Computers & Electrical Engineering最新文献

{"title":"LFGNet: Low-level feature-guided network for drivers’ calling behavior detection","authors":"Hao Li,&nbsp;Changming Song,&nbsp;Dongxu Cheng,&nbsp;Zenghui Li,&nbsp;Caihong Wu,&nbsp;Kang Chen","doi":"10.1016/j.compeleceng.2025.110401","DOIUrl":"10.1016/j.compeleceng.2025.110401","url":null,"abstract":"<div><div>Drivers’ calling behavior probably leads to traffic accidents. Thus, there is a significant need to detect such distracted driving behavior. Mobile phones are easily overlooked in detection due to their small size and limited visibility. This paper proposes a low-level feature-guided network (LFGNet) for the drivers’ calling behavior detection, which integrates spatial and semantic information. Specifically, a cross-feature extraction (CFE) module is designed to extract low-level and high-level features by utilizing filters in dual directions. It leverages cross-attention with multi-branch convolutions (CMC) to learn and establish spatial representations between the extracted features from contextual information. As the network deepens, an excessive amount of low-level information can impede the network’s capacity for feature representation. Consequently, an irrelevant feature filter (IFF) module is introduced to selectively filter out irrelevant feature information. Two remote sensing datasets are employed to explore the effectiveness of the proposed method in detecting small objects in general. The public distracted driving datasets State Farm and SynDD1 are used for validation. Furthermore, the LFGNet is evaluated on a private driver’s calling behavior (DCB) dataset. The experimental results demonstrate the effectiveness of the proposed method in drivers’ calling behavior detection.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110401"},"PeriodicalIF":4.0,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144106794","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":"MDR-LOD2 Model: Forgery Detection using Modified Depth ResNet features and Layer Optimized Dunnock Deep Model from Videos","authors":"Meena Ugale ,&nbsp;J. Midhunchakkaravarthy","doi":"10.1016/j.compeleceng.2025.110423","DOIUrl":"10.1016/j.compeleceng.2025.110423","url":null,"abstract":"<div><div>Digital forgery detection implies the identification of any modifications or manipulation of the digital content, typically image, video, or document, to confirm their authenticity. Consequently, this contribution seeks to address the challenges experienced by existing techniques by introducing the Modified DepthResNet descriptor and Layer Optimized Dunnock Deep model (MDR-LOD2) model. MDR descriptor is proficient at generating features in ResNet architecture and hence it helps in the fusion of a DepthNet to detect depth-related cues which plays a crucial role in spotting forgery. More specifically, the MDR descriptor captures the subtle details via the spatial connections and depth perception, resulting in boosting the detection performance. The hybrid optimizer strategy combines meticulous exploration and dynamic adaptation together increasing the model's ability to detect splicing forgery. The proposed approach exploits the LOD2 architecture well suited for capturing the temporal aspects and effectively analyzes the intricate patterns of video data. Additionally, the LOD2 model is enabled with the Dunnock Hunt Optimization (DHO) algorithm for layer optimization facilitating optimal performance of every layer in LSTM. Moreover, the integration of LOD2 and MDR descriptor in conjunction with the DHO algorithm in the proposed approach assist in identifying the forged regions in the video frames. The experimental results demonstrate that the proposed approach attains an accuracy of 98.54 %, sensitivity of 98.54 %, specificity of 98.53 %, and F1-score of 98.54 % for DSO-1. For DSI-1 DTS, the proposed approach achieves remarkable results with high accuracy of 98.47 %, sensitivity of 98.41 %, specificity of 98.52 %, and F1-score of 98.47 %. Finally, the proposed model obtained the remarkable results for the Face Forensics database achieving high accuracy of 97.83 %, sensitivity of 97.76 %, specificity of 97.89 %, and F1-score of 97.83 % outperforming other existing techniques.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110423"},"PeriodicalIF":4.0,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144106795","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":"A novel post-quantum lightweight security model and directed acyclic graph based blockchain integration for mobile cyber-physical systems","authors":"Aykut Karakaya","doi":"10.1016/j.compeleceng.2025.110415","DOIUrl":"10.1016/j.compeleceng.2025.110415","url":null,"abstract":"<div><div>In today’s interconnected world, the increasing connectivity and data exchange in fields such as mobile cyber–physical systems (MCPS) and the internet of things (IoT) create a growing need for secure communication and data protection. Traditional security protocols and blockchain technologies may pose disadvantages in terms of performance and resource usage, especially for resource-constrained devices. This study proposes a comprehensive model that integrates a lightweight and quantum-resistant security protocol with a directed acyclic graph (DAG)-based blockchain structure for resource-constrained MCPS applications. The model is demonstrated using connected vehicles as an example of an MCPS application. The proposed protocol ensures secure communication and data integrity by employing quantum-resistant symmetric and asymmetric encryption. The DAG-based blockchain structure is utilized to reduce computational workload and enhance scalability in these devices. The blockchain is encrypted with AES-256 and hashed with SHA-256. Experimental results demonstrate that the proposed protocol and its integration with a DAG-based blockchain can provide a secure and efficient communication environment for MCPS applications. Security analysis reveals that the protocol is resilient against various attacks, including man-in-the-middle (MITM), denial-of-service (DoS), replay attacks, brute force attacks, and quantum attacks.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110415"},"PeriodicalIF":4.0,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144090500","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":"A real-time detector for small-object remote sensing","authors":"Xin Wang ,&nbsp;Guangmei Xu ,&nbsp;Chen Hong ,&nbsp;Ning He ,&nbsp;Runjie Li ,&nbsp;Fengxi Sun ,&nbsp;Wenjing Han","doi":"10.1016/j.compeleceng.2025.110413","DOIUrl":"10.1016/j.compeleceng.2025.110413","url":null,"abstract":"<div><div>In the field of object detection, small-object detection has always been a difficult task. Remote sensing images have complex backgrounds and small objects can be densely distributed. Moreover, remote sensing detection must meet real-time requirements. To address these challenges, this paper proposes a detector called NanoDet-Drone for the real-time detection of small objects in remote sensing scenes. The baseline model lacks a sufficient receptive field to capture both local and long-distance information, and cannot achieve satisfactory detection results when directly applied to remote sensing detection. Our project improves the baseline network. First, the receptive field module is proposed, which uses dilated convolution at different dilation rates to expand the model’s receptive field while fully exploiting the contextual information of the small objects, incorporating the coordinate attention mechanism to highlight the features of small objects. Then, the adaptive fusion feature pyramid network (AF-FPN) is proposed to reasonably fuse the features of different branches; this efficiently uses multi-scale features and provides the network with more detailed information about small objects. Finally, the improved training auxiliary module, called the assign guidance module, is used to guide the detection head training and help the network learn richer feature representations to improve the accuracy and robustness of the model. In this study, we conducted extensive experiments on two challenging remote sensing datasets, VisDrone and AI-TOD, to demonstrate the effectiveness and robustness of NanoDet-Drone. Results show that NanoDet-Drone is capable of running at 56.8 frames per second on a CPU, outperforming other advanced detectors (YOLOv9-T and YOLOv10-N) at the same scale. Our model achieves a better trade-off between accuracy and inference speed. The proposed AF-FPN can be easily embedded into a one-stage detector, which effectively improves detection performance while significantly reducing the number of model parameters and computations. Compared with the baseline, NanoDet-Drone increased average precision (AP) and <span><math><mrow><mi>A</mi><msub><mrow><mi>P</mi></mrow><mrow><mn>0</mn><mo>.</mo><mn>5</mn></mrow></msub></mrow></math></span> by 5.2% and 8.6%, respectively, on VisDrone, and increased AP and <span><math><mrow><mi>A</mi><msub><mrow><mi>P</mi></mrow><mrow><mn>0</mn><mo>.</mo><mn>5</mn></mrow></msub></mrow></math></span> by 4.8% and 10.9%, respectively, on AI-TOD.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110413"},"PeriodicalIF":4.0,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144107238","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":"A comprehensive review of microgrid control methods: Focus on AI, optimization, and predictive techniques","authors":"Tariq Limouni ,&nbsp;Reda Yaagoubi ,&nbsp;Khalid Bouziane ,&nbsp;Khalid Guissi ,&nbsp;El Houssain Baali","doi":"10.1016/j.compeleceng.2025.110442","DOIUrl":"10.1016/j.compeleceng.2025.110442","url":null,"abstract":"<div><div>With the depletion of fossil fuels, the integration of renewable energy sources as distributed energy resources has become mandatory. However, the uncertainty and intermittent nature of these sources introduce significant challenges to their integration into microgrids. Effective control systems are essential for ensuring smooth integration, managing energy storage systems, and maintaining microgrid safety. In this study, a review of recent control methods applied in microgrid management was conducted with a focus on AI, optimization, and predictive techniques. These advanced and intelligent control methods were chosen for their potential to address current challenges. This study examined the benefits, limitations, and areas for future improvement. In addition, it explores the potential and the challenges of hybrid control techniques, which are less discussed in the literature, to further enhance control system efficiency and performance.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110442"},"PeriodicalIF":4.0,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144090501","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":"Low-cost smart irrigation solution for efficient water use and requirement prediction","authors":"Sangita Roy ,&nbsp;Rajat Subhra Chakraborty","doi":"10.1016/j.compeleceng.2025.110420","DOIUrl":"10.1016/j.compeleceng.2025.110420","url":null,"abstract":"<div><div>The agricultural sector in India consumes a substantial amount of water annually, with precipitation primarily concentrated during the monsoon season and irrigation needs varying significantly throughout the year. To address these challenges, this study presents a fully automated, intelligent irrigation control system that integrates low-cost sensors (temperature, humidity, soil moisture, and illumination) with a microcontroller within an Internet of Things framework. The system effectively regulates irrigation and provides precise seasonal and short-term water requirement forecasts using computationally efficient data analytics. Featuring a user-friendly graphical interface, the prototype was developed and tested in both scaled alpha and beta environments. Designed with sustainability, scalability, and international applicability in mind, the system demonstrates its ability to adapt to seasonal changes and achieves 94.3% prediction accuracy for real-time environmental monitoring through machine learning-based water demand forecasting. The results confirm its capability to manage water flow via automated pump control and deliver accurate forecasts, highlighting its potential to enhance water management in agriculture.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110420"},"PeriodicalIF":4.0,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144090499","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":"Energy-deadline optimization with minimal task failure aware task partitioning model in heterogeneous cloud computing framework","authors":"KN Divyaprabha,&nbsp;TSB Sudarshan","doi":"10.1016/j.compeleceng.2025.110438","DOIUrl":"10.1016/j.compeleceng.2025.110438","url":null,"abstract":"<div><div>The central processing Unit (CPU) and graphical processing unit (GPU) will be used in high-performance computing (HPC) to provide scalable and effective computing paradigms for data-intensive scientific workloads. Nonetheless, energy use is a significant aspect that should be considered due to rising operational costs and green computing standards. Scientific workload scheduling is a challenging task since heterogeneous cloud computing (HCC) infrastructures consume more energy, which raises carbon emissions and lowers the reliability of the infrastructures. Although using the dynamic voltage-frequency scaling (DVFS) approach can improve the energy management of cloud infrastructure, it also decreases dependability and increases the error rate of workload scheduling on a CPU-GPU HCC architecture; thus, reducing task failure and minimizing energy are core issues that the current work addresses. The work first introduces the energy-deadline-aware task scheduling optimization (EDATSO) technique; secondly, it introduces the task-failure minimization-aware optimal scheduling (TFMOS) technique for the execution of scientific workflows. Simulation study demonstrates EDATSO reduces energy usage by 40.3 %, and 33.12 %, reduces makespan by 90.35 %, and 53.56 %, and overhead of additional energies used due to task failures by 95.56 %, 87.59 % as compared to energy minimized scheduling (EMS), multi-objective prioritized workflow scheduling through deep reinforcement learning (MOPWSDRL) for realistic scientific workloads, respectively. Further, TFMOS reduces energy usage by 40.33 %, and 46.4 %, reduces makespan by 90.4 %, and 53.95 %, and overhead of additional energies used due to task failures by 95.58 %, 87.61 % as compared to EMS, MOPWSDRL for realistic scientific workloads, respectively.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110438"},"PeriodicalIF":4.0,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071492","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":"Development of adaptive model-based digital twins for evolving power systems","authors":"Zhiwei Shen,&nbsp;Felipe Arraño-Vargas,&nbsp;Georgios Konstantinou","doi":"10.1016/j.compeleceng.2025.110418","DOIUrl":"10.1016/j.compeleceng.2025.110418","url":null,"abstract":"<div><div>Adaptation is a critical function that guarantees a digital twin (DT) remains accurate and provides reliable and trustworthy information about its behaviour. Lack of a suitable adaptation function compromises the efficiency and reliability of DT-based applications. Data-driven DTs that rely on machine learning (ML) adapt to new datasets acquired from the physical twin (PT) by employing transfer learning techniques or by undergoing complete reconstruction. However, these approaches cannot be implemented on model-based DTs that are based on known laws and principles of physics, since their accuracy is dependent on specific parameters that may be neither estimated from the measurements nor derived from existing datasets. This paper proposes a generic workflow to adapt model-based DTs to minimise their deviation and introduced errors from their corresponding PTs. The two-step method uses ML to first identify the deviating components within an interval of confidence and then estimate new parameters based on information from the PT. A relational database is adopted for flexible and efficient data access and storage. To verify the effectiveness and feasibility of the proposed method, a DT testbed is used for a power system digital twin (PSDT) based on real-time simulations. The PSDT can be successfully adapted for specific changes, including system configurations and component parameters. The proposed adaptation workflow provides an opportunity to adapt system-level model-based PSDTs across wider scenarios and/or conditions.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110418"},"PeriodicalIF":4.0,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071493","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":"Model-free predictive current control of IPMSMs based on an improved extended state observer with parallel resonant controller switching control strategy","authors":"Pan Li,&nbsp;Jianyong Su,&nbsp;Han Wang,&nbsp;Guijie Yang","doi":"10.1016/j.compeleceng.2025.110414","DOIUrl":"10.1016/j.compeleceng.2025.110414","url":null,"abstract":"<div><div>Conventional deadbeat predictive current control (DPCC) relies on an accurate model, making it unable to handle both DC and AC unmodeled disturbances present in interior permanent magnet synchronous motor (IPMSM) drive systems. Model-free predictive current control (MFPCC) based on an extended state observer (ESO) with a ultra-local model reduces sensitivity to certain motor parameters and enhances system robustness. Nevertheless, this approach is limited by the bandwidth of the ESO, leading to poor disturbance observation for AC disturbances under multiple operating conditions, resulting in non-negligible current harmonics in the system. This paper introduces an enhanced MFPCC based on an improved extended state observer with parallel resonant controller switching control strategy(PRCSC-IESO). It observes major AC disturbances without amplitude attenuation and phase delay. Additionally, the introduction of a vector resonant controller (VRC) further suppresses current harmonics. The proposed observer can adaptively track AC disturbance frequencies and switch the number of VRCs according to actual rotational speed. The proposed MFPCC eliminates both DC and AC disturbances without requiring additional parameter information. Finally, experiments on a 7.1kw IPMSM validate the effectiveness of this approach in suppressing total harmonic distortion (THD) across various speed ranges and load conditions. Experimental results demonstrate that, compared to the traditional ESO method, the proposed method improves harmonic suppression capability by more than 40%. Additionally, the introduction of the switching control strategy reduces execution time by 24.4% at the rated motor speed, thereby enhancing the system’s operational efficiency.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110414"},"PeriodicalIF":4.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143948765","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":"Identity-based searchable encryption with cryptographic reverse firewalls for IoT-based healthcare systems","authors":"Mazin Taha ,&nbsp;Ting Zhong ,&nbsp;Rashad Elhabob ,&nbsp;Hu Xiong ,&nbsp;Saru Kumari ,&nbsp;Chien-Ming Chen ,&nbsp;Mohammed J.F. Alenazi","doi":"10.1016/j.compeleceng.2025.110404","DOIUrl":"10.1016/j.compeleceng.2025.110404","url":null,"abstract":"<div><div>A new healthcare trend is the use of the Internet of Things (IoT) to establish a system of healthcare. Doctors can monitor patients’ health and respond to sudden illnesses. However, concerns about data security are preventing widespread use. Encrypting sensitive data prior to transmission to a Healthcare Cloud Server (HCS) is a common solution. Yet, employing this method results in the incapacity to perform searches within the encrypted data. To overcome these challenges, we propose a novel Identity-Based Searchable Encryption with Cryptographic Reverse Firewalls (IB-SE-CRF). The suggested scheme offers an effective and secure approach for searching data that is encrypted in HCS. Meanwhile, the scheme resolves traditional public-key encryption with keyword search (PEKS) problems that use the Public Key Infrastructure (PKI). Furthermore, the security examination confirms that the proposed IB-SE-CRF enables resistance and prevents chosen keyword attacks (CKA), keyword guessing attacks (KGA), and algorithm substitution attacks (ASA). The performance analysis reveals that the IB-SE-CRF scheme has advantages in communication and computational costs. Therefore, our IB-SE-CRF scheme is more practical and suitable in IoT-Based Healthcare Systems environments.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110404"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143923208","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}