E.G.S. Pillay Engineering College

The effective management of microgrids, which incorporate DERs such as generators and batteries, is crucial for ensuring stability and efficiency in the power system. By evenly distributing the load across modules’ capabilities, frequencies, and voltages, a network of micropower systems can be created, capable of transitioning between various states such as islanding, leaving, and reentering the grid. Synchronizing controllers play a vital role in regulating these transitional phases and maintaining system stability, and we propose a Deep Learning approach for power regulation and optimization. By monitoring voltages, phases, and frequencies on both sides of the fixed switch, these controllers employ various control strategies to stabilize the system. Effective control mechanisms are necessary for achieving a sustainable energy economy as renewable energy sources become increasingly prevalent. Our analysis emphasizes the importance of such control methods in developing a reliable and efficient micropower system network.

Supplementary Cementitious Materials (SCMs) have been utilised for decades to lower the OPC concrete's alkalinity. However, the usage of SCMs to lower the alkalinity of Vegetation Porous Concrete (VPC) is limited. The present study examined the effects of Fly Ash (FA) and Silica Fume (SF) on the alkalinity, strength and planting properties of VPC. Since the Coarse Aggregate Size Ratio (CASR) has a substantial impact on the VPC strength, the current-study also examines the influence of CASR on the void content, strength and planting properties of VPC. The blending of cement with FA and SF reduced the alkalinity of the VPC, and that increasing the dose rate of FA and SF lowered the alkalinity of the VPC even more. The pozzolonic reaction of FA and SF in the VPC consumes CH crystals to form C–S–H gels, and the reduction in the quantity of CH crystals causes the pH of the VPC to decrease. Consequently, the plant's root length growth and LRWC improved by 7.91% and 4.95%, respectively. The inclusion of FA decreased the compressive strength due to the lower activity of the FA with the cement matrix; however, the accelerated pozzolanic reaction between Ca(OH)2 and SiO2 in the SF enhanced VPC strength. Despite an increase in CASR improves the aggregate interlocking property and the strength, it also reduces the void content of the VPC. The reduction in VPC pores hampered root mobility through the concrete, delaying root development and reducing the availability of water and nutrients.

Summary In this research study, trajectory planning of mobile robot is accomplished using two techniques, namely, a new variant of multi-objective differential evolution (heterogeneous multi-objective differential evolution) and popular elitist non-dominated sorting genetic algorithm (NSGA-II). For this research problem, a wheeled mobile robot with differential drive is considered. A practical, feasible and optimal trajectory between two locations in the presence of obstacles is determined through the proposed algorithms. A safer path is obtained by optimizing certain objectives (travel time and actuators effort) taking into account the limitations of mobile robot’s geometric, kinematic and dynamic parameters. Robot motion is represented by a cubic NURBS trajectory curve. The capability of the proposed optimization techniques is analyzed through numerical simulations. Results ensure that the proposed techniques are more desirable for this problem.

AbstractConvolutional neural networks a type of deep learning technology, are used for forecasting future power usage. The mean absolute error, mean square error, root mean square error, and mean constant percentage error are used to evaluate the performance of the models. These metrics are used to rank the models. Among the models tested, the CNN stack demonstrates the highest precision in estimating energy consumption and solar power output, with a mean absolute error of 0.015% points, a root mean square error of 0.23% points, and an average absolute percentage deviation of 1.71% points. However, for wind turbine (WT) energy generation, the recurrent neural network proves for most accurate model, achieving 0.070 as the median absolute percentage error is 2.65, Both the root of the mean square error and the average absolute error are 0.38. The training and validation data utilized in this study comprise the International Renewable Energy Agency's data on solar power production, WT power generation, and the "ensue" dataset, which includes hourly power consumption information from the Pennsylvania, New Jersey, and Maryland interconnection.Keywords: demand side power controlstacked CNNdeep learningrenewable energy systems Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsHimanshu ShekharHimanshu Shekhar has completed his AMIE (I) in Electronics and Communication Engineering from The Institute of Engineers (India), in 1999. He obtained his M.Tech degree in Digital Electronics from VTU, Karnataka in 2002. He obtained his Ph.D in Software Defined Radio from B.R.A. Bihar University, Muzaffarpur in 2014. He has served in Vellamal Engineering college, Chennai and St Peter's Engg College, Avadi, Chennai. At present he is Professor in ECE Dept in Hindustan Institute of Technology and science, Padur, Chennai since 2007 till date. He has published more than 29 indexed papers in International/National Journal/Conferences. His research interests include Software Defined radio, Communication systems and VLSI.Chandra Bhushan MahatoChandra Bhushan Mahato, received his B. Sc. Engineering and M.Tech from MIT Muzaffarpur, in 1987 and 1991 respectively. He has obtained his Ph.D degree from BRA Bihar University in 2004. He has joined MIT Muzaffarpur as an Assistant Professor in Jan 1993. In August 2008, he has joined as a Principal in NEC Chandi. Currently he is Principal at MIT Muzaffarpur since July 2021. His main focus of is to empower students with sound knowledge, acumen, experience and training both at the academic level of Engineering and in the cutting edge of global market.Sanjay Kumar SumanSanjay Kumar Suman, received his Ph.D (ICE) and M.E. (ESCS) from MIT Campus, Anna University Chennai and NIT Rourkela, respectively. He has 28 years of experience in teaching, research and industry. Currently he is Dean R&D of St. Martin's Engineering College, Secunderabad, Telangana, India. He holds a credit of 100 plus publications including Books, Patents, Journals and Conference Proceedings. He is a part of the Reviewer Board for the many Journals like KSII-TIIS, IEEE Access, IET, IETE and Wireless Network. His areas of specialization are Wireless Ad hoc and Sensor Networks, Cognitive Radio, Wireless Communications, Signal Processing, Machine learning application is healthcare and renewable energy.Satyanand SinghSatyanand Singh have earned his M.E. and Ph.D. degrees in Electronics & Communication Engineering from NIT Rourkela and Jawaharlal Nehru Technological University, Hyderabad (India). He has two years of post-doctoral research experience with the University of South Pacific Fiji. Presently, he is working with Fiji National University, Fiji, College of Engineering, Science, & Technology, as an associate professor in the School of Electrical & Electronics Engineering. Dr. Singh is a fellow member and chartered engineer of the Institution of Engineers India. Recently, he received a professional membership from the Fiji Institution of Engineers. His primary research interests include speaker recognition, robust speech modeling, feature extraction, pattern recognition, biometrics, and 5G antenna design.L. BhagyalakshmiL. Bhagyalakshmi, received her Ph.D and M.E. from the university campus, Anna University Chennai in the faculty of ICE and Electronics Engineering respectively. After working at Electronics industry for four years, she joined the teaching profession in 2003. Currently she is Professor and Head for the Dept. of ECE, Rajalakshmi Engineering College, Chennai, TN, India. She holds a credit of 100 plus publications including Books, Patents, Journals and Conference Proceedings. She is a part of the Reviewer Board for the Journals like IEEE Access, IET, IETE and Wireless Network. Her areas of specialization are Cognitive Radio, Wireless Communications, Sensor Networks and Signal Processing. Her research work is in Wireless Sensor Networks, application of mobile based technology in agriculture and health sector, 5G Networks and renewable Energy.Mahendra Prasad SharmaMahendra Prasad Sharma received his PhD. Degree in Computer Science & Engineering, M.Tech (CSE) and B.TECH (Information Technology) degree from Institute of Engineering and Technology, Uttar Pradesh Technical University, Lucknow. He has more than 18 years of teaching experience. He has authored many papers in International and national journals/conferences in the area of Deep learning, Pattern Recognition, Network Security, Cryptography and Network Security, Wireless Communication, Ad-Hoc Networking etc. He has more than 22 publications in Indexed journals and conferences, 05 Published Patents, 01 UK Grant Patent, 03 Published Books. Currently, he is Professor and Head of the Department Information Technology, IIMT College of Engineering, Greater Noida. B. Laxmi KanthaB. Laxmi Kantha completed her B.Tech (Computer Science and Engineering) from the Gurunanak Engineering College, JNTUH, Hyderabad, Telangana. M.Tech (Computer Science and Engineering) from Malla Reddy Group of Institutions, JNTUH, Hyderabad, Telangana and Ph.D from OPJS University, Churu, Rajasthan. Currently, she is working as Associate Professor with St. Martin's Engineering College, Dullapally, Secunderabad, Telangana. She has 8 years of teaching experience. She has published 5 research papers in both national and international journals with IEEE conference.Helan Vidhya THelan Vidhya T, is AP of Dept. of ECE, Rajalakshmi Engineering College, Chennai, India. She is having 12 years of teaching experience. She is a member of ISTE and IACSIT, SAEINDIA. She completed B.E (Electronics and communication engineering) in Bhajarang Engineering College, India in 2009 and M.E (Applied Electronics) in St. Joseph's college of Engineering, India in 2011. Her areas of interests are communication engineering, image processing and Deep Learning.Siva Kumar AgraharamSiva Kumar Agraharam working as an Associate professor in Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Vijayawada, Andhra Pradesh, India. He is having 12 years of teaching experience.A. RajaramA. Rajaram received the B.E. degree in Electronics and Communication Engineering from the Government College of Technology, Coimbatore, Anna University, Chennai, India. The M.E. degree in Electronics and Communication Engineering (Applied Electronics) from the Government College of Technology, Anna University, Chennai, India, and he received the Full Time Ph.D. degree in Electronics and Communication Engineering from the Anna University of Technology, Coimbatore, India. He is currently working as a Professor, ECE Department in E.G.S Pillay Engineering College, Nagapattinam, Tamil Nadu 611002 India. His research interests include Mobile Ad Hoc networks, wireless communication networks (WiFi, WiMax HighSlot GSM), novel VLSI NOC Design approaches to address issues such as low-power, cross-talk, hardware acceleration, Design issues includes OFDM MIMO and noise Suppression in MAI Systems, ASIC design, Control systems, Fuzzy logic and Networks, AI, Sensor Networks, Medical image processing.

The electrocardiogram (ECG), electroencephalogram (EEG), and electromyogram (EMG) are all very useful diagnostic techniques. The widespread availability of mobile devices plus the declining cost of ECG, EEG, and EMG sensors provide a unique opportunity for making this kind of study widely available. The fundamental need for enhancing a country’s healthcare industry is the ability to foresee the plethora of ailments with which people are now being diagnosed. It’s no exaggeration to say that heart disease is one of the leading causes of mortality and disability in the world today. Diagnosing heart disease is a difficult process that calls for much training and expertise. Electrocardiogram (ECG) signal is an electrical signal produced by the human heart and used to detect the human heartbeat. Emotions are not simple phenomena, yet they do have a major impact on the standard of living. All of these mental processes including drive, perception, cognition, creativity, focus, attention, learning, and decision making are greatly influenced by emotional states. Electroencephalogram (EEG) signals react instantly and are more responsive to changes in emotional states than peripheral neurophysiological signals. As a result, EEG readings may disclose crucial aspects of a person’s emotional states. The signals generated by electromyography (EMG) are gaining prominence in both clinical and biological settings. Differentiating between neuromuscular illnesses requires a reliable method of detection, processing, and classification of EMG data. This study investigates potential deep learning applications by constructing a framework to improve the prediction of cardiac-related diseases using electrocardiogram (ECG) data, furnishing an algorithmic model for sentiment classification utilizing EEG data, and forecasting neuromuscular disease classification utilizing EMG signals.

The performance of photovoltaic (PV) systems must be predicted through accurate simulation designs before proceeding to a real-time application to avoid errors. However, predicting the cohesive relationship between current and voltage and estimating the parameters of a single diode model become a perplexing task due to insufficient data in the datasheet of PV panels. This research work presents single-diode solar PV system simulation analysis under different conditions, and the performance is improved by introducing an optimization-based maximum power point tracking (MPPT) strategy. Before simulation, a mathematical model for a single diode and optimization approaches are presented in this research work. Particle swarm optimization (PSO), genetic algorithm (GA), BAT optimization, and grey wolf optimization (GWO) model-based MPPT circuits are designed, and the performances are comparatively analyzed. The simulation results identify the nonlinear relationship between current and voltage and between power and voltage as characteristic curves for different temperature and irradiance values. For maximum power (Pmax), the maximum peak point tracking power and efficiency are analyzed to verify the optimization-based MPPT system. The simulation results demonstrate that the GWO model obtains a maximum tracking efficiency (TE) of 98%, which is much better than that of other optimization techniques.

Global warming is a phenomenon whereby the planet's exposure to the sun's radiation worsens from the high emission of gasses believed to trap heat within the atmosphere. Carbon dioxide (CO2) is the leading greenhouse gas majorly responsible for global warming and other related issues and is a danger to global society. This one has a particular role in portraying the key importance of the shifting climate that invariably influences water supply and agricultural production. Global warming presents complex challenges to aquatic organisms and stocks and other natural aquatic life resources. This study examines how freshwater and marine species are affected by climate change in aquatic habitats. Aquatic species' metabolism, growth, reproduction, and dispersal are all impacted by rising temperatures and altered water chemistry brought on by increased greenhouse gas emissions, especially CO 2 . The goal is to pinpoint the ecosystems and vulnerable species that are most impacted by these changes and suggest flexible management techniques. The suggested remedies center on creating sustainable conservation strategies that lessen the effects of climate change on aquatic biodiversity and increase these ecosystems' resilience. The socio-economic interdependencies between water and climate change impact agricultural and water resources, and the pressures exerted on water bodies and water supply landscapes. Another area is related to alterations in the physical and chemical properties of the water, such as the temperature, which is a well-known effect of climate change: 'This causes abnormalities in the metabolism and physiology of aquatic species.' These alterations flow through the chain and regime of growth, reproduction, feeding habits and distribution, migration, and mass of fish and other creatures in the water system. However, the long-term effect of climate variation and climate change on freshwater ecosystems requires much scientific investigation to address challenges in aquatic ecosystem conservation and sustainability. This being the case, adaptive management solutions that address the interrelated impacts of climate change have to be applied and implemented to reduce vulnerability in aquatic ecosystems worldwide.

The purpose of this study is to provide a broad idea about current control scheme and equilibrating voltages in DC‐link capacitors of the neutral‐point clamped multilevel inverter (NPC‐MLI), using an innovative hexagonal space vector hysteresis current control (SVHCC) scheme. The main ideology is to force the literal current vector to reach the reference current vector through an appropriate voltage vector selection sequence. This proposed scheme defines two hexagonal hysteresis bands encompassing the error vector, as a first step. With respect to the error vector location, the selection of the adjacent vector is acted to minimise the error vector. In addition to the error vector selection, the capacitor voltage is also equilibrated by controlling the degree of freedom available in selecting the switching vectors. The SVHCC scheme is intelligent in performing modulation depth dependent selection of switching vectors between the groups namely closest three vector and preferred three vector (PTV). This scheme balances the DC‐link capacitors’ voltages within a tolerance limit for any value of modulation index. The proposed scheme is asserted through MATLAB/Simulink software. The superiority of the proposed technique is validated through the 2 kW NPC‐MLI supported with SPARTAN III 3AN –XC3S400 field programmable gate array.

An open network known as the "energy internet" links every component of the whole energy supply chains, from the generations. Due to their ability to mimic regional flow dynamics that have an impact on wind farm production, regional meteorological models are increasingly being used as a general tool for wind resource forecasting. In this study, higher vertical and horizontal resolutions WRF (weather research and forecasting) paradigm simulation are used to anticipate and validate production for a genuine onshore wind farm. This paper proposed a DeepFore which is a power forecasting system for hybrid renewable energy systems. Initially, the dataset is generated by the hybrid system. This data is preprocessed to improve the quality of the data by incorporating, filtering and outlier detection techniques. Then, this enriched data is fed into K++ means clustering algorithm to separate the normal data from faulty data. With the normal and original data, Teaching-Learning based optimization algorithm attempts to realize the optimal features which are important for forecasting. Finally, Deep SARSA which is deep reinforcement learning algorithm is incorporated to determine the power generated by the hybrid system. Better winds energy prediction estimations enable more efficient utilization of the produced electricity, according to computational models.

The pursuit of accurate electrical power demand forecasting has led to the application of deep learning algorithms, notably demonstrating promising outcomes despite the prerequisite of substantial training data. This study pioneers a new learning paradigm, employing sophisticated deep learning models specifically, Long Short-Term Memory networks and recurrent neural networks (RNNs). Leveraging historical load data, temperature, wind speed, and day-ahead predicted spot prices, this approach follows a structured flow involving data preprocessing, sequence generation, model training, and subsequent prediction of future load demand using LSTM-based RNN variants. The study's paramount findings underscore the substantial advancement achieved by this proposed methodology over prevailing techniques. The method significantly improves prediction accuracy by over 11%, demonstrating the efficacy of deep learning models and a significant leap forward in forecasting precision. Beyond its superior predictive capabilities, this novel strategy serves as a catalyst for enhancing energy distribution management in local energy communities. Its effectiveness lies not only in its precision but also in enabling the optimization and cost-effective control of energy distribution, vital for sustainable energy management in these communities. Ultimately, this pioneering approach presents a robust solution poised to revolutionize the landscape of electrical power demand forecasting and its practical application in local energy systems.

The best layout design related to the sensor node distribution represents one among the major research questions in Wireless Sensor Networks (WSNs). It has a direct impact on WSNs' cost, detection capabilities, and monitoring quality. The optimization of several conflicting objectives, including as load balancing, coverage, cost, lifetime, connection, and energy consumption of sensor nodes, is necessary for layout optimization. Layout optimization represents an NP-hard combinatorial issue. A number of meta-heuristic optimization strategies have been put out to address this issue in the past ten years. Nevertheless, these methods only addressed a subset of the objectives-combinations of energy consumption, count of sensor nodes, area coverage, and lifetime-or they offered computationally costly solutions. Therefore, this research paper presents a layout optimization problem using novel intelligent deep learning-based optimization methodology. Here, the major objective is to cover numerous objectives associated with optimal layouts of homogeneous WSNs that involves connectivity, coverage, energy consumption, lifetime, and the number of sensor nodes. The layout optimization problem is handled by the novel Advanced Generative Adversarial Network (AGAN), where the parameter tuning is performed by the nature inspired optimization algorithm called Piranha Foraging Optimization Algorithm (PFOA), with the consideration of deriving the objective function. Simulation findings revealed that the proposed novel AGAN-PFOA generated optimal Pareto front of non-dominated solutions having better hyper-volumes as well as spread of solutions than the state-of-the-art solutions. The proposed AGAN-PFOA for the WSN layout optimization problem in terms of PDR, coverage, energy consumption, lifetime, alive node count, delay, and routing overhead is 61.46%, 15.12%, 12.67%, 65.91%, 70.59%, 44.88%, and 68.86% better than the existing methods respectively.

The ambition of this research work is to evaluate the hardness and wear behavior of titanium alloy reinforced with tungsten carbide particle (WC) composite prepared by powder metallurgy route. Titanium alloy with 5 and 10 wt% tungsten carbide reinforced particle (WC) composites was manufactured through powder metallurgy technique. The hardness and wear properties of the composite are measured in hardness and wear tests. The microstructures of the composite are evaluated by utilized optical microscopy. The fabricated titanium composites exhibit improved hardness and wear resistance. The hardness and wear specimens were prepared and tested by used Vickers hardness tester and a pin-on-disk wear test apparatus machine at room temperature. The hardness, wear rate, and CoF of TMCs are 476.79 VHN, 13.158 mg/m (×10−3), and 0.955420243, respectively. The results elucidated the microstructure, hardness, wear rate, coefficient of friction, and SEM images of wear for the effects of added reinforcement tungsten carbide.

MANETs aredecentralized network that involves mobile nodes. As the overall network is mobile and has no centralization, network management, routing, and security become very challenging. Though many works have been presented, still there is a lack in organizing the network due to unauthorized access, centralized security schemes, and the dynamic nature of the nodes. This paper proposed a novel Blockchain-assisted Secure Routing (Block-Sec) protocol for MANETs. All mobile nodes are authenticated by Distributed One-Time Passcode (DOT) based authorization scheme. All authorized nodes are segregated into multiple clusters based on Weight based Dynamic Clustering (WDC) algorithm in which multiple metrics are considered in clustering and re-clustering processes. After cluster formation, each cluster is elected with optimal Cluster Head (CH) by Strawberry Optimization (SBO) algorithm with a new objective function. After cluster formation, the optimal route is selected by Fast Neural Net-assisted Fuzzy (FNNF) algorithm by combining multiple variables. Data transmission is secured by Efficient Elliptic Curve (E2C2) algorithm. With the combined algorithms, the proposed approach obtainedimproved efficiency in packet delivery ratio (PDR), throughput, time analysis, and security level.

The recent developments in manufacturing organizations recognize sustainability as an important value addition for survival in the competitive scenario.The design engineers are in search of approaches for creating environmental conscious products.The purpose of this paper is to report a research carried out for ensuring sustainable product design by the integration of Design for Environment (DFE) and Design for Manufacture and Assembly (DFMA) methodologies.In this context, this paper reports a case study carried out in an automotive component.The candidate product is the charge alternator pulley.The existing pulley has been created using Computer Aided Design.Then sustainability analysis was conducted on the existing component for determining environmental impact.This is followed by the engineering analysis of the component using ANSYS.Then conceptual design changes were developed in the proposed product using DFMA concept.Then the environmental impact has been evaluated in terms of carbon footprint, energy consumption and air/water impacts on proposed product.It has been found that the optimized pulley design possesses minimal environmental impact.The result of the case study indicated that the integration of DFE and DFMA concept could initiate new developments in sustainable designs with minimal impact to the environment and it also reduces the product cost.

Shielded metal arc welding (SMAW) is one of the most important processes of joining two metals or materials because of its high efficiency and low time requirement. This work studied the tensile strength of SMAW dissimilar mild steel (MS) and medium carbon steel (CS) with various process variables such as Welding Current (WC), Electrode Angle (EA), and Root Face (RF). The chosen variable ranges are WC of 140,180 and 200Amp, EA of 30,45 and 60 degrees and RF of 1,2 and 3 mm respectively to identify the important variables on Tensile strength (TS). Design of experiments (DOE) is executed as per Taguchi L9 OA for recognizing the optimal level of variables to accomplish maximum tensile strength. The experimental result is witnessed that the highest TS (201.38 MPa) is attained at sample-8 when WC −140 Amp, EA-45 degree and RF-1mm are maintained whereas the lowest TS (41.61 MPa) is obtained at sample-9 due to increment of the electrode angle (60 degree) and root face (2 mm), Analysis of variance result is revealed that Electrode Angle is the most important variable (73.97%) which improves TS of the SMAW joints, followed by Root face (6.24%) and Welding current (5.12%).

Recommender systems based on sentiment analysis become challenging due to the presence of enormous data available over the internet. With the lack of proper data cleaning and analysis methods, existing machine learning (ML) techniques fail to generate accurate recommendations. To overcome this issue, this paper proposes a Light Deep Learning (LightDL)-based recommender system that uses Twitter-based reviews. First, the data is collected from Twitter and cleaned by subsequent data cleaning processes. Then, this pre-processed data is fed into the LightDL model, which learns the important features like hashtags, unigrams, multigrams, etc. from each piece of data. Here, we have learned about four groups of features, including semantic features, syntactic features, symbolic features, and tweet-based features. Finally, the data is classified into positive, negative, and neutral categories according to the learned features. On the basis of classified sentiment, the review is generated to the users. Finally, the model is evaluated in terms of accuracy, precision, recall, f-measure, and error rate through extensive experiments in Matlab. The proposed LightDL model outperforms in all performance measures; specifically, it achieves 95% accuracy for the Twitter dataset.

In past few decades, solar energy plays a vital role in energy production among the different renewable energy resources. In shaded/unshaded photovoltaic (PV) systems, tracking of maximum power under different environmental conditions is provided by maximum power point tracking (MPPT). In recent years many works available on different types of MPPT techniques to track maximum power from PV systems with own pros and cons. This article comprehensively reviews the different traditional methods like perturb and observation (P&O), open circuit voltage (OCV), short circuit current (SCC), hill climbing (HC), incremental conductance (IC). Also recall the advanced MPPT techniques like particle swarm optimization (PSO), grey wolf optimization (GWO), cuckoo search (CS), artificial neural networks (ANN), fuzzy logic controller (FLC) available in literature. This review is conducted based on implementation, accuracy, tracking speed, cost, merits, and demerits of each technique. Traditional MPPT methods can’t able to track global maximum power point under partial shaded conditions and exhibits less efficiency when compared with advanced soft computing methods. Hybrid methods provide good efficiency and performance than traditional and advanced methods. Authors powerfully confirm that this article offers convenient information’s to enthusiastic engineers and new researchers those who are all working in solar PV systems.

Abstract Diabetes is an extremely serious hazard to global health and its incidence is increasing vividly. In this paper, we develop an effective system to diagnose diabetes disease using a hybrid optimization-based Support Vector Machine (SVM).The proposed hybrid optimization technique integrates a Crow Search algorithm (CSA) and Binary Grey Wolf Optimizer (BGWO) for exploiting the full potential of SVM in the diabetes diagnosis system. The effectiveness of our proposed hybrid optimization-based SVM (hereafter called CS-BGWO-SVM) approach is carefully studied on the real-world databases such as UCIPima Indian standard dataset and the diabetes type dataset from the Data World repository. To evaluate the CS-BGWO-SVM technique, its performance is related to several state-of-the-arts approaches using SVM with respect to predictive accuracy, Intersection Over-Union (IoU), specificity, sensitivity, and the area under receiver operator characteristic curve (AUC). The outcomes of empirical analysis illustrate that CS-BGWO-SVM can be considered as a more efficient approach with outstanding classification accuracy. Furthermore, we perform the Wilcoxon statistical test to decide whether the proposed cohesive CS-BGWO-SVM approach offers a substantial enhancement in terms of performance measures or not. Consequently, we can conclude that CS-BGWO-SVM is the better diabetes diagnostic model as compared to modern diagnosis methods previously reported in the literature.

The Internet of Things (IoT) is a significant avenue for research in renewable energy, particularly in enhancing windmill performance, reducing wind energy costs, and mitigating risks in wind power. This article concentrates on leveraging IoT for assessing wind and solar energy, as well as estimating module lifespans. IoT has improved assessment methods, monitoring precision, and product testing, influencing power network reliability and inventory management in green energy. Predicting green energy output is crucial but challenging due to wind speed fluctuations. Machine learning (ML) techniques are applied to predict wind-based electricity output, with a comparative evaluation of forecasting methods. IoT technologies and algorithms enable energy consumption forecasts, yielding more accurate predictions and lower root mean square error (RMSE). Accurate meteorological forecasts are paramount in the green energy sector, necessitating predictive models for authentic wind generator data. The research aims to develop technologies for precise forecasts, with a focus on comprehensive wind forecast algorithms for photovoltaic systems. Various ML techniques and green energy prediction software are assessed for their accuracy in this endeavor.

Crop diseases pose significant challenges to global food security and agricultural sustainability. Timely and accurate disease detection is crucial for effective disease management and minimizing crop losses. In recent years, hyperspectral imaging has emerged as a promising technology for non-destructive and early disease detection in crops. This research paper presents an advanced deep learning approach for enhancing crop disease detection using hyperspectral imaging. The primary objective is to propose a hybrid Autoencoder-Generative Adversarial Network (AE-GAN) model that effectively extracts meaningful features from hyperspectral images and addresses the limitations of existing techniques. The hybrid AE-GAN model combines the strengths of the Autoencoder for feature extraction and the Generative Adversarial Network for synthetic sample generation. Through extensive evaluation, the proposed model outperforms existing techniques, achieving exceptional accuracy in crop disease detection. The results demonstrate the superiority of the hybrid AE-GAN model, offering substantial advantages in terms of feature extraction, synthetic sample generation, and utilization of spatial and spectral information. The proposed model’s contributions to sustainable agriculture and global food security make it a valuable tool for advancing agricultural practices and enhancing crop health monitoring. With its promising implications, the hybrid AE-GAN model represents a significant advancement in crop disease detection, paving the way for a more resilient and food-secure future.