Search

The IETE Journal of Research's first issue of Volume 70 covers a wide range of topics in communications, electromagnetics, opto-electronics, computers and computing, control engineering, electronic circuits, devices and components, instrumentation and measurement, medical electronics, and power electronics. The articles in this issue discuss various subjects, including improved network performance in wireless sensor networks, machine learning-based classification of cervical cancer, optimal energy reduction in 5G communication systems, and secure data transmission in the Internet of Things. The issue also includes papers on photonic sensors, detection of diabetic retinopathy, optimisation models for home health care scheduling and wind-integrated power systems, and efficient task scheduling in cloud computing environments. One research paper introduces a smartwatch-based machine learning model for monitoring epilepsy and detecting seizures, achieving a high accuracy of 99.40% in cross-validation. The document provides a summary of articles published in the journal, with authors who are experts in their fields and provide experimental findings and simulations to support their research. [Extracted from the article]

The Coronavirus disease, i.e. (COVID-19) pandemic outbreaks has inevitably lead to a corresponding movement restrictive measure by the members of both central and state government leadership. The current limitation of healthcare systems cannot predict the COVID-19 outbreaks and vaccination drive. The need of the hour is to use Blockchain Technology for the construction of immutable ledger. In this paper a Blockchain and Artificial Intelligence (AI) enabled COVID-19 vaccine tracking system has been proposed. The proposed system is designed using the Ethereum Virtual Machine (EVM), decentralized storage by Inter Planetary File System (IPFS) and implemented using Truffle and Ganache Tool. The smart contract interaction among the entities is developed with Drizzle and the front-end using ReactJS. The performance of the proposed framework has been presented with Keccack 256 transaction hash, the total number of transactions, gas consumed by each contract. Additionally the performance parameters such as latency, throughput, traffic in, out, CPU, and memory utilization of the blockchain framework are also calculated. The artificial neural network (ANN) has been used to classify the vaccination group. Such an attempt is a worthwhile addition to the state of the art as evident from the results presented herein. The proposed framework provides a way for vaccinated members of the community to be tracked and indexed so as to avail the benefits, for example, less restrictive movements nationally, internationally, or simply in their own respective communities. This paper leverages the advantages of Blockchain Technology to obtain a reliable and accurate way to facilitate the entire tracking process. [ABSTRACT FROM AUTHOR]

An Artificial Neural Network (ANN) based Substrate Integrated Waveguide Band Pass Filter (SIW BPF) is proposed in this paper. A Feed Forward Back Propagation Neural Network (FF-BP NN) is utilized to optimize the filter dimensions. The Gradient Descent with Momentum and Adaptive Learning Rate algorithm is used to train the network at a learning rate of 0.01. The high pass characteristics of the SIW is converted into band pass by incorporating U slots on its top plane. Defected Ground Structure (DGS) is utilized in the bottom plane to improve the impedance matching. To validate, the prototype is fabricated using RT/Duroid 5880 and tested. The proposed filter has a center frequency at 14.68 GHz with a wide pass band from 12.92 to 16.43 GHz with a 3-dB Fractional Bandwidth (FBW) of 24%, return loss more than 20 dB and insertion loss of about 1.9 dB within the pass band. The filter has a small dimension of about 0.63 $ \lambda _g^2 $ λ g 2 , where λg is the guided wavelength at the center frequency. This filter offers wide passband, smaller size, low insertion loss, good return loss and it is useful in Ku-band satellite communication applications. [ABSTRACT FROM AUTHOR]

Children without obvious disabilities (hearing loss/low intellectual capacity) may have language skill development issues due to specific language impairment (SLI), a communication disorder. The SLI has a significant impact on a child's speaking, listening, reading, and writing abilities. SLI is typically known as development language disorder, developmental dysphasia, or language delay. Recently, machine learning as well as deep learning techniques have been quite effective in predicting the early stage of SLI, analyzing the disorder severity, and predicting the treatment efficiency. Existing approaches primarily exploited auditory indicators to diagnose communication disorders, frequently leaving out hidden information acquired in the temporal domain. To overcome this drawback, an optimized Bidirectional Long Short Term Memory (BiLSTM) architecture is presented in this paper to handle the speech dynamics. The Improved Hybrid Aquila Optimizer and Flow Directional algorithm known as IHAOFDA is integrated with the BiLSTM architecture to optimize the hyperparameters of the BiLSTM structure. When assessed using the information from the SLI children in the Laboratory of Artificial Neural Network Applications (LANNA) dataset, the proposed model performs better. The IHAOFDA-optimized BiLSTM architecture improves accuracy in classifying different severity levels such as mild, moderate, and severe. [ABSTRACT FROM AUTHOR]

Data security concerns safeguarding the data from unauthorized users. Numerous research works have been conducted using Reversible Data Hiding (RDH) technique, but not been found to be fooproof. In this paper, a novel reversible data hiding method, based on an Artificial Neural Network, called Histogram Transpose and Naor Pseduorandom Arnold (HT-NPA) data security system for handling health care reports and securely transferring patient information, is proposed to evaluate the embedding capacity, improve the visual quality of the recovered image and ensure security via duplex scramble. This entire process is performed by means of an Artificial Neural Network (i.e. multilayer perceptron). The experimental results reveal that the HT-NPA performs better with 29%, 16%, 19%, and 9% improvement in embedding rate, PSNR, SSIM, entropy, and NPCR, and 26% reduction of bit error rate, respectively for retrieved medical images compared to existing works. [ABSTRACT FROM AUTHOR]

Multimedia security is important as privacy and protection has to be ensured when images from military, medical and other confidential services are sent through the unprotected channel. In this paper, an attempt to develop reconfigurable hardware for an encryption scheme using FPGA has been carried out and tested successfully for its features. In this proposed encryption scheme, chaos and a novel artificial neural network-based diffusion have been used along with zig-zag permutation for pixel level and novel enhanced Fisher-Yates permutation for bit level. The ANN is composed of additive and multiplicative convolution and the 2D cellular automata as an activation function for diffusion. A novel key generation algorithm is adopted to produce the key values for generating the chaos sequence. Every image gets a new key, hence differential attack possibility is negligible. The encryption algorithm is designed in MATLAB and coded in Verilog HDL to develop it as reconfigurable hardware. The hamming distance is analyzed to know the difference between the key sequence generated. The average hamming distance is 0.5111 and the highest value is 0.8796 to show that the randomness of the sequence. Similarly, equidistribution, autocorrelation and periodicity analysis are performed. The NIST SP 800–22 randomness test was also performed on keys and encrypted images to analyze its randomness. The results obtained from the encryption process are tested for their efficiency related to statistical and differential attacks. It gives better results when compared with a few encryption algorithms in the literature. [ABSTRACT FROM AUTHOR]

The current issue of the IETE Journal of Research (Volume 69 Number 12, December 2023) contains seventy articles covering various fields of technology and engineering. These articles discuss topics such as error rate analysis, antenna development, optical DEMUX, computer science, and engineering. Each paper presents a unique study or proposal, highlighting methodologies, techniques, and findings. The articles cover a wide range of topics, including IoT security, keyphrase extraction, deep learning, object detection, emotion recognition, insulin dose prediction, antenna array synthesis, cardiac MRI segmentation, fire detection systems, fault detection in rolling bearings, medical image processing, and optimization techniques for photovoltaic systems. The authors of these articles are experts in their respective fields and have made significant contributions to their areas of study. [Extracted from the article]

Lung cancer is a disease caused by a spontaneous proliferation of cells in the lung tissue. It is very important to detect cancer cells in the lungs that release oxygen to the human body and carbon dioxide in the body as a result of vital functions. Hence, in this paper, Novel Hybrid Deep Learning Model (HDLM) and Fuzzy C Means Clustering Method (FCM) are developed for Pulmonary Nodule Detection in CT Images. The HDLM is a combination of a Deep Neural Network (DNN) and an Arithmetic Optimization Algorithm (AOA). In the HDLM, the weight parameters are selected with the help of the AOA algorithm. The proposed methodology is working based on four phases: pre-processing phase, candidate nodule detection phase, feature extraction phase, and classification phase. In the pre-processing phase, the median filter is utilized to remove unwanted features from the input image. In the candidate module detection phase, FCM is utilized for reducing computational complexity and speeding up nodule detection. In the feature extraction phase, intensity-based features are utilized such as first-order statistics and second-order statistics. The first-order statistics are considered various features such as mean, variance, entropy, energy, and skewness. The second-order statistics are considered as gray level co-occurrence matrix (GLCM) features. At last, the HDLM is utilized in the classification phase which is used to reduce the false-positive result and improve the overall sensitivity of the system. The proposed methodology is evaluated by performance metrics and compared with conventional methods. [ABSTRACT FROM AUTHOR]

The standard communication protocols transfer big data over the internet. However, the challenge lies while sharing the massive amount of genomics data quickly over limited bandwidth networks. Managed File Transfer (MFT) that uses File Transfer Protocol Secure (FTPS) or Secure Shell File Transfer Protocol (SFTP) is a scalable and secure alternative for the purpose. This paper proposes a framework consisting of a Variable-length Genomic Binary Encoding (VGBE) scheme and a hybrid Gated Recurrent Unit-Convolutional Neural Network model (GRU-CNN). The Method exploits Managed File Transfer to reduce the bit size before transmission and increases the bit rate during the transmission of genomics data. Consequently, the method ensures a minimum number of bits per word and less latency. The methodology is tested on various communication protocols. It is validated in terms of performance metrics viz. transfer rate and the size of transferred data using diverse benchmark datasets such as protein sequences and human reference genome taken from the University of California Santa Cruz (UCSC) and National Center for Biotechnology Information (NCBI), respectively. Furthermore, simulation and implementation results show that the model is 98% faster, has 96% less data size, and is more secure than standard communication protocols. Thus, the proposed method is an efficient and secure genomics data transfer method using deep learning techniques. [ABSTRACT FROM AUTHOR]

The authors of the paper titled "Towards Neuro-Fuzzy Compensated PID Control of Lower Extremity Exoskeleton System for Passive Gait Rehabilitation" designed a neuro-fuzzy compensated PID control for passive gait rehabilitation using a lower extremity exoskeleton system. In the paper "A Comparative Survey of Convex Combination of Adaptive Filters", the authors evaluate the convex combination of adaptive filters, which are mostly based on the least mean square (LMS) algorithm, the affine projection (AP) algorithm, and the recursive least mean square (RLS) algorithm. The paper "A Novel Weighted Superposition Attraction Algorithm-based Optimization Approach for State of Charge and Power Management of an Islanded System with Battery and Super Capacitor-based Hybrid Energy Storage System" proposes a Hybrid Energy Storage System (HESS) employing a Battery and a Super Capacitor (SC). The authors of the paper titled "Computer-Aided Detection and Diagnosis of Thyroid Nodules Using Machine and Deep Learning Classification Algorithms" propose a computer-assisted method for detecting and segmenting tumour regions in ultrasound thyroid images using machine and deep learning classification algorithms. [Extracted from the article]

Wearable devices equipped with a multitude of compact, lightweight, biometric sensors are helpful in tracking the real-time physiological data for healthcare-related analysis. However, a survey of devices under the smart-wearable market segment revealed that the contemporary focus is limited to capturing and displaying some of the biometrics like pulse rate, movement of the user, calorie counter, etc. on a smart screen. Employing machine learning techniques can be particularly helpful in analyzing the trends of user-specific biometric data for pre-emptive actions. This paper presents a meaningful analysis in real-time by using machine learning approaches to interpret this physiological data and alert the user about his behavioral pattern through IoT. This research focuses on classifying the mood of the user as agitated or non-agitated, by analyzing the biometrics to help the user decipher meaningful conclusions and take suitable pre-emptive measures to refrain from any unintentional impulsive outburst. Machine learning algorithms like Polynomial regression with threshold, Decision Tree, Random Forest ensemble and variants of Deep Neural Networks (DNN) have been employed to analyse the biometric patterns from the experimental data acquired under different circumstances and detect the user's mood to assign a score to the user. The proposed approach uses a reinforcement learning algorithm to calibrate the user's current temperament by taking intermediate user feedback and comparing the score with the temperament. The results reveal that the proposed system detects the user's mood fluctuations with higher accuracy and relevance compared to any contemporary model. [ABSTRACT FROM AUTHOR]

Global solar radiation is variable in nature, hence its forecasting is very important. This paper aims to predict the global solar radiations using real experimental data collected over time by developing time series based neural networks in MATLAB. In this research work three models are developed, one for the daily prediction of global solar radiations and two for the hourly (with and without night times) prediction of the global solar radiations. The results obtained are evaluated using statistical analysis which confirmed that nonlinear autoregressive models are a good choice for predicting the global solar radiations. The regression coefficient was found high in the case of hourly prediction (including night hours) followed by hourly prediction (excluding night hours) and daily prediction (after averaging) respectively. The value of the best validation performance for hourly prediction (including night hours) was found 0.060887 with a regression coefficient of 0.96481. To further validate the applicability of the proposed algorithm, the model was compared with four time-series models developed in Waikato Environment for Knowledge Analysis. The results confirmed the high efficiency of our proposed models among others, based on the performance parameters root mean square error and mean Absolute error. The root mean square error for our proposed model came 1.28 which is the lowest as compared to other time series models. Also, the accuracy of the hourly prediction model was found higher as compared to daily prediction models. Further, the critical analysis of our method with various available methods in the literature is also discussed. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to analyze the frequent power quality (PQ) issues happening in distributed generation, the outcomes of the PQ harmonics, the methods used to assess the quantity of harmonic distortion which occurs in the power system (PS), and, in the end, classification of these disturbances using recent advance artificial intelligent techniques like a neural network, fuzzy logic, and the genetic algorithm has been further stated. To protect the PS detection and classification of voltage (V) and current (I) issues are essential tasks and due to increasing interest in a distributed generation, it is becoming more popular. Most PQ disturbances are unstable and ephemeral especially in a distributed generation; therefore, the call for detection and classification of voltage and current disruptions are essential tasks to protect the PS. Many disturbances of (PQ are unpredictable and transient. By using wavelet transforms, expert systems, and artificial neural networks, some intelligent system technologies control fault analysis precisely saying it can help to detect the fault locations. The most important part of the generalized classification system of PQ events is the extraction and classification of features for PQ event classification. [ABSTRACT FROM AUTHOR]

The second paper, titled "Design and Analysis of Zeta Converter for Power Factor Correction using Cascade PSO-GSA Tuned PI and Reduced-Order SMC" describes a single-phase power factor correction method employing a DCDC Zeta converter in continuous conduction mode.To increase converter performance, it presents a non-linear cascade control of particle swarm optimization-gravitational search algorithm (PSO-GSA) tuned proportional-integral and sliding mode controller in outer and inner loops. In particular, an optimisation framework is developed that accounts for several processes, including data gathering from various sources, KPI description, and the optimisation procedure itself. Wind farm plan optimization or WFLOP, is a difficult optimisation problem with many constraints. Heuristic optimisation techniques outperformed standard methods in the study. [Extracted from the article]

Deep neural networks (DNN) oblige large preprocessed samples of training annotated images for successful training, which makes the approach costly particularly in the biomedical imaging domain. The data augmentation technique is regularly used by researchers to enlarge the volume of training data, creating, and producing augmented data capable to train the network about the essential properties of uniformity and stoutness. The use of conventional methods of data augmentation in most training system scenarios strictly restrict its capabilities and negatively impact the output accuracy. In this paper, we propose an automatic data augmentation technique for synthesizing high-quality brain tumor images using generative adversarial network architecture to facilitate deep learning-based methods to be trained with the limited preprocessed samples more competently. The tumor segmentation has been performed through geodesic active contour via a level set formulation. The proposed technique has been validated with different modalities of magnetic resonance imaging brain image obtained from BRATS13 datasets. Simulational results showed an enhanced performance yielding a dice similarity coefficient of 0.942. [ABSTRACT FROM AUTHOR]

The paper presents a robust design of Artificial Neural Network Classifier used for the classification of faults occurring on Extra High Voltage Transmission lines with multiple series compensation. The feature selection and model parameters play a vital role in providing better accuracy as well as stability of Classifier in recognition of fault patterns. The paper describes the use of Particle Swarm Optimization (PSO)-assisted training of Artificial Neural Network (ANN). The PSO is used to find the optimal number of features to attain sufficiently high accuracy along with optimal design parameters of ANN so as to reduce the computational burden. A combined use of Multiresolution Wavelet Analysis (MRA) and Statistical Features (SF) module is shown for fault pattern analysis. A Particle Swarm optimization based Neural Network with Feature Selection (PSONNFS) Algorithm developed is applied on a large database of fault patterns with a wide range of operating conditions in series compensated system. The best features found from the PSONNFS algorithm are later used to find the optimal structure of ANN. The results obtained provide an enhanced model of ANN with a high degree of accuracy with optimality in Classifier parameters. A Genetic Algorithm based Neural Network optimization with Feature Selection (GANNFS) is also developed to verify the performance of the classifier. The results of the PSONNFS algorithm are further compared with the GANNFS algorithm. The results obtained show an enhanced model of ANN using PSONNFS which has a high degree of accuracy with optimality in Classifier parameters. [ABSTRACT FROM AUTHOR]

This paper presents the design and implementation of three-phase four-wire shunt active power filter (SAPF). It consists of insulated gate bipolar transistors, IGBT based current-controlled voltage source inverter (CC-VSI), series coupling inductor and self-supported DC bus. Power electronics based converters and non-linear loads generate waveform-driven power quality issue as harmonics. Three-phase four-wire SAPF mitigates harmonics, compensates for reactive power, neutral current and power factor correction. Conventionally, the positive sequence detection control strategy using phase-locked loop (PLL) is applied as the synchronizing unit vector element to generate reference source currents. Conventional controller tuning process is difficult and fails to perform satisfactorily under supply voltage variation conditions. In this paper, Levenberg-Marquardt back propagation training algorithm based artificial neural network (ANN) controller is proposed to regulate DC link voltage due to its self-adapting and rapid calculation characteristics that allow the controller to handle high nonlinearity and uncertainty in a non-linear system. Weights of a neuron are adapted to minimize total harmonic distortion (THD) of source current under the step, ramp, time series amplitude variation and frequency and amplitude of modulation conditions. The proposed system is modelled in MATLAB/SIMULINK environment and laboratory prototype with dSpace1104 control card is developed. Experimentation results validate the simulated results of the proposed scheme under supply voltage variations for three-phase four-wire distribution system. [ABSTRACT FROM AUTHOR]

The components include E-shape single element slot antenna, Wilkinson Power Divider, Hybrid Directional Coupler, Loaded Line Phase Shifter, and Switched Line Phase Shifter. The following paper on "An Optimized DTW Algorithm using RMSE Approach to Classify the Liquids in Ka-Band", presents an algorithm to classify liquids with high level accuracy using transmission parameter of liquids with microwave spectroscopy. The authors study four types of textile antennas with wash cotton and denim substrate and compare the performance with standard substrate antenna for circular polarization, gain and return loss. The algorithm uses Dissolved Gas Analysis samples from real power transformers and genetic algorithm based fuzzy classifier. [Extracted from the article]

Electroencephalogram (EEG) can track the brain waves which contain the neural activity of the brain. EEG signals help to understand the physiological and functional details and activities of the brain. In the era of Artificial Intelligence (AI), machine learning algorithms were useful in brain disorder detection and classification. Recently, a rapid increase in using Deep Learning (DL) methods in various applications in EEG signals not only helps in the detection of brain disorders but also facilitates the recognition of human emotions and various psycho-neuro disorders. In order to offer a beneficial and broad perspective, a detailed survey on the application of deep learning architecture in EEG signals has been carried out in this paper. Different deep learning methods, using varied architecture in EEG signal analysis, offer an understanding to develop the next level of AI-based systems. This review will provide information about how deep learning methods are used in EEG signals and the challenges and limitations of each method in classification; moreover making it helpful for those who are exploring EEG signals using DL algorithms. [ABSTRACT FROM AUTHOR]

Diseases is an unusual circumstance that affects single or more parts of a human's body. Because of lifestyle and patrimonial, different kinds of disease are increasing day by day. Among all those diseases, heart disease turns out to be the most common disease and the impact of this ailment is dangerous than all other diseases. In this paper, we compared a number of computational intelligence techniques for the prediction of coronary artery heart disease. Seven computational intelligence techniques named as Logistic Regression (LR), Support Vector Machine (SVM), Deep Neural Network (DNN), Decision Tree (DT), Naïve Bayes (NB), Random Forest (RF), and K-Nearest Neighbor (K-NN) were applied and a comparative study was drawn. The performance of each technique was evaluated using Statlog and Cleveland heart disease dataset which are retrieved from the UCI machine learning repository database with several evaluation techniques. From the study, it can be carried out that the highest accuracy of 98.15% obtained by deep neural network with sensitivity and precision 98.67% and 98.01% respectively. The outcomes of the study were compared with the outcomes of the state of the art focusing on heart disease prediction that outperforms the previous study. [ABSTRACT FROM AUTHOR]

The plant diseases cause damage and monetary losses in crops. The farmers monitor the crops in the field at regular intervals in order to detect various diseases. Instead of manual diagnosis, computers have been used to provide automatic detection and classification of different types of diseases. In this paper, the lesion areas affected by diseases are segmented. Further, discrete wavelet transform based image fusion technique is used to improve the imaging quality reducing redundancy. The colour, texture and structural based features of the fused images are extracted and given as an input to the ANN for classification which provides better performance. [ABSTRACT FROM AUTHOR]

In view of the recent development and phenomenal growth in the field of electrical/power engineering, various new enhanced and sophisticated power control techniques have emerged which have got the enormous capabilities to produce the desired power in the most efficient and effective manner. This paper presents the permanent magnet synchronous generator (PMSG) connected to the wind turbine to extract the maximum power using the integral sliding mode control technique and artificial neural network (ANN). The real power produced by the generator is directly dependent on the internal characteristic of the wind turbine like TSR (tip speed ratio), Power Coefficient, etc. To extract the maximum power from the wind turbine, it has been depicted that ANN a is more efficient and reliable form than the sliding mode control technique. [ABSTRACT FROM AUTHOR]

In this paper, parallel ant-lion optimizer (ALO) and artificial neural network (ANN) for the micro-grid (MG) connected system with AC load is proposed. The proposed algorithm is the combined performance of ALO type I and II algorithms. The aim of the proposed algorithm is to increase the power transfer capability between the source and load sides and to offer several benefits like enhanced predicting capability, degradation in complexity, and randomization. ALO type I is utilized for active power controller parameter optimization with enhanced searching behaviour like crossover and mutation. Using the ALO type II, the reactive power controller parameters' optimization is performed with online predictor ANN. The exact control signals of the power controller are determined based on the system power deviations using the parallel operation of the algorithms. With the performance of the proposed controller, the power exchange is enhanced and ensured between the sources to load. The implementation is done by the MATLAB/Simulink platform. The performance of the proposed method is analysed using comparison analysis with the existing techniques. [ABSTRACT FROM AUTHOR]

In this paper, the design of a novel efficient QCA-based universal logic gate (ULG) is presented. Compact and efficient implementation layout with only one clock phase delay and also the implementation of the 13 standard functions without extra ULG or gate are the advantages of the proposed ULG. The results show that the proposed ULG is an efficient tool in designing any QCA circuit. Also, an accurate artificial neural network (ANN) model of the proposed ULG is presented. This model can be simply imported into any circuit simulators such as HSPICE, MATLAB Simulink and etc., for modeling and simulation of QCA circuits at the Gate level with high precision in a short time. [ABSTRACT FROM AUTHOR]

This paper emphasizes on the hand movement recognition using artificial neural network (ANN). It shows the methodology that analyses and classifies the electromyography (EMG) signals using neural networks to control multifunction prostheses. The control of these prostheses can be made using myoelectric signals taken from surface electrodes. The linear neural network was employed in the EMG signal classification system as EMG signals contain many artifacts and noise, so linear classification helps to give the accurate classification results which can be further used for myoelectric controls. The experimental results show a promising performance in the classification of hand movements based on EMG pattern. The hand movements used were Flexion and Extension of wrist, Flexion and Extension of elbow, Closing and opening of hand, and the Supination and Pronation of forearm. [ABSTRACT FROM AUTHOR]

This paper presents the hybridized fuzzy-neural predictive intelligent (HFNPI) based approach for predicting FinFET model. The proposed model is an improved approach over artificial neural network (ANN) model and adaptive neuro fuzzy inference system (ANFIS) model that provides optimum model parameters. In this paper, the challenge of optimization of large number of parameters is reduced. It assesses the performance of resultant structure on the basis of selected RF figure-of-merit. Based on the application requirements, RF figure-of-merit such as fT and fmax are used as appropriate performance parameters to analyse the device performance. The framework for the HFNPI model is underlapped FinFET structural/process parameters. The mean prediction error was found 2.8 × 10−4 GHz. The comparative analysis of HFNPI with ANN and ANFIS model is done. It is found that combination of fuzzy and neural logic shows better result rather than individual ANFIS and ANN model to redevelop the model and increase the number of inputs. [ABSTRACT FROM AUTHOR]

Modification of process parameters of the Fin shaped Field Effect Transistor (FinFET) is the field of research which has drawn attention after it has been inferred that these transistors diminish the leakage effects, which occur in planar transistors. The research paper presents a novel approach in which Artificial Neural Network (ANN) and Genetic Algorithm (GA) have been combined to optimize the structure of 14 nm Dual Gate Material Dual Gate Dielectric Material Heterojunction (DGMDGDM-Hetero) Silicon On Insulator (SOI) FinFET. The dataset mandatory for the training of ANN has been obtained through designing and simulating the DGMDGDM-Hetero SOI FinFET structure by varying the Si1-xGex height (HSiGe) and mole fraction (MFSiGe) in TCAD simulator. Through GA optimization, the optimal value of HSiGe and MFSiGe for which minimum Subthreshold Swing (SS), off-current (Id,off), Drain-Induced-Barrier-Lowering (DIBL) along with maximum on-current (Id,on) and Id,on–Id,off ratio achieved have been discovered. The considered FinFET structure was designed and simulated with optimal value of HSiGe and MFSiGe which resulted in ultimate best performance parameters. DIBL and leakage of 15.8 mV/V and 1.37 × 10−17A respectively, suggesting that DGMDGDM-Hetero SOI FinFET has more control over undesired Short Channel Effects (SCEs). Only 1.4% difference in the value of ANN-GA optimized and TCAD simulated performance parameters substantiate the effectiveness of optimization process. [ABSTRACT FROM AUTHOR]

This paper clarifies the optimal control strategy of Hybrid Renewable Energy System (HRES), which has the parallel execution of Lightning Search algorithm with Artificial Neural Network and Recurrent Neural Network (PLSANN). The projected system is composed of Photovoltaic (PV), Wind Turbine (WT), Fuel Cell (FC), and Battery, which can associate DC link and competent to balance the real and reactive power. The introduction of wind/PV power within an electric grid origin the PQ troubles are considered. At this point, the recompense policy of DC/DC converter is examined by PLSANN/RNN technique to provide the optimal power flow management of HRES. Here, LSA is exploited for the optimization process of real power and the Recurrent Neural Network (RNN) is utilized for the optimal reactive management. The projected process recognizes the finest control pulses of the DC/DC converter derived from the foundation part and load part limitation. The projected system is competent to establish the active power into the grid and additionally it is capable of enhancing the PQ. With proper control, HRES significantly enhance the dynamic security of the power system. The proposed method is implemented in MATLAB/Simulink working platform and analyzed their performances. The statistical analysis of proposed method is analyzed in terms of mean, median and standard deviation factors. In order to prove the effectiveness, the proposed method is compared with current techniques such as Combined Modified Bat Search algorithm–artificial neural network (CMBSNN) technique, Particle Swarm Optimization (PSO), Genetic Algorithm (GA) and PI controller. [ABSTRACT FROM AUTHOR]

This paper presents an approach of neural modeling for the diagnosis of fetus abnormality using ultrasound (US) images. The proposed algorithm is a hybrid approach wherein image processing methods have been used for preprocessing the image data, and an artificial neural network has been used as a classifier to extract fetus abnormality. Initially, 350 US images were collected in DICOM format directly from the radiologist and were preprocessed to extract the fetal biometric parameters using a morphological operator and a gradient vector flow algorithm. The extracted parameters were labeled as normal and abnormal fetal parameters. The extracted parameters were then applied to a Feed-Forward Back-propagation Neural Network (FFNN) for the training and validation purpose. These neural networks are capable to provide excellent performance in the critical cases especially in the field of pattern recognition. The result found from the proposed FFNNs was in closed confirmation with the real-time results. This modeling will help radiologist to take appropriate decisions in the boundary line cases. [ABSTRACT FROM AUTHOR]

Antinuclear antibody (ANA) testing is best performed using the indirect immunofluorescence (IIF) method with human epithelial type-2 (HEp-2) cells as the substrate. IIF is a subjective procedure in which HEp-2 patterns are analyzed manually from the microscope. Therefore, ANA test results greatly rely on the experience and expertise of pathologists. Hence, complete automation of the ANA test is required to avoid incorrect diagnoses. This paper represents an algorithm for the complex HEp-2 cell classification problem. The proposed algorithm used a small hybrid feature set that characterizes the texture and morphology of the HEp-2 cells along with artificial neural network (ANN). The hybrid features were extracted by breaking up the image into eight binary images. The proposed hybrid descriptors were more efficient than the popular co-occurrence matrix descriptor and local binary pattern descriptors for texture analysis. The proposed algorithm was evaluated on the ICPR 2016 IIF HEp-2 cell image dataset. The results indicated that the hybrid descriptor with an ANN approach achieved improved performance, with "96.8%" mean class accuracy. [ABSTRACT FROM AUTHOR]

In the paper, a combined strategy of moth–flame optimization (MFO) algorithm and fuzzy logic controller (FLC) for incipient fault diagnosis of the synchronous generator is proposed. The motivation behind the proposed topology is to analyse the beginning issues exhibited by an asynchronous generator under different situations like healthy and unhealthy conditions. Initially, a synchronous generator is assessed in the ordinary condition and from that point onwards, fault is made in the synchronous generator and the framework practices are checked and signals are measured which can be viewed as mis-shaped waveforms. For the collection of data-set from the input current signal, MFO is presented which extracts the signal and structures the possible data-sets. In light of the fulfilled data-set, the FLC performs and diagnoses the kind of fault that has happened in the stator winding of the synchronous generator. In order to evaluate the effectiveness of the proposed method, the incipient faults are analysed. The proposed technique is implemented in MATLAB/Simulink platform and this is approved utilizing execution measures, for example, accuracy, precision, recall, and specificity. Likewise, the proposed method is analysed with factual measures, for example, the root mean square error, mean absolute percentage error, mean bias error, and consumption time; and the execution is evaluated by utilizing the examination at various strategies like artificial neural network, fuzzy, and adaptive neuro fuzzy inference system techniques. [ABSTRACT FROM AUTHOR]

The PI control structure is based on neural network models wherein real power is controlled by an artificial neural network model and reactive power is controlled by a recurrent neural network model. The design was fabricated, and its performance study is compared with simulation study and is reported in the paper. The VSWR performance, peak antenna gain and radiation patterns are presented as function of various antenna parameters from simulation studies and measurements from fabricated antenna. [Extracted from the article]

In this paper, the design procedure of a novel neuron is discussed. Starting from the activation function circuit which is based on the modification of regulated cascode structure, a new scheme is presented which can produce the logistic function with high percentage of accuracy. The main advantage of the proposed function generator circuit is its full programmability feature in which its output waveform slope can easily be adjusted by means of the control voltages applied to the bulks of input stage metal oxide semiconductor (MOS) transistors. Also, the output waveform can easily be converted to a step function with the help of bias changes for the input transistors. Following the concepts of the previous work by the authors, the designed activation function has a good compatibility with the employed synapse. Low power and small active-area consumption are the other features of the proposed circuit which qualify it for hardware implementation of neural networks. Post-layout simulation results based on complementary metal-oxide-semiconductor (CMOS) 0.18 µm twin-tub fabrication standard process depict the correct behaviour of the designed circuits and demonstrate 96% accuracy for the proposed activation function structure. The power dissipation of the activation function circuit is 72 µW at the worst case for 1.8 power supply voltage. [ABSTRACT FROM AUTHOR]

In this paper, a method is proposed to control the movements of a manipulator using image-based visual servoing, which integrates computational intelligence for object tracking. The objective is to visually servo the 6 DOF PUMA 560 using a charge-coupled device camera attached to the end-effector of the manipulator whereby image is acquired (which is called eye-in-hand camera configuration). The image features are then extracted to form the image Jacobian matrix. The proposed method is based on an artificial neural network (ANN), which is capable of approximating complex and nonlinear image motions to the manipulator motions in order to control the manipulator system. For the visual servoing problem, the gradient descent (GD) and Levenberg-Marquardt (LM) algorithms have been implemented and compared, concluding that the LM algorithm has got better performance than the GD algorithm in visually controlling the manipulator based on ANN. The LM algorithm is integrated into the ANN-based visual control for tracking the periodic moving object in the presence of noise. The simulations show that the controller is noise tolerant too. [ABSTRACT FROM AUTHOR]

Recently, the renewable energy systems play the major role to meet the electricity demand. The Distributed energy source provision of balance between the generation and distribution is an attractive research area in the (DES) for providing better power quality during the Distributed Energy Sources deployment. Hence, this paper focuses on the design of an efficient controlling structure to reduce the noise level in the output voltage. Due to the combination of two renewable resources, there is a need for special controlling architecture for switching devices under dynamic load conditions. The generation of the control signals through the Neuro Fuzzy with variations such as the rate of carrier frequency, duty cycle and the pulse position reduces the impulse response that leads to regulated power to the load. Based on the irradiance of the PV system and the torque variations in the induction motor system, the output from the Neuro Fuzzy- with three varied rate parameters as Rate of Carrier Frequency level (RCF), Ratio of Duty Cycle (RDC), and the Rate of Pulse Position (RPP) unit passes to the Space-Vector Pulse Width modulation (SVPWM) block for switching pulse generation. The difference between the frequency of reference and carrier signals has direct impact on the changes in the pulse width that leads to additional noise in the traditional controller techniques. Alternatively, the proposed work provides pulses to the switching devices based on rate analysis that leads to high switching speed and regulated output voltage. The comparative analysis between the proposed NFRRR-SVPWM with the existing methods states the effectiveness of the rate-based controlling technique in the development of renewable energy resources. [ABSTRACT FROM AUTHOR]

This research paper introduces an outline of a simplified version of single-input neuro-fuzzy controller (NFC) method via a decoupling-controlled intuitive feedback linearization (FBL) approach of induction motor (IM) model. The proposed NFC with FBL extensively reduces the torque and speed ripple along with better performance enhancement. A simplified state-space feedback linearization technique-based nonlinear IM model is designed and simulated in the stationary reference frame. Again, the parameter and plant uncertainties in the feedback-linearized model of the IM are continuous phenomenon which led to the design of a robust, simplified NFC to overcome these issues in the real-time industrial application. The proposed reduced membership function (MF) based simplified NFC is the integration of fuzzy logic and neural network concept with single input as an error (speed and torque) unlike two inputs error and change in error of conventional NFC. This has the advantage of improving the computational efficiency due to its simple structure and robustness over conventional NFC. This makes the system easy and simple to implement in a realistic situation. The performance and effectiveness of the proposed method using FBL concept of IM drive is analyzed using MATLAB software in different modes of operation and is distinguished with the conventional PI-controller and conventional NFC to show its superiority. The proposed system with the different control strategies is also validated by extensive experimental results using DSP 2812. [ABSTRACT FROM AUTHOR]

In this paper, a low-power analogue complementary metal oxide semiconductor (CMOS) artificial neuron circuit is presented. The analogue neuron is composed of multiplier and programmable activation function circuits. The proposed four-quadrant multiplier has a single ended current output which eliminates the extra summation circuit at the output of the neuron that reduces the chip area as well as power consumption. In addition, programmability of activation function improves the neural network design process while enables the proposed neuron circuit to be used properly in learning algorithms such as back propagation. The most important feature of the proposed circuit is low power consumption and simple circuit topology. The performance of the circuit is confirmed by HSPICE simulations using 0.18 μm CMOS technology parameters. The circuit operates at 1 V supply voltage and consumes only 15 μW. Finally, different neural networks are realized using the proposed neuron circuit, which are successfully used to solve exclusive OR (XOR) problem and region classification problem to verify the accuracy and performance of the proposed circuit. [ABSTRACT FROM AUTHOR]

In this paper, artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) are used for the modelling and simulation of quantum-dot cellular automata (QCA) circuits. For this purpose, all QCA basis components and gates are modelled using ANN and ANFIS. The accuracy and performance of the proposed methods are analysed through a few circuits. Finally, we compared the simulation speed of the proposed methods with QCADesigner software. The results show that the proposed ANN and ANFIS models are much faster than QCADesigner. Also, these models are imported into HSPICE software to design and simulate complex QCA logic circuits. [ABSTRACT FROM AUTHOR]

In this paper, two well-known artificial intelligence techniques, artificial neural network (ANN) and upport vector machine (SVM) have been modelled for fault type classification for a transmission line equipped with thyristor controlled series compensator (TCSC) to compare their performance. Due to the non-linear changes introduced by the compensation devices, protection of the series compensated transmission line has been a difficult task. The problem is still complex for advanced series compensated transmission lines. The relaying procedure for a compensated transmission line usually involves fault type identification and fault section identification to conclude for the final decision. The algorithm modelled in this paper has been devised on the analysis of a half cycle post-fault current signals, with the help of discrete wavelet transform as a feature extraction tool. The training and testing of ANN and SVM have been performed with an identical fault data set for comparison. The accuracy of the classifiers had been tested with a large number of fault cases encircling different system conditions and fault conditions. These system conditions are simulated on Power System Computer Aided Design/ElectroMagnetic Transients Program (PSCAD/EMTP) with variation in system parameters such as change in firing angle of TCSC, fault resistance, fault inception angle, loading angle of generator, and source impedance variation for all 10 types of faults. The classifiers are compared in detail with their performance at various firing angles of TCSC and for different fault types. [ABSTRACT FROM PUBLISHER]

Number of attempts have been made in the past to improve the generalization performance of artificial neural networks (ANN). Internal adjustment in ANN deals with tuning of various parameters like learning rate, activation function, etc. Majority of activation functions that exist in the literature are transcendental in nature. In this paper, a novel parametric algebraic activation (PAA) function has been proposed. The function PAA is a generalized function of which Elliott activation function is a special case. PAA is a family of S-shaped curves and satisfies all the important properties of activation functions. This activation is employed on resilient propagation algorithm (RPROP) learning algorithm. Comparative performance evaluation with the widely known activation functions has been carried out on various benchmark datasets taken from University of California Irvine (UCI) machine learning repository. Comparative performance evaluation in terms of number of epochs and testing error of the proposed PAA has been made with the standard activation functions. It has been observed that decrease in number of epochs and testing error for the proposed PAA in RPROP is highly statistically significant for most of the UCI datasets when compared with standard activation functions. Thus incorporating PAA in RPROP can make it more powerful for classification. [ABSTRACT FROM AUTHOR]

This paper presents an algorithm to extract symbolic rules from trained artificial neural networks (ANNs), called ERANN. In many applications, it is desirable to extract knowledge from ANNs for the users to gain a better understanding of how the networks solve the problems. Although ANN usually achieves high classification accuracy, the obtained results sometimes may be incomprehensible, because the knowledge embedded within them is distributed over the activation functions and the connection weights. This problem can be solved by extracting rules from trained ANNs. To do so, a rule extraction algorithm has been proposed in this paper to extract symbolic rules from trained ANNs. A standard three-layer feedforward ANN with four-phase training is the basis of the proposed algorithm. Extensive experimental studies on a set of benchmark classification problems, including breast cancer, iris, diabetes, wine, season, golfplaying, and lenses classification, demonstrates the applicability of the proposed method. Extracted rules are comparable with other methods in terms of number of rules, average number of conditions for a rule, and the rules accuracy. The proposed method achieved accuracy values 96.28%, 98.67%, 76.56%, 91.01%, 100%, 100%, and 100% for the above problems, respectively. It has been seen that these results are one of the best results comparing with results obtained from related previous studies [ABSTRACT FROM AUTHOR]

Hand gesture recognition system can be a particularly challenging task because of the presence of several spatio-temporal variations like hand trembling, self co-articulation within a gesture, etc. during the segmentation stage. In this paper, we focus our attention on self co-articulation problem which has not been addressed before. With the addition of a new feature, i.e. removing the hand movement during pause state along with the velocity features within the gestures, we were able to perform the gesture spotting more smoothly for the isolated gestures. Moreover, a new set of novel features was added in the feature extraction stage: (1) number of self co-articulated stroke; (2) orientation of the self co-articulated strokes; (3) position of the hand; (4) distance between the start and end points of a gesture; and (5) ratio between the longest and shortest distances from centre. These features were fed to neural network classifier. The results of experimentation were carried out with 40 gestures and it showed an average true positive rate of 91.25%. [ABSTRACT FROM PUBLISHER]

Design of an optimized planar coplanar waveguide (CPW) fed complementing C-shaped patch antenna for broadband communication is presented. It resonates at 2.1 GHz with bandwidth spanning from 1.2 to 2.45 GHz for the return loss of −10 dB or more. In the absence of closed form design formulae for its resonant frequency, this paper proposes use of either artificial neural network (ANN) or simulated annealing (SA). Results from these stochastic methods are in good agreement with those from electromagnetic (EM) simulations as well as prototype measurements. The EM simulations show good radiation characteristics and moderate gain in the entire operating band of the antenna. [ABSTRACT FROM PUBLISHER]

In this paper, artificial neural network (ANN) and fuzzy-based adaptive neuro-fuzzy inference system (ANFIS) approach to automatic generation control of three unequal area hydro-thermal power systems has been introduced. The proposed ANFIS controller combines the advantages of fuzzy controller as well as quick response and adaptability nature of ANN. Area 1 and area 2 consist of thermal reheat power plant whereas area 3 consists of hydro power plant with electric governor. Performance evaluation is carried out by using ANN, fuzzy, and ANFIS control approaches. To enhance the performance of intelligent controller, sliding surface is included. The performances of the controllers are simulated using MATLAB/SIMULINK software. A comparison of ANFIS, ANN, fuzzy-based approaches shows the superiority of proposed ANFIS over ANN, fuzzy for change in frequency and tie-line power deviation in three area interconnected power system. [ABSTRACT FROM AUTHOR]

This paper deals with the usage of a combination of fuzzy system and artificial techniques, which are called adaptive neuro fuzzy inference system (ANFIS), in order to minimize the distance between the signal and SNR transmitting channel noise and then reduce the error rate of bit error rate (BER) transmission. The authors are focusing on a real implementation of ANFIS channel equalizer on software-defined radio (SDR) system working on PCI eXtensions for instrumentation (PXI) platform. This sophisticated modular measuring system consists of a vector signal generator RF VSG NI PXI-5670 and a vector signal analyzer RF VSA NI PXI-5661. Experimental results suggest that researched ANFIS equalizer embodies better BER values in comparison to commercially most common equalizers of the least mean square algorithm group. Moreover, the conducted experiments show that the usage of the SDR conception is very suitable for testing new principles in channel equalization field. [ABSTRACT FROM PUBLISHER]

In the present paper, hybrid bearing faults classification scheme based on wavelet transformation and neural network is proposed. Basically, the proposed methodology identifies four different types of bearing faults. For classification of the faults, vibration signals have been utilized. The vibration signals are first decomposed into components in different sub-bands using discrete wavelet transformation. Subsequently, variance and variance of autocorrelation value extracted from decomposed signal have been used as input features for the neural network. The time interval between the impacts of original signal is also exploited to characterize the bearing vibration signals. A neural network follows to classify the extracted feature vector. Trained neural networks are able to classify different states of the bearing with 100% accuracy. The proposed procedure requires only a few input features, resulting in simple preprocessing and faster training. Effectiveness of the proposed method is illustrated using the bearing vibration data obtained experimentally. [ABSTRACT FROM AUTHOR]

In this paper, an intelligent technique for detecting the turn fault and supply voltage unbalances in an induction machine is proposed under varying load conditions. The proposed probabilistic neural network (PNN) technique is based on well-established statistical principles rather than heuristic approaches that are adopted in the multi-layer perceptrons. The PNN is derived from the Bayes decision strategy and nonparametric kernel-based estimators of probability density functions. The machine model is developed for inter-turn short circuit fault and it is compared with its a priori models for its robustness in detecting the fault at incipient stages under various operating conditions of the machine. This algorithm is proposed for first time and training, testing, and validation results using the method appear promising and easily realizable in the industries. [ABSTRACT FROM AUTHOR]

Paraphrasing is the restatement of a given text using alternate words. Recognition of paraphrases is vital in applications such as question answering, information extraction, and multi-document summarization. Lexical, syntactic, and semantic features of text can be used either individually or in combinations for recognizing paraphrases. Several machine-learning classifiers such as support vector machines (SVM), nearest neighbour method, and decision trees have been used for paraphrase recognition with SVM recognizers being the most popular ones. This paper explores the applicability of neural networks for paraphrase recognition. A radial basis function neural network (RBFNN) has been designed and implemented for recognizing paraphrases. Experiments have been carried out on the Microsoft research paraphrase corpus. From the results of the experiments, it has been observed that the RBFNN recognizer consistently outperforms the SVM recognizer with respect to accuracy and that the best performance was achieved when a combination of lexical, syntactic, and semantic features were used. [ABSTRACT FROM AUTHOR]

In this paper, the fuzzy logic, neuro-fuzzy logic, and artificial neural network speed controllers in feedforward and recurrent architectures are designed and modeled to control the permanent magnet synchronous motor (PMSM) drive. The fundamentals of artificial intelligence-based control algorithms are illustrated. The detailed performance of the PMSM drive is studied by applying various mechanical disturbances such as starting performance, speed reversal, flux weakening, and load perturbations [ABSTRACT FROM AUTHOR]

This paper deals with an artificial neural network based control of the voltage and frequency (VF) of autonomous wind power generation using an isolated asynchronous generator (IAG) feeding three-phase four-wire loads. The reference generator currents are estimated using the adaptive linear neuron and its training through least mean square (LMS) algorithm to control the VF of an IAG system. Three-leg voltage source converter (VSC) with an isolated T-connected transformer is used as an integrated VSC. The integrated VSC with a battery energy storage system is used to control the active power of the wind energy conversion system (WECS). Bi-directional power flow capabilities of the proposed VF controller in WECS are demonstrated through simulation results. The proposed controller functions as a VF regulator, a load leveler, a load balancer and a harmonic eliminator in the WECS. The WECS is modeled and simulated in the MATLAB using the Simulink and the sim power system toolboxes. [ABSTRACT FROM AUTHOR]