Computers & Electrical Engineering最新文献_第3页

Monitoring and machine learning-based classification of human activities in bed using wireless devices and a fusion of acceleration and sEMG signals 利用无线设备和加速度和表面肌电信号的融合对床上的人类活动进行监测和基于机器学习的分类

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-09-05 DOI: 10.1016/j.compeleceng.2025.110655

Chawakorn Intongkum, Yoschanin Sasiwat, Kiattisak Sengchuai, Dujdow Buranapanichkit, Apidet Booranawong, Nattha Jindapetch, Pornchai Phukpattaranont

{"title":"Monitoring and machine learning-based classification of human activities in bed using wireless devices and a fusion of acceleration and sEMG signals","authors":"Chawakorn Intongkum, Yoschanin Sasiwat, Kiattisak Sengchuai, Dujdow Buranapanichkit, Apidet Booranawong, Nattha Jindapetch, Pornchai Phukpattaranont","doi":"10.1016/j.compeleceng.2025.110655","DOIUrl":"10.1016/j.compeleceng.2025.110655","url":null,"abstract":"<div><div>This research aims to develop a system for monitoring and classifying human activities in bed using three-axis accelerometer (ACM) and surface electromyography (sEMG) signals. The contributions of this work are that, first, we develop and implement 2.4 GHz IEEE 802.15.4 wireless sensor nodes combined with a three-axis ACM (i.e., GY-521) and an sEMG sensor (i.e., OYMotion), where sensor data are wirelessly sent to a receiver connected to a computer for processing. Second, nine human activities in bed, including rapid breathing, seizure sleeping, and falling from the bed, as the critical events, are considered. Third, human activity classification is carried out using a machine learning-based classification framework with 150 features and six classifiers with several sub-functions, including Decision Tree (DT), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Naive Bayes (NB), Neural Networks (NN), and Ensemble. Three cases of input data for classification are evaluated: only ACM data (for motion), only sEMG data (for muscle contraction), and fusion data. Experimental results demonstrate that three-axis ACM and sEMG data are successfully sent via wireless communications for both line-of-sight (LOS) and non-line-of-sight (NLOS) environments, where efficient monitoring can be achieved. Additionally, we can obtain 98 % classification accuracy when both sensor data and the Ensemble Subspace KNN method are used. Specifically, we can accurately detect abnormal events such as rapid breathing, seizure sleeping, falling from the bed, and lying down on the ground, with an accuracy of 98.8 %, 97.7 %, 92.0 %, and 99.3 %, respectively.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110655"},"PeriodicalIF":4.9,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144997050","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

An enhanced social network search algorithm for accurate dynamic parameter identification of Li-ion batteries in electric vehicles 一种用于电动汽车锂离子电池动态参数准确识别的增强社会网络搜索算法

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-09-05 DOI: 10.1016/j.compeleceng.2025.110691

Hany S.E. Mansour , Hassan M. Hussein Farh , Abdullrahman A. Al-Shamma'a , Badr Al Faiya , Zuhair M. Alaas , Gamal A. Elnashar

{"title":"An enhanced social network search algorithm for accurate dynamic parameter identification of Li-ion batteries in electric vehicles","authors":"Hany S.E. Mansour , Hassan M. Hussein Farh , Abdullrahman A. Al-Shamma'a , Badr Al Faiya , Zuhair M. Alaas , Gamal A. Elnashar","doi":"10.1016/j.compeleceng.2025.110691","DOIUrl":"10.1016/j.compeleceng.2025.110691","url":null,"abstract":"<div><div>Accurate modeling of lithium-ion batteries (LIBs) is crucial for enhancing the performance and safety of electric vehicles (EVs) and optimizing energy storage systems. This study proposes an Enhanced Social Networking Search Algorithm (ESNSA) for precise dynamic parameter identification in LIBs models. Building on the original SNSA, ESNSA introduces an Effective Exploitation Technique (EET) and adaptive parameter adjustment to achieve a more effective balance between global exploration and local exploitation. The algorithm’s performance was rigorously evaluated using experimental and simulation data from a 40-Ah Kokam LIB under the assessment and reliability of transport emission models inventory systems’ driving cycle. ESNSA achieved minimum objective function values of 0.007638 and 0.004394 in the first and second case studies, respectively, substantially outperforming conventional and state-of-the-art algorithms, such as the Arithmetic Technique, Jellyfish Search Technique, and Grey Wolf Optimizer. The proposed approach also delivered the lowest mean error 0.00801 and standard deviation of 0.000177 across comparative tests, confirming its superior accuracy and robustness. Statistical analyses (Friedman and Wilcoxon tests) demonstrated significant performance improvements over 9 out of 10 competing algorithms. The results affirm the ESNSA as a highly effective tool for robust, accurate LIB parameter estimation, offering tangible benefits for advanced battery management systems in EVs and renewable energy applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110691"},"PeriodicalIF":4.9,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144997048","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

CPIGAN: Infrared and visible image fusion via cross-scale progressive interaction network with adversarial learning 基于对抗学习的跨尺度渐进交互网络红外和可见光图像融合

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-09-05 DOI: 10.1016/j.compeleceng.2025.110672

Zihao Zhang, Jian Zhou, Junyi Shi, Jian Lu

{"title":"CPIGAN: Infrared and visible image fusion via cross-scale progressive interaction network with adversarial learning","authors":"Zihao Zhang, Jian Zhou, Junyi Shi, Jian Lu","doi":"10.1016/j.compeleceng.2025.110672","DOIUrl":"10.1016/j.compeleceng.2025.110672","url":null,"abstract":"<div><div>The objective of infrared and visible image fusion is to synthesize a single fused image that retains the salient target features and texture details of the source image. However, existing image fusion algorithms have not yet fully considered the intrinsic depth characteristics of images, ignoring the correlation between their information at different scales, thus limiting the fusion performance. Toward this end, we propose a cross-scale progressively interacting adversarial fusion network, called CPIGAN. In particular, in the generator, we design a progressively interacting feature extractor, which consists of the dual-stream gradient residual enhancement module (DGREM) and the multimodal cross perception module (MCPM). This design not only achieves feature-level texture enhancement, but also facilitates the full interaction of relevant and complementary information of multimodal images at different scales. Furthermore, we propose a cross-scale cross-fusion strategy that combines global and local attention models. It enables the accurate capture of local details at the spatial level while providing a comprehensive grasp of global information at the channel level. Extensive experiments show that our CPIGAN outperforms other advanced methods in subjective and objective evaluations. Meanwhile, we demonstrate the superiority of our method by evaluating it in the downstream task of object detection.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110672"},"PeriodicalIF":4.9,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144997046","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 rippling surveillance model with subsequent tracking in UAV-enabled spaces 涟漪监视模型，在无人机启用的空间中进行后续跟踪

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-09-02 DOI: 10.1016/j.compeleceng.2025.110654

Minsoo Kim, Hyunbum Kim

{"title":"A rippling surveillance model with subsequent tracking in UAV-enabled spaces","authors":"Minsoo Kim, Hyunbum Kim","doi":"10.1016/j.compeleceng.2025.110654","DOIUrl":"10.1016/j.compeleceng.2025.110654","url":null,"abstract":"<div><div>A surveillance has emerged as a critical research since a critical security surveillance system can affect various applications including transportation services, smart cities, mobile computing, etc. Existing surveillance models primarily focus on how to perform initial or preliminary detection against intruders into the target spaces. Also, existing surveillance systems had limitations in detecting intruders following nonlinear paths by relying on static sensors, but this study introduced a method of tracking the intrusion path by activating dynamic sensors after detection. In particular, while existing studies have focused on detection at the moment of intrusion, this study is differentiated in that it attempted to strengthen security through tracking after detection. In this paper, we introduce a rippling surveillance model to provide sustainable surveillance with subsequent tracking after initial detection in UAV-enabled applications. The proposed model performs a cooperation of a static configuration and a dynamic formation deployed in a k-means clustering method to strengthen the surveillance and tracking function in the difficult-to-predict intrusion path. The system evaluated dynamic sensing radius and intruder speed as variables, and as a result, the tracking accuracy improves as the radius increases, but the resource efficiency decreases when the radius becomes too large. In addition, as the intruder speed increases, the tracking accuracy tends to decrease significantly in the linear path. The system combines the stability of static sensors with the flexibility of dynamic sensors to achieve high tracking accuracy across different intrusion paths, emphasizing that the optimization of dynamic sensing radius and sensor placement is an important factor.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110654"},"PeriodicalIF":4.9,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926564","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

CropCapsNet: Enhanced capsule network for crop disease classification CropCapsNet：用于作物病害分类的增强胶囊网络

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-09-02 DOI: 10.1016/j.compeleceng.2025.110635

Juan Qin , Linfan Deng , Cong Li , Junjie He , Haibo Pen , Zhaoxia Wang

{"title":"CropCapsNet: Enhanced capsule network for crop disease classification","authors":"Juan Qin , Linfan Deng , Cong Li , Junjie He , Haibo Pen , Zhaoxia Wang","doi":"10.1016/j.compeleceng.2025.110635","DOIUrl":"10.1016/j.compeleceng.2025.110635","url":null,"abstract":"<div><div>The prevention and treatment of crop diseases are crucial for the development of smart agriculture. The classification of crop diseases based on deep learning for early disease monitoring and control has become the mainstream direction of research. This paper proposes a novel deep learning model called ”CropCapsNet”, which combines Squeeze-and-Excitation Inception (SE-Inception) module and has improved capsule structure for crop disease classification. The network first extracts shallow features of input samples through double-layer convolution, then uses SE-Inception to achieve deep multi-scale feature acquisition, and finally outputs classification results through an improved capsule structure. SE-Inception adds Squeeze-and-Excitation(SE) attention after each multi-scale feature extraction block to improve the model’s perception of diseases without increasing the number of parameters. The improved capsule structure is embedded with a parameter grouping strategy, which can control trainable parameters by adjusting the number of capsule groups to adapt to different application scenarios. To verify the generalization of the network, this paper uses three datasets containing different experimental scenarios (PlantVillage, Xinong Apple Dataset, and FGVC8) to evaluate the performance of CropCapsNet. The results show that CropCapsNet has achieved classification accuracies of 99.99%, 98.18%, and 98.09% in the three datasets, respectively. Compared with methods such as ConvNeXt, RegNet, and ResNeSt, CropCapsNet performs excellently. In addition, this paper uses image reconstruction networks and heatmaps to visualize CropCapsNet, improving the interpretability of the model.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110635"},"PeriodicalIF":4.9,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926565","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

Zero-day attack detection with a Dynamic-Weighted Contractive Autoencoder and GAN-based evaluation 基于动态加权压缩自编码器和gan评估的零日攻击检测

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-09-01 DOI: 10.1016/j.compeleceng.2025.110650

M. Franckie Singha, Ripon Patgiri, Zeba Shamsi, Laiphrakpam Dolendro Singh

{"title":"Zero-day attack detection with a Dynamic-Weighted Contractive Autoencoder and GAN-based evaluation","authors":"M. Franckie Singha, Ripon Patgiri, Zeba Shamsi, Laiphrakpam Dolendro Singh","doi":"10.1016/j.compeleceng.2025.110650","DOIUrl":"10.1016/j.compeleceng.2025.110650","url":null,"abstract":"<div><div>Anomaly detection, which has faced quite a challenge in zero-day attacks whose nature is novel and unpredictable, shall be addressed here. This research proposes a novel method for zero-day attacks with an adaptive loss-based Dynamic-Weighted Contractive Autoencoder (DW-CAE). The proposed method differs from the traditional autoencoder approach because it balances reconstruction and Contractive penalty and pays particular attention to features that are difficult to reconstruct. The training of DW-CAE on normal data learns invariant feature representations that enable the efficient detection of anomalies based on high reconstruction errors. The dynamic weighting mechanism further enhances the adaptive balancing of reconstruction and Contractive penalty to increase the model’s sensitivity and robustness against unseen attacks. Furthermore, we have utilized GANs to generate novel synthetic zero-day attack data for rigorous evaluation of the model. CAE and dynamic weight coordination introduce an innovative and robust model for detecting zero-day attacks. Experimental results are shown on the CICIoT2023, CICDDoS2019, ToN-IoT, and synthetic datasets, validating the performance of the proposed approach. The proposed DW-CAE demonstrates a significant performance gain over the fixed-weight CAE, achieving a significant improvement across the three benchmark datasets, highlighting its effectiveness across diverse intrusion detection scenarios.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110650"},"PeriodicalIF":4.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922415","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

Intelligent target detection and encrypted transmission system based on FPGA 基于FPGA的智能目标检测与加密传输系统

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-09-01 DOI: 10.1016/j.compeleceng.2025.110653

Dongxu Liu, Yuzhuo Zhao, Zhiyan Ma, Qun Ding

引用次数: 0

Modeling impairments of computing systems considering hardware–software interaction failures and dependability quantification 考虑软硬件交互故障和可靠性量化的计算系统建模缺陷

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-08-31 DOI: 10.1016/j.compeleceng.2025.110632

Antony Gratas Varuvel , Rajendra Prasath

{"title":"Modeling impairments of computing systems considering hardware–software interaction failures and dependability quantification","authors":"Antony Gratas Varuvel , Rajendra Prasath","doi":"10.1016/j.compeleceng.2025.110632","DOIUrl":"10.1016/j.compeleceng.2025.110632","url":null,"abstract":"<div><div>The computing systems deployed in safety-critical applications often comprise complex hardware with highly intensive software/firmware. The development and validation of computing systems for safety-critical applications shall comply with the Design Assurance Level-A as per RTCA DO-254/DO-178 or Safety Integrity Level-4 as per IEC-61508 towards certification. However, adherence to this process does not assure dependability. Quantifying the reliability to assess the risk associated with using these systems for safety-critical applications is necessary. Hence, dependability quantification of the computing system has been undertaken in this research, with significant improvements over the conventional approaches. In the classical approach, hardware faults and software errors were treated as independent events, and failures arising from interactions were ignored. It is proposed to model dependent states arising due to hardware–software interaction, such as hardware-triggered software failure and software-triggered hardware failures, in addition to hardware and software failures, to model the failure characteristics of the system completely. A stochastic Petri Net (SPN) based methodology is adopted to model the error/fault propagation by considering all possible places, transitions, and tokens. SPN is then transformed into a Continuous-Time Markov Chain to quantify reliability analytically. This enhanced methodology enables more accurate dependability quantification and risk assessment.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110632"},"PeriodicalIF":4.9,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144919969","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

Preemptive crash risk reduction through a real-time cost-based safety prediction model (RECOSAM) for traffic signal control 基于实时成本安全预测模型（RECOSAM）的交通信号控制先发制人降低碰撞风险

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-08-31 DOI: 10.1016/j.compeleceng.2025.110639

Lok Sang Chan, Neema Nassir, Xiaocai Zhang, Mobin Yazdani, Majid Sarvi

{"title":"Preemptive crash risk reduction through a real-time cost-based safety prediction model (RECOSAM) for traffic signal control","authors":"Lok Sang Chan, Neema Nassir, Xiaocai Zhang, Mobin Yazdani, Majid Sarvi","doi":"10.1016/j.compeleceng.2025.110639","DOIUrl":"10.1016/j.compeleceng.2025.110639","url":null,"abstract":"<div><div>This paper proposes a novel real-time cost-based safety prediction model (RECOSAM) and incorporating it in intersection traffic signal control optimisation, complementing the recent advances in deep reinforcement learning (RL)-based adaptive traffic signal control (ATSC). The primary contribution is the development of RECOSAM, a model designed to predict traffic safety risks one step ahead of time, for various signal phase configurations at intersections. The proposed model offers a dynamic safety evaluation strategy, estimating near-future safety metrics for seamless integration into machine learning-based ATSC systems. Extensive experiments validate the model’s effectiveness, demonstrating its potential for adaptive adjustments to mitigate impending safety risks. Perhaps more importantly from an operational policy perspective, the proposed model is capable of finding an optimal and justifiable trade-off between the efficiency of traffic flow and its safety in real-time.</div><div>A case study showcases the integration of RECOSAM into deep RL for green time optimisation. Results suggest that extended dedicated right turn phases may reduce safety risks, while overly protected phases could lead to inefficiencies in green time allocation and increased congestion. The model’s adaptability across different scenarios is further illustrated, showing its capability to evaluate critical trade-offs between safety and efficiency especially for vehicles trying to make a right turn by finding gaps through traffic coming form the opposing direction (in left-hand-side driving countries—same applies for left turns in right-hand-side driving countries).</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110639"},"PeriodicalIF":4.9,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922416","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

Lightweight spatial attention pyramid network-based image forgery detection optimized for real-time edge TPU deployment 针对实时边缘TPU部署优化的基于轻量级空间注意力金字塔网络的图像伪造检测

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-08-31 DOI: 10.1016/j.compeleceng.2025.110645

Baby Sree Gangarapu , Rama Muni Reddy Yanamala , Archana Pallakonda , Hindupur Raghavender Vardhan , Rayappa David Amar Raj

{"title":"Lightweight spatial attention pyramid network-based image forgery detection optimized for real-time edge TPU deployment","authors":"Baby Sree Gangarapu , Rama Muni Reddy Yanamala , Archana Pallakonda , Hindupur Raghavender Vardhan , Rayappa David Amar Raj","doi":"10.1016/j.compeleceng.2025.110645","DOIUrl":"10.1016/j.compeleceng.2025.110645","url":null,"abstract":"<div><div>The widespread accessibility of image editing software has made image forgery a considerable threat in journalism, legal contexts, and social media, requiring effective and precise detection techniques. The Authors propose a Spatial Attention Pyramid Network (SAPN) that integrates multi-scale residual feature extraction with an adaptive spatial attention mechanism to tackle the difficulties of identifying subtle and localized alterations. SAPN attains enhanced forgery detection performance and computational efficiency by utilizing hierarchical feature learning and selectively augmenting regions susceptible to manipulation. Extensive experiments conducted on four benchmark datasets illustrate the effectiveness and generalizability of SAPN. On the CASIA V1 dataset, SAPN attains an accuracy of 94% and an AUC of 0.99, outperforming 29 state-of-the-art models. An ablation study further supports the contributions of the pyramid feature extraction and spatial attention modules to the overall performance improvements. Moreover, a lightweight model architecture, containing merely 0.57 million parameters, enables efficient real-time deployment on Edge TPU devices, with an average inference latency of 1.17 s per image. These results proclaim SAPN as a scalable and robust framework for image forgery detection and localization in real-world applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110645"},"PeriodicalIF":4.9,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144919966","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