A study of Wireless Sensor Networks has been growing tremendously these days. Wireless Sensor Networks play a major role in various fields ranging from smart homes to health care. WSN’s operate independently in remote places. Because of tiny size of the nodes in such type of networks, they have a limited number of resources in terms of energy and power. Basically, sensor networks can be classified into flat and cluster based Wireless Sensor Networks. But, Clustering based Sensor Networks play a major role in reducing the energy consumption in Wireless Sensor Networks. Clustering also focuses on solving the No.s that arise during transmission of data. Clustering will group nodes into clusters and elects Cluster Heads for all clusters in the network. Then the nodes sense data and send that data to cluster head where the aggregation of data will take place. This paper focuses on various novel clustering techniques that improve the network’s lifetime.
{"title":"Novel Clustering Techniques in Wireless Sensor Networks – A Survey","authors":"T.C. Swetha Priya, R. Sridevi","doi":"10.32985/ijeces.14.7.1","DOIUrl":"https://doi.org/10.32985/ijeces.14.7.1","url":null,"abstract":"A study of Wireless Sensor Networks has been growing tremendously these days. Wireless Sensor Networks play a major role in various fields ranging from smart homes to health care. WSN’s operate independently in remote places. Because of tiny size of the nodes in such type of networks, they have a limited number of resources in terms of energy and power. Basically, sensor networks can be classified into flat and cluster based Wireless Sensor Networks. But, Clustering based Sensor Networks play a major role in reducing the energy consumption in Wireless Sensor Networks. Clustering also focuses on solving the No.s that arise during transmission of data. Clustering will group nodes into clusters and elects Cluster Heads for all clusters in the network. Then the nodes sense data and send that data to cluster head where the aggregation of data will take place. This paper focuses on various novel clustering techniques that improve the network’s lifetime.","PeriodicalId":41912,"journal":{"name":"International Journal of Electrical and Computer Engineering Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136025298","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}
Cellular network is the most popular network setup among today’s wireless communication systems. The primary resource in a cellular system is the spectrum for communication, and owing to the rising number of cellular users, the spectrum that is currently accessible from different service providers is depleting quickly. The resource or channel allocation is the most hindering task in cellular networks. Many efforts have been taken by many researchers to allocate the resources properly in order to increase the channel utilization and it is found that one effective method for reusing the channels inside a cell is device to device (D2D) communication. D2D communication was first developed in order to achieve the fundamental goals of fast data rates, widespread coverage with little latency, energy efficiency, and low per-information transmission costs. The dynamic behaviour of this network set-up again increases the risk of different types of interferences, which is another issue faced by the researchers. In this paper an effort is taken to understand and solve various aspects of channel allocation and Cellular networks have incorporated interference management in D2D communication especially. The two major issues of allocation of resource and management of interference in D2D communication is addressed here. This paper considers the meta heuristic algorithm namely Ant Colony Optimization (ACO) for resource allocation issue and interference management. The sum rate maximization is achieved through Game theory along with the concept of resource exchange in turn to increase the consistency of D2D communication setup. The results demonstrate that our algorithm can significantly increase the sum rate of D2D pairs when compared to other algorithms suggested by related works.
{"title":"Sum Rate Maximization and Consistency in D2D Communication Based on ACO and Game Theory","authors":"Amel Austine, Suji Pramila R","doi":"10.32985/ijeces.14.7.2","DOIUrl":"https://doi.org/10.32985/ijeces.14.7.2","url":null,"abstract":"Cellular network is the most popular network setup among today’s wireless communication systems. The primary resource in a cellular system is the spectrum for communication, and owing to the rising number of cellular users, the spectrum that is currently accessible from different service providers is depleting quickly. The resource or channel allocation is the most hindering task in cellular networks. Many efforts have been taken by many researchers to allocate the resources properly in order to increase the channel utilization and it is found that one effective method for reusing the channels inside a cell is device to device (D2D) communication. D2D communication was first developed in order to achieve the fundamental goals of fast data rates, widespread coverage with little latency, energy efficiency, and low per-information transmission costs. The dynamic behaviour of this network set-up again increases the risk of different types of interferences, which is another issue faced by the researchers. In this paper an effort is taken to understand and solve various aspects of channel allocation and Cellular networks have incorporated interference management in D2D communication especially. The two major issues of allocation of resource and management of interference in D2D communication is addressed here. This paper considers the meta heuristic algorithm namely Ant Colony Optimization (ACO) for resource allocation issue and interference management. The sum rate maximization is achieved through Game theory along with the concept of resource exchange in turn to increase the consistency of D2D communication setup. The results demonstrate that our algorithm can significantly increase the sum rate of D2D pairs when compared to other algorithms suggested by related works.","PeriodicalId":41912,"journal":{"name":"International Journal of Electrical and Computer Engineering Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136024966","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}
Ricardo Yauri, Oscar Llerena, Jorge Santiago, Jean Gonzales
Frosts reduce the ambient temperature to the freezing point of water, affecting the agricultural sector and the integrity of plant tissues, severely damaged by freezing, destroying plant cells. In addition, losses are generated in the economy due to the death of cattle due to cold, hunger, diseases, etc. Latin America is a region that depends, to a considerable extent, on its crops for its consumption and export, so frost represents an urgent problem to solve, considering that in Perú the area of agriculture is not technical. Among the methods most used by farmers is anticipated irrigation, through automatic learning techniques, which allows predicting the behavior of a variable based on previous historical data. In this paper, sprinkler irrigation is implemented in crops exposed to frost, using an automated system with machine learning techniques and prediction models. Therefore, three types of models are evaluated (linear regression, random forests, and decision trees) to predict the occurrence of frosts, reducing damage to plants. The results show that the protection activation indicator from 1.1°C to 1.7°C was updated to decrease the number of false positives. On the three models evaluated, it is determined that the most accurate method is the Random Forest Regression method, which has 80.91% reliability, absolute mean error, and mean square error close to zero.
{"title":"Sprinkler Irrigation Automation System to Reduce the Frost Impact Using Machine Learning","authors":"Ricardo Yauri, Oscar Llerena, Jorge Santiago, Jean Gonzales","doi":"10.32985/ijeces.14.7.8","DOIUrl":"https://doi.org/10.32985/ijeces.14.7.8","url":null,"abstract":"Frosts reduce the ambient temperature to the freezing point of water, affecting the agricultural sector and the integrity of plant tissues, severely damaged by freezing, destroying plant cells. In addition, losses are generated in the economy due to the death of cattle due to cold, hunger, diseases, etc. Latin America is a region that depends, to a considerable extent, on its crops for its consumption and export, so frost represents an urgent problem to solve, considering that in Perú the area of agriculture is not technical. Among the methods most used by farmers is anticipated irrigation, through automatic learning techniques, which allows predicting the behavior of a variable based on previous historical data. In this paper, sprinkler irrigation is implemented in crops exposed to frost, using an automated system with machine learning techniques and prediction models. Therefore, three types of models are evaluated (linear regression, random forests, and decision trees) to predict the occurrence of frosts, reducing damage to plants. The results show that the protection activation indicator from 1.1°C to 1.7°C was updated to decrease the number of false positives. On the three models evaluated, it is determined that the most accurate method is the Random Forest Regression method, which has 80.91% reliability, absolute mean error, and mean square error close to zero.","PeriodicalId":41912,"journal":{"name":"International Journal of Electrical and Computer Engineering Systems","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136024773","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}
This paper presents a parallel approach of the genetic algorithm (GA) over the Graphical Processing Unit (GPU) to solve the Traveling Salesman Problem (TSP). Since the earlier studies did not focus on implementing the island model in a persistent way, this paper introduces an approach, named Lightweight Island Model (LIM), that aims to implement the concept of persistent threads in the island model of the genetic algorithm. For that, we present the implementation details to convert the traditional island model, which is separated into multiple kernels, into a computing paradigm based on a persistent kernel. Many synchronization techniques, including cooperative groups and implicit synchronization, are discussed to reduce the CPU-GPU interaction that existed in the traditional island model. A new parallelization strategy is presented for distributing the work among live threads during the selection and crossover steps. The GPU configurations that lead to the best possible performance are also determined. The introduced approach will be compared, in terms of speedup and solution quality, with the traditional island model (TIM) as well as with related works that concentrated on suggesting a lighter version of the master-slave model, including switching among kernels (SAK) and scheduled light kernel (SLK) approaches. The results show that the new approach can increase the speed-up to 27x over serial CPU, 4.5x over the traditional island model, and up to 1.5–2x over SAK and SLK approaches.
提出了一种基于图形处理单元(GPU)的遗传算法并行求解旅行商问题(TSP)的方法。由于早期的研究没有关注以持久的方式实现岛模型，本文引入了一种名为轻量级岛模型(Lightweight island model, LIM)的方法，旨在在遗传算法的岛模型中实现持久线程的概念。为此，我们提出了将传统的岛模型(划分为多个核)转换为基于持久核的计算范式的实现细节。为了减少传统孤岛模型中存在的CPU-GPU交互，讨论了多种同步技术，包括协作组和隐式同步。提出了一种新的并行化策略，用于在选择和交叉步骤中在活动线程之间分配工作。还确定了导致最佳性能的GPU配置。在加速和解决方案质量方面，将介绍的方法与传统岛模型(TIM)以及专注于建议主从模型的轻量级版本的相关工作进行比较，包括在内核之间切换(SAK)和调度轻内核(SLK)方法。结果表明，该方法比串行CPU提高了27倍，比传统孤岛模型提高了4.5倍，比SAK和SLK方法提高了1.5-2x。
{"title":"A Lightweight Island Model for the Genetic Algorithm over GPGU","authors":"Mohammad Alraslan, Ahmad Hilal AlKurdi","doi":"10.32985/ijeces.14.7.3","DOIUrl":"https://doi.org/10.32985/ijeces.14.7.3","url":null,"abstract":"This paper presents a parallel approach of the genetic algorithm (GA) over the Graphical Processing Unit (GPU) to solve the Traveling Salesman Problem (TSP). Since the earlier studies did not focus on implementing the island model in a persistent way, this paper introduces an approach, named Lightweight Island Model (LIM), that aims to implement the concept of persistent threads in the island model of the genetic algorithm. For that, we present the implementation details to convert the traditional island model, which is separated into multiple kernels, into a computing paradigm based on a persistent kernel. Many synchronization techniques, including cooperative groups and implicit synchronization, are discussed to reduce the CPU-GPU interaction that existed in the traditional island model. A new parallelization strategy is presented for distributing the work among live threads during the selection and crossover steps. The GPU configurations that lead to the best possible performance are also determined. The introduced approach will be compared, in terms of speedup and solution quality, with the traditional island model (TIM) as well as with related works that concentrated on suggesting a lighter version of the master-slave model, including switching among kernels (SAK) and scheduled light kernel (SLK) approaches. The results show that the new approach can increase the speed-up to 27x over serial CPU, 4.5x over the traditional island model, and up to 1.5–2x over SAK and SLK approaches.","PeriodicalId":41912,"journal":{"name":"International Journal of Electrical and Computer Engineering Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136024808","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 for reliable user recognition (identification/authentication) techniques has grown in response to heightened security concerns and accelerated advances in networking, communication, and mobility. Biometrics, defined as the science of recognizing an individual based on his or her physical or behavioral characteristics, is gaining recognition as a method for determining an individual's identity. Various commercial, civilian, and forensic applications now use biometric systems to establish identity. The purpose of this paper is to design an efficient multimodal biometric system based on iris and retinal features to assure accurate human recognition and improve the accuracy of recognition using deep learning techniques. Deep learning models were tested using retinographies and iris images acquired from the MESSIDOR and CASIA-IrisV1 databases for the same person. The Iris region was segmented from the image using the custom Mask R-CNN method, and the unique blood vessels were segmented from retinal images of the same person using principal curvature. Then, in order to aid precise recognition, they optimally extract significant information from the segmented images of the iris and retina. The suggested model attained 98% accuracy, 98.1% recall, and 98.1% precision. It has been discovered that using a custom Mask R-CNN approach on Iris-Retina images improves efficiency and accuracy in person recognition.
{"title":"Achieving Information Security by multi-Modal Iris-Retina Biometric Approach Using Improved Mask R-CNN","authors":"Mohamed A. El-Sayed, Mohammed A. Abdel- Latif","doi":"10.32985/ijeces.14.6.5","DOIUrl":"https://doi.org/10.32985/ijeces.14.6.5","url":null,"abstract":"The need for reliable user recognition (identification/authentication) techniques has grown in response to heightened security concerns and accelerated advances in networking, communication, and mobility. Biometrics, defined as the science of recognizing an individual based on his or her physical or behavioral characteristics, is gaining recognition as a method for determining an individual's identity. Various commercial, civilian, and forensic applications now use biometric systems to establish identity. The purpose of this paper is to design an efficient multimodal biometric system based on iris and retinal features to assure accurate human recognition and improve the accuracy of recognition using deep learning techniques. Deep learning models were tested using retinographies and iris images acquired from the MESSIDOR and CASIA-IrisV1 databases for the same person. The Iris region was segmented from the image using the custom Mask R-CNN method, and the unique blood vessels were segmented from retinal images of the same person using principal curvature. Then, in order to aid precise recognition, they optimally extract significant information from the segmented images of the iris and retina. The suggested model attained 98% accuracy, 98.1% recall, and 98.1% precision. It has been discovered that using a custom Mask R-CNN approach on Iris-Retina images improves efficiency and accuracy in person recognition.","PeriodicalId":41912,"journal":{"name":"International Journal of Electrical and Computer Engineering Systems","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49579576","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}
One of the most promising forms of renewable energy is solar energy. However, efficient exploitation of this energy form is a topic of great interest, especially in obtaining the maximum amount of power from the solar photovoltaic (PV) system under changing environmental conditions. To solve this problem, it is necessary to propose an optimal algorithm. Therefore, this paper presents a feasible maximum power point tracking (MPPT) technique for DC/DC boost converters applied in load-connected stand-alone PV systems to extract the maximum available power. This proposed method is based on the combination of the modified perturb and observe (P&O) and fractional open circuit voltage (FOCV) algorithms. The effectiveness of the proposed technique is verified via time-domain simulation of the load-connected stand-alone PV system using PSIM software. The simulation results show a tracking efficiency with an average value of 99.85%, 99.87%, and 99.96% for tracking the MPP under varying loads, irradiation, and simultaneously varying temperature, load, and irradiation, respectively. In addition, tracking time is always stable at 0.02 sec for changing weather conditions in the large range. Therefore, the results of the proposed method indicate advantages compared to the conventional method.
{"title":"A Feasible MPPT Algorithm for the DC/DC Boost Converter","authors":"Hong Thanh Pham, Le Van Dai","doi":"10.32985/ijeces.14.6.11","DOIUrl":"https://doi.org/10.32985/ijeces.14.6.11","url":null,"abstract":"One of the most promising forms of renewable energy is solar energy. However, efficient exploitation of this energy form is a topic of great interest, especially in obtaining the maximum amount of power from the solar photovoltaic (PV) system under changing environmental conditions. To solve this problem, it is necessary to propose an optimal algorithm. Therefore, this paper presents a feasible maximum power point tracking (MPPT) technique for DC/DC boost converters applied in load-connected stand-alone PV systems to extract the maximum available power. This proposed method is based on the combination of the modified perturb and observe (P&O) and fractional open circuit voltage (FOCV) algorithms. The effectiveness of the proposed technique is verified via time-domain simulation of the load-connected stand-alone PV system using PSIM software. The simulation results show a tracking efficiency with an average value of 99.85%, 99.87%, and 99.96% for tracking the MPP under varying loads, irradiation, and simultaneously varying temperature, load, and irradiation, respectively. In addition, tracking time is always stable at 0.02 sec for changing weather conditions in the large range. Therefore, the results of the proposed method indicate advantages compared to the conventional method.","PeriodicalId":41912,"journal":{"name":"International Journal of Electrical and Computer Engineering Systems","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45189665","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}
Electronic Health Records, or EHRs, include private and sensitive information of a patient. The privacy of personal healthcare data can be protected through Hyperledger Fabric, a permissioned blockchain framework. A few Hyperledger Fabric- integrated EHR solutions have emerged in recent years. However, none of them implements the privacy-preserving techniques of Hyperledger Fabric to make transactions anonymous or preserve the transaction data privacy during the consensus. Our proposed architecture is built on Hyperledger Fabric and its privacy-preserving mechanisms, such as Identity Mixer, Private Data Collections, Channels and Transient Fields to securely store and transfer patient-sensitive data while providing anonymity and unlinkability of transactions.
电子健康记录(Electronic Health Records，简称ehr)包含患者的私人和敏感信息。个人医疗数据的隐私可以通过Hyperledger Fabric(一个经过许可的区块链框架)得到保护。近年来出现了一些集成了超级账本结构的电子病历解决方案。然而，它们都没有实现超级账本结构的隐私保护技术，使交易匿名或在共识期间保护交易数据隐私。我们提出的架构建立在超级账本结构及其隐私保护机制(如身份混合器、私有数据集合、通道和瞬态字段)之上，以安全地存储和传输患者敏感数据，同时提供交易的匿名性和不可链接性。
{"title":"A Privacy-Preserving Framework Using Hyperledger Fabric for EHR Sharing Applications","authors":"V. Thakkar, Vrushank Shah","doi":"10.32985/ijeces.14.6.6","DOIUrl":"https://doi.org/10.32985/ijeces.14.6.6","url":null,"abstract":"Electronic Health Records, or EHRs, include private and sensitive information of a patient. The privacy of personal healthcare data can be protected through Hyperledger Fabric, a permissioned blockchain framework. A few Hyperledger Fabric- integrated EHR solutions have emerged in recent years. However, none of them implements the privacy-preserving techniques of Hyperledger Fabric to make transactions anonymous or preserve the transaction data privacy during the consensus. Our proposed architecture is built on Hyperledger Fabric and its privacy-preserving mechanisms, such as Identity Mixer, Private Data Collections, Channels and Transient Fields to securely store and transfer patient-sensitive data while providing anonymity and unlinkability of transactions.","PeriodicalId":41912,"journal":{"name":"International Journal of Electrical and Computer Engineering Systems","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45299735","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}
This Paper is dedicated to the analysis of the evolution of the tangent vector during the Continuous Power Flow (CPF) iterations. The flow of the tangent slope (measured in degrees) is shown through the coefficient of lambda tangent vector component and the maximum voltage tangent vector component. A 17 Node Network was used for the purposes of this Paper. The system was modelled in MATLAB software. The admittance matrix of the node voltage equations was formulated and the functions in MATLAB were developed for the systematic formation of the node admittance matrix. Equations for the calculated network were generated in MATLAB. 32 Iterations were performed. Iterations and corrections of iterations were done manually. Firstly, the results for the tangent vectors calculated through the CPF program were compared to the results for the tangents directly calculated with mathematical formula for the tangent, and both results match. The chart, which contains the classical PV curve and the flow of tangent vectors during the CPF iterations, was developed based on the results obtained. The increase in the slope of the tangent in the PV diagram imposes a clear numerical stability limit by specifying an angle limit value, which can be used to trigger an alarm. In addition to the classic Power-Voltage (PV) curve, this serves as an additional indicator for ensuring voltage stability of the examined system.
{"title":"Illustration of the voltage stability by using the slope of the tangent vector component","authors":"Agron Bislimi","doi":"10.32985/ijeces.14.6.12","DOIUrl":"https://doi.org/10.32985/ijeces.14.6.12","url":null,"abstract":"This Paper is dedicated to the analysis of the evolution of the tangent vector during the Continuous Power Flow (CPF) iterations. The flow of the tangent slope (measured in degrees) is shown through the coefficient of lambda tangent vector component and the maximum voltage tangent vector component. A 17 Node Network was used for the purposes of this Paper. The system was modelled in MATLAB software. The admittance matrix of the node voltage equations was formulated and the functions in MATLAB were developed for the systematic formation of the node admittance matrix. Equations for the calculated network were generated in MATLAB. 32 Iterations were performed. Iterations and corrections of iterations were done manually. Firstly, the results for the tangent vectors calculated through the CPF program were compared to the results for the tangents directly calculated with mathematical formula for the tangent, and both results match. The chart, which contains the classical PV curve and the flow of tangent vectors during the CPF iterations, was developed based on the results obtained. The increase in the slope of the tangent in the PV diagram imposes a clear numerical stability limit by specifying an angle limit value, which can be used to trigger an alarm. In addition to the classic Power-Voltage (PV) curve, this serves as an additional indicator for ensuring voltage stability of the examined system.","PeriodicalId":41912,"journal":{"name":"International Journal of Electrical and Computer Engineering Systems","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47178459","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}
S. Prathima, Praveena N G, Sivachandar K, Srigitha S Nath, Sarala B
Rice is the primary food for almost half of the world’s population, especially for the people of Asian countries. There is a demand to improve the quality and increase the quantity of rice production to meet the food requirements of the increasing population. Bulk cultivation and quality production of crops need appropriate technology assistance over manual traditional methods. In this work, six popular Deep-CNN architectures, namely AlexNet, VGG-19, VGG-16, InceptionV3, MobileNet, and ResNet-50, are exploited to identify the diseases in paddy plants since they outperform most of the image classification applications. These CNN models are trained and tested with Plant Village dataset for classifying the paddy plant images into one of the four classes namely, Healthy, Brown Spot, Hispa, or Leaf Blast, based on the disease condition. The performance of the chosen architectures is compared with different hyper parameter settings. AlexNet outperformed other convolutional neural networks (CNNs) in this multiclass classification task, achieving an accuracy of 89.4% at the expense of a substantial number of network parameters, indicating the large model size of AlexNet. For developing mobile applications, the ResNet-50 architecture was adopted over other CNNs, since it has a comparatively smaller number of network parameters and a comparable accuracy of 86.1%. A fine-tuned ResNet-50 architecture supported mobile app, “Generic Paddy Plant Disease Detector (GP2D2)” has been developed for the identification of most commonly occurring diseases in paddy plants. This tool will be more helpful for the new generation of farmers in bulk cultivation and increasing the productivity of paddy. This work will give insight into the performance of CNN architectures in rice plant disease detection task and can be extended to other plants too.
{"title":"Generic Paddy Plant Disease Detector (GP2D2)","authors":"S. Prathima, Praveena N G, Sivachandar K, Srigitha S Nath, Sarala B","doi":"10.32985/ijeces.14.6.4","DOIUrl":"https://doi.org/10.32985/ijeces.14.6.4","url":null,"abstract":"Rice is the primary food for almost half of the world’s population, especially for the people of Asian countries. There is a demand to improve the quality and increase the quantity of rice production to meet the food requirements of the increasing population. Bulk cultivation and quality production of crops need appropriate technology assistance over manual traditional methods. In this work, six popular Deep-CNN architectures, namely AlexNet, VGG-19, VGG-16, InceptionV3, MobileNet, and ResNet-50, are exploited to identify the diseases in paddy plants since they outperform most of the image classification applications. These CNN models are trained and tested with Plant Village dataset for classifying the paddy plant images into one of the four classes namely, Healthy, Brown Spot, Hispa, or Leaf Blast, based on the disease condition. The performance of the chosen architectures is compared with different hyper parameter settings. AlexNet outperformed other convolutional neural networks (CNNs) in this multiclass classification task, achieving an accuracy of 89.4% at the expense of a substantial number of network parameters, indicating the large model size of AlexNet. For developing mobile applications, the ResNet-50 architecture was adopted over other CNNs, since it has a comparatively smaller number of network parameters and a comparable accuracy of 86.1%. A fine-tuned ResNet-50 architecture supported mobile app, “Generic Paddy Plant Disease Detector (GP2D2)” has been developed for the identification of most commonly occurring diseases in paddy plants. This tool will be more helpful for the new generation of farmers in bulk cultivation and increasing the productivity of paddy. This work will give insight into the performance of CNN architectures in rice plant disease detection task and can be extended to other plants too.","PeriodicalId":41912,"journal":{"name":"International Journal of Electrical and Computer Engineering Systems","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46472075","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}
Unsharp Masking is a popular image processing technique used for improving the sharpness of structures on dental radiographs. However, it produces overshoot artefact and intolerably amplifies noise. On radiographs, the overshoot artefact often resembles the indications of prosthesis misfit, pathosis, and pathological features associated with restorations. A noise- robust alternative to the Unsharp Masking algorithm, termed Gradient-adaptive Nonlinear Sharpening (GNS) which is free from overshoot and discontinuity artefacts, is proposed in this paper. In GNS, the product of the arbitrary scalar termed as ‘scale’ and the difference between the output of the Adaptive Edge Smoothing Filter (AESF) and the input image, weighted by the normalized gradient magnitude is added to the input image. AESF is a locally-adaptive 2D Gaussian smoothing kernel whose variance is directly proportional to the local value of the gradient magnitude. The dataset employed in this paper is downloaded from the Mendeley data repository having annotated panoramic dental radiographs of 116 patients. On 116 dental radiographs, the values of Saturation Evaluation Index (SEI), Sharpness of Ridges (SOR), Edge Model Based Contrast Metric (EMBCM), and Visual Information Fidelity (VIF) exhibited by the Unsharp Masking are 0.0048 ± 0.0021, 4.4 × 1013 ± 3.8 × 1013, 0.2634 ± 0.2732 and 0.9898 ± 0.0122. The values of these quality metrics corresponding to the GNS are 0.0042 ± 0.0017, 2.2 × 1013 ± 1.8 × 1013, 0.5224 ± 0.1825, and 1.0094 ± 0.0094. GNS exhibited lower values of SEI and SOR and higher values of EMBCM and VIF, compared to the Unsharp Masking. Lower values of SEI and SOR, respectively indicate that GNS is free from overshoot artefact and saturation and the quality of edges in the output images of GNS is less affected by noise. Higher values of EMBCM and VIF, respectively confirm that GNS is free from haloes as it produces thin and sharp edges and the sharpened images are of good information fidelity.
{"title":"Gradient-adaptive Nonlinear Sharpening for Dental Radiographs","authors":"Manoj T Joy, B. Priestly Shan, Geevarghese Titus","doi":"10.32985/ijeces.14.6.8","DOIUrl":"https://doi.org/10.32985/ijeces.14.6.8","url":null,"abstract":"Unsharp Masking is a popular image processing technique used for improving the sharpness of structures on dental radiographs. However, it produces overshoot artefact and intolerably amplifies noise. On radiographs, the overshoot artefact often resembles the indications of prosthesis misfit, pathosis, and pathological features associated with restorations. A noise- robust alternative to the Unsharp Masking algorithm, termed Gradient-adaptive Nonlinear Sharpening (GNS) which is free from overshoot and discontinuity artefacts, is proposed in this paper. In GNS, the product of the arbitrary scalar termed as ‘scale’ and the difference between the output of the Adaptive Edge Smoothing Filter (AESF) and the input image, weighted by the normalized gradient magnitude is added to the input image. AESF is a locally-adaptive 2D Gaussian smoothing kernel whose variance is directly proportional to the local value of the gradient magnitude. The dataset employed in this paper is downloaded from the Mendeley data repository having annotated panoramic dental radiographs of 116 patients. On 116 dental radiographs, the values of Saturation Evaluation Index (SEI), Sharpness of Ridges (SOR), Edge Model Based Contrast Metric (EMBCM), and Visual Information Fidelity (VIF) exhibited by the Unsharp Masking are 0.0048 ± 0.0021, 4.4 × 1013 ± 3.8 × 1013, 0.2634 ± 0.2732 and 0.9898 ± 0.0122. The values of these quality metrics corresponding to the GNS are 0.0042 ± 0.0017, 2.2 × 1013 ± 1.8 × 1013, 0.5224 ± 0.1825, and 1.0094 ± 0.0094. GNS exhibited lower values of SEI and SOR and higher values of EMBCM and VIF, compared to the Unsharp Masking. Lower values of SEI and SOR, respectively indicate that GNS is free from overshoot artefact and saturation and the quality of edges in the output images of GNS is less affected by noise. Higher values of EMBCM and VIF, respectively confirm that GNS is free from haloes as it produces thin and sharp edges and the sharpened images are of good information fidelity.","PeriodicalId":41912,"journal":{"name":"International Journal of Electrical and Computer Engineering Systems","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46691186","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：