Computers & Electrical Engineering最新文献

{"title":"From global to local: A lightweight CNN approach for long-term time series forecasting","authors":"Site Mo ,&nbsp;Chengteng Yang ,&nbsp;Yipeng Mo ,&nbsp;Zuhua Yao ,&nbsp;Bixiong Li ,&nbsp;Songhai Fan ,&nbsp;Haoxin Wang","doi":"10.1016/j.compeleceng.2025.110192","DOIUrl":"10.1016/j.compeleceng.2025.110192","url":null,"abstract":"<div><div>In the context of the artificial intelligence revolution, the demand for long-term time series forecasting (LTSF) across various applications continues to rise. Contemporary deep learning models such as Transformer-based and MLP-based models have shown promise. However, these state-of-the-art (SOTA) approaches encounter notable limitations: Transformer-based models suffer from low computational efficiency and the inherent restrictions of point-wise attention mechanisms, while MLP-based models struggle to effectively capture local temporal dependencies. To overcome these challenges, this paper introduces a novel lightweight architecture centered around CNN-based models with an inherent receptive field, GLCN, explicitly designed to capture and discern intricate relationships in time series. The architecture features a key component, the global–local block, which initially segments the time series into subseries levels to preserve the underlying semantic information of temporal variations and subsequently captures both inter- and intra-patch inherent global and local temporal dynamics. In particular, GLCN utilizes a lightweight CNN-based architecture for prediction to significantly enhance training speed by 65.1% and 86.0% on the Weather and ETTh1 datasets, respectively, while reducing parameters by 94.8% and 94.4%. Comprehensive experiments on seven real-world datasets demonstrate that GLCN reduces contemporary SOTA approaches by 1.6% and 1.8% in Mean Squared Error and Mean Absolute Error.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110192"},"PeriodicalIF":4.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510799","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":"Objective-oriented efficient robotic manipulation: A novel algorithm for real-time grasping in cluttered scenes","authors":"Yufeng Li,&nbsp;Jian Gao,&nbsp;Yimin Chen,&nbsp;Yaozhen He","doi":"10.1016/j.compeleceng.2025.110190","DOIUrl":"10.1016/j.compeleceng.2025.110190","url":null,"abstract":"<div><div>Grasping unknown objects in non-structural environments autonomously is challenging for robotic manipulators, primarily due to the variability in environmental conditions and the unpredictable orientations of objects. To address this issue, this paper proposes a grasping algorithm that can segment the target object from a single view of the scene and generate collision-free 6-DOF(Degrees of Freedom) grasping poses. Initially, we develop a YOLO-CMA algorithm for object recognition in dense scenes. Building upon this, a point cloud segmentation algorithm based on object detection algorithm is used to extract the target object from the scene. Following this, a learning network is designed that takes into account both the target point cloud and the global point cloud. This network can achieve grasping pose generation, grasping pose scoring, and grasping pose collision detection. We integrate these grasping candidates with our bespoke online algorithm to generate the most optimal grasping pose. The recognition results in dense scenes demonstrate that the proposed YOLO-CMA structure can achieve better classification. Furthermore, real experimental with a UR3 manipulator results indicate that the proposed method can achieve real-time grasping of objects, achieving a grasping success rate of 88.3% and a completion rate of 93.3% in cluttered environments.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110190"},"PeriodicalIF":4.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143512127","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":"Advanced restoration management strategies in smart grids: The role of distributed energy resources and load priorities","authors":"Bahman Ahmadi ,&nbsp;Oguzhan Ceylan ,&nbsp;Aydogan Ozdemir","doi":"10.1016/j.compeleceng.2025.110196","DOIUrl":"10.1016/j.compeleceng.2025.110196","url":null,"abstract":"<div><div>Fast restoration following long outages is a challenge in the smart city management process. It is necessary to accurately characterize the real operating conditions of the system for optimal restoration. This study focuses on two key factors of a practical distribution system restoration. The first factor is cold load pickup (CLPU), which commonly occurs after an outage and is caused by thermostatically controlled loads. A time-dependent CLPU is modeled to accurately describe the restored load behaviors. The second factor is the effect of the distributed generators (DG), energy storage systems (ESSs), and load priority factors on the system’s restoration process. To address this challenge, a robust optimization model is proposed that fully considers the effect of DG, and ESS units and uncertainty of CLPU. The proposed models are tested on the IEEE 33-node and 69-node test systems using the Advanced Grey Wolf Algorithm (AGWO). The simulation scenarios are designed to uncover optimal scheduling strategies for the restoration process corresponding to each Pareto solution of a previous study. The results are discussed for several distinct initial conditions. Moreover, a comparative evaluation is done, contrasting the outcomes achieved through the AGWO algorithm with those stemming from alternative heuristic methods.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110196"},"PeriodicalIF":4.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143512141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring text-to-image generation models: Applications and cloud resource utilization","authors":"Sahani Pooja Jaiprakash ,&nbsp;Choudhary Shyam Prakash","doi":"10.1016/j.compeleceng.2025.110194","DOIUrl":"10.1016/j.compeleceng.2025.110194","url":null,"abstract":"<div><div>Generating images from text presents a significant challenge in computer vision. Moreover, manually acquiring images from multiple perspectives for object or product generation is a resource-intensive and expensive endeavor. However, recent breakthroughs in deep learning and artificial intelligence have opened doors to creating new images from diverse data sources, and cloud resources play a pivotal role in alleviating the resource-intensive nature of this endeavor. As a result, substantial research efforts have been directed toward advancing image generation techniques, yielding impressive results. This paper aims to provide a comprehensive overview of existing image generation methods, offering insights into this evolving field of text-to-image generation. It traces the historical development of this technology. It examines the key models that have shaped its evolution, including Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Conditional GANs (CGANs), StackGAN, Transformers, and diffusion models. The paper offers insights into the functioning of text-to-image generation within the GAN architecture, elucidating the mechanisms behind transforming textual descriptions into visual content.</div><div>Additionally, the integration of text-to-image generation with cloud and edge-cloud computing highlights the synergistic potential of these technologies while addressing the challenges and considerations associated with cloud infrastructure. The paper concludes by surveying the diverse applications of text-to-image generation across various domains, such as art, e-commerce, entertainment, and education. It also discusses the evaluation metrics commonly used in assessing the quality of generated images and the challenges that exist both within the methods and in their application across different domains. This review offers a comprehensive overview of the capabilities and limitations of text-to-image generation. Also, we have introduced a new HiResGAN model using a single generator/discriminator pair of networks to produce high-resolution 256 × 256 images from textual descriptions. We illustrate the efficacy of our model in producing high-resolution images based on contextually rich text descriptions that are visually plausible and semantically consistent through a series of experiments and analyses.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110194"},"PeriodicalIF":4.0,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510797","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":"High-speed system-on-chip-based platform for real-time crop disease and pest detection using deep learning techniques","authors":"MD Tausif Mallick ,&nbsp;D Omkar Murty ,&nbsp;Ranita Pal ,&nbsp;Swagata Mandal ,&nbsp;Himadri Nath Saha ,&nbsp;Amlan Chakrabarti","doi":"10.1016/j.compeleceng.2025.110182","DOIUrl":"10.1016/j.compeleceng.2025.110182","url":null,"abstract":"<div><div>Crop diseases significantly threaten global agricultural productivity and food security, leading to economic losses and increased pesticide use, which pollutes soil and water and disrupts ecological balance. <em>Mustard</em> and <em>mung bean</em> crops are particularly affected by various diseases and pests such as Alternaria blight, aphids, charcoal rot, bruchids, and mosaic. Timely and accurately identifying these diseases and pests are crucial for effective crop management. This research tackles disease classification in <em>mustard</em> and <em>mung bean</em> crops by employing transfer learning, a MobileNetV3-based CNN model, and a System-on-Chip (SoC) computing platform. The processing system and processing logic of SoC enhance computing flexibility. Xilinx Deep Learning Processor Unit (DPU) intellectual property (IP) accelerates disease classification 24 times compared to software counterparts. At the same time, our proposed design enhances the throughput by around 29% and reduces the power consumption by around 19%. MobileNetV3 achieves classification accuracies of 96.14% on <em>mung bean</em> and 93.25% on <em>mustard</em> datasets, surpassing other state-of-the-art methods. A vital aspect of this research is developing a user-friendly mobile application for image capture, communication with SoC, and result display, making disease and pest detection more convenient and accessible. The SoC-based system is versatile and can be extended to classify various crop varieties beyond <em>mung bean</em> and <em>mustard</em> without hardware modifications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110182"},"PeriodicalIF":4.0,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510798","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":"Diagnosing tic disorders from videos using multi-phase learning","authors":"Xiaojing Xu ,&nbsp;Ruizhe Zhang ,&nbsp;Zihao Bo ,&nbsp;Junfeng Lyu ,&nbsp;Yuchen Guo ,&nbsp;Feng Xu","doi":"10.1016/j.compeleceng.2025.110216","DOIUrl":"10.1016/j.compeleceng.2025.110216","url":null,"abstract":"<div><div>Worldwidely, the number of individuals with tic disorder has reached 59 million, while the prevalence of this disorder is still rapidly increasing. In this work, we proposed a multi-phase learning method for diagnosing childhood tic disorders from facial videos. To handle the problem of limited data annotation, we design an Entropy Gain (EG) metric to generate and select samples with pseudo labels and propose a multi-phase learning algorithm to efficiently leverage the EG-labeled data in a \"from easy to difficult\" manner. In our method, we use aligned facial landmarks as a compact data representation to further protect patient privacy and achieve efficient learning. Through extensive experiments on the test dataset, we demonstrate that our method behaves extraordinarily better compared to baseline approaches, improving AUC by 3.9 %, and facilitating expedited diagnostic assessment for medical practitioners.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110216"},"PeriodicalIF":4.0,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143488853","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":"Adaptive coil and compensation integration design (ACCID) for enhancing wireless charging for electric vehicles with efficient power transfer","authors":"Annai Raina TA ,&nbsp;Marshiana D","doi":"10.1016/j.compeleceng.2025.110184","DOIUrl":"10.1016/j.compeleceng.2025.110184","url":null,"abstract":"<div><div>The rapid adoption of Electric Vehicles (EVs) necessitates the development of efficient and reliable Wireless Power Transfer (WPT) systems. However, conventional WPT designs face challenges such as alignment sensitivity, high leakage inductance, and efficiency variations under dynamic load conditions. This research proposes an Adaptive Coil and Compensation Integration Framework (ACCIF) to enhance wireless EV charging by optimizing magnetic coupling and ensuring stable power transfer. A novel nested coil configuration is introduced, wherein the primary and secondary windings follow an interleaving pattern to enhance electromagnetic coupling, minimize leakage inductance, and mitigate electromagnetic interference (EMI). The nested design improves field alignment and ensures consistent power transfer over unipolar coils. Additionally, a double-sided LCC (D-LCC) compensation circuit is employed to maintain resonance stability and optimize efficiency across varying load conditions. The system leverages Resonant Inductive Power Transfer to sustain a constant current in the transmitter-side inductor, further enhancing power transfer efficiency. Experimental validation demonstrates a power transfer capability of 0.6 kW across a 243 mm air gap, achieving an efficiency of 94.68 %. By integrating advanced coil structures with adaptive compensation mechanisms, this research provides a scalable and practical solution for improving WPT technologies, contributing to the advancement of efficient and reliable wireless EV charging systems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110184"},"PeriodicalIF":4.0,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143488854","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":"Detection and localization of dynamic load altering attacks in power systems","authors":"Fatemeh Najafi ,&nbsp;Shaghayegh Nobakht ,&nbsp;Marzieh Samimiat ,&nbsp;Ali-Akbar Ahmadi ,&nbsp;Abolfazl Nateghi","doi":"10.1016/j.compeleceng.2025.110207","DOIUrl":"10.1016/j.compeleceng.2025.110207","url":null,"abstract":"<div><div>Cyber-attacks in power systems which are a type of cyber-physical systems (CPSs) can cause many problems, including system instability and blackouts. Meanwhile, dynamic load altering attacks (D-LAAs) could have a very destructive effect. In this paper, detection of the <span>d</span>-LAA in the power systems is discussed. The power system in presence of the <span>d</span>-LAA is modeled as a singular system and then an appropriate attack detection observer is designed. Then, using a bank of unknown input observers, the location of the attack is determined. Comparing to the existing results, no restrictive assumption such as presence of phasor measurement units (PMUs) in all buses or on the attack signal are considered. The design is done in the discrete-time domain and thus is suitable for practical implementation in the power systems where most of the relays and equipment are numerical. The design of the ADO and attack localization observers (ALOs) are performed using a centralized approach which facilitates taking the necessary actions to maintain the stability of the power system. Finally, simulation results on the IEEE 39-bus system with the help of MATLAB show the efficiency and capability of the proposed method.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110207"},"PeriodicalIF":4.0,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479141","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":"GAL-GAN: Global styles and local high-frequency learning based generative adversarial network for image cartoonization","authors":"Luoyi Li,&nbsp;Lintao Zheng,&nbsp;Chunlei Yang,&nbsp;Yongsheng Dong","doi":"10.1016/j.compeleceng.2025.110164","DOIUrl":"10.1016/j.compeleceng.2025.110164","url":null,"abstract":"<div><div>The style transfer of cartoon images has always been a challenging problem in computer vision. Currently, there are still two aspects that need to be improved in this field: (1) existing methods can only perform simple domain-to-domain cartoon style transfer, ignoring the global style information of the image, and (2) the neglect of local features in image style transfer, such as edge information and texture information, leads to lower quality of stylized images. To alleviate these two issues, we propose a novel global styles and local high-frequency learning based generative adversarial network (GAL-GAN) for image cartoonization. Specifically, the feature information of each channel is weighted by cartoon feature mapping to improve the quality of the global cartoon style of the generated image. In order to enrich the local feature information of generated images, we introduce a high-frequency learning strategy to reduce noise and enhance texture and detail extraction. Experiments reveal that GAL-GAN can generate high-quality stylized images with a specific style and have advantages over current state-of-the-art models.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110164"},"PeriodicalIF":4.0,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479142","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":"HybridCISN: Integrating 2D/3D convolutions and involutions with hyperspectral imaging and blood biomarkers for neonatal disease detection","authors":"Mücahit CİHAN,&nbsp;Murat CEYLAN","doi":"10.1016/j.compeleceng.2025.110193","DOIUrl":"10.1016/j.compeleceng.2025.110193","url":null,"abstract":"<div><div>Early detection and accurate diagnosis of neonatal diseases are crucial for improving health outcomes and reducing infant mortality. This study introduces a novel Hybrid Convolutional and Involutional Spectral Network (HybridCISN) that integrates hyperspectral imaging (HSI) data with blood biomarker analysis to enhance neonatal health diagnostics. By combining 2D convolution, 3D convolution, and involution layers, the HybridCISN model extracts spatial, spectral, and channel-specific features, addressing limitations in traditional diagnostic methods. The model was evaluated through two distinct approaches: (1) using only HSI spectral data and (2) integrating HSI spectral data with blood biomarkers such as haemoglobin and bilirubin levels. These approaches were tested for both binary classification (healthy vs. unhealthy neonates) and multiclass classification (specific neonatal diseases such as intracranial hemorrhage, necrotizing enterocolitis, pneumothorax, and respiratory distress syndrome). Experimental results demonstrate the HybridCISN model's superior performance, achieving an overall accuracy of 93.64% for binary classification and 90.25% for multiclass classification. Compared to state-of-the-art methods such as the involution-based HarmonyNet and the 2D/3D convolution-based HybridSN, the HybridCISN model achieved accuracy improvements of 0.8% and 1.5%, respectively, in multiclass classification. The second approach, integrating blood biomarkers, improved diagnostic sensitivity and specificity, emphasizing the value of multimodal data fusion. Involution layers reduced channel redundancy and optimized feature extraction, as confirmed by ablation studies. The HybridCISN model offers a scalable and non-invasive diagnostic framework, addressing clinical applicability and biomarker accessibility, while combining precision, efficiency, and robustness to advance neonatal disease detection and set a benchmark for future research in medical imaging.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110193"},"PeriodicalIF":4.0,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479140","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}