovery and data mining group (KDD), performs better in terms of detection rate (DR) and cost per example (CPE) when compared with some other machine learning methods, as well. [ABSTRACT FROM AUTHOR]

Nowadays using DG (distributed generation) in vast variety of cases has been more considerable due to its beneficial advantages, but interconnecting DG to radial distribution systems has some impact on the coordination of protection devices. The main point in the protection scheme is the diagnosis of fault locations, so producing a new method to identify fault location with high accuracy is necessary. This paper presents a novel approach to fault location identification with DG in distributed systems by the means of neural networks. According to this method using a distributed system as intentional islanding in necessary conditions is possible and reduces the ENS (Energy Not Supplied) of the net. Using separate NNs (neural networks) for each island (zone) will increase the accuracy of this method. Implementation results of this scheme on actual distributed systems has been simulated and reported. [ABSTRACT FROM AUTHOR]

In this paper a very intelligent tool with low computational complexity is presented for Electroencephalogram (ECG) signal classification. The proposed classifier is based on Discrete Wavelet Transform (DWT) and Probabilistic Neural Network (PNN). The novelty of this approach is that signal statistics, morphological analysis and DWT of the histogram of signal (density estimation) altogether have been used to achieve a higher recognition rate. ECG signals and their density estimation are decomposed into sub-classes using DWT. A PNN is used to classify ECG signals using statistical discriminating features which are extracted from ECG and its sub-classes. Experimental results on five classes of ECG signals from MIT-BIH arrhythmia database show that the proposed method learns very fast, low computational complexity, and a very high performance compared to the previous methods. [ABSTRACT FROM AUTHOR]

In this paper a neuro-fuzzy controller is proposed to enhance transient stability and increase critical clearing time (CCT) in the static synchronous compensator (STATCOM). For achieving this idea, first the controller is designed based on the Lyapunov energy function. In order to avoid complexity of computation and overcome system uncertainty a neuro-fuzzy controller is proposed. In this controller, Neural network determines the system rules and membership functions. In order to design a neural network and its training patterns, the energy function controller is used under various system conditions. This controller has learning abilities due to its robust fuzzy controller and neural network. Simulation results on the single-machine infinite-bus (SMIB) show that the neuro-fuzzy controller damps electromechanical oscillations and increases the critical clearing time. [ABSTRACT FROM AUTHOR]

In this paper, the signal-to-noise ratio (SNR) of dynamic communication channels, using a radial basis function (RBF) neural network with time-delay structure, is estimated. The exactitude of the estimation is sufficient for systems which are based on link adaptation techniques. The proposed system for estimating SNR doesn't demand on having any prior knowledge about transmitted symbols. This feature of the proposed model results to save system resources. This saving is one of the benefits of proposed estimator as compared to transmitted data aided (TxDA) estimators. The performance index of the system, in terms of normalized mean squared error (NMSE) criterion, is achieved less than 0.001 for practical applications. [ABSTRACT FROM AUTHOR]