The widespread implementation of the Internet of Things (IoT) has introduced several potential opportunities and benefits in all aspects of our life. However, regrettably, IoT is also accompanied by a range of vulnerabilities and susceptibility to attacks and anomalies. The primary goal of these attacks is to illicitly acquire confidential information from the system while also causing disruptions in system availability for authorized users. This research introduces an improved Long Short-Term Memory (LSTM) architecture designed to accurately detect attacks in an IoT environment. The hyper-parameters of LSTM are tuned employing a novel Memetic Self Adaptive Firefly Algorithm (MAFA). This research introduced a perturbation operator and integrated it into the proposed MAFA to prevent the occurrence of local optimum solutions in the standard firefly approach. With comparative assessment of the suggested methodology and other competing deep learning (DL) approaches, it has been determined that the proposed method outperforms in different performance measures including F1 score, F2 score, Fbeta score, precision, recall, ROC-AUC score and accuracy. The MAFA-LSTM methodology is superior to all other approaches studied, with an accuracy of 99.99%. It is highly efficient for accurately detecting intrusions in an IoT environment.
{"title":"Improved perturbation based hybrid firefly algorithm and long short-term memory based intelligent security model for IoT network intrusion detection","authors":"Janmenjoy Nayak , Pooja Puspita Priyadarshani , Pandit Byomakesha Dash","doi":"10.1016/j.compeleceng.2024.109926","DOIUrl":"10.1016/j.compeleceng.2024.109926","url":null,"abstract":"<div><div>The widespread implementation of the Internet of Things (IoT) has introduced several potential opportunities and benefits in all aspects of our life. However, regrettably, IoT is also accompanied by a range of vulnerabilities and susceptibility to attacks and anomalies. The primary goal of these attacks is to illicitly acquire confidential information from the system while also causing disruptions in system availability for authorized users. This research introduces an improved Long Short-Term Memory (LSTM) architecture designed to accurately detect attacks in an IoT environment. The hyper-parameters of LSTM are tuned employing a novel Memetic Self Adaptive Firefly Algorithm (MAFA). This research introduced a perturbation operator and integrated it into the proposed MAFA to prevent the occurrence of local optimum solutions in the standard firefly approach. With comparative assessment of the suggested methodology and other competing deep learning (DL) approaches, it has been determined that the proposed method outperforms in different performance measures including F1 score, F2 score, Fbeta score, precision, recall, ROC-AUC score and accuracy. The MAFA-LSTM methodology is superior to all other approaches studied, with an accuracy of 99.99%. It is highly efficient for accurately detecting intrusions in an IoT environment.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"121 ","pages":"Article 109926"},"PeriodicalIF":4.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142757337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
An adequate and reliable precautionary upkeep plan in power generation systems is required to reduce failures, to improve the generator's lifespan, to diminish repair costs and to ensure consistent power supply to consumers with managing the energy flows in power systems. The Generators’ Precautionary Upkeep Planning (GPUP) problem is a complex optimization problem. It is a critical challenge in the power generation industry, involving the optimization of maintenance schedules for power generators to minimize the generation reserve and maximize the reliability. This problem consists of several important restrictions which include the load power demand and the labour force restrictions. In this research paper, a Discrete Chaotic Mayfly Optimization (DCMFO) algorithm which uses Lévy flight random walk for female mayflies and chaotic local search move rule for male ones, is adapted for designing an appropriate precautionary upkeep scheme of a list of generators in power generation systems. The DCMFO algorithm is evaluated using 21-unit test thermal power system. The results indicate that unlike the classical DMFO algorithm, the DCMFO algorithm has proven to have superior optimization capabilities and to surpass all earlier adopted algorithms in performance. This reinforces DCMFO's standing as the current leading optimization algorithm for solving this particular problem, ever since its initial inception. The DCMFO's efficiency and reliability have been demonstrated with different cases through several statistical tests.
{"title":"Reliability-based preventive maintenance scheduling in power generation systems: A lévy flight and chaotic local search-based discrete mayfly algorithm","authors":"Soufiane Belagoune , Konstantinos Zervoudakis , Bousaadia Baadji , Atif Karim , Noureddine Bali","doi":"10.1016/j.compeleceng.2024.109904","DOIUrl":"10.1016/j.compeleceng.2024.109904","url":null,"abstract":"<div><div>An adequate and reliable precautionary upkeep plan in power generation systems is required to reduce failures, to improve the generator's lifespan, to diminish repair costs and to ensure consistent power supply to consumers with managing the energy flows in power systems. The Generators’ Precautionary Upkeep Planning (GPUP) problem is a complex optimization problem. It is a critical challenge in the power generation industry, involving the optimization of maintenance schedules for power generators to minimize the generation reserve and maximize the reliability. This problem consists of several important restrictions which include the load power demand and the labour force restrictions. In this research paper, a Discrete Chaotic Mayfly Optimization (DCMFO) algorithm which uses Lévy flight random walk for female mayflies and chaotic local search move rule for male ones, is adapted for designing an appropriate precautionary upkeep scheme of a list of generators in power generation systems. The DCMFO algorithm is evaluated using 21-unit test thermal power system. The results indicate that unlike the classical DMFO algorithm, the DCMFO algorithm has proven to have superior optimization capabilities and to surpass all earlier adopted algorithms in performance. This reinforces DCMFO's standing as the current leading optimization algorithm for solving this particular problem, ever since its initial inception. The DCMFO's efficiency and reliability have been demonstrated with different cases through several statistical tests.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"121 ","pages":"Article 109904"},"PeriodicalIF":4.0,"publicationDate":"2024-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-30DOI: 10.1016/j.compeleceng.2024.109820
Vishnu Namboodiri V , Rahul Goyal
Efficient wind speed forecasting is crucial for operations, optimizations, and decision-making interventions in wind energy systems. However, capturing nonlinearity and relevant information from the wind speed data poses challenges in developing efficient wind speed forecasting models. The present study proposes a novel hybrid ensemble wind speed forecasting model based on signal decomposition, deep learning model, and hyperparameter optimization for short-term applications to improve the model performances. This study comprises a novel architecture, a novel hybrid ensemble wind speed forecasting model, a two-level optimization strategy, and a transfer learning approach. The present study consists of three stages: model development, validation, and transfer learning. The proposed model employs wavelet transform, deep learning models such as Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BiLSTM), Convolutional Neural Network (CNN), and a combined model using Convolutional Neural Network and Bidirectional Long Short-Term Memory (CNN-BiLSTM) and meta-heuristic optimization algorithms. The novel architecture of the CNN-BiLSTM model is capable of exhibiting better results than baseline models. Artificial Bee Colony (ABC) and the Differential Evolution (DE) algorithms are explored to optimize the model hyperparameters. The ensemble weights of the proposed model are optimized through a DE algorithm. The model implementation is presented through a transfer learning technique using pre-trained models from the model development and validation phases. The model comparison results indicate that the proposed models outperform these models. The transfer learning results of Proposed Model-1 (PM-1) are Root Mean Squared Error (RMSE)- 0.1943 m/s, Mean Squared Error (MSE)- 0.0378 m/s, Mean Absolute Error (MAE) 0.1542 m/s, coefficient of determination (R2)- 0.9883, and Index of Agreement (IA)- 0.9997. The Proposed Model-2 (PM-2) is 0.1554 m/s (RMSE), 0.0241 m/s (MSE), 0.1263 m/s (MAE), 0.9915 (R2), and 0.9998 (IA). The proposed model architecture and the transfer learning are viable approaches for wind speed forecasting applications.
有效的风速预测对风能系统的运行、优化和决策干预至关重要。然而，从风速数据中获取非线性和相关信息对开发有效的风速预报模型提出了挑战。本文提出了一种基于信号分解、深度学习和超参数优化的混合集合风速预报模型，以提高模型的短期应用性能。本研究包括一种新的体系结构、一种新的混合集合风速预测模型、两级优化策略和迁移学习方法。本研究分为三个阶段：模型开发、验证和迁移学习。该模型采用小波变换、长短期记忆（LSTM）、双向长短期记忆（BiLSTM）、卷积神经网络（CNN）等深度学习模型，以及卷积神经网络和双向长短期记忆（CNN-BiLSTM）组合模型和元启发式优化算法。CNN-BiLSTM模型的新结构能够比基线模型显示更好的结果。探讨了人工蜂群（ABC）算法和差分进化（DE）算法来优化模型超参数。通过DE算法对模型的集成权值进行优化。模型实现是通过迁移学习技术来实现的，该技术使用来自模型开发和验证阶段的预训练模型。模型对比结果表明，本文提出的模型优于这些模型。提议模型-1 （PM-1）的迁移学习结果为均方根误差(RMSE)- 0.1943 m/s，均方误差(MSE)- 0.0378 m/s，平均绝对误差（MAE） 0.1542 m/s，决定系数(R2)- 0.9883，一致指数(IA)- 0.9997。模型-2 （PM-2）分别为0.1554 m/s （RMSE）、0.0241 m/s （MSE）、0.1263 m/s （MAE）、0.9915 （R2）和0.9998 （IA）。所提出的模型结构和迁移学习是风速预报应用的可行方法。
{"title":"A Novel Hybrid Ensemble Wind Speed Forecasting Model Employing Wavelet Transform and Deep Learning","authors":"Vishnu Namboodiri V , Rahul Goyal","doi":"10.1016/j.compeleceng.2024.109820","DOIUrl":"10.1016/j.compeleceng.2024.109820","url":null,"abstract":"<div><div>Efficient wind speed forecasting is crucial for operations, optimizations, and decision-making interventions in wind energy systems. However, capturing nonlinearity and relevant information from the wind speed data poses challenges in developing efficient wind speed forecasting models. The present study proposes a novel hybrid ensemble wind speed forecasting model based on signal decomposition, deep learning model, and hyperparameter optimization for short-term applications to improve the model performances. This study comprises a novel architecture, a novel hybrid ensemble wind speed forecasting model, a two-level optimization strategy, and a transfer learning approach. The present study consists of three stages: model development, validation, and transfer learning. The proposed model employs wavelet transform, deep learning models such as Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BiLSTM), Convolutional Neural Network (CNN), and a combined model using Convolutional Neural Network and Bidirectional Long Short-Term Memory (CNN-BiLSTM) and meta-heuristic optimization algorithms. The novel architecture of the CNN-BiLSTM model is capable of exhibiting better results than baseline models. Artificial Bee Colony (ABC) and the Differential Evolution (DE) algorithms are explored to optimize the model hyperparameters. The ensemble weights of the proposed model are optimized through a DE algorithm. The model implementation is presented through a transfer learning technique using pre-trained models from the model development and validation phases. The model comparison results indicate that the proposed models outperform these models. The transfer learning results of Proposed Model-1 (PM-1) are Root Mean Squared Error (RMSE)- 0.1943 m/s, Mean Squared Error (MSE)- 0.0378 m/s, Mean Absolute Error (MAE) 0.1542 m/s, coefficient of determination (R<sup>2</sup>)- 0.9883, and Index of Agreement (IA)- 0.9997. The Proposed Model-2 (PM-2) is 0.1554 m/s (RMSE), 0.0241 m/s (MSE), 0.1263 m/s (MAE), 0.9915 (R<sup>2</sup>), and 0.9998 (IA). The proposed model architecture and the transfer learning are viable approaches for wind speed forecasting applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"121 ","pages":"Article 109820"},"PeriodicalIF":4.0,"publicationDate":"2024-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-30DOI: 10.1016/j.compeleceng.2024.109903
Mohammad Sarkhosh, Abbas Fattahi
The increasing adoption of electric vehicles (EVs) poses significant challenges for power system operations, requiring scalable coordination to mitigate their negative impacts and leverage their potential to enhance grid conditions. This paper introduces a scalable, three-layer hierarchical framework for optimal EV charge and discharge scheduling (EVCDS) that coordinates key agents: EVs, EV aggregators (EVAs), and the distribution network operator (DNO). The optimization problem is developed as an exchange problem and solved using the alternating direction method of multipliers (ADMM) in a decentralized approach. The proposed EVCDS addresses economic factors by minimizing battery degradation costs at the EV level and charging costs at the EVA level, while managing technical aspects at the DNO level by minimizing load curve variance and limiting power capacity. Moreover,voltages at network nodes are calculated using the DistFlow model to simplify the optimization and ensure compliance with standard operational limits. Compared to uncoordinated EV charging, EVCDS reduces load profile deviations by 85% and total costs by 91%, while also improving bus voltage profiles.
{"title":"Network-aware electric vehicle charging/discharging scheduling for grid load management in a hierarchical framework","authors":"Mohammad Sarkhosh, Abbas Fattahi","doi":"10.1016/j.compeleceng.2024.109903","DOIUrl":"10.1016/j.compeleceng.2024.109903","url":null,"abstract":"<div><div>The increasing adoption of electric vehicles (EVs) poses significant challenges for power system operations, requiring scalable coordination to mitigate their negative impacts and leverage their potential to enhance grid conditions. This paper introduces a scalable, three-layer hierarchical framework for optimal EV charge and discharge scheduling (EVCDS) that coordinates key agents: EVs, EV aggregators (EVAs), and the distribution network operator (DNO). The optimization problem is developed as an exchange problem and solved using the alternating direction method of multipliers (ADMM) in a decentralized approach. The proposed EVCDS addresses economic factors by minimizing battery degradation costs at the EV level and charging costs at the EVA level, while managing technical aspects at the DNO level by minimizing load curve variance and limiting power capacity. Moreover,voltages at network nodes are calculated using the DistFlow model to simplify the optimization and ensure compliance with standard operational limits. Compared to uncoordinated EV charging, EVCDS reduces load profile deviations by 85% and total costs by 91%, while also improving bus voltage profiles.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"121 ","pages":"Article 109903"},"PeriodicalIF":4.0,"publicationDate":"2024-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The use of IoT in healthcare has undoubtedly brought many significant adaptations and benefits that changed medical facilities. However, the possibility of unauthorized access to private medical data is a serious issue that requires appropriate attention to protect the user’s privacy. Recently, a proposed scheme by Gurjot et al. suggested an authentication mechanism to provide anonymity and other security characteristics. We did the security analysis and informally proved that their scheme is prone to various attacks, such as failure to offer perfect forward secrecy, ephemeral secret leakage, traceability, replay, stolen device attacks, and also face desynchronization issues. These issues make the proposed scheme unsuitable for the healthcare system. Therefore, there is an impelling need to design an authentication mechanism that can restrict the attacker from getting any sensitive information. Considering the above requirements, we present a novel Zero Knowledge Proof based Authenticated Key Agreement (ZKP-AKA) protocol. The security of our proposed authentication mechanism is examined using the informal (non-mathematical) and formal (Scyther tool) security verification to confirm that the proposed protocol offers the prominent security features mentioned above. We also measure the performance to show that our proposed mechanism is suitable for IoT devices in the healthcare intelligent system by doing a comparative analysis with its competitors in terms of communication, computational, message exchange and energy consumption costs.
{"title":"iZKP-AKA: A secure and improved ZKP-AKA protocol for sustainable healthcare","authors":"Shubham Kumar , Kanhaiya Kumar , Abhishek Anand , Awaneesh Kumar Yadav , Manoj Misra , An Braeken","doi":"10.1016/j.compeleceng.2024.109886","DOIUrl":"10.1016/j.compeleceng.2024.109886","url":null,"abstract":"<div><div>The use of IoT in healthcare has undoubtedly brought many significant adaptations and benefits that changed medical facilities. However, the possibility of unauthorized access to private medical data is a serious issue that requires appropriate attention to protect the user’s privacy. Recently, a proposed scheme by Gurjot et al. suggested an authentication mechanism to provide anonymity and other security characteristics. We did the security analysis and informally proved that their scheme is prone to various attacks, such as failure to offer perfect forward secrecy, ephemeral secret leakage, traceability, replay, stolen device attacks, and also face desynchronization issues. These issues make the proposed scheme unsuitable for the healthcare system. Therefore, there is an impelling need to design an authentication mechanism that can restrict the attacker from getting any sensitive information. Considering the above requirements, we present a novel Zero Knowledge Proof based Authenticated Key Agreement (ZKP-AKA) protocol. The security of our proposed authentication mechanism is examined using the informal (non-mathematical) and formal (Scyther tool) security verification to confirm that the proposed protocol offers the prominent security features mentioned above. We also measure the performance to show that our proposed mechanism is suitable for IoT devices in the healthcare intelligent system by doing a comparative analysis with its competitors in terms of communication, computational, message exchange and energy consumption costs.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"122 ","pages":"Article 109886"},"PeriodicalIF":4.0,"publicationDate":"2024-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-30DOI: 10.1016/j.compeleceng.2024.109897
Wenjiang Shang , Hailing Li , Xiaoze Ni , Ting Chen , Tao Liu
In the swiftly advancing media sector, piracy remains a significant challenge, eroding consumer willingness to pay, undermining rightful economic gains for copyright holders, and diluting creative incentives for content creators. Existing copyright protection mechanisms are inadequate for robust intellectual property safeguarding within complex digital environments, especially lacking in lifecycle tracking, authenticity verification, and dispute resolution. This paper introduces BlockGuard, a pioneering blockchain-based credible digital copyright management system designed to mitigate these issues through strategic use of blockchain and digital watermarking techniques. Furthermore, it enhances issue resolution via the application of Non-Fungible Token (NFT) contracts. BlockGuard aims to achieve three primary objectives. Firstly, it enables comprehensive lifecycle tracking of digital assets, ensuring visibility from content creation to its diverse applications. Secondly, by employing digital watermarking, it provides stringent authenticity verification to drastically reduce copyright infringements. Lastly, leveraging blockchain’s immutability and transparency, it streamlines dispute resolution processes. BlockGuard presents an efficient, secure, and transparent approach for managing digital copyrights in today’s media landscape. It showcases a detailed protection center and public appraisal workflow, and verifies the effectiveness of three originality detection processes. In terms of performance, BlockGuard requires 88% of the storage space on secondary storage compared to conventional solutions (that store only the original image) and incurs minimal storage overhead at the kilobyte level on blockchain storage. Furthermore, its most resource-intensive operation consumes no more than 200,000 gas, with other operations requiring no more than 100,000 gas, equivalent to a standard Ethereum transaction.
{"title":"BlockGuard: Advancing digital copyright integrity with blockchain technique","authors":"Wenjiang Shang , Hailing Li , Xiaoze Ni , Ting Chen , Tao Liu","doi":"10.1016/j.compeleceng.2024.109897","DOIUrl":"10.1016/j.compeleceng.2024.109897","url":null,"abstract":"<div><div>In the swiftly advancing media sector, piracy remains a significant challenge, eroding consumer willingness to pay, undermining rightful economic gains for copyright holders, and diluting creative incentives for content creators. Existing copyright protection mechanisms are inadequate for robust intellectual property safeguarding within complex digital environments, especially lacking in lifecycle tracking, authenticity verification, and dispute resolution. This paper introduces BlockGuard, a pioneering blockchain-based credible digital copyright management system designed to mitigate these issues through strategic use of blockchain and digital watermarking techniques. Furthermore, it enhances issue resolution via the application of Non-Fungible Token (NFT) contracts. BlockGuard aims to achieve three primary objectives. Firstly, it enables comprehensive lifecycle tracking of digital assets, ensuring visibility from content creation to its diverse applications. Secondly, by employing digital watermarking, it provides stringent authenticity verification to drastically reduce copyright infringements. Lastly, leveraging blockchain’s immutability and transparency, it streamlines dispute resolution processes. BlockGuard presents an efficient, secure, and transparent approach for managing digital copyrights in today’s media landscape. It showcases a detailed protection center and public appraisal workflow, and verifies the effectiveness of three originality detection processes. In terms of performance, BlockGuard requires 88% of the storage space on secondary storage compared to conventional solutions (that store only the original image) and incurs minimal storage overhead at the kilobyte level on blockchain storage. Furthermore, its most resource-intensive operation consumes no more than 200,000 gas, with other operations requiring no more than 100,000 gas, equivalent to a standard Ethereum transaction.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"122 ","pages":"Article 109897"},"PeriodicalIF":4.0,"publicationDate":"2024-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-29DOI: 10.1016/j.compeleceng.2024.109891
Nayana N. Murthy, K. Thippeswamy
Globally, Lung Cancer (LC) continues to be the primary cause of cancer-related death. Effective diagnosis is essential to save the lives of people. Nevertheless, manual Computed Tomography (CT) scan analysis takes more time and is inaccurate. The principal intention of this paper is to establish a hybrid Fuzzy-based Efficient Residual Network (Fuzzy-ER Net) for LC classification. The prime phase is the acquisition of input CT images from the database and the obtained CT image is sent to the pre-processing stage where noise is eradicated utilizing a Double bilateral filter. Thereafter, segmentation of the lung lobe is done by using a Dual-Attention V-network (DAV-Net). Moreover, feature extraction is performed, where features that are extracted include area, irregularity index, Local Vector Pattern (LVP), Local Gabor XOR Pattern (LGXP), and Statistical Fuzzy Local Binary Pattern (SFLBP). Eventually, LC classification is done by utilizing the proposed hybrid Fuzzy-ER Net. Here, the proposed Fuzzy-ER Net is newly devised by assimilating fuzzy concepts, EfficientNet, and Deep Residual Network (DRN). Additionally, the evaluation of the Fuzzy-ER Net on the basis of various metrics shows that it achieved maximum accuracy, True Positive Rate (TPR), of 93.2 % and 94.8 %, minimum False Positive Rate (FPR) is 5.7 %, maximum precision of 92.6 %, and maximum F-measure of 93.7 %.
{"title":"Fuzzy-ER Net: Fuzzy-based Efficient Residual Network-based lung cancer classification","authors":"Nayana N. Murthy, K. Thippeswamy","doi":"10.1016/j.compeleceng.2024.109891","DOIUrl":"10.1016/j.compeleceng.2024.109891","url":null,"abstract":"<div><div>Globally, Lung Cancer (LC) continues to be the primary cause of cancer-related death. Effective diagnosis is essential to save the lives of people. Nevertheless, manual Computed Tomography (CT) scan analysis takes more time and is inaccurate. The principal intention of this paper is to establish a hybrid Fuzzy-based Efficient Residual Network (Fuzzy-ER Net) for LC classification. The prime phase is the acquisition of input CT images from the database and the obtained CT image is sent to the pre-processing stage where noise is eradicated utilizing a Double bilateral filter. Thereafter, segmentation of the lung lobe is done by using a Dual-Attention V-network (DAV-Net). Moreover, feature extraction is performed, where features that are extracted include area, irregularity index, Local Vector Pattern (LVP), Local Gabor XOR Pattern (LGXP), and Statistical Fuzzy Local Binary Pattern (SFLBP). Eventually, LC classification is done by utilizing the proposed hybrid Fuzzy-ER Net. Here, the proposed Fuzzy-ER Net is newly devised by assimilating fuzzy concepts, EfficientNet, and Deep Residual Network (DRN). Additionally, the evaluation of the Fuzzy-ER Net on the basis of various metrics shows that it achieved maximum accuracy, True Positive Rate (TPR), of 93.2 % and 94.8 %, minimum False Positive Rate (FPR) is 5.7 %, maximum precision of 92.6 %, and maximum F-measure of 93.7 %.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"121 ","pages":"Article 109891"},"PeriodicalIF":4.0,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The complexity of system identification problems has been escalated due to their diverse range of applications. In this paper, the non-linear system identification problem is addressed by proposing a deep random vector functional link network (Deep-RVFLN) based on the optimized variational mode decomposition (OVMD). The proposed method has a faster learning speed and trains the network accurately without tuning parameters. Introducing a random link network connecting the input and output layers may lead to reduction in model complexity. To enhance the accuracy and reduce errors, a random vector functional link network (RVFLN) has been implemented with an increased number of hidden layers. The variational mode decomposition (VMD) algorithm is applied to decompose the signal and select optimum modes using an improved particle swarm optimization (IPSO) algorithm. In this method, the data fidelity factor () and the number of decomposition modes () are chosen by a new discrete Teaser energy operator (DTEO). The DTEO algorithm is utilized to estimate Teaser energy and it serves as a dependable indicator of overall system reliability. To test the efficacy of the model, three complex non-linear benchmark models named autoregressive (AR), moving average (MA), and autoregressive moving average (ARMA) have been considered with examples 1, 2, and 3 respectively. Based on the results and analysis, the proposed method was found to be better than other state-of-the-art methods. Finally, the proposed Deep-RVFLN identifier is implemented on a high-speed reconfigurable field-programmable gate array (FPGA) to validate the efficacy of the proposed method for non-linear system identification in the hardware platform.
{"title":"A robust variational mode decomposition based deep random vector functional link network for dynamic system identification","authors":"Rakesh Kumar Pattanaik , Susanta Kumar Rout , Mrutyunjaya Sahani , Mihir Narayan Mohanty","doi":"10.1016/j.compeleceng.2024.109887","DOIUrl":"10.1016/j.compeleceng.2024.109887","url":null,"abstract":"<div><div>The complexity of system identification problems has been escalated due to their diverse range of applications. In this paper, the non-linear system identification problem is addressed by proposing a deep random vector functional link network (Deep-RVFLN) based on the optimized variational mode decomposition (OVMD). The proposed method has a faster learning speed and trains the network accurately without tuning parameters. Introducing a random link network connecting the input and output layers may lead to reduction in model complexity. To enhance the accuracy and reduce errors, a random vector functional link network (RVFLN) has been implemented with an increased number of hidden layers. The variational mode decomposition (VMD) algorithm is applied to decompose the signal and select optimum modes using an improved particle swarm optimization (IPSO) algorithm. In this method, the data fidelity factor (<span><math><mi>α</mi></math></span>) and the number of decomposition modes (<span><math><mi>k</mi></math></span>) are chosen by a new discrete Teaser energy operator (DTEO). The DTEO algorithm is utilized to estimate Teaser energy and it serves as a dependable indicator of overall system reliability. To test the efficacy of the model, three complex non-linear benchmark models named autoregressive (AR), moving average (MA), and autoregressive moving average (ARMA) have been considered with examples 1, 2, and 3 respectively. Based on the results and analysis, the proposed method was found to be better than other state-of-the-art methods. Finally, the proposed Deep-RVFLN identifier is implemented on a high-speed reconfigurable field-programmable gate array (FPGA) to validate the efficacy of the proposed method for non-linear system identification in the hardware platform.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"122 ","pages":"Article 109887"},"PeriodicalIF":4.0,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-28DOI: 10.1016/j.compeleceng.2024.109857
Roop Singh , Raju Pal , Deepak Joshi
Optimal embedding factor selection is still an open challenging issue in video watermarking. To address the same, this paper introduces a modified gravitational search algorithm (MGSA) based video watermarking (VW) scheme, termed VW-MGSA. In this proposed method, a novel variant of gravitational search algorithm i.e MGSA is employed to attain multiple optimal embedding factors (MOEF). VW-MGSA embeds watermark logo into maximum entropy blocks of size 8 × 8 followed by 1-level RDWT and Schur transform. The proposed GSA variant (MGSA) was evaluated experimentally and statistically using 22 standard benchmark functions, covering unimodal, multimodal, and fixed-dimension categories. The performance has been assessed using key metrics such as mean, standard deviation, Friedman test, and convergence graphs. These results confirm that the proposed variant outperforms existing meta-heuristic algorithms. Moreover, VW-MGSA has been validated on 8 standard benchmark videos over 19 attacks and evaluated using PSNR, SSIM, and NC metrics. The experimental and statistical results confirm that VW-MGSA outperforms existing video watermarking methods. It significantly improves the balance between imperceptibility and robustness compared to existing methods, with a measured improvement of 39.63%. The improved performance of the VW-MGSA can be applied to real-world platforms like Netflix and Amazon Prime to safeguard licensed content, with watermarks aiding in tracing piracy sources.
{"title":"Optimal frame selection-based watermarking using a meta-heuristic algorithm for securing video content","authors":"Roop Singh , Raju Pal , Deepak Joshi","doi":"10.1016/j.compeleceng.2024.109857","DOIUrl":"10.1016/j.compeleceng.2024.109857","url":null,"abstract":"<div><div>Optimal embedding factor selection is still an open challenging issue in video watermarking. To address the same, this paper introduces a modified gravitational search algorithm (MGSA) based video watermarking (VW) scheme, termed VW-MGSA. In this proposed method, a novel variant of gravitational search algorithm i.e MGSA is employed to attain multiple optimal embedding factors (MOEF). VW-MGSA embeds watermark logo into maximum entropy blocks of size 8 × 8 followed by 1-level RDWT and Schur transform. The proposed GSA variant (MGSA) was evaluated experimentally and statistically using 22 standard benchmark functions, covering unimodal, multimodal, and fixed-dimension categories. The performance has been assessed using key metrics such as mean, standard deviation, Friedman test, and convergence graphs. These results confirm that the proposed variant outperforms existing meta-heuristic algorithms. Moreover, VW-MGSA has been validated on 8 standard benchmark videos over 19 attacks and evaluated using PSNR, SSIM, and NC metrics. The experimental and statistical results confirm that VW-MGSA outperforms existing video watermarking methods. It significantly improves the balance between imperceptibility and robustness compared to existing methods, with a measured improvement of 39.63%. The improved performance of the VW-MGSA can be applied to real-world platforms like Netflix and Amazon Prime to safeguard licensed content, with watermarks aiding in tracing piracy sources.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"121 ","pages":"Article 109857"},"PeriodicalIF":4.0,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-28DOI: 10.1016/j.compeleceng.2024.109932
Javad Rahmani-Fard , Mohammed Jamal Mohammed
This paper focuses on enhancing the sensorless control performance of a 12slots/19 poles yokeless and segmented armature axial flux-switching sandwiched permanent-magnet motor by proposing a rotor position Extended State Observer based on a extended back-EMF model method. Additionally, an adaptive sliding mode speed loop compensation method is introduced to address the significant cogging torque of the motor. By injecting the observed cogging torque as compensation into the q-axis current harmonic, this method aims to improve the motor's vibration and disturbance rejection performance in sliding mode control while eliminating steady-state errors in rotor speed and position estimation. The effectiveness of these control algorithms is validated through simulations and experiments under various operating conditions, demonstrating their potential for improving the position signal-free tracking performance of the investigated motor. The results indicate that the proposed control strategies achieve a maximum speed estimation error of approximately 1 rpm during steady-state operation and a maximum position estimation error of about 1.5°, showcasing high accuracy and robustness against disturbances.
{"title":"Advanced sensorless control of a 12S/19P YASA-AFFSSPM motor using extended state observer and adaptive sliding mode control","authors":"Javad Rahmani-Fard , Mohammed Jamal Mohammed","doi":"10.1016/j.compeleceng.2024.109932","DOIUrl":"10.1016/j.compeleceng.2024.109932","url":null,"abstract":"<div><div>This paper focuses on enhancing the sensorless control performance of a 12slots/19 poles yokeless and segmented armature axial flux-switching sandwiched permanent-magnet motor by proposing a rotor position Extended State Observer based on a extended back-EMF model method. Additionally, an adaptive sliding mode speed loop compensation method is introduced to address the significant cogging torque of the motor. By injecting the observed cogging torque as compensation into the q-axis current harmonic, this method aims to improve the motor's vibration and disturbance rejection performance in sliding mode control while eliminating steady-state errors in rotor speed and position estimation. The effectiveness of these control algorithms is validated through simulations and experiments under various operating conditions, demonstrating their potential for improving the position signal-free tracking performance of the investigated motor. The results indicate that the proposed control strategies achieve a maximum speed estimation error of approximately 1 rpm during steady-state operation and a maximum position estimation error of about 1.5°, showcasing high accuracy and robustness against disturbances.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"121 ","pages":"Article 109932"},"PeriodicalIF":4.0,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号