In recent years, the whole globe has been afflicted with a devastating viral virus known as COVID-19 that has interrupted the operations of every organization. COVID-19 has significantly impacted education, causing it to struggle to function as smoothly as before. However, it has also ushered in a new era of e-learning, necessitating the provision of suitable facilities for users and learners. The growing number of users has led to an increase in digital threats to vulnerable systems on the widespread web of devices. The need for more diverse, versatile, and robust techniques is rising day by day, and Adversarial Neural Cryptography has the potential to be in the Line. The notions of Machine Learning and Digital Securities are being implemented in numerous manners for which ANC can perform the role of new technology to secure communication lines of a Digital learner from several learning platforms over the Cloud. This paper explores the possible threats, reasons, and potential steps taken to secure the user of the Digital Learning Platforms by various organizations. In extension to this, the concept of Adversarial Neural Cryptography is also introduced in the light of E-Learning Platforms with a conceptual model to secure communication.
{"title":"Cruciality of securing user data due to increasing Digital Learner traffic over the Internet using Adversarial Neural Cryptography","authors":"Basil Hanafi","doi":"10.52783/jes.3655","DOIUrl":"https://doi.org/10.52783/jes.3655","url":null,"abstract":"In recent years, the whole globe has been afflicted with a devastating viral virus known as COVID-19 that has interrupted the operations of every organization. COVID-19 has significantly impacted education, causing it to struggle to function as smoothly as before. However, it has also ushered in a new era of e-learning, necessitating the provision of suitable facilities for users and learners. The growing number of users has led to an increase in digital threats to vulnerable systems on the widespread web of devices. The need for more diverse, versatile, and robust techniques is rising day by day, and Adversarial Neural Cryptography has the potential to be in the Line. The notions of Machine Learning and Digital Securities are being implemented in numerous manners for which ANC can perform the role of new technology to secure communication lines of a Digital learner from several learning platforms over the Cloud. This paper explores the possible threats, reasons, and potential steps taken to secure the user of the Digital Learning Platforms by various organizations. In extension to this, the concept of Adversarial Neural Cryptography is also introduced in the light of E-Learning Platforms with a conceptual model to secure communication.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bagasse, an abundantly available crop residue has a high potential that remains unutilized or burnt as fuel. The complex structure of bagasse poses recalcitrance to its sustainable utilization through anaerobic digestion. So, to enhance biogas production 2% NaOH pretreatment of bagasse and filter cake were carried out in this study at ambient temperature for a day. Biogas production was observed for 35 days of retention period at mesophilic temperature in batch process mode. Proximate analysis and analytical techniques such as Fourier Transform Infra-Red (FTIR) were used to characterize the residues and observe the effect on chemical structures of pretreated bagasse and filter cake respectively. Raw Filter Cake was found to produce the highest biogas production.
{"title":"Study of Biogas Production from Bagasse and Filter Cake","authors":"Maninder Kaur, Milan Pahwa","doi":"10.52783/jes.3661","DOIUrl":"https://doi.org/10.52783/jes.3661","url":null,"abstract":"Bagasse, an abundantly available crop residue has a high potential that remains unutilized or burnt as fuel. The complex structure of bagasse poses recalcitrance to its sustainable utilization through anaerobic digestion. So, to enhance biogas production 2% NaOH pretreatment of bagasse and filter cake were carried out in this study at ambient temperature for a day. Biogas production was observed for 35 days of retention period at mesophilic temperature in batch process mode. Proximate analysis and analytical techniques such as Fourier Transform Infra-Red (FTIR) were used to characterize the residues and observe the effect on chemical structures of pretreated bagasse and filter cake respectively. Raw Filter Cake was found to produce the highest biogas production.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Distribution systems have a lot of obstacles to deal with, like increasing load demands, environmental issues, operating limits, and infrastructure development limitations. On the other hand, the number of plug-in hybrid electric vehicles (PHEVs) has grown significantly in recent years and is likely to continue due to concerns over the environment and fossil fuel shortages. Due to the increasing use of PHEVs, distribution systems were not built to accept them, requiring planners to create parking lots that support PHEV charging. To address these issues, in this study, optimal planning of distributed generation (DG) and electric vehicle charging stations (EVCS) in radial distribution systems by the maiden application of a novel Pareto-based multi-objective artificial hummingbird optimization (MOAHO) algorithm is addressed. Three technical aspects of the distribution system are improved by optimal planning of various types of DGs and EVCSs: active power loss reduction, total voltage deviation minimization, and voltage stability improvement. The Pareto-based MOAHO is employed to generate the optimal front between the three competing objectives and later TOPSIS method is employed for selecting the most compromised solution from the optimal front. The proposed methodology is tested on IEEE-33, IEEE-69 bus radial distribution test systems. To validate the efficacy of the MOAHO algorithm, the simulation outcomes of the proposed methodology are generated using a multi-objective non-dominated sorting genetic algorithm (NSGA2), particle swarm optimization algorithm (PSO), grey wolf optimization algorithm (GWO) and compared with the outcomes of the MOAHO algorithm.
{"title":"Optimal Deployment of DGs, DSTATCOMs and EVCSs in Distribution System using Multi-Objective Artificial Hummingbird Optimization","authors":"Varun Krishna Paravasthu","doi":"10.52783/jes.3665","DOIUrl":"https://doi.org/10.52783/jes.3665","url":null,"abstract":"Distribution systems have a lot of obstacles to deal with, like increasing load demands, environmental issues, operating limits, and infrastructure development limitations. On the other hand, the number of plug-in hybrid electric vehicles (PHEVs) has grown significantly in recent years and is likely to continue due to concerns over the environment and fossil fuel shortages. Due to the increasing use of PHEVs, distribution systems were not built to accept them, requiring planners to create parking lots that support PHEV charging. To address these issues, in this study, optimal planning of distributed generation (DG) and electric vehicle charging stations (EVCS) in radial distribution systems by the maiden application of a novel Pareto-based multi-objective artificial hummingbird optimization (MOAHO) algorithm is addressed. Three technical aspects of the distribution system are improved by optimal planning of various types of DGs and EVCSs: active power loss reduction, total voltage deviation minimization, and voltage stability improvement. The Pareto-based MOAHO is employed to generate the optimal front between the three competing objectives and later TOPSIS method is employed for selecting the most compromised solution from the optimal front. The proposed methodology is tested on IEEE-33, IEEE-69 bus radial distribution test systems. To validate the efficacy of the MOAHO algorithm, the simulation outcomes of the proposed methodology are generated using a multi-objective non-dominated sorting genetic algorithm (NSGA2), particle swarm optimization algorithm (PSO), grey wolf optimization algorithm (GWO) and compared with the outcomes of the MOAHO algorithm.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The need of energy for railway is rising due to the increased speed at which trains must operate to maintain safety and dependability. This situation implies more electricity consumption and more challenges to railway operation stability. Therefore, this research suggests configuring wind energy integration with the current railway traction substations built on the current traction substation. The suggested setup consists of a converter that converts DC to DC with RBFN-based MPPT regulator wind energy source linked to a permanent magnet synchronous generator (PMSG), a rectifier, and a conventional traction system. The proposed system is modelled and analyzed by utilizing a radial basis function network (RBFN) in this study. Three traction substations: Aysha, Adegla and Dewanle:-are the subject of the case study, which integrates wind energy with the railway electric power system working at 25 kV AC. For the Aysha wind farm, a MATLAB/Simulink simulation is run in order to confirm the suggested technology. The setup with or without MPPT was used in order to evaluate the results. The proposed system produces an average output of 260.3kW without MPPT and 289.3kW with MPPT controller at wind speed of 20m/sec. The simulation findings suggest that the RBFN-based control method performs better under diverse wind conditions and is more suited for wind energy integration with traction system.
{"title":"Study and Analysis of RBFN based MPPT controller for wind energy integrated with Traction Power Supply System","authors":"Mebratu Delelegn","doi":"10.52783/jes.3609","DOIUrl":"https://doi.org/10.52783/jes.3609","url":null,"abstract":"The need of energy for railway is rising due to the increased speed at which trains must operate to maintain safety and dependability. This situation implies more electricity consumption and more challenges to railway operation stability. Therefore, this research suggests configuring wind energy integration with the current railway traction substations built on the current traction substation. The suggested setup consists of a converter that converts DC to DC with RBFN-based MPPT regulator wind energy source linked to a permanent magnet synchronous generator (PMSG), a rectifier, and a conventional traction system. The proposed system is modelled and analyzed by utilizing a radial basis function network (RBFN) in this study. Three traction substations: Aysha, Adegla and Dewanle:-are the subject of the case study, which integrates wind energy with the railway electric power system working at 25 kV AC. For the Aysha wind farm, a MATLAB/Simulink simulation is run in order to confirm the suggested technology. The setup with or without MPPT was used in order to evaluate the results. The proposed system produces an average output of 260.3kW without MPPT and 289.3kW with MPPT controller at wind speed of 20m/sec. The simulation findings suggest that the RBFN-based control method performs better under diverse wind conditions and is more suited for wind energy integration with traction system.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140982624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapid growth in the quantity of Internet of Things (IoT) devices linked with the network, there exists a concurrent rise in network attacks, including overwhelming and service disruption incidents. The increasing prevalence of network attacks, such as overwhelming and service denial, poses a threat to IoT devices, leading to network disruptions and service disruption. Detecting these attacks is challenging due to the diverse array of heterogeneous devices in the IoT environment, making traditional rule-based security solutions less effective. Developing optimal security models for diverse device types is challenging. Machine learning (ML) offers an alternative approach, enabling the creation of effective security models by leveraging empirical data specific to each device. We utilize machine learning techniques for the detection of Internet of Things (IoT) attacks. Our focus is on botnet attacks directed at variety of IoT devices. We undertake the development of machine learning-based models tailored to each specific category of device for enhanced security. We utilize the N-BaIoT dataset, which incorporates injected botnet attacks (specifically Gafgyt and Mirai) across diverse IoT device types, including Doorbell, Baby Monitor, Security Camera, and Webcam. We develop models for detecting botnets for each IoT device by utilizing diverse machine learning algorithms. Following model development, we assess the utility of the models with a strong detection F1-score through classification analysis. The novelty of this work lies in crafting a Machine Learning-based framework designed to identify IoT botnet attacks, followed by successful detection of such attacks across diverse IoT devices utilizing this framework. Among the most widely used machine learning algorithms on the NBaIoT dataset, Decision Trees, Random Forests, and K-Nearest Neighbors (KNN) demonstrate superior performance.
{"title":"Detection of Various Botnet Attacks Using Machine Learning Techniques","authors":"Rituparna Borah, Satyajit Sarmah","doi":"10.52783/jes.3669","DOIUrl":"https://doi.org/10.52783/jes.3669","url":null,"abstract":"With the rapid growth in the quantity of Internet of Things (IoT) devices linked with the network, there exists a concurrent rise in network attacks, including overwhelming and service disruption incidents. The increasing prevalence of network attacks, such as overwhelming and service denial, poses a threat to IoT devices, leading to network disruptions and service disruption. Detecting these attacks is challenging due to the diverse array of heterogeneous devices in the IoT environment, making traditional rule-based security solutions less effective. Developing optimal security models for diverse device types is challenging. Machine learning (ML) offers an alternative approach, enabling the creation of effective security models by leveraging empirical data specific to each device. We utilize machine learning techniques for the detection of Internet of Things (IoT) attacks. Our focus is on botnet attacks directed at variety of IoT devices. We undertake the development of machine learning-based models tailored to each specific category of device for enhanced security. We utilize the N-BaIoT dataset, which incorporates injected botnet attacks (specifically Gafgyt and Mirai) across diverse IoT device types, including Doorbell, Baby Monitor, Security Camera, and Webcam. We develop models for detecting botnets for each IoT device by utilizing diverse machine learning algorithms. Following model development, we assess the utility of the models with a strong detection F1-score through classification analysis. The novelty of this work lies in crafting a Machine Learning-based framework designed to identify IoT botnet attacks, followed by successful detection of such attacks across diverse IoT devices utilizing this framework. Among the most widely used machine learning algorithms on the NBaIoT dataset, Decision Trees, Random Forests, and K-Nearest Neighbors (KNN) demonstrate superior performance.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cloud computing is experiencing unprecedented demand, offering scalable and flexible resources for a wide range of applications. However, this surge in demand has raised concerns about energy consumption and the need for environmentally sustainable solutions. Green computing has emerged as a critical consideration in this context. Virtual Machine Placement (VMP) is a key component of optimizing cloud resources, aiming to allocate virtual machines efficiently while minimizing energy consumption, cost, and load balancing. This paper addresses the VMP problem by introducing a novel approach based on multifactor optimization, specifically the Diversity Constraint Digger Snake Optimizer (DCD-SO). It offers an innovative perspective on optimizing virtual machine placement by considering energy efficiency, load balancing, and resource utilization simultaneously with the aim to reduce VM migration count, time and cost. Proposed method provides a more comprehensive and sustainable solution, aligning with the principles of green computing. Through extensive simulations and experiments, we have rigorously evaluated the performance of DCD-SO in comparison to traditional optimization techniques such as Particle Swarm Optimization (PSO) and Snake Optimization. In our analysis of actual cloud environments, we compared the results of our method with existing state-of-the-art techniques. Result outcomes determine showed that proposed approach has reduced migration count of 5 and 3 for scheduling 42VMs and 84VMs on 16 and 32 host units respectively than traditional MOGANS, GA-S, GA-N and GA-NN methods. This comprehensive evaluation reinforces the effectiveness and practicality of our approach in addressing the intricate challenges of Virtual Machine Placement (VMP) in dynamic cloud computing settings. As cloud computing continues to evolve, our study contributes to more sustainable and efficient resource management, addressing both current demands and future needs.
{"title":"Optimizing Cloud Computing Resources: An Energy Efficient Multi-QoS Factor-Based VM Placement Strategy","authors":"Manpreet Kaur, Sarpreet Singh","doi":"10.52783/jes.3659","DOIUrl":"https://doi.org/10.52783/jes.3659","url":null,"abstract":"Cloud computing is experiencing unprecedented demand, offering scalable and flexible resources for a wide range of applications. However, this surge in demand has raised concerns about energy consumption and the need for environmentally sustainable solutions. Green computing has emerged as a critical consideration in this context. Virtual Machine Placement (VMP) is a key component of optimizing cloud resources, aiming to allocate virtual machines efficiently while minimizing energy consumption, cost, and load balancing. This paper addresses the VMP problem by introducing a novel approach based on multifactor optimization, specifically the Diversity Constraint Digger Snake Optimizer (DCD-SO). It offers an innovative perspective on optimizing virtual machine placement by considering energy efficiency, load balancing, and resource utilization simultaneously with the aim to reduce VM migration count, time and cost. Proposed method provides a more comprehensive and sustainable solution, aligning with the principles of green computing. Through extensive simulations and experiments, we have rigorously evaluated the performance of DCD-SO in comparison to traditional optimization techniques such as Particle Swarm Optimization (PSO) and Snake Optimization. In our analysis of actual cloud environments, we compared the results of our method with existing state-of-the-art techniques. Result outcomes determine showed that proposed approach has reduced migration count of 5 and 3 for scheduling 42VMs and 84VMs on 16 and 32 host units respectively than traditional MOGANS, GA-S, GA-N and GA-NN methods. This comprehensive evaluation reinforces the effectiveness and practicality of our approach in addressing the intricate challenges of Virtual Machine Placement (VMP) in dynamic cloud computing settings. As cloud computing continues to evolve, our study contributes to more sustainable and efficient resource management, addressing both current demands and future needs.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Frequency synthesizers play a crucial role in providing stable and precise frequency sources for various electronic systems, contributing to the reliability and performance of communication and signal processing applications. A frequency synthesizer is an electronic circuit or device that generates output signals with a specified frequency. It is commonly used in communication systems, radio transmitters and receivers, radar systems, and various other electronic applications where precise and stable frequency sources are required. In this work a frequency Synthesizer is designed and developed for the specifications of output Frequency Range of 20 MHz to 100 MHz, Frequency Accuracy up to 10 Hz, High Switching Speed of 20 µSec, Low Phase Noise of 110 dBc/Hz at 10KHz from carrier, Frequency Modulation with Selectable Deviation, Frequency Chirp with Selectable Step Size, TDM mode up to 4 Pre Selected Frequencies, Fixed Frequency, FM and Chirp. The Synthesizer is digitally controllable with FTW, With the simulations Frequency Range achieved is 0-400MHz against 20 – 100 MHz, Resolution achieved is 2 Hz against 10 Hz, Phase Noise performance is 120 dBc @ 10kHz, against 110 dBc, Switching Time of 2µS against 20µS, and 4 Modes of Operations achieved successfully. Xilinx fpga 2v250fg256 is used for implementation. Number of Slices used are 1264 out of 1536 with 82% , Number of Slice Flip Flops used are 536 out of 3072 with 17% ,Number of 4 input LUTs used are 2238 out of 3072 with 72%, Number of bonded IOBs used are 52 out of 172 with 30%, Number of GCLKs used are 3 out of 16 with 18%. Compared to other DDFS implementations, this work ensured implementation of 32-bit FTW with various modes, better utilization, low power consumption, flexible coding.
{"title":"Fpga Based Implementation of Ddfs for Pll","authors":"G. Vimala, Dr. F. Vincy Lloyd, K. Prasad","doi":"10.52783/jes.3656","DOIUrl":"https://doi.org/10.52783/jes.3656","url":null,"abstract":"Frequency synthesizers play a crucial role in providing stable and precise frequency sources for various electronic systems, contributing to the reliability and performance of communication and signal processing applications. A frequency synthesizer is an electronic circuit or device that generates output signals with a specified frequency. It is commonly used in communication systems, radio transmitters and receivers, radar systems, and various other electronic applications where precise and stable frequency sources are required. In this work a frequency Synthesizer is designed and developed for the specifications of output Frequency Range of 20 MHz to 100 MHz, Frequency Accuracy up to 10 Hz, High Switching Speed of 20 µSec, Low Phase Noise of 110 dBc/Hz at 10KHz from carrier, Frequency Modulation with Selectable Deviation, Frequency Chirp with Selectable Step Size, TDM mode up to 4 Pre Selected Frequencies, Fixed Frequency, FM and Chirp. The Synthesizer is digitally controllable with FTW, With the simulations Frequency Range achieved is 0-400MHz against 20 – 100 MHz, Resolution achieved is 2 Hz against 10 Hz, Phase Noise performance is 120 dBc @ 10kHz, against 110 dBc, Switching Time of 2µS against 20µS, and 4 Modes of Operations achieved successfully. Xilinx fpga 2v250fg256 is used for implementation. Number of Slices used are 1264 out of 1536 with 82% , Number of Slice Flip Flops used are 536 out of 3072 with 17% ,Number of 4 input LUTs used are 2238 out of 3072 with 72%, Number of bonded IOBs used are 52 out of 172 with 30%, Number of GCLKs used are 3 out of 16 with 18%. Compared to other DDFS implementations, this work ensured implementation of 32-bit FTW with various modes, better utilization, low power consumption, flexible coding.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Indoor air pollution has become a severe concern on human health due to improper ventilation, pets and fine dust particles. The demand for efficient air purifiers has surged, yet many existing solutions are generally pricey and lack portability. The suggested air purifier uses modern filtration technologies, including activated carbon filters, to remove a wide range of airborne contaminants, such as dust, allergies, pet hair, and volatile organic compounds (VOCs). By adopting a tiny and lightweight design, the purifier offers outstanding portability, enabling customers to experience clean and fresh air wherever they go. The proposed air purifier possesses a distinctive design that integrates a high electric field generator and UV light source. The high electric field technique effectively accumulates and neutralizes airborne particles, including dust, pollen, mold spores, and germs. Simultaneously, the UV light component kills dangerous microbes, such as viruses and bacteria, by breaking their DNA structure, offering cleaner and healthier air. To achieve best performance and energy economy the air purifier adopts an automated operation mode. The device operates only upon the detection of motion a human being.
由于通风不当、宠物和微尘颗粒等原因,室内空气污染已成为影响人类健康的严重问题。人们对高效空气净化器的需求激增,但现有的许多解决方案普遍价格昂贵,而且缺乏便携性。建议的空气净化器采用现代过滤技术,包括活性炭过滤器,可去除空气中的各种污染物,如灰尘、过敏原、宠物毛发和挥发性有机化合物(VOC)。该空气净化器采用小巧轻便的设计,具有出色的便携性,让消费者无论走到哪里,都能体验到清新的空气。该空气净化器设计独特,集成了高电场发生器和紫外线光源。高电场技术可有效聚集和中和空气中的微粒,包括灰尘、花粉、霉菌孢子和病菌。同时,紫外线组件通过破坏病毒和细菌等危险微生物的 DNA 结构来杀死它们,从而提供更清洁、更健康的空气。为了达到最佳性能和节能效果,空气净化器采用了自动运行模式。只有在检测到人体运动时,设备才会运行。
{"title":"Cost-Effective Automatic Portable Air Purifier","authors":"Deekshitha Arasa","doi":"10.52783/jes.3607","DOIUrl":"https://doi.org/10.52783/jes.3607","url":null,"abstract":"Indoor air pollution has become a severe concern on human health due to improper ventilation, pets and fine dust particles. The demand for efficient air purifiers has surged, yet many existing solutions are generally pricey and lack portability. The suggested air purifier uses modern filtration technologies, including activated carbon filters, to remove a wide range of airborne contaminants, such as dust, allergies, pet hair, and volatile organic compounds (VOCs). By adopting a tiny and lightweight design, the purifier offers outstanding portability, enabling customers to experience clean and fresh air wherever they go. The proposed air purifier possesses a distinctive design that integrates a high electric field generator and UV light source. The high electric field technique effectively accumulates and neutralizes airborne particles, including dust, pollen, mold spores, and germs. Simultaneously, the UV light component kills dangerous microbes, such as viruses and bacteria, by breaking their DNA structure, offering cleaner and healthier air. To achieve best performance and energy economy the air purifier adopts an automated operation mode. The device operates only upon the detection of motion a human being.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140986151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The rice yield is poorly impacted due to lack of expertise in identifying the rice diseases in the field. Deep learning architectures are applied for classification of different crop diseases in some studies but they suffer performance degradation, less accuracy and overfitting posing a challenge for implementation in the real rice fields. To overcome the above challenges this study aims to propose a novel framework by fusing Visual Geometry Group16 (VGG16) with Convolutional Neural Network (CNN). The improved framework consists of 18 layers. The Convolution layer is added after pretrained VGG16 with max pooling layer to prevent overfitting. The set of optimal hyperparameters applied to the proposed framework is obtained through rigorous experimentation. The batch normalization and dropout layers are added with focus on improving accuracy and preventing overfitting. The proposed framework is evaluated in two stages. In stage 1 the proposed framework is compared with fine-tuned state-of-the-art VGG16, Inceptionv3, GoogLeNet, Resnet50, DenseNet121 and MobileNetV2. For stage 2 comparative analysis transfer learning models are optimized and compared. The proposed improved framework outperforms all the above-mentioned models in both the stages of comparative evaluation achieving the testing accuracy of 99.66%. The proposed framework performs without any sign of performance degradation and overfitting when tested on different datasets.
{"title":"A Novel Improved Framework for Multiclass Rice Disease Detection using Deep Learning","authors":"S. Kazi, Bhakti Palkar","doi":"10.52783/jes.3670","DOIUrl":"https://doi.org/10.52783/jes.3670","url":null,"abstract":"The rice yield is poorly impacted due to lack of expertise in identifying the rice diseases in the field. Deep learning architectures are applied for classification of different crop diseases in some studies but they suffer performance degradation, less accuracy and overfitting posing a challenge for implementation in the real rice fields. To overcome the above challenges this study aims to propose a novel framework by fusing Visual Geometry Group16 (VGG16) with Convolutional Neural Network (CNN). The improved framework consists of 18 layers. The Convolution layer is added after pretrained VGG16 with max pooling layer to prevent overfitting. The set of optimal hyperparameters applied to the proposed framework is obtained through rigorous experimentation. The batch normalization and dropout layers are added with focus on improving accuracy and preventing overfitting. The proposed framework is evaluated in two stages. In stage 1 the proposed framework is compared with fine-tuned state-of-the-art VGG16, Inceptionv3, GoogLeNet, Resnet50, DenseNet121 and MobileNetV2. For stage 2 comparative analysis transfer learning models are optimized and compared. The proposed improved framework outperforms all the above-mentioned models in both the stages of comparative evaluation achieving the testing accuracy of 99.66%. The proposed framework performs without any sign of performance degradation and overfitting when tested on different datasets.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In order to detect plant diseases in the leaves of chili plants, automatic learning is used in this study. Farmers are planting chilies with the intention of exporting them worldwide. Chili is a need for regular meals. There aren't many illnesses that need to be found in the leaves of chili plants. There are three types of chili plants: weak, diseased, and healthy. Weak and sick chili plants can be affected by diseases such as a harsh leaf, spot leaf, whitefly, yellowish, etc. It has been reported that research is underway to determine whether chile plants are safe to grow or polluted. But when it comes to agriculture, it's critical to recognize the damaged plant by its unique type. Various category diseases are studied using the HOG (Histogram of Oriented Gradients) of the leaf of the chili plant. The representative feature vectors in the feature vector are created using the mean value of every feature point. A typical feature vector and the Euclidean distance are used to calculate the outliers. For the Euclidean distance larger than 0.0025, 0.0016, and 0.00125, the average accuracy rate was 61.6%, 73.2%, and 81.00%, respectively, with the modified border point in the feature vector being 0.0016, 0.00125, and 0.0009. The results presented above suggest that machine-learning techniques for image processing can be used to determine the type of plant disease.
{"title":"Chili Disease Detection Using HOG with Euclidean Distance","authors":"Chauhan Pareshbhai Mansangbhai, Chintan Makwana, Hardikkumar Harishbhai Maheta","doi":"10.52783/jes.3654","DOIUrl":"https://doi.org/10.52783/jes.3654","url":null,"abstract":"In order to detect plant diseases in the leaves of chili plants, automatic learning is used in this study. Farmers are planting chilies with the intention of exporting them worldwide. Chili is a need for regular meals. There aren't many illnesses that need to be found in the leaves of chili plants. There are three types of chili plants: weak, diseased, and healthy. Weak and sick chili plants can be affected by diseases such as a harsh leaf, spot leaf, whitefly, yellowish, etc. It has been reported that research is underway to determine whether chile plants are safe to grow or polluted. But when it comes to agriculture, it's critical to recognize the damaged plant by its unique type. Various category diseases are studied using the HOG (Histogram of Oriented Gradients) of the leaf of the chili plant. The representative feature vectors in the feature vector are created using the mean value of every feature point. A typical feature vector and the Euclidean distance are used to calculate the outliers. For the Euclidean distance larger than 0.0025, 0.0016, and 0.00125, the average accuracy rate was 61.6%, 73.2%, and 81.00%, respectively, with the modified border point in the feature vector being 0.0016, 0.00125, and 0.0009. The results presented above suggest that machine-learning techniques for image processing can be used to determine the type of plant disease.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.4,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}