Computers & Electrical Engineering最新文献

{"title":"Facial expression recognition in the wild: A new Adaptive Attention-Modulated Contextual Spatial Information network","authors":"Xue Li ,&nbsp;Chunhua Zhu ,&nbsp;Shuzhi Yang","doi":"10.1016/j.compeleceng.2025.110258","DOIUrl":"10.1016/j.compeleceng.2025.110258","url":null,"abstract":"<div><div>Facial expression recognition (FER) is an important and widely applied task. This paper proposes an Adaptive Attention-modulated Contextual Spatial Information (Ad-ACSI) model to improve FER in uncontrolled environments. The proposed Ad-ACSI model incorporates an Attention-modulated Contextual Spatial Information Network (ACSI-Net), a joint loss, and an adaptive attention modulator (AAM). The ACSI-Net, built on ResNet with contextual convolution (CoConv) and coordinated attention (CA), effectively captures global and local contextual features. The adaptive attention modulator (AAM) refines the features and generates dynamic weights for the center loss. The cross-entropy (CE) loss is refined into an equilibrium loss and combined with a sparse center loss to improve inter-class discrimination and intra-class clustering. Experiments on the RAF-DB and AffectNet datasets show that the proposed method achieves results comparable to state-of-the-art methods of FER in the wild, with it promising for integration into popular architectures.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110258"},"PeriodicalIF":4.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817400","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}

{"title":"Active implementation of Chua’s diode employing MOSFET","authors":"Vivek Bhatt,&nbsp;Ashish Ranjan","doi":"10.1016/j.compeleceng.2025.110306","DOIUrl":"10.1016/j.compeleceng.2025.110306","url":null,"abstract":"<div><div>This research work contributes a Chua’s circuit design using only two Metal-Oxide- Semiconductor-Field-Effect-Transistor (MOSFET) based Chua’s diode. This design enables the following advantages like: <span><math><mrow><mo>(</mo><mi>i</mi><mo>)</mo></mrow></math></span> Use of a minimum number of transistors, <span><math><mrow><mo>(</mo><mi>i</mi><mi>i</mi><mo>)</mo></mrow></math></span> Absence of passive components in Chua’s diode, <span><math><mrow><mo>(</mo><mi>i</mi><mi>i</mi><mi>i</mi><mo>)</mo></mrow></math></span> High packaging density with 108.9 <span><math><mi>μ</mi></math></span>m<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> chip area, <span><math><mrow><mo>(</mo><mi>i</mi><mi>v</mi><mo>)</mo></mrow></math></span> Suitable for the generation of all fundamental bifurcation sequences. The workability of the circuit is verified using Cadence’s Virtuoso tool with gpdk 180 nm technology parameters, along with the process, biasing (bias current), and temperature variation analysis. Moreover, an experimental validation is performed using commercially available N-MOSFET (2N7000). The proposed design is suitable for Chaotic-Amplitude-Shift-Keying (CASK) transmission for secure communication. At end, a comparative analysis is done with the available Chua’s circuit.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110306"},"PeriodicalIF":4.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817406","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}

{"title":"Performance improvement of MIMOOFDM communication systems based on non-linear equalization","authors":"Khaled Ramadan","doi":"10.1016/j.compeleceng.2025.110287","DOIUrl":"10.1016/j.compeleceng.2025.110287","url":null,"abstract":"<div><div>This paper introduces a nonlinear equalizer for Multiple Input Multiple Output (MIMO) Orthogonal Frequency Division Multiplexing (OFDM) systems based on Discrete Wavelet Transform (DWT). It is referred to as the Joint Non-Linear Combining Zero Forcing-Successive Interference Cancellation (JNLCZF-SIC) equalizer. Unlike traditional equalizers, the JNLCZF-SIC equalizer performs both equalization and Carrier Frequency Offset (CFO) correction simultaneously. The main advantage of the proposed JNLCZF-SIC equalizer over existing methods is its ability to reduce simulation times without compromising performance by minimizing the number of arithmetic operations required. To assess its effectiveness, we evaluate its Bit-Error-Rate (BER) and computational load against standard equalization techniques such as Linear Zero-Forcing (LZF), Linear Minimum Mean Squared Error (LMMSE), and MMSE-Successive Interference Cancellation (MMSE-SIC) equalizers. Simulation results reveal that the JNLCZF-SIC equalizer not only achieves a lower BER but also significantly decreases computational complexity. This improvement in simulation time is particularly beneficial for large-scale MIMO systems, where DWT is employed to accelerate processing by breaking down the signal into multiple frequency bands, optimizing the equalization process. The equalizer's ability to simultaneously handle equalization and CFO compensation with reduced computational demands makes it highly suitable for real-time applications and large-scale implementations. Additionally, a closed-form expression for the count of arithmetic operations for the proposed equalizer in a general 2^σ × 2^σ MIMO configuration is provided.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110287"},"PeriodicalIF":4.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817402","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}

{"title":"Underwater target detection algorithm based on multi-scale feature fusion","authors":"Xiao Chen ,&nbsp;Qi Yang ,&nbsp;Xiaoqi Ge ,&nbsp;Jiayi Chen ,&nbsp;Haiyan Wang","doi":"10.1016/j.compeleceng.2025.110327","DOIUrl":"10.1016/j.compeleceng.2025.110327","url":null,"abstract":"<div><div>Underwater target detection technology is an important way to realize the biological monitoring of the marine ranching. Nevertheless, since light absorption of the water and particles in the water will have a scattering effect on the light, the majority of the captured underwater optical images have low contrast and color bias, which blurs the local details of the measured biological targets. In addition, due to the mutual occlusion of underwater organisms, which will lead to a higher rate of missed targets detection. To address the above problems, we propose a new target detection algorithm for complex underwater environments based on the YOLOv7 (You Only Look Once Version 7). Firstly, in order to enhance the underwater image quality, while improving the color bias and reducing the image noise. By comparing different image enhancement methods, RGHS (Relative Global Histogram Stretching) is used to enhance the quality of dataset. Secondly, in order to realize the network's perception of biological detail features, the MIS (Multi-Gradient Interaction Structure) is proposed. The structural innovation aims to mitigate the challenges posed by target proximity and overlap. Finally, after the backbone feature extraction, we propose the multiscale feature fusion structure. It facilitates the cross-channel communication of semantic information, thereby enhancing the network's capability to express features. The experimental results indicate that our proposed algorithm has achieved a detection accuracy improvement of 1.35 % compared to the original YOLOv7 (You Only Look Once Version 7). Simultaneously, it has reduced instances of missed detections and misjudgments of underwater targets, surpassing common object detection algorithms.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110327"},"PeriodicalIF":4.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817404","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}

{"title":"Measurement framework for the consistent and fast measurement of conducted grid emissions in the 9-500 kHz range","authors":"Alexander Gallarreta ,&nbsp;Jon González-Ramos ,&nbsp;Stefano Lodetti ,&nbsp;Peter Davis ,&nbsp;Igor Fernández ,&nbsp;David de la Vega ,&nbsp;Itziar Angulo ,&nbsp;Amaia Arrinda","doi":"10.1016/j.compeleceng.2025.110314","DOIUrl":"10.1016/j.compeleceng.2025.110314","url":null,"abstract":"<div><div>There is currently no standardized measurement framework for the characterization of conducted emissions in the low-voltage grid for the 9–500 kHz range. Several methods are proposed for the 9–150 kHz band in power quality standards, while the only method defined for the 150–500 kHz range is not designed for power quality measurements. The different configuration of the existing methods prevents consistency of results in the entire band.</div><div>This work analyzes drawbacks of the current standardized methods and summarizes the recently published research methods, to propose a measurement framework for the characterization of conducted emissions in the 9–500 kHz range. This framework solves the identified drawbacks by proposing a set of six measurement methods to obtain different metrics for consistent results in the whole range. For that, the use of a common method for obtaining root-mean-square values in the entire 9–500 kHz range is proposed to assess aggregated values and quasi-peak (QP) outputs. Two novel techniques (Approximated-QP and Conservative-QP) are also defined to cover the existing gap in the literature in the estimation of the QP spectra in the 150–500 kHz band. The measurement framework includes a time-frequency domain analysis method to detect and characterize impulsive emissions.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110314"},"PeriodicalIF":4.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817401","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}

{"title":"The stochastic economic model for integrated energy system with carbon mechanism","authors":"Chong Cheng,&nbsp;Shufei Li","doi":"10.1016/j.compeleceng.2025.110304","DOIUrl":"10.1016/j.compeleceng.2025.110304","url":null,"abstract":"<div><div>As energy conversion technology progresses and evolves, interconnected energy networks with diverse attributes have emerged. The traditional model of energy networks has changed from isolated operation to the combined optimization and scheduling of integrated energy system. To efficiently decrease carbon dioxide emissions, it is necessary to vigorously develop green energy and fully consider carbon emission factors. To tackle the aforementioned issue, this paper proposes a stochastic optimal economic model within the carbon mechanism for integrated energy system. The model incorporates carbon trading, the volatility of renewable energy, and the deviation of real-time electricity prices into the objective function. By applying convex and robust optimization approaches, the primary problem is divided into the master problem and subproblem characterized by mixed-integer linearity, subsequently addressed iteratively. Convex optimization is mainly used to transform the deviation term of electricity price, and robust optimization is employed to find out the economically optimal scheme based on the worst scenario. Simulation results indicate that as the uncertainty in electricity market prices decreases, the electricity market cost can be reduced by up to 22.28 %, while the total cost of the integrated energy system can be reduced by up to 8.56 %. Finally, in the context of the carbon mechanism, the proposed stochastic optimization model was validated through simulations.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110304"},"PeriodicalIF":4.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817616","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}

{"title":"Identification of source of image degradation using a new hybrid dense F-LSTM network and image restoration","authors":"Poonam Yogesh Pawar,&nbsp;Dr. Bharati Sanjay Ainapure","doi":"10.1016/j.compeleceng.2025.110309","DOIUrl":"10.1016/j.compeleceng.2025.110309","url":null,"abstract":"<div><div>Image degradation has been garnering huge interest from researchers in the field of image processing and computer vision as images may contain several degradations that lead to different types of blurring, noise, and distortions. Hence, a new hybrid optimized network named DenseNet Fused Long Short Term Memory (Dense F-LSTM) is proposed for the identification of the source of image degradation. Initially, the input image with noise and blur is taken from the database and is subjected to noisy pixel identification, and identification of image source degradation, where the noise pixel identification is performed by Deep Convolutional Neural Network (DCNN), and the image source degradation is employed by proposed Dense F-LSTM. The identified noisy pixel is fed to the Type 2 Fuzzy and Cuckoo Search (T2FCS) filter for noisy correction for obtaining the denoised images. Once the image source is identified, the identified source of image degradation and the denoised image is used for performing deblurring. Here, deblurring is done by kernel estimation, which is optimally selected employing Jaya Walrus Optimization (JWaO). The JWaO is formed by the integration of the Jaya Algorithm (JA) and Walrus Optimization Algorithm (WaOA). Both the denoised image and deblurred image are fused to gain the final output image. The devised Dense F-LSTM method provided superior identification performance and achieved a Second-Derivative-like Measure of Enhancement (SDME) is 59.956, Peak Signal Noise Ratio (PSNR) is 49.924 dB and Structural Similarity Index Measure (SSIM) is 0.979, and Mean Squared Error (MSE) of 0.2.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110309"},"PeriodicalIF":4.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817407","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}

{"title":"Mobile node authentication with risk-based modified lattice cryptography enabled adaptive multifactor authentication for secure data transmission","authors":"Qureshi Imran M Hussain,&nbsp;Vijay Kale","doi":"10.1016/j.compeleceng.2025.110272","DOIUrl":"10.1016/j.compeleceng.2025.110272","url":null,"abstract":"<div><div>With the rapid proliferation of mobile services, the strategies for protecting the availability, confidentiality, and integrity of systems emerged to meet the demands of mobile networks. More specifically, the insecure mobile networks are more prone to different attacks and interrupt secure data communications between legitimate users. Despite the intensive research, the design of a secure and efficient multi-factor authentication scheme is still a challenging problem that ends with poor security, poor session management, and vulnerability to new and enhanced attacks. In order to tackle the challenges in the existing techniques, Risk-based modified lattice cryptography-enabled adaptive multifactor authentication (R-mLC-AMf) is proposed in the research. The ultimate intention of the research lies in the authentication of mobile nodes specifically in case of handover, or even reconfiguration with the same network that happens due to the risk factors. The proposed authentication in the research is performed with the AMf mechanism that authenticates the user with the help of multi-factors that evolve dynamically based on environmental factors. Specifically, the application of modified lattice cryptography into the research model works in encrypting the data and improves the security against attacks, addresses the scalability issues, and provides high computation efficiency. Further, the incorporation of Delegated Proof of Stake (DPoS) in the smart contract of blockchain addresses effective security purposes and offers the benefits of high transaction volume, low cost, faster confirmation time, and high efficiency. The Simulation results demonstrate that the proposed mechanism is effective even in the presence of malicious attacks in the network.Finally, the performance evaluation demonstrates that the proposed approach is efficient in terms of decryption time, encryption time, Genuine User Rate (GUR), memory, responsiveness, and time complexity that attained 1.091 ms, 0.895 ms, 0.87, 131.256 KB, 0.343 ms, and 0.497 ms respectively outperforming the other state-of-the-art approaches.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110272"},"PeriodicalIF":4.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817405","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}

{"title":"Enhanced fall prevention: A real-time hybrid analysis with smart walking stick & Edge-based IoMT","authors":"Pratik Bhattacharjee ,&nbsp;Indranil Sarkar ,&nbsp;Suparna Biswas","doi":"10.1016/j.compeleceng.2025.110312","DOIUrl":"10.1016/j.compeleceng.2025.110312","url":null,"abstract":"<div><div>Human fall poses a significant risk for the elderly. A fall can result in hospitalization or, tragically, death. The primary causes of falls among the elderly are often linked to a loss of balance or insufficient limb support.</div><div>While fall prevention is difficult, fall risk analysis can help predict and prevent future falls. The present work proposes a real-time 3-way hybrid fall risk factor analysis methodology, , employing a smart walking stick. It uses an Edge-based IoMT (Internet of Medical Things) architecture that is extendable to the Cloud. The smart walking stick has a 10 kg load cell (YZC-133) with HX711 (mounted on the grip) and a MPU 6050 kinematic sensor paired with an ESP8266 WiFi Micro Controller (MCU) to transfer the accelerometer, gyroscope and load cell data to the processing unit.</div><div>A Raspberry Pi-based edge device evaluates pressure (support) on the grip and walking patterns using an accelerometer, gyroscope, and load sensor signals connected with ESP 8266. The system could perform fine grain fall analysis by classifying the subjects into the risk categories of High/Medium/Low/None. The system used the clinically established parameters and tests for its multimodal analysis at low cost based on Timed Up and Go (TUG), Force test and Gait analysis modules. The individual results from each module were then combined to predict the final risk category. The long-term analysis is done on a cloud server and the system could predict falls with a maximum of 92% accuracy.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110312"},"PeriodicalIF":4.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817403","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}

{"title":"Ensure authentication and confidentiality in blockchain-based IoT with cryptanalysis and machine learning in 6G-enabled heterogeneous IoT-Blockchain","authors":"Dr. Bharati B Pannyagol ,&nbsp;Dr. Santosh L Deshpande","doi":"10.1016/j.compeleceng.2025.110303","DOIUrl":"10.1016/j.compeleceng.2025.110303","url":null,"abstract":"<div><div>Presently, the Internet of Things (IoT) is considered the major network, which includes multiple intelligent devices for interacting and transferring data throughout the Internet. The IoT is applicable in commercial, military, and industrial applications. With the popularity of IoT devices, security is the main issue for data privacy. Hence, authentication and secure data transmission are crucial parameters for the secure communication of IoT devices. Moreover, blockchain is employed for providing efficient data sharing and secure authentication in IoT. This research proposes authentication based on data protection (DPro_Auth) for blockchain-based IoT. Entities like users, IoT devices, blockchain, and a smart contract are utilized to attain authentication and confidentiality. The steps like initialization, registration, key generation, authentication, data verification, and access control are carried out. The initialization is based on the physical unclonable function-based chaotic pseudorandom number generators (PUF-CPRNG). Moreover, the pseudorandom number generator-based pseudo-randomly enhanced logistic map (PRNG–PELM) is employed in the key generation process. In addition, the memory, and computational time are used to validate the DPro_Auth, with the finest outcome of 5.277 MB, and 0.256 s are obtained.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110303"},"PeriodicalIF":4.0,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792747","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}