Efficient energy collection from photovoltaic (PV) systems in environments that change is still a challenge, especially when partial shading conditions (PSC) come into play. This research shows a new method called Maximum Power Point Tracking (MPPT) that uses fuzzy logic and neural networks to make PV systems more flexible and accurate when they are exposed to PSC. Our method uses a fuzzy logic controller (FLC) that is specifically made to deal with uncertainty and imprecision. This is different from other MPPT methods that have trouble with the nonlinearity and transient dynamics of PSC. At the same time, an artificial neural network (ANN) is taught to guess where the Global Maximum Power Point (GMPP) is most likely to be by looking at patterns of changes in irradiance and temperature from the past. The fuzzy controller fine-tunes the ANN’s prediction, ensuring robust and precise MPPT operation. We used MATLAB/Simulink to run a lot of simulations to make sure our proposed method would work. The results showed that combining fuzzy logic with neural networks is much better than using traditional MPPT algorithms in terms of speed, stability, and response to changing shading patterns. This innovative technique proposes a dual-layered control mechanism where the robustness of fuzzy logic and the predictive power of neural networks converge to form a resilient and efficient MPPT system, marking a significant advancement in PV technology.
In this paper, a hierarchical Arabic phoneme recognition system is proposed in which Mel Frequency Cepstrum Coefficients (MFCC) features is used to train the hierarchical neural networks architecture. Here, separate neural networks (subnetworks) are to be recursively trained to recognize subsets of phonemes. The overall recognition process is a combination of the outputs of these subnetworks. Experiments that explore the performance of the proposed hierarchical system in comparison to non-hierarchical (flat) baseline systems are also presented in this paper.
WiFi-based human activity and gesture recognition explore the interaction between the human hand or body movements and the reflected WiFi signals to identify various activities. This type of recognition has received much attention in recent years since it does not require wearing special sensors or installing cameras. This paper aims to investigate human activity and gesture recognition schemes that use Channel State Information (CSI) provided by WiFi devices. To achieve high accuracy in the measurement, deep learning models such as AlexNet, VGG 19, and SqueezeNet were used for classification and extracting features automatically. Firstly, outliers are removed from the amplitude of each CSI stream during the preprocessing stage by using the Hampel identifier algorithm. Next, the RGB images are created for each activity to feed as input to Deep Convolutional Neural Networks. After that, data augmentation is implemented to reduce the overfitting problems in deep learning models. Finally, the proposed method is evaluated on a publicly available dataset called WiAR, which contains 10 volunteers, each of whom executes 16 activities. The experiment results demonstrate that AlexNet, VGG19, and SqueezeNet all have high recognition accuracy of 99.17 %, 96.25%, and 100 %, respectively.
Epilepsy, a neurological disorder characterized by recurring seizures, necessitates early and precise detection for effective management. Deep learning techniques have emerged as powerful tools for analyzing complex medical data, specifically electroencephalogram (EEG) signals, advancing epileptic detection. This review comprehensively presents cutting-edge methodologies in deep learning-based epileptic detection systems. Beginning with an overview of epilepsy’s fundamental concepts and their implications for individuals and healthcare are present. This review then delves into deep learning principles and their application in processing EEG signals. Diverse research papers to know the architectures—convolutional neural networks, recurrent neural networks, and hybrid models—are investigated, emphasizing their strengths and limitations in detecting epilepsy. Preprocessing techniques for improving EEG data quality and reliability, such as noise reduction, artifact removal, and feature extraction, are discussed. Present performance evaluation metrics in epileptic detection, such as accuracy, sensitivity, specificity, and area under the curve, are provided. This review anticipates future directions by highlighting challenges such as dataset size and diversity, model interpretability, and integration with clinical decision support systems. Finally, this review demonstrates how deep learning can improve the precision, efficiency, and accessibility of early epileptic diagnosis. This advancement allows for more timely interventions and personalized treatment plans, potentially revolutionizing epilepsy management.
Bin picking robots require vision sensors capable of recognizing objects in the bin irrespective of the orientation and pose of the objects inside the bin. Bin picking systems are still a challenge to the robot vision research community due to the complexity of segmenting of occluded industrial objects as well as recognizing the segmented objects which have irregular shapes. In this paper a simple object recognition method is presented using singular value decomposition of the object image matrix and a functional link neural network for a bin picking vision system. The results of the functional link net are compared with that of a simple feed forward net. The network is trained using the error back propagation procedure. The proposed method is robust for recognition of objects.
In this paper a radial distribution feeder protection scheme against short circuit faults is introduced. It is based on utilizing the substation measured current signals in detecting faults and obtaining useful information about their types and locations. In order to facilitate important measurement signals features extraction such that better diagnosis of faults can be achieved, the discrete wavelet transform is exploited. The captured features are then utilized in detecting, identifying the faulted phases (fault type), and fault location. In case of a fault occurrence, the detection scheme will make a decision to trip out a circuit breaker residing at the feeder mains. This decision is made based on a criteria that is set to distinguish between the various system states in a reliable and accurate manner. After that, the fault type and location are predicted making use of the cascade forward neural networks learning and generalization capabilities. Useful information about the fault location can be obtained provided that the fault distance from source, as well as whether it resides on the main feeder or on one of the laterals can be predicted. By testing the functionality of the proposed scheme, it is found that the detection of faults is done fastly and reliably from the view point of power system protection relaying requirements. It also proves to overcome the complexities provided by the feeder structure to the accuracy of the identification process of fault types and locations. All the simulations and analysis are performed utilizing MATLAB R2016b version software package.
In this paper, a modified wavelet neural network (WNN) (or wavenet)-based predictor is introduced to predict link status (congestion with load indication) of each link in the computer network. On the contrary of previous wavenet-based predictors, the proposed modified wavenet-based link state predictor (MWBLSP) generates two indicating outputs for congestion and load status of each link based on th e premeasured power burden (square values) of utilization on each link in the previous time intervals. Fortunately, WNNs possess all learning and generalization capabilities of traditional neural networks. In addition, the ability of such WNNs are efficiently enhanced by the local characteristics of wavelet functions to deal with sudden changes and burst network load. The use of power burden utilization at the predictor input supports some non-linear distri butions of the predicted values in a more efficient manner. The proposed MWBLSP pre dictor can be used in the context of active congestion control and link load balancing techniques to improve the performance of all links in the network with best utilization of network resources.
Various methods have been exploited in the blind source separation problems, especially in cocktail party problems. The most commonly used method is the independent component analysis (ICA). Many linear and nonlinear ICA methods, such as the radial basis functions (RBF) and self-organizing map (SOM) methods utilise neural networks and genetic algorithms as optimisation methods. For the contrast function, most of the traditional methods, especially the neural networks, use the gradient descent as an objective function for the ICA method. Most of these methods trap in local minima and consume numerous computation requirements. Three metaheuristic optimisation methods, namely particle, quantum particle, and glowworm swarm optimisation methods are introduced in this study to enhance the existing ICA methods. The proposed methods exhibit better results in separation than those in the traditional methods according to the following separation quality measurements: signal-to-noise ratio, signal-to-interference ratio, log-likelihood ratio, perceptual evaluation speech quality and computation time. These methods effectively achieved an independent identical distribution condition when the sampling frequency of the signals is 8 kHz.
This work presents aneural and fuzzy based ECG signal recognition system based on wavelet transform. The suitable coefficients that can be used as a feature for each fuzzy network or neural network is found using a proposed best basis technique. Using the proposed best bases reduces the dimension of the input vector and hence reduces the complexity of the classifier. The fuzzy network and the neural network parameters are learned using back propagation algorithm.
Brain machine interface provides a communication channel between the human brain and an external device. Brain interfaces are studied to provide rehabilitation to patients with neurodegenerative diseases; such patients loose all communication pathways except for their sensory and cognitive functions. One of the possible rehabilitation methods for these patients is to provide a brain machine interface (BMI) for communication; the BMI uses the electrical activity of the brain detected by scalp EEG electrodes. Classification of EEG signals extracted during mental tasks is a technique for designing a BMI. In this paper a BMI design using five mental tasks from two subjects were studied, a combination of two tasks is studied per subject. An Elman recurrent neural network is proposed for classification of EEG signals. Two feature extraction algorithms using overlapped and non overlapped signal segments are analyzed. Principal component analysis is used for extracting features from the EEG signal segments. Classification performance of overlapping EEG signal segments is observed to be better in terms of average classification with a range of 78.5% to 100%, while the non overlapping EEG signal segments show better classification in terms of maximum classifications.
In recent years, artificial intelligence techniques such as wavelet neural network have been applied to control the speed of the BLDC motor drive. The BLDC motor is a multivariable and nonlinear system due to variations in stator resistance and moment of inertia. Therefore, it is not easy to obtain a good performance by applying conventional PID controller. The Recurrent Wavelet Neural Network (RWNN) is proposed, in this paper, with PID controller in parallel to produce a modified controller called RWNN-PID controller, which combines the capability of the artificial neural networks for learning from the BLDC motor drive and the capability of wavelet decomposition for identification and control of dynamic system and also having the ability of self-learning and self-adapting. The proposed controller is applied for controlling the speed of BLDC motor which provides a better performance than using conventional controllers with a wide range of speed. The parameters of the proposed controller are optimized using Particle Swarm Optimization (PSO) algorithm. The BLDC motor drive with RWNN-PID controller through simulation results proves a better in the performance and stability compared with using conventional PID and classical WNN-PID controllers.
Many assistive devices have been developed for visually impaired (VI) person in recent years which solve the problems that face VI person in his/her daily moving. Most of researches try to solve the obstacle avoidance or navigation problem, and others focus on assisting VI person to recognize the objects in his/her surrounding environment. However, a few of them integrate both navigation and recognition capabilities in their system. According to above needs, an assistive device is presented in this paper that achieves both capabilities to aid the VI person to (1) navigate safely from his/her current location (pose) to a desired destination in unknown environment, and (2) recognize his/her surrounding objects. The proposed system consists of the low cost sensors Neato XV-11 LiDAR, ultrasonic sensor, Raspberry pi camera (CameraPi), which are hold on a white cane. Hector SLAM based on 2D LiDAR is used to construct a 2D-map of unfamiliar environment. While A* path planning algorithm generates an optimal path on the given 2D hector map. Moreover, the temporary obstacles in front of VI person are detected by an ultrasonic sensor. The recognition system based on Convolution Neural Networks (CNN) technique is implemented in this work to predict object class besides enhance the navigation system. The interaction between the VI person and an assistive system is done by audio module (speech recognition and speech synthesis). The proposed system performance has been evaluated on various real-time experiments conducted in indoor scenarios, showing the efficiency of the proposed system.
The segmentation methods for image processing are studied in the presented work. Image segmentation can be defined as a vital step in digital image processing. Also, it is used in various applications including object co-segmentation, recognition tasks, medical imaging, content based image retrieval, object detection, machine vision and video surveillance. A lot of approaches were created for image segmentation. In addition, the main goal of segmentation is to facilitate and alter the image representation into something which is more important and simply to be analyzed. The approaches of image segmentation are splitting the images into a few parts on the basis of image’s features including texture, color, pixel intensity value and so on. With regard to the presented study, many approaches of image segmentation are reviewed and discussed. The techniques of segmentation might be categorized into six classes: First, thresholding segmentation techniques such as global thresholding (iterative thresholding, minimum error thresholding, otsu's, optimal thresholding, histogram concave analysis and entropy based thresholding), local thresholding (Sauvola’s approach, T.R Singh’s approach, Niblack’s approaches, Bernsen’s approach Bruckstein’s and Yanowitz method and Local Adaptive Automatic Binarization) and dynamic thresholding. Second, edge-based segmentation techniques such as gray-histogram technique, gradient based approach (laplacian of gaussian, differential coefficient approach, canny approach, prewitt approach, Roberts approach and sobel approach). Thirdly, region based segmentation approaches including Region growing techniques (seeded region growing (SRG), statistical region growing, unseeded region growing (UsRG)), also merging and region splitting approaches. Fourthly, clustering approaches, including soft clustering (fuzzy C-means clustering (FCM)) and hard clustering (K-means clustering). Fifth, deep neural network techniques such as convolution neural network, recurrent neural networks (RNNs), encoder-decoder and Auto encoder models and support vector machine. Finally, hybrid techniques such as evolutionary approaches, fuzzy logic and swarm intelligent (PSO and ABC techniques) and discusses the pros and cons of each method.
This paper deals with the application of Fuzzy-Neural Networks (FNNs) in multi-machine system control applied on hot steel rolling. The electrical drives that used in rolling system are a set of three-phase induction motors (IM) controlled by indirect field-oriented control (IFO). The fundamental goal of this type of control is to eliminate the coupling influence though the coordinate transformation in order to make the AC motor behaves like a separately excited DC motor. Then use Fuzzy-Neural Network in control the IM speed and the rolling plant. In this work MATLAB/SIMULINK models are proposed and implemented for the entire structures. Simulation results are presented to verify the effectiveness of the proposed control schemes. It is found that the proposed system is robust in that it eliminates the disturbances considerably.
PID controller is the most popular controller in many applications because of many advantages such as its high efficiency, low cost, and simple structure. But the main challenge is how the user can find the optimal values for its parameters. There are many intelligent methods are proposed to find the optimal values for the PID parameters, like neural networks, genetic algorithm, Ant colony and so on. In this work, the PID controllers are used in three different layers for generating suitable control signals for controlling the position of the UAV (x,y and z), the orientation of UAV (θ, Ø and ψ) and for the motors of the quadrotor to make it more stable and efficient for doing its mission. The particle swarm optimization (PSO) algorithm is proposed in this work. The PSO algorithm is applied to tune the parameters of proposed PID controllers for the three layers to optimize the performances of the controlled system with and without existences of disturbance to show how the designed controller will be robust. The proposed controllers are used to control UAV, and the MATLAB 2018b is used to simulate the controlled system. The simulation results show that, the proposed controllers structure for the quadrotor improve the performance of the UAV and enhance its stability.
In this paper a fully neural network-based structure have been proposed to control speeds of rolling stands of a steel rolling mill. The structure has property of controlling the motors speed such that the loop height between each successive stands tracks the required height reference. Synchronization between these stands is also maintained so that the metal flow rate from first stand to the last stand is kept constant. This structure is robust against the disturbance effects such as, torque loading, plant parameter change... etc. The results reveal performance of the structure as a comparison with the conventional control method for a practical worksheet data.
A composite PD and sliding mode neural network (NN)-based adaptive controller, for robotic manipulator trajectory tracking, is presented in this paper. The designed neural networks are exploited to approximate the robotics dynamics nonlinearities, and compensate its effect and this will enhance the performance of the filtered error based PD and sliding mode controller. Lyapunov theorem has been used to prove the stability of the system and the tracking error boundedness. The augmented Lyapunov function is used to derive the NN weights learning law. To reduce the effect of breaching the NN learning law excitation condition due to external disturbances and measurement noise; a modified learning law is suggested based on e-modification algorithm. The controller effectiveness is demonstrated through computer simulation of cylindrical robot manipulator.
nan
This paper applied an artificial intelligence technique to control Variable Speed in a wind generator system. One of these techniques is an offline Artificial Neural Network (ANN-based system identification methodology, and applied conventional proportional-integral-derivative (PID) controller). ANN-based model predictive (MPC) and remarks linearization (NARMA-L2) controllers are designed, and employed to manipulate Variable Speed in the wind technological knowledge system. All parameters of controllers are set up by the necessities of the controller's design. The effects show a neural local (NARMA-L2) can attribute even higher than PID. The settling time, upward jab time, and most overshoot of the response of NARMA-L2 is a notable deal an awful lot less than the corresponding factors for the accepted PID controller. The conclusion from this paper can be to utilize synthetic neural networks of industrial elements and sturdy manageable to be viewed as a dependable desire to normal modeling, simulation, and manipulation methodologies. The model developed in this paper can be used offline to structure and manufacturing points of conditions monitoring, faults detection, and troubles shooting for wind generation systems.
Data-intensive science is a critical science paradigm that interferes with all other sciences. Data mining (DM) is a powerful and useful technology with wide potential users focusing on important meaningful patterns and discovers a new knowledge from a collected dataset. Any predictive task in DM uses some attribute to classify an unknown class. Classification algorithms are a class of prominent mathematical techniques in DM. Constructing a model is the core aspect of such algorithms. However, their performance highly depends on the algorithm behavior upon manipulating data. Focusing on binarazaition as an approach for preprocessing, this paper analysis and evaluates different classification algorithms when construct a model based on accuracy in the classification task. The Mixed National Institute of Standards and Technology (MNIST) handwritten digits dataset provided by Yann LeCun has been used in evaluation. The paper focuses on machine learning approaches for handwritten digits detection. Machine learning establishes classification methods, such as K-Nearest Neighbor(KNN), Decision Tree (DT), and Neural Networks (NN). Results showed that the knowledge-based method, i.e. NN algorithm, is more accurate in determining the digits as it reduces the error rate. The implication of this evaluation is providing essential insights for computer scientists and practitioners for choosing the suitable DM technique that fit with their data.
In recent years, there has been a considerable rise in the applications in which object or image categorization is beneficial for example, analyzing medicinal images, assisting persons to organize their collections of photos, recognizing what is around self-driving vehicles, and many more. These applications necessitate accurately labeled datasets, in their majority involve an extensive diversity in the types of images, from cats or dogs to roads, landscapes, and so forth. The fundamental aim of image categorization is to predict the category or class for the input image by specifying to which it belongs. For human beings, this is not a considerable thing, however, learning computers to perceive represents a hard issue that has become a broad area of research interest, and both computer vision techniques and deep learning algorithms have evolved. Conventional techniques utilize local descriptors for finding likeness between images, however, nowadays; progress in technology has provided the utilization of deep learning algorithms, especially the Convolutional Neural Networks (CNNs) to auto-extract representative image patterns and features for classification The fundamental aim of this paper is to inspect and explain how to utilize the algorithms and technologies of deep learning to accurately classify a dataset of images into their respective categories and keep model structure complication to a minimum. To achieve this aim, must focus precisely and accurately on categorizing the objects or images into their respective categories with excellent results. And, specify the best deep learning-based models in image processing and categorization. The developed CNN-based models have been proposed and a lot of pre-training models such as (VGG19, DenseNet201, ResNet152V2, MobileNetV2, and InceptionV3) have been presented, and all these models are trained on the Caltech-101 and Caltech-256 datasets. Extensive and comparative experiments were conducted on this dataset, and the obtained results demonstrate the effectiveness of the proposed models. The obtained results demonstrate the effectiveness of the proposed models. The accuracy for Caltech-101 and Caltech-256 datasets was (98.06% and 90%) respectively.
In smart cities, health care, industrial production, and many other fields, the Internet of Things (IoT) have had significant success. Protected agriculture has numerous IoT applications, a highly effective style of modern agriculture development that uses artificial ways to manipulate climatic parameters such as temperature to create ideal circumstances for the growth of animals and plants. Convolutional Neural Networks (CNNs) is a deep learning approach that has made significant progress in image processing. From 2016 to the present, various applications for the automatic diagnosis of agricultural diseases, identifying plant pests, predicting the number of crops, etc., have been developed. This paper involves a presentation of the Internet of Things system in agriculture and its deep learning applications. It summarizes the most essential sensors used and methods of communication between them, in addition to the most important deep learning algorithms devoted to intelligent agriculture.
The problem of automatic signature recognition and verification has been extensively investigated due to the vitality of this field of research. Handwritten signatures are broadly used in daily life as a secure way for personal identification. In this paper a novel approach is proposed for handwritten signature recognition in an off-line environment based on Weightless Neural Network (WNN) and feature extraction. This type of neural networks (NN) is characterized by its simplicity in design and implementation. Whereas no weights, transfer functions and multipliers are required. Implementing the WNN needs only Random Access Memory (RAM) slices. Moreover, the whole process of training can be accomplished with few numbers of training samples and by presenting them once to the neural network. Employing the proposed approach in signature recognition area yields promising results with rates of 99.67% and 99.55% for recognition of signatures that the network has trained on and rejection of signatures that the network has not trained on, respectively.
In this paper, enhancing dynamic performance in power systems through load frequency control (LFC) is explored across diverse operating scenarios. A new Neural Network Model Predictive Controller (NN-MPC) specifically tailored for two-zone load frequency power systems is presented. ” Make your paper more scientific. The NN-MPC marries the predictive accuracy of neural networks with the robust capabilities of model predictive control, employing the nonlinear Levenberg-Marquardt method for optimization. Utilizing local area error deviation as feedback, the proposed controller’s efficacy is tested against a spectrum of operational conditions and systemic variations. Comparative simulations with a Fuzzy Logic Controller (FLC) reveal the proposed NN-MPC’s superior performance, underscoring its potential as a formidable solution in power system regulation.
The electrical consumption in Basra is extremely nonlinear; so forecasting the monthly required of electrical consumption in this city is very useful and critical issue. In this Article an intelligent techniques have been proposed to predict the demand of electrical consumption of Basra city. Intelligent techniques including ANN and Neuro-fuzzy structured trained. The result obtained had been compared with conventional Box-Jenkins models (ARIMA models) as a statistical method used in time series analysis. ARIMA (Autoregressive integrated moving average) is one of the statistical models that utilized in time series prediction during the last several decades. Neuro- Fuzzy Modeling was used to build the prediction system, which give effective in improving the predict operation efficiency. To train the prediction system, a historical data were used. The data representing the monthly electric consumption in Basra city during the period from (Jan 2005 to Dec 2011). The data utilized to compare the proposed model and the forecasting of demand for the subsequent two years (Jan 2012-Dec 2013). The results give the efficiency of proposed methodology and show the good performance of the proposed Neuro-fuzzy method compared with the traditional ARIMA method.
The brain tumors are among the common deadly illness that requires early, reliable detection techniques, current identification, and imaging methods that depend on the decisions of neuro-specialists and radiologists who can make possible human error. This takes time to manually identify a brain tumor. This work aims to design an intelligent model capable of diagnosing and predicting the severity of magnetic resonance imaging (MRI) brain tumors to make an accurate decision. The main contribution is achieved by adopting a new multiclass classifier approach based on a collected real database with new proposed features that reflect the precise situation of the disease. In this work, two artificial neural networks (ANNs) methods namely, Feed Forward Back Propagation neural network (FFBPNN) and support vector machine (SVM), used to expectations the level of brain tumors. The results show that the prediction result by the (FFBPN) network will be better than the other method in time record to reach an automatic classification with classification accuracy was 97% for 3-class which is considered excellent accuracy. The software simulation and results of this work have been implemented via MATLAB (R2012b).
This article introduces a novel Quantum-inspired Future Search Algorithm (QFSA), an innovative amalgamation of the classical Future Search Algorithm (FSA) and principles of quantum mechanics. The QFSA was formulated to enhance both exploration and exploitation capabilities, aiming to pinpoint the optimal solution more effectively. A rigorous evaluation was conducted using seven distinct benchmark functions, and the results were juxtaposed with five renowned algorithms from existing literature. Quantitatively, the QFSA outperformed its counterparts in a majority of the tested scenarios, indicating its superior efficiency and reliability. In the subsequent phase, the utility of QFSA was explored in the realm of fault detection in underground power cables. An Artificial Neural Network (ANN) was devised to identify and categorize faults in these cables. By integrating QFSA with ANN, a hybrid model, QFSA-ANN, was developed to optimize the network’s structure. The dataset, curated from MATLAB simulations, comprised diverse fault types at varying distances. The ANN structure had two primary units: one for fault location and another for detection. These units were fed with nine input parameters, including phase- currents and voltages, current and voltage values from zero sequences, and voltage angles from negative sequences. The optimal architecture of the ANN was determined by varying the number of neurons in the first and second hidden layers and fine-tuning the learning rate. To assert the efficacy of the QFSA-ANN model, it was tested under multiple fault conditions. A comparative analysis with established methods in the literature further accentuated its robustness in terms of fault detection and location accuracy. this research not only augments the field of search algorithms with QFSA but also showcases its practical application in enhancing fault detection in power distribution systems. Quantitative metrics, detailed in the main article, solidify the claim of QFSA-ANN’s superiority over conventional methods.