Computers & Electrical Engineering最新文献

英文中文

Underwater image restoration via multiscale optical attenuation compensation and adaptive dark channel dehazing

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2025-03-02 DOI: 10.1016/j.compeleceng.2025.110228

Shuai Liu , Peng Chen , Jianyu Lan , Jianru Li , Zhengxiang Shen , Zhanshan Wang

Underwater images often suffer from color cast and low visibility due to inherent factors such as light absorption, scattering, and turbidity. The quality-degraded underwater images are unfavorable for underwater research and applications.To effectively deal with these quality degradation issues, this paper presents a novel restoration framework tailored specifically for underwater images, aiming to restore their natural clarity and improve their visual quality. Firstly, a multi-scale optical attenuation compensation color correction algorithm is employed to correct the color deviations of underwater images. Subsequently, an adaptive dark channel dehazing algorithm is proposed, including the global background light estimation algorithm based on multiple optical prior properties and a more sensitive segmentation transmission map estimation algorithm. Our approach integrates advanced image restoration techniques with domain-specific optimizations, ensuring robust performance across diverse underwater conditions. We comprehensively evaluate our method on a wide range of underwater image datasets, demonstrating its effectiveness in restoring color fidelity, contrast, and texture details. Furthermore, we analyze the quantitative and qualitative impacts of our framework, showcasing its advantages over existing state-of-the-art methods. Our work not only advances the field of underwater image restoration but also provides valuable insights into designing future restoration algorithms for this domain.

{"title":"Underwater image restoration via multiscale optical attenuation compensation and adaptive dark channel dehazing","authors":"Shuai Liu , Peng Chen , Jianyu Lan , Jianru Li , Zhengxiang Shen , Zhanshan Wang","doi":"10.1016/j.compeleceng.2025.110228","DOIUrl":"10.1016/j.compeleceng.2025.110228","url":null,"abstract":"<div><div>Underwater images often suffer from color cast and low visibility due to inherent factors such as light absorption, scattering, and turbidity. The quality-degraded underwater images are unfavorable for underwater research and applications.To effectively deal with these quality degradation issues, this paper presents a novel restoration framework tailored specifically for underwater images, aiming to restore their natural clarity and improve their visual quality. Firstly, a multi-scale optical attenuation compensation color correction algorithm is employed to correct the color deviations of underwater images. Subsequently, an adaptive dark channel dehazing algorithm is proposed, including the global background light estimation algorithm based on multiple optical prior properties and a more sensitive segmentation transmission map estimation algorithm. Our approach integrates advanced image restoration techniques with domain-specific optimizations, ensuring robust performance across diverse underwater conditions. We comprehensively evaluate our method on a wide range of underwater image datasets, demonstrating its effectiveness in restoring color fidelity, contrast, and texture details. Furthermore, we analyze the quantitative and qualitative impacts of our framework, showcasing its advantages over existing state-of-the-art methods. Our work not only advances the field of underwater image restoration but also provides valuable insights into designing future restoration algorithms for this domain.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110228"},"PeriodicalIF":4.0,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143527229","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}

引用次数: 0

A PUF-based lightweight identity authentication protocol for Internet of Vehicles

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2025-03-01 DOI: 10.1016/j.compeleceng.2025.110210

Honglei Men, Li Cao, Guoli Zheng, Liang Chen

To address the efficiency issues of vehicle identity authentication schemes based on cryptographic primitives in vehicular networks, a novel lightweight identity authentication and key agreement protocol based on Physical Unclonable Functions (PUFs) is proposed. The proposed protocol authenticates identities by generating Challenge-Response Pair (CRP) data in real time, avoiding the privacy leaks and security risks associated with traditional PUF authentication, which relies on the verifier’s pre-stored CRP data. Additionally, the proposed protocol eliminates the use of complex cryptographic primitives and digital certificates in the authentication process, thereby reducing the computational and communication overhead for verifiers and the trusted authority, significantly enhancing authentication efficiency. The security analysis shows that the protocol not only protects the real identities of vehicles but also provides traceability of malicious identities, effectively defending against various security threats, including physical cloning and replay attacks. Compared to cryptographic-based identity authentication protocols, this lightweight protocol is better suited for resource-constrained and latency-sensitive vehicular network environments.

{"title":"A PUF-based lightweight identity authentication protocol for Internet of Vehicles","authors":"Honglei Men, Li Cao, Guoli Zheng, Liang Chen","doi":"10.1016/j.compeleceng.2025.110210","DOIUrl":"10.1016/j.compeleceng.2025.110210","url":null,"abstract":"<div><div>To address the efficiency issues of vehicle identity authentication schemes based on cryptographic primitives in vehicular networks, a novel lightweight identity authentication and key agreement protocol based on Physical Unclonable Functions (PUFs) is proposed. The proposed protocol authenticates identities by generating Challenge-Response Pair (CRP) data in real time, avoiding the privacy leaks and security risks associated with traditional PUF authentication, which relies on the verifier’s pre-stored CRP data. Additionally, the proposed protocol eliminates the use of complex cryptographic primitives and digital certificates in the authentication process, thereby reducing the computational and communication overhead for verifiers and the trusted authority, significantly enhancing authentication efficiency. The security analysis shows that the protocol not only protects the real identities of vehicles but also provides traceability of malicious identities, effectively defending against various security threats, including physical cloning and replay attacks. Compared to cryptographic-based identity authentication protocols, this lightweight protocol is better suited for resource-constrained and latency-sensitive vehicular network environments.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110210"},"PeriodicalIF":4.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143519979","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}

引用次数: 0

Hybrid-Network based Dynamic Wireless Power Transfer With Reduced Power Pulsation

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2025-03-01 DOI: 10.1016/j.compeleceng.2025.110229

Shibajee Nath, Gao Tek Lim, Wei Hong Lim, K.M. Begam, Anandan Shanmugam

Dynamic wireless power transfer (DWPT) is a promising solution for extending electric vehicle range, reducing the need for large onboard batteries, and promoting sustainability. However, existing DWPT systems encounter several challenges including the large number of compensation components, power loss, pad misalignment, and receiver power fluctuations. This paper proposes a hybrid-network based DWPT system consisting of LCC-S and S-LCC networks, along with a bipolar coupling pad design, to address these challenges. The hybrid networks are connected in parallel to a common inverter and the bipolar pads are loosely placed on the track to reduce costs. A mathematical model was developed to model the system, then a misalignment tolerance tuning method was used to tune the resonant network. A 75W system was developed, and a laboratory prototype was built to validate the proposed hybrid-network based DWPT system. The system achieved approximately 70.6% efficiency, with output fluctuations less than ±10%, ±15% tolerance to lateral misalignment, and no null power when charging. The proposed system demonstrated similar performance at different receiver speeds and misalignment.

{"title":"Hybrid-Network based Dynamic Wireless Power Transfer With Reduced Power Pulsation","authors":"Shibajee Nath, Gao Tek Lim, Wei Hong Lim, K.M. Begam, Anandan Shanmugam","doi":"10.1016/j.compeleceng.2025.110229","DOIUrl":"10.1016/j.compeleceng.2025.110229","url":null,"abstract":"<div><div>Dynamic wireless power transfer (DWPT) is a promising solution for extending electric vehicle range, reducing the need for large onboard batteries, and promoting sustainability. However, existing DWPT systems encounter several challenges including the large number of compensation components, power loss, pad misalignment, and receiver power fluctuations. This paper proposes a hybrid-network based DWPT system consisting of LCC-S and S-LCC networks, along with a bipolar coupling pad design, to address these challenges. The hybrid networks are connected in parallel to a common inverter and the bipolar pads are loosely placed on the track to reduce costs. A mathematical model was developed to model the system, then a misalignment tolerance tuning method was used to tune the resonant network. A 75W system was developed, and a laboratory prototype was built to validate the proposed hybrid-network based DWPT system. The system achieved approximately 70.6% efficiency, with output fluctuations less than ±10%, ±15% tolerance to lateral misalignment, and no null power when charging. The proposed system demonstrated similar performance at different receiver speeds and misalignment.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110229"},"PeriodicalIF":4.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143527230","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}

引用次数: 0

Optimizing reliability and safety of wind turbine systems through a hybrid control technique for low-voltage ride-through capability

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2025-03-01 DOI: 10.1016/j.compeleceng.2025.110205

Nima Khosravi , Masrour Dowlatabadi , Adel Oubelaid , Youcef Belkhier

This study addresses a significant challenge in reliability engineering and system safety, specifically the operation of wind turbines under fault conditions. It proposes an asymmetrical fault ride-through (AFRT) control method designed for the doubly fed induction generator (DFIG) rotor-side converter (RSC) used in wind turbines. The DFIG model is analyzed in both positive and negative rotating synchronous reference frames (PR-SRF and NR-SRF), incorporating four key components to prevent overcurrent in the RSC during AFRT conditions. The proposed control method is divided into two segments: first, reducing the four components based on boundary constraints and reference value configuration; and second, determining the control characteristic ‘ k ’ through an optimization loop using the particle swarm optimization (PSO) algorithm. The effectiveness of the PSO algorithm is compared with three other optimization methods genetic algorithm (GA), differential evolution (DE), and ant colony optimization (ACO). The dynamic performance of the proposed method is assessed under Line-to-Line (LL) and Line-to-Line-to-Ground (LLG) fault scenarios. Simulation results demonstrate that the method successfully mitigates fluctuations caused by asymmetrical faults (AFs), achieving a 7.2% higher efficiency in AFRT than similar approaches. Ultimately, this research enhances wind turbine system safety and reliability, ensuring more robust power generation during asymmetrical fault conditions.

{"title":"Optimizing reliability and safety of wind turbine systems through a hybrid control technique for low-voltage ride-through capability","authors":"Nima Khosravi , Masrour Dowlatabadi , Adel Oubelaid , Youcef Belkhier","doi":"10.1016/j.compeleceng.2025.110205","DOIUrl":"10.1016/j.compeleceng.2025.110205","url":null,"abstract":"<div><div>This study addresses a significant challenge in reliability engineering and system safety, specifically the operation of wind turbines under fault conditions. It proposes an asymmetrical fault ride-through (AFRT) control method designed for the doubly fed induction generator (DFIG) rotor-side converter (RSC) used in wind turbines. The DFIG model is analyzed in both positive and negative rotating synchronous reference frames (PR-SRF and NR-SRF), incorporating four key components to prevent overcurrent in the RSC during AFRT conditions. The proposed control method is divided into two segments: first, reducing the four components based on boundary constraints and reference value configuration; and second, determining the control characteristic ‘ k ’ through an optimization loop using the particle swarm optimization (PSO) algorithm. The effectiveness of the PSO algorithm is compared with three other optimization methods genetic algorithm (GA), differential evolution (DE), and ant colony optimization (ACO). The dynamic performance of the proposed method is assessed under Line-to-Line (LL) and Line-to-Line-to-Ground (LLG) fault scenarios. Simulation results demonstrate that the method successfully mitigates fluctuations caused by asymmetrical faults (AFs), achieving a 7.2% higher efficiency in AFRT than similar approaches. Ultimately, this research enhances wind turbine system safety and reliability, ensuring more robust power generation during asymmetrical fault conditions.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110205"},"PeriodicalIF":4.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143527232","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}

引用次数: 0

Complex chromatic imaging for enhanced radar face recognition

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2025-03-01 DOI: 10.1016/j.compeleceng.2025.110198

Simy M. Baby, E.S. Gopi

Face recognition with millimeter-wave radar surpasses traditional cameras with better range, less intrusion, and safe material penetration using non-ionizing radiation. However, using complex-valued millimeter wave radar data for face recognition encounters challenges in extracting and representing features due to its complex nature and compatibility issues with high-performing image-based recognition systems. This paper introduces a novel approach utilizing Complex Chromatic Images (CCI) to address these challenges and enhance radar-based face recognition. Proposed Complex Chromatic Images retain both the magnitude and phase information of radar signals, providing a comprehensive representation of facial characteristics. A Complex Chromatic Image-Convolutional Neural Network (CCI-CNN) is developed to extract features from Complex Chromatic Images. Various sub-space analysis techniques are employed to tackle the high-dimensional nature of the complex-valued data. The effectiveness of the proposed approach is evaluated using various classifiers like Support Vector Machine (SVM), Random Forest (RF), and Convolutional Neural Network (CNN). Extensive experimental results and different evaluation metrics reveal that the proposed images approach consistently outperforms the conventional complex data images. Furthermore, when compared to existing mm-wave radar face recognition methods, our approach stands out with an impressive 99.7% accuracy. This study showcases superior recognition performance on complex-valued data, successfully addressing a large multiclass scenario with 206 distinct classes.

{"title":"Complex chromatic imaging for enhanced radar face recognition","authors":"Simy M. Baby, E.S. Gopi","doi":"10.1016/j.compeleceng.2025.110198","DOIUrl":"10.1016/j.compeleceng.2025.110198","url":null,"abstract":"<div><div>Face recognition with millimeter-wave radar surpasses traditional cameras with better range, less intrusion, and safe material penetration using non-ionizing radiation. However, using complex-valued millimeter wave radar data for face recognition encounters challenges in extracting and representing features due to its complex nature and compatibility issues with high-performing image-based recognition systems. This paper introduces a novel approach utilizing Complex Chromatic Images (CCI) to address these challenges and enhance radar-based face recognition. Proposed Complex Chromatic Images retain both the magnitude and phase information of radar signals, providing a comprehensive representation of facial characteristics. A Complex Chromatic Image-Convolutional Neural Network (CCI-CNN) is developed to extract features from Complex Chromatic Images. Various sub-space analysis techniques are employed to tackle the high-dimensional nature of the complex-valued data. The effectiveness of the proposed approach is evaluated using various classifiers like Support Vector Machine (SVM), Random Forest (RF), and Convolutional Neural Network (CNN). Extensive experimental results and different evaluation metrics reveal that the proposed images approach consistently outperforms the conventional complex data images. Furthermore, when compared to existing mm-wave radar face recognition methods, our approach stands out with an impressive 99.7% accuracy. This study showcases superior recognition performance on complex-valued data, successfully addressing a large multiclass scenario with 206 distinct classes.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110198"},"PeriodicalIF":4.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143527231","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}

引用次数: 0

Deep learning based medical image segmentation for encryption with copyright protection through data hiding

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2025-03-01 DOI: 10.1016/j.compeleceng.2025.110202

Monu Singh , Kedar Nath Singh , Amrita Mohan , Amit Kumar Singh , Huiyu Zhou

The prevention of medical information leakage has gained significant attention in recent times. As a result, numerous image encryption schemes are gaining prominence in protecting the privacy of original images. However, third-party users can easily compromise and access encrypted data after decryption. Therefore, it is imperative to develop encryption systems with enhanced confidentiality to address this issue. To tackle these problems, 3D-chaos-based encryption combined with copyright protection is proposed. This achieves high security at a low time cost. The method first segments the most significant information, i.e. the region of interest (ROI) part of the medical image, through the recent deep learning-based segmentation, i.e., you only look once (YOLO) version 8, for image encryption. The 3D-chaos-based encryption encodes only the ROI part, making it well-suited for secure healthcare with a low time cost. Finally, the hash of the ROI and the MAC address of the sender system is embedded into the non-region of interest (NROI) part of the image, making it effective against copyright violation, high bandwidth and storage costs. The results of extensive experiments on COVID-19 and COCO2017 datasets indicate that the method is highly secure, cost-effective and resistant to brute-force attacks. Given the advantages of encryption and data hiding, the proposed method could be an apt choice for medical data transmission and protection against any brute-force, statistical or differential attacks.

{"title":"Deep learning based medical image segmentation for encryption with copyright protection through data hiding","authors":"Monu Singh , Kedar Nath Singh , Amrita Mohan , Amit Kumar Singh , Huiyu Zhou","doi":"10.1016/j.compeleceng.2025.110202","DOIUrl":"10.1016/j.compeleceng.2025.110202","url":null,"abstract":"<div><div>The prevention of medical information leakage has gained significant attention in recent times. As a result, numerous image encryption schemes are gaining prominence in protecting the privacy of original images. However, third-party users can easily compromise and access encrypted data after decryption. Therefore, it is imperative to develop encryption systems with enhanced confidentiality to address this issue. To tackle these problems, 3D-chaos-based encryption combined with copyright protection is proposed. This achieves high security at a low time cost. The method first segments the most significant information, i.e. the region of interest (ROI) part of the medical image, through the recent deep learning-based segmentation, i.e., you only look once (YOLO) version 8, for image encryption. The 3D-chaos-based encryption encodes only the ROI part, making it well-suited for secure healthcare with a low time cost. Finally, the hash of the ROI and the MAC address of the sender system is embedded into the non-region of interest (NROI) part of the image, making it effective against copyright violation, high bandwidth and storage costs. The results of extensive experiments on COVID-19 and COCO2017 datasets indicate that the method is highly secure, cost-effective and resistant to brute-force attacks. Given the advantages of encryption and data hiding, the proposed method could be an apt choice for medical data transmission and protection against any brute-force, statistical or differential attacks.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110202"},"PeriodicalIF":4.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143519978","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}

引用次数: 0

Improved bidirectional long short-term memory network-based short-term forecasting of photovoltaic power for different seasonal types and weather factors

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2025-03-01 DOI: 10.1016/j.compeleceng.2025.110219

Ruixian Wang, Rui Ma, Linjun Zeng, Qin Yan, Archie James Johnston

Current photovoltaic (PV) power forecasts have not rigorously investigated the intrinsic characteristics of PV data clustering associated with various seasonal weather types to explore the potential for enhanced predictive accuracy. To address this issue, a short-term prediction method that correlates seasonal weather patterns with improved bi-directional long and short-term memory network (BiLSTM) modelling is proposed. Firstly, an improved k-means clustering algorithm is employed to categorize PV data according to each season, thereby enabling an in-depth analysis of PV characteristics under distinct seasonal weather conditions. Using a variational modal decomposition (VMD) algorithm for data decomposition, the dimensionality is then reduced using a kernel principal component analysis (KPCA) and this minimizes data redundancy. An improved bidirectional long and short-term memory network (BiLSTM) model is also deployed, and this aims to comprehensively incorporate the temporal characteristics of the data. Finally, the simulation results demonstrate that the forecast accuracy of the proposed model produces improvements of up to 58.2 %, 41.3 %, and 35.4 % over the CNN, BiLSTM, and VMD-KPCA-BiLSTM models, respectively.

{"title":"Improved bidirectional long short-term memory network-based short-term forecasting of photovoltaic power for different seasonal types and weather factors","authors":"Ruixian Wang, Rui Ma, Linjun Zeng, Qin Yan, Archie James Johnston","doi":"10.1016/j.compeleceng.2025.110219","DOIUrl":"10.1016/j.compeleceng.2025.110219","url":null,"abstract":"<div><div>Current photovoltaic (PV) power forecasts have not rigorously investigated the intrinsic characteristics of PV data clustering associated with various seasonal weather types to explore the potential for enhanced predictive accuracy. To address this issue, a short-term prediction method that correlates seasonal weather patterns with improved bi-directional long and short-term memory network (BiLSTM) modelling is proposed. Firstly, an improved k-means clustering algorithm is employed to categorize PV data according to each season, thereby enabling an in-depth analysis of PV characteristics under distinct seasonal weather conditions. Using a variational modal decomposition (VMD) algorithm for data decomposition, the dimensionality is then reduced using a kernel principal component analysis (KPCA) and this minimizes data redundancy. An improved bidirectional long and short-term memory network (BiLSTM) model is also deployed, and this aims to comprehensively incorporate the temporal characteristics of the data. Finally, the simulation results demonstrate that the forecast accuracy of the proposed model produces improvements of up to 58.2 %, 41.3 %, and 35.4 % over the CNN, BiLSTM, and VMD-KPCA-BiLSTM models, respectively.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110219"},"PeriodicalIF":4.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143527233","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}

引用次数: 0

SSARS: Secure smart-home activity recognition system

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2025-02-28 DOI: 10.1016/j.compeleceng.2025.110203

C. Anna Palagan , T. Selvin Retna Raj , N. Muthuvairavan Pillai , K. Anish Pon Yamini

Smart homes provide assistance services that enhance the well-being, independence, and health of the residents, particularly the elderly. As techniques for human activity recognition in smart homes continue to advance, current methods face challenges such as insecure transmission of raw data and individual movement classification. To overcome these challenges, this study proposes Secure Smart-Home Activity Recognition System (SSARS). The proposed methodology utilizes an advanced preprocessing technique, AI-PSD, to reduce impulse noise in the data by combining adaptive interpolation (AI) and power spectral density (PSD). The Fractional Fast Fourier Transform (F-FFT) effectively captures statistical and dynamic aspects of human activities, offering a more detailed understanding of movement patterns. The extracted features are securely transmitted through encryption based on Factor private Key-based Elliptic Curve Cryptography (FK-ECC). Additionally, this study introduces the Pade activation function with a modified Physical Neural Network (P-PNN) to improve the system's classification ability. The proposed SSARS showed outstanding performance across various metrics, including an accuracy of 98.68 % and a precision of 98.93 % when compared with existing state-of-the-art approaches.

{"title":"SSARS: Secure smart-home activity recognition system","authors":"C. Anna Palagan , T. Selvin Retna Raj , N. Muthuvairavan Pillai , K. Anish Pon Yamini","doi":"10.1016/j.compeleceng.2025.110203","DOIUrl":"10.1016/j.compeleceng.2025.110203","url":null,"abstract":"<div><div>Smart homes provide assistance services that enhance the well-being, independence, and health of the residents, particularly the elderly. As techniques for human activity recognition in smart homes continue to advance, current methods face challenges such as insecure transmission of raw data and individual movement classification. To overcome these challenges, this study proposes Secure Smart-Home Activity Recognition System (SSARS). The proposed methodology utilizes an advanced preprocessing technique, AI-PSD, to reduce impulse noise in the data by combining adaptive interpolation (AI) and power spectral density (PSD). The Fractional Fast Fourier Transform (F-FFT) effectively captures statistical and dynamic aspects of human activities, offering a more detailed understanding of movement patterns. The extracted features are securely transmitted through encryption based on Factor private Key-based Elliptic Curve Cryptography (FK-ECC). Additionally, this study introduces the Pade activation function with a modified Physical Neural Network (P-PNN) to improve the system's classification ability. The proposed SSARS showed outstanding performance across various metrics, including an accuracy of 98.68 % and a precision of 98.93 % when compared with existing state-of-the-art approaches.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110203"},"PeriodicalIF":4.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143519977","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}

引用次数: 0

Development of BiLSTM deep learning model to detect URL-based phishing attacks

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2025-02-28 DOI: 10.1016/j.compeleceng.2025.110212

Öznur Şifa Akçam , Adem Tekerek , Mehmet Tekerek

Phishing attacks steal critical information by exploiting security vulnerabilities in information systems. This study aims to detect URL-based phishing attacks. In this study, a deep learning model based on character and word-based feature extraction is developed. With the developed model, URLs are classified as legitimate or phishing. Bidirectional Long Short-Term Memory (BiLSTM) algorithm and GramBeddings, Malicious and Benign URLs, and Ebbu2017 Phishing datasets were used to develop the model. Also, Mendeley Data Web Page Phishing Detection datasets were used to test the developed model. The developed model achieved test results of 98.24% accuracy and 0.9977 area under curve (AUC) for the GramBeddings dataset, 99.32% accuracy and 0.9986 AUC for the Malicious and Benign URLs dataset, 98.34% accuracy and 0.9981 AUC for the Ebbu2017 dataset, and 90.33% accuracy and 0.9694 AUC for the Mendeley Data Web Page Phishing Detection dataset. These results prove the effectiveness of the model in detecting phishing attacks. The model's uniqueness is that it analyses the structural patterns of URLs through character-based inference and evaluates the contextual meaning through word-based inference. This enables effective detection of phishing URLs at both character and word levels.

{"title":"Development of BiLSTM deep learning model to detect URL-based phishing attacks","authors":"Öznur Şifa Akçam , Adem Tekerek , Mehmet Tekerek","doi":"10.1016/j.compeleceng.2025.110212","DOIUrl":"10.1016/j.compeleceng.2025.110212","url":null,"abstract":"<div><div>Phishing attacks steal critical information by exploiting security vulnerabilities in information systems. This study aims to detect URL-based phishing attacks. In this study, a deep learning model based on character and word-based feature extraction is developed. With the developed model, URLs are classified as legitimate or phishing. Bidirectional Long Short-Term Memory (BiLSTM) algorithm and GramBeddings, Malicious and Benign URLs, and Ebbu2017 Phishing datasets were used to develop the model. Also, Mendeley Data Web Page Phishing Detection datasets were used to test the developed model. The developed model achieved test results of 98.24% accuracy and 0.9977 area under curve (AUC) for the GramBeddings dataset, 99.32% accuracy and 0.9986 AUC for the Malicious and Benign URLs dataset, 98.34% accuracy and 0.9981 AUC for the Ebbu2017 dataset, and 90.33% accuracy and 0.9694 AUC for the Mendeley Data Web Page Phishing Detection dataset. These results prove the effectiveness of the model in detecting phishing attacks. The model's uniqueness is that it analyses the structural patterns of URLs through character-based inference and evaluates the contextual meaning through word-based inference. This enables effective detection of phishing URLs at both character and word levels.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110212"},"PeriodicalIF":4.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143512140","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}

引用次数: 0

Fault diagnosis of uncertain photovoltaic systems using deep recurrent neural networks based Lissajous curves

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2025-02-27 DOI: 10.1016/j.compeleceng.2025.110191

Zahra Yahyaoui , Walid Touti , Mansour Hajji , Majdi Mansouri , Yassine Bouazzi , Kais Bouzrara

Data-driven approaches have gained significant interest in the fault detection and diagnosis (FDD) field, often utilizing numerous sensors for accurate and reliable monitoring. However, extensive sensor deployment can lead to increased costs, maintenance complexity, potential data redundancies, and uncertainties. This study proposes an innovative methodology to enhance model representation and improve decision-making processes by strategically reducing the number of sensors required, thereby addressing sensor-related challenges while maintaining effective fault diagnosis capabilities. The paper investigates the most prevalent experimental faults that can occur in grid-connected photovoltaic (GCPV) systems, such as sensor faults, PV panel faults, inverter faults, and grid connection faults, to ensure a thorough analysis of the system. Firstly, the number of required sensors is reduced. Then, Lissajous curves are applied to extract additional informative features, which are subsequently fed into deep learning classifiers; such as Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM); for fault diagnosis. Additionally, an extended approach based on interval-valued data representation is introduced to handle uncertainties, including measurement errors, noise, and variable variability. The methodology is experimentally validated using GCPV systems, comprehensively analyzing potential faults and their mitigation.

The results, demonstrated using noisy testing data, highlight the robustness and effectiveness of the proposed approach, achieving average accuracies of 94.36% and 99.50%. This confirms the approach’s capability to manage FDD challenges in PV systems, even under conditions that mimic real-world noise and uncertainties.

{"title":"Fault diagnosis of uncertain photovoltaic systems using deep recurrent neural networks based Lissajous curves","authors":"Zahra Yahyaoui , Walid Touti , Mansour Hajji , Majdi Mansouri , Yassine Bouazzi , Kais Bouzrara","doi":"10.1016/j.compeleceng.2025.110191","DOIUrl":"10.1016/j.compeleceng.2025.110191","url":null,"abstract":"<div><div>Data-driven approaches have gained significant interest in the fault detection and diagnosis (FDD) field, often utilizing numerous sensors for accurate and reliable monitoring. However, extensive sensor deployment can lead to increased costs, maintenance complexity, potential data redundancies, and uncertainties. This study proposes an innovative methodology to enhance model representation and improve decision-making processes by strategically reducing the number of sensors required, thereby addressing sensor-related challenges while maintaining effective fault diagnosis capabilities. The paper investigates the most prevalent experimental faults that can occur in grid-connected photovoltaic (GCPV) systems, such as sensor faults, PV panel faults, inverter faults, and grid connection faults, to ensure a thorough analysis of the system. Firstly, the number of required sensors is reduced. Then, Lissajous curves are applied to extract additional informative features, which are subsequently fed into deep learning classifiers; such as Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM); for fault diagnosis. Additionally, an extended approach based on interval-valued data representation is introduced to handle uncertainties, including measurement errors, noise, and variable variability. The methodology is experimentally validated using GCPV systems, comprehensively analyzing potential faults and their mitigation.</div><div>The results, demonstrated using noisy testing data, highlight the robustness and effectiveness of the proposed approach, achieving average accuracies of 94.36% and 99.50%. This confirms the approach’s capability to manage FDD challenges in PV systems, even under conditions that mimic real-world noise and uncertainties.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110191"},"PeriodicalIF":4.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510800","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}

引用次数: 0

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Computers & Electrical Engineering

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀