Computers & Electrical Engineering最新文献_第4页

Parameter estimation of solar photovoltaic models using fitness-based diversified cluster division and multi-mutation learned differential evolution 基于适应度的多样化聚类划分和多突变学习差分进化的太阳能光伏模型参数估计

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-04-01 Epub Date: 2026-01-27 DOI: 10.1016/j.compeleceng.2026.110995

Deepak Sahu, Shubham Gupta

Precise estimation of parameters is crucial for solar photovoltaic models and analysis of characteristics of associated photovoltaic systems, as the non-linear and implicit behavior of the current–voltage relationship makes this problem significantly challenging. This objective has emerged as a key area of interest for researchers. The rapid advancement of evolutionary algorithms and computer technology has resulted in the development of various metaheuristic algorithms to accelerate this trend further. This study aims to design a robust evolutionary algorithm named FDC-DE by modifying the conventional differential evolution algorithm using different search strategies to enrich the algorithm with effective explorative and exploitative search mechanisms. The FDC-DE comprises fitness-based diversified cluster division and multi-mutation learning strategies to guide the search by the representative member of the population and to provide diverse learning strategies at different stages of the search procedure. These strategies will provide reasonable balancing ability to the algorithm in accelerating convergence and avoiding issues of stagnation and premature convergence at local optimal solutions. To evaluate the proposed FDC-DE algorithm, it is tested on the 23 classical benchmark problems and the IEEE CEC2022 benchmark suite, followed by six experimental sets of single, double, and triple-diode models and three photovoltaic module models. Extensive experiments are performed, and a comparison of the FDC-DE is performed with advanced state-of-the-art metaheuristic algorithms based on accuracy comparison, statistical analysis of the results, and convergence characteristics. The results verify the outperforming search efficiency of the FDC-DE.

精确的参数估计对于太阳能光伏模型和相关光伏系统的特性分析至关重要，因为电流-电压关系的非线性和隐式行为使这一问题变得非常具有挑战性。这一目标已成为研究人员感兴趣的一个关键领域。进化算法和计算机技术的快速发展导致了各种元启发式算法的发展，进一步加速了这一趋势。本研究旨在通过使用不同的搜索策略对传统的差分进化算法进行改进，设计一种鲁棒的FDC-DE进化算法，以丰富有效的探索性和剥削性搜索机制。FDC-DE包括基于适应度的多样化聚类划分和多突变学习策略，以指导群体中代表性成员的搜索，并在搜索过程的不同阶段提供多样化的学习策略。这些策略将为算法在加速收敛和避免局部最优解停滞和过早收敛问题上提供合理的平衡能力。为了对所提出的FDC-DE算法进行评估，在23个经典基准问题和IEEE CEC2022基准测试套件上进行了测试，随后进行了单、双、三二极管模型和三种光伏组件模型的6个实验集的测试。进行了大量的实验，并将FDC-DE与基于精度比较、结果统计分析和收敛特性的最先进的元启发式算法进行了比较。结果验证了FDC-DE算法的搜索效率。

{"title":"Parameter estimation of solar photovoltaic models using fitness-based diversified cluster division and multi-mutation learned differential evolution","authors":"Deepak Sahu, Shubham Gupta","doi":"10.1016/j.compeleceng.2026.110995","DOIUrl":"10.1016/j.compeleceng.2026.110995","url":null,"abstract":"<div><div>Precise estimation of parameters is crucial for solar photovoltaic models and analysis of characteristics of associated photovoltaic systems, as the non-linear and implicit behavior of the current–voltage relationship makes this problem significantly challenging. This objective has emerged as a key area of interest for researchers. The rapid advancement of evolutionary algorithms and computer technology has resulted in the development of various metaheuristic algorithms to accelerate this trend further. This study aims to design a robust evolutionary algorithm named FDC-DE by modifying the conventional differential evolution algorithm using different search strategies to enrich the algorithm with effective explorative and exploitative search mechanisms. The FDC-DE comprises fitness-based diversified cluster division and multi-mutation learning strategies to guide the search by the representative member of the population and to provide diverse learning strategies at different stages of the search procedure. These strategies will provide reasonable balancing ability to the algorithm in accelerating convergence and avoiding issues of stagnation and premature convergence at local optimal solutions. To evaluate the proposed FDC-DE algorithm, it is tested on the 23 classical benchmark problems and the IEEE CEC2022 benchmark suite, followed by six experimental sets of single, double, and triple-diode models and three photovoltaic module models. Extensive experiments are performed, and a comparison of the FDC-DE is performed with advanced state-of-the-art metaheuristic algorithms based on accuracy comparison, statistical analysis of the results, and convergence characteristics. The results verify the outperforming search efficiency of the FDC-DE.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110995"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080169","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

Short-term scheduling strategy of renewable integrated hydrothermal system using chaotic chimp-sine cosine algorithm considering wind uncertainty and grid stability 考虑风力不确定性和电网稳定性的混沌黑猩猩-正弦余弦算法的可再生综合热液系统短期调度策略

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-04-01 Epub Date: 2026-02-09 DOI: 10.1016/j.compeleceng.2026.111025

Shahid A. Iqbal , Saurav Raj , Chandan Kumar Shiva

The integration of renewable energy sources (RES) is vital for achieving long-term sustainability in power systems; however, it introduces significant operational challenges owing to the inherent variability of wind and solar generation. Existing research often neglects uncertainties or fails to address them within the realistic constraints of hydrothermal systems. This study proposes a robust and comprehensive short-term scheduling framework for renewable-integrated hydrothermal systems, accounting for the stochastic nature of RES. The proposed chaotic chimp sine cosine algorithm (C-CHOA-SC) effectively tackles the non-convex hydrothermal wind solar scheduling problem by enhancing exploration via chaotic dynamics and avoiding local optima. In this model, wind uncertainty is modelled using the Weibull distribution, and solar generation is capped at 30% of the load demand to maintain transient stability. Numerical simulations revealed that C-CHOA-SC reduced fuel costs by 9.5% compared to differential evolution (DE), 3.1% compared to particle swarm optimization (PSO), and 1.5% compared to grey wolf optimization (GWO). Emission reductions were even more pronounced, being 92% lower than DE, 21% lower than PSO, and 97% lower than GWO. Sensitivity analyses confirmed the algorithm's robustness and adaptability to real-world variations in RES availability. Overall, this framework offers an efficient and practical solution for smart grid operators and policymakers aiming to optimize economic performance, reduce emissions, and enhance operational reliability in renewable-dominated power systems.

可再生能源的整合对于实现电力系统的长期可持续性至关重要；然而，由于风能和太阳能发电固有的可变性，它带来了重大的操作挑战。现有的研究经常忽略不确定性，或者未能在热液系统的现实限制下解决这些不确定性。本文针对可再生集成热液系统的随机特性，提出了一种鲁棒且全面的短期调度框架。提出的混沌黑猩猩正弦余弦算法（C-CHOA-SC）通过加强混沌动力学的探索，避免了局部最优，有效地解决了非凸热液风能太阳能调度问题。在该模型中，风的不确定性使用威布尔分布建模，太阳能发电被限制在负荷需求的30%以保持暂态稳定。数值模拟结果表明，与差分进化（DE）相比，C-CHOA-SC的燃料成本降低了9.5%，与粒子群优化（PSO）相比降低了3.1%，与灰狼优化（GWO）相比降低了1.5%。减排更为显著，比DE低92%，比PSO低21%，比GWO低97%。灵敏度分析证实了算法的鲁棒性和对现实世界RES可用性变化的适应性。总体而言，该框架为智能电网运营商和决策者提供了一个高效实用的解决方案，旨在优化可再生能源主导的电力系统的经济性能、减少排放和提高运行可靠性。

{"title":"Short-term scheduling strategy of renewable integrated hydrothermal system using chaotic chimp-sine cosine algorithm considering wind uncertainty and grid stability","authors":"Shahid A. Iqbal , Saurav Raj , Chandan Kumar Shiva","doi":"10.1016/j.compeleceng.2026.111025","DOIUrl":"10.1016/j.compeleceng.2026.111025","url":null,"abstract":"<div><div>The integration of renewable energy sources (RES) is vital for achieving long-term sustainability in power systems; however, it introduces significant operational challenges owing to the inherent variability of wind and solar generation. Existing research often neglects uncertainties or fails to address them within the realistic constraints of hydrothermal systems. This study proposes a robust and comprehensive short-term scheduling framework for renewable-integrated hydrothermal systems, accounting for the stochastic nature of RES. The proposed chaotic chimp sine cosine algorithm (C-CHOA-SC) effectively tackles the non-convex hydrothermal wind solar scheduling problem by enhancing exploration via chaotic dynamics and avoiding local optima. In this model, wind uncertainty is modelled using the Weibull distribution, and solar generation is capped at 30% of the load demand to maintain transient stability. Numerical simulations revealed that C-CHOA-SC reduced fuel costs by 9.5% compared to differential evolution (DE), 3.1% compared to particle swarm optimization (PSO), and 1.5% compared to grey wolf optimization (GWO). Emission reductions were even more pronounced, being 92% lower than DE, 21% lower than PSO, and 97% lower than GWO. Sensitivity analyses confirmed the algorithm's robustness and adaptability to real-world variations in RES availability. Overall, this framework offers an efficient and practical solution for smart grid operators and policymakers aiming to optimize economic performance, reduce emissions, and enhance operational reliability in renewable-dominated power systems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 111025"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174133","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 low-latency deep learning approach for human action recognition in medical internet of things applications 医疗物联网应用中人体动作识别的低延迟深度学习方法

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-04-01 Epub Date: 2026-02-06 DOI: 10.1016/j.compeleceng.2026.111005

Hoangcong Le, Cheng-Kai Lu

Real-time human action recognition (HAR) plays a vital role in healthcare monitoring, particularly for elderly care and assistive environments. However, existing HAR systems often struggle with high computational demands, large model sizes, and vulnerability to background noise, limiting their use on edge devices in the Internet of Medical Things (IoMT) settings. This study proposes Temporal-SpatialCNN, a lightweight framework built on a novel CNNBlock architecture that integrates convolution, batch normalization, and Spatial-Dropout to enhance both efficiency and generalization. The study systematically analyzes various layer arrangements within CNNBlock and identifies an optimal configuration that improves recognition performance while maintaining minimal computational overhead. The model incorporates diverse skeletal input modalities – joint coordinates, joint collection distances, slow motion, and velocity – to capture enriched spatio-temporal features. Extensive experiments on five well-known benchmark datasets validate the effectiveness of the proposed approach, achieving state-of-the-art accuracy (up to 99.66% on the Florence-3D dataset) with an inference time of 9.6 ms. To demonstrate real-world applicability, a real-time Save Our Soul (SOS) system was implemented on standard hardware, capable of detecting emergency gestures such as calls for assistance, thereby highlighting the model’s practical potential in real-time, resource-constrained healthcare scenarios.

实时人体动作识别（HAR）在医疗保健监测中起着至关重要的作用，特别是在老年人护理和辅助环境中。然而，现有的HAR系统通常难以满足高计算需求、大模型尺寸和易受背景噪声影响，这限制了它们在医疗物联网（IoMT）设置中的边缘设备上的使用。本研究提出了一种基于新颖的CNNBlock架构的轻量级框架Temporal-SpatialCNN，该框架集成了卷积、批处理归一化和Spatial-Dropout，以提高效率和泛化。该研究系统地分析了CNNBlock内的各种层安排，并确定了在保持最小计算开销的同时提高识别性能的最佳配置。该模型结合了不同的骨骼输入模式-关节坐标，关节收集距离，慢动作和速度-以捕获丰富的时空特征。在五个知名基准数据集上进行的大量实验验证了所提出方法的有效性，在推断时间为9.6 ms的情况下，达到了最先进的精度（在Florence-3D数据集上高达99.66%）。为了证明在现实世界中的适用性，我们在标准硬件上实现了实时SOS系统，该系统能够检测紧急手势，例如呼叫援助，从而突出了该模型在实时、资源受限的医疗保健场景中的实际潜力。

{"title":"A low-latency deep learning approach for human action recognition in medical internet of things applications","authors":"Hoangcong Le, Cheng-Kai Lu","doi":"10.1016/j.compeleceng.2026.111005","DOIUrl":"10.1016/j.compeleceng.2026.111005","url":null,"abstract":"<div><div>Real-time human action recognition (HAR) plays a vital role in healthcare monitoring, particularly for elderly care and assistive environments. However, existing HAR systems often struggle with high computational demands, large model sizes, and vulnerability to background noise, limiting their use on edge devices in the Internet of Medical Things (IoMT) settings. This study proposes Temporal-SpatialCNN, a lightweight framework built on a novel CNNBlock architecture that integrates convolution, batch normalization, and Spatial-Dropout to enhance both efficiency and generalization. The study systematically analyzes various layer arrangements within CNNBlock and identifies an optimal configuration that improves recognition performance while maintaining minimal computational overhead. The model incorporates diverse skeletal input modalities – joint coordinates, joint collection distances, slow motion, and velocity – to capture enriched spatio-temporal features. Extensive experiments on five well-known benchmark datasets validate the effectiveness of the proposed approach, achieving state-of-the-art accuracy (up to 99.66% on the Florence-3D dataset) with an inference time of 9.6 ms. To demonstrate real-world applicability, a real-time Save Our Soul (SOS) system was implemented on standard hardware, capable of detecting emergency gestures such as calls for assistance, thereby highlighting the model’s practical potential in real-time, resource-constrained healthcare scenarios.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 111005"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174182","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

Advancements and challenges in deepfake medical imaging: generation and detection techniques 深度假医学成像的进展和挑战：生成和检测技术

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-04-01 Epub Date: 2026-02-12 DOI: 10.1016/j.compeleceng.2026.111038

Sayeli Dey, Smita Das, Penumala Nani

In medical imaging, deepfake generation challenges the verification of image authenticity, raising concerns about trust and diagnostic accuracy. Deepfake medical images can be generated using Generative Adversarial Networks (GANs), one of the popular models capable of creating images using existing inputs and modifying the image as per the requirement. This paper presents an in-depth review of the current deepfake detection techniques in medical imaging. It systematically categorizes current approaches, evaluates key factors affecting image integrity, and outlines essential performance metrics. The review identifies major challenges and open research questions, providing a foundation for future exploration. By highlighting both gaps and advancements, the study contributes to the development of secure and reliable Artificial Intelligence (AI) applications in medical diagnostics.

在医学成像领域，深度假生成挑战了图像真实性的验证，引发了对信任和诊断准确性的担忧。深度伪造医学图像可以使用生成式对抗网络（gan）生成，这是一种流行的模型，能够使用现有输入创建图像并根据需要修改图像。本文对目前医学成像中的深度假检测技术进行了深入的综述。它系统地分类了当前的方法，评估了影响图像完整性的关键因素，并概述了基本的性能指标。这篇综述指出了主要的挑战和开放的研究问题，为未来的探索提供了基础。通过突出差距和进步，该研究有助于开发安全可靠的人工智能（AI）在医疗诊断中的应用。

引用次数: 0

Early detection of mental health disorders using machine learning models: An analysis based on behavioral and voice data 使用机器学习模型早期检测精神健康障碍：基于行为和语音数据的分析

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-04-01 Epub Date: 2026-02-10 DOI: 10.1016/j.compeleceng.2026.110996

Prashant Vats , Tan Kuan Tak , Kamal Upreti , Shubham Mahajan , Pravin R. Kshirsagar , Govind Murari Upadhyay

Mental illnesses are to be detected promptly and correctly to intervene effectively and in time. In this paper, a multi-stage NeuroVibeNet model of early mental disorders detection based on multimodal behavioral and voice data is proposed. It starts with the preprocessing of data that is high-quality and consistent, such as mean imputation, min-max normalization, outlier detection, noise reduction, and short-time energy extraction. The majority of the advanced methods employed in extracting temporal, spectral, and complex features include multiscale entropy, soft dynamic time warping, spectral contrast analysis, formant frequency analysis, and a one-dimensional convolutional neural network autoencoder. The feature selection is done via a sparse autoencoder that is used to maximize relevance and minimize redundancy. The chosen features are fed into the NeuroVibeNet architecture, where TabNet is used to process behavioral data, and Capsule Networks are used to process voice data to allow learning representations with attention and hierarchy. Lastly, a voting-based ensemble classifier uses the two modalities to combine the predictions to make strong classification decisions. The structure is coded in Python and tested on three benchmark datasets with the accuracy of 0.9839, 0.9856, and 0.9855, which is better than the current approaches.

精神疾病要及时、正确地发现，及时有效地进行干预。本文提出了一种基于多模态行为和语音数据的多阶段神经vibenet早期精神障碍检测模型。它从高质量和一致性的数据预处理开始，如均值输入、最小-最大归一化、离群值检测、降噪和短时能量提取。大多数用于提取时间、频谱和复杂特征的先进方法包括多尺度熵、软动态时间翘曲、频谱对比分析、形成峰频率分析和一维卷积神经网络自编码器。特征选择是通过稀疏自编码器完成的，该编码器用于最大化相关性和最小化冗余。选择的特征被输入到NeuroVibeNet架构中，其中TabNet用于处理行为数据，Capsule Networks用于处理语音数据，以允许学习具有注意力和层次结构的表示。最后，基于投票的集成分类器使用这两种模式来组合预测以做出强分类决策。该结构是用Python编写的，并在三个基准数据集上进行了测试，准确率分别为0.9839、0.9856和0.9855，优于目前的方法。

{"title":"Early detection of mental health disorders using machine learning models: An analysis based on behavioral and voice data","authors":"Prashant Vats , Tan Kuan Tak , Kamal Upreti , Shubham Mahajan , Pravin R. Kshirsagar , Govind Murari Upadhyay","doi":"10.1016/j.compeleceng.2026.110996","DOIUrl":"10.1016/j.compeleceng.2026.110996","url":null,"abstract":"<div><div>Mental illnesses are to be detected promptly and correctly to intervene effectively and in time. In this paper, a multi-stage NeuroVibeNet model of early mental disorders detection based on multimodal behavioral and voice data is proposed. It starts with the preprocessing of data that is high-quality and consistent, such as mean imputation, min-max normalization, outlier detection, noise reduction, and short-time energy extraction. The majority of the advanced methods employed in extracting temporal, spectral, and complex features include multiscale entropy, soft dynamic time warping, spectral contrast analysis, formant frequency analysis, and a one-dimensional convolutional neural network autoencoder. The feature selection is done via a sparse autoencoder that is used to maximize relevance and minimize redundancy. The chosen features are fed into the NeuroVibeNet architecture, where TabNet is used to process behavioral data, and Capsule Networks are used to process voice data to allow learning representations with attention and hierarchy. Lastly, a voting-based ensemble classifier uses the two modalities to combine the predictions to make strong classification decisions. The structure is coded in Python and tested on three benchmark datasets with the accuracy of 0.9839, 0.9856, and 0.9855, which is better than the current approaches.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110996"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174188","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

Real-time phishing uniform resource locator detection based on hybrid embedding transformer and retraining-free inferencing 基于混合嵌入变压器和无需再训练推理的实时网络钓鱼统一资源定位器检测

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-04-01 Epub Date: 2026-02-02 DOI: 10.1016/j.compeleceng.2026.111001

Dam Minh Linh , Huynh Trong Thua , Tran Cong Hung

Phishing attacks that evade traditional detection mechanisms by exploiting deceptive uniform resource locators (URLs) remain a significant cybersecurity threat. This study proposes an adaptive phishing URL detection framework that integrates Levenshtein distance-based string similarity, a hybrid embedding transformer (HET) encoder-based server-side verification mechanism, and a dynamically updated local blacklist. First, a rapid local lookup is executed to identify known phishing URLs. If the input URL is absent from the blacklist, the Levenshtein distance algorithm detects subtle character-level variations, identifying typosquatting and obfuscation effectively. For ambiguous cases, the HET-based module uses a lightweight post-hoc inference method that classifies URL embeddings via k-nearest neighbor voting based on Euclidean similarity in the latent space, thereby avoiding retraining and enabling real-time adaptation to emerging phishing threats. Confirmed phishing URLs are added iteratively to the local repository to improve detection continuously, enhancing future classification accuracy. Experimental evaluation on a large-scale dataset comprising 235,795 URLs revealed that the proposed method outperforms state-of-the-art approaches, achieving a detection accuracy of 99.8 %, with a false-positive rate of 0.441 % and false-negative rate of 0.0617 %. Additionally, real-time validation using a Chrome browser extension confirmed rapid processing, with an average processing time of 4.43–6.84 ms per URL on a dataset comprising 5,000 URLs. These results highlight the efficiency of the proposed framework in real-world cybersecurity contexts, enabling high detection accuracy, fast response times, and adaptability to evolving phishing strategies, and underscore the importance of proactive threat intelligence and real-time phishing mitigation in developing scalable, high-performance security infrastructures.

通过利用欺骗性的统一资源定位器（url）来逃避传统检测机制的网络钓鱼攻击仍然是一个重大的网络安全威胁。本研究提出了一种自适应网络钓鱼URL检测框架，该框架集成了基于Levenshtein距离的字符串相似性、基于混合嵌入转换器（HET）编码器的服务器端验证机制和动态更新的本地黑名单。首先，执行快速本地查找以识别已知的网络钓鱼url。如果输入URL不在黑名单中，Levenshtein距离算法会检测细微的字符级变化，有效地识别误输入和混淆。对于模棱两可的情况，基于het的模块使用轻量级的即时推理方法，通过基于潜在空间欧几里得相似性的k近邻投票对URL嵌入进行分类，从而避免了重新训练并能够实时适应新出现的网络钓鱼威胁。已确认的网络钓鱼url被迭代地添加到本地存储库中，以不断改进检测，提高未来的分类准确性。在包含235,795个url的大规模数据集上进行的实验评估表明，该方法优于现有的方法，检测准确率为99.8%，假阳性率为0.441%，假阴性率为0.0617%。此外，使用Chrome浏览器扩展的实时验证证实了快速处理，在包含5,000个URL的数据集上，每个URL的平均处理时间为4.43-6.84 ms。这些结果突出了所提出的框架在现实网络安全环境中的效率，实现了高检测精度、快速响应时间和对不断发展的网络钓鱼策略的适应性，并强调了主动威胁情报和实时网络钓鱼缓解在开发可扩展、高性能安全基础设施中的重要性。

{"title":"Real-time phishing uniform resource locator detection based on hybrid embedding transformer and retraining-free inferencing","authors":"Dam Minh Linh , Huynh Trong Thua , Tran Cong Hung","doi":"10.1016/j.compeleceng.2026.111001","DOIUrl":"10.1016/j.compeleceng.2026.111001","url":null,"abstract":"<div><div>Phishing attacks that evade traditional detection mechanisms by exploiting deceptive uniform resource locators (URLs) remain a significant cybersecurity threat. This study proposes an adaptive phishing URL detection framework that integrates Levenshtein distance-based string similarity, a hybrid embedding transformer (HET) encoder-based server-side verification mechanism, and a dynamically updated local blacklist. First, a rapid local lookup is executed to identify known phishing URLs. If the input URL is absent from the blacklist, the Levenshtein distance algorithm detects subtle character-level variations, identifying typosquatting and obfuscation effectively. For ambiguous cases, the HET-based module uses a lightweight post-hoc inference method that classifies URL embeddings via k-nearest neighbor voting based on Euclidean similarity in the latent space, thereby avoiding retraining and enabling real-time adaptation to emerging phishing threats. Confirmed phishing URLs are added iteratively to the local repository to improve detection continuously, enhancing future classification accuracy. Experimental evaluation on a large-scale dataset comprising 235,795 URLs revealed that the proposed method outperforms state-of-the-art approaches, achieving a detection accuracy of 99.8 %, with a false-positive rate of 0.441 % and false-negative rate of 0.0617 %. Additionally, real-time validation using a Chrome browser extension confirmed rapid processing, with an average processing time of 4.43–6.84 ms per URL on a dataset comprising 5,000 URLs. These results highlight the efficiency of the proposed framework in real-world cybersecurity contexts, enabling high detection accuracy, fast response times, and adaptability to evolving phishing strategies, and underscore the importance of proactive threat intelligence and real-time phishing mitigation in developing scalable, high-performance security infrastructures.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 111001"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174203","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 ultralightweight and reliable authentication protocol for secure communication in UAV-assisted IoAV systems 一种用于无人机辅助IoAV系统安全通信的超轻量级可靠认证协议

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-04-01 Epub Date: 2026-02-05 DOI: 10.1016/j.compeleceng.2026.110998

Sanjeev Kumar , Mohd Shariq , Gopal Singh Rawat , Muhammad Shafiq , Khalid Alsubhi , Mehedi Masud , Hossam Meshref

The Internet of Vehicles (IoV) enables intelligent transportation systems in the efficient management of autonomous vehicles (AVs) by enabling real-time data exchange and message communication over the Internet. Rapid advances in autonomous systems, hardware sensors, software, and the integration of artificial intelligence have enabled the development of automated services and improved convenience for users. In the IoV, heavy traffic, connectivity issues, and frequent handoffs create significant challenges. Unmanned aerial vehicles (UAVs, sometimes called drones) offer a promising solution to these issues by helping to alleviate network congestion and improving overall network performance. Because UAVs are highly mobile devices, potential security breaches pose a significant challenge for communication between UAVs and autonomous vehicles. To address this, we propose a secure and efficient ultralightweight protocol that uses UAV technology in an IoV environment. Our protocol employs elliptic-curve cryptography and cryptographic operators such as exclusive-or operations and one-way hashing. A formal security analysis of the protocol using the Scyther simulation tool reveals that it is resilient against security attacks, while an informal security analysis shows that the protocol is secure against several known security and privacy threats. The computational and communication costs of the proposed protocol are lower than those of other existing protocols, while being efficient, outperforming other solutions in terms of security features.

汽车互联网（IoV）通过在互联网上实现实时数据交换和信息通信，使智能交通系统能够有效管理自动驾驶汽车（av）。自主系统、硬件传感器、软件、人工智能融合等快速发展，推动自动化服务发展，提升用户便利性。在车联网中，繁忙的流量、连接问题和频繁的切换带来了重大挑战。无人驾驶飞行器（uav，有时被称为无人机）通过帮助缓解网络拥塞和提高整体网络性能，为这些问题提供了一个有希望的解决方案。由于无人机是高度移动设备，潜在的安全漏洞对无人机和自动驾驶车辆之间的通信构成了重大挑战。为了解决这个问题，我们提出了一种安全高效的超轻量级协议，该协议在车联网环境中使用无人机技术。我们的协议采用椭圆曲线加密和密码操作符，如异或操作和单向哈希。使用Scyther仿真工具对协议进行的正式安全分析表明，它对安全攻击具有弹性，而非正式的安全分析表明，该协议对几种已知的安全和隐私威胁是安全的。该协议的计算和通信成本低于其他现有协议，同时效率高，在安全特性方面优于其他方案。

{"title":"An ultralightweight and reliable authentication protocol for secure communication in UAV-assisted IoAV systems","authors":"Sanjeev Kumar , Mohd Shariq , Gopal Singh Rawat , Muhammad Shafiq , Khalid Alsubhi , Mehedi Masud , Hossam Meshref","doi":"10.1016/j.compeleceng.2026.110998","DOIUrl":"10.1016/j.compeleceng.2026.110998","url":null,"abstract":"<div><div>The Internet of Vehicles (IoV) enables intelligent transportation systems in the efficient management of autonomous vehicles (AVs) by enabling real-time data exchange and message communication over the Internet. Rapid advances in autonomous systems, hardware sensors, software, and the integration of artificial intelligence have enabled the development of automated services and improved convenience for users. In the IoV, heavy traffic, connectivity issues, and frequent handoffs create significant challenges. Unmanned aerial vehicles (UAVs, sometimes called drones) offer a promising solution to these issues by helping to alleviate network congestion and improving overall network performance. Because UAVs are highly mobile devices, potential security breaches pose a significant challenge for communication between UAVs and autonomous vehicles. To address this, we propose a secure and efficient ultralightweight protocol that uses UAV technology in an IoV environment. Our protocol employs elliptic-curve cryptography and cryptographic operators such as exclusive-or operations and one-way hashing. A formal security analysis of the protocol using the Scyther simulation tool reveals that it is resilient against security attacks, while an informal security analysis shows that the protocol is secure against several known security and privacy threats. The computational and communication costs of the proposed protocol are lower than those of other existing protocols, while being efficient, outperforming other solutions in terms of security features.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110998"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174181","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

Fuzzy-enhanced variable weight graph convolutional networks for recommender systems 推荐系统的模糊增强变权图卷积网络

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-03-01 Epub Date: 2026-01-08 DOI: 10.1016/j.compeleceng.2026.110970

Wanna Cui, Hak-Keung Lam

Recommender systems play an essential role in alleviating information overload by delivering personalized suggestions to users across domains such as e-commerce, restaurant services, and digital media. In recent years, graph-based approaches, particularly those leveraging graph convolutional networks (GCNs), have shown strong performance by modeling high-order connectivity. However, their effectiveness remains constrained by three critical challenges: the sparsity of user–item interactions, the presence of noisy or transient behaviors that distort preference modeling, and the underutilization of contextual information contained in reviews and product descriptions. To address these limitations, we propose a novel framework, termed fuzzy and variable weight graph convolutional network (FVW-GCN). The framework incorporates a fuzzy relation modeling module that enriches the adjacency structure by applying fuzzy C-means clustering to semantic embeddings extracted from pre-trained language models, thereby improving connectivity for sparse and long-tail items. In addition, a variable-weight GCN module is introduced, where a tuning GCN learns localized weight matrices from sampled subgraphs, which are then used by a tuned GCN to adaptively refine embeddings and suppress noisy signals. Through this combination, FVW-GCN effectively strengthens meaningful relations while reducing the influence of unreliable interactions. Extensive experiments conducted on benchmark datasets demonstrate that FVW-GCN consistently outperforms state-of-the-art baselines across several standard evaluation metrics, including recall, normalized discounted cumulative gain, and hit ratio. These results confirm the robustness and effectiveness of the proposed framework, highlighting its potential to support more accurate, diverse, and user-centric recommendation services in real-world applications.

推荐系统通过向跨领域（如电子商务、餐饮服务和数字媒体）的用户提供个性化建议，在减轻信息过载方面发挥着重要作用。近年来，基于图的方法，特别是那些利用图卷积网络（GCNs）的方法，通过建模高阶连接显示出强大的性能。然而，它们的有效性仍然受到三个关键挑战的限制：用户-项目交互的稀疏性，扭曲偏好建模的嘈杂或瞬态行为的存在，以及评论和产品描述中包含的上下文信息的利用不足。为了解决这些限制，我们提出了一个新的框架，称为模糊和变权图卷积网络（FVW-GCN）。该框架包含一个模糊关系建模模块，通过对预训练语言模型中提取的语义嵌入应用模糊c均值聚类来丰富邻接结构，从而提高稀疏和长尾项目的连通性。此外，还引入了变权GCN模块，其中调优GCN从采样子图中学习局部权矩阵，然后由调优GCN自适应地细化嵌入并抑制噪声信号。通过这种组合，FVW-GCN有效地加强了有意义的关系，同时减少了不可靠交互的影响。在基准数据集上进行的大量实验表明，FVW-GCN在几个标准评估指标上始终优于最先进的基线，包括召回率、标准化贴现累积增益和命中率。这些结果证实了所提出框架的鲁棒性和有效性，突出了其在现实应用中支持更准确、更多样化和以用户为中心的推荐服务的潜力。

{"title":"Fuzzy-enhanced variable weight graph convolutional networks for recommender systems","authors":"Wanna Cui, Hak-Keung Lam","doi":"10.1016/j.compeleceng.2026.110970","DOIUrl":"10.1016/j.compeleceng.2026.110970","url":null,"abstract":"<div><div>Recommender systems play an essential role in alleviating information overload by delivering personalized suggestions to users across domains such as e-commerce, restaurant services, and digital media. In recent years, graph-based approaches, particularly those leveraging graph convolutional networks (GCNs), have shown strong performance by modeling high-order connectivity. However, their effectiveness remains constrained by three critical challenges: the sparsity of user–item interactions, the presence of noisy or transient behaviors that distort preference modeling, and the underutilization of contextual information contained in reviews and product descriptions. To address these limitations, we propose a novel framework, termed fuzzy and variable weight graph convolutional network (FVW-GCN). The framework incorporates a fuzzy relation modeling module that enriches the adjacency structure by applying fuzzy C-means clustering to semantic embeddings extracted from pre-trained language models, thereby improving connectivity for sparse and long-tail items. In addition, a variable-weight GCN module is introduced, where a tuning GCN learns localized weight matrices from sampled subgraphs, which are then used by a tuned GCN to adaptively refine embeddings and suppress noisy signals. Through this combination, FVW-GCN effectively strengthens meaningful relations while reducing the influence of unreliable interactions. Extensive experiments conducted on benchmark datasets demonstrate that FVW-GCN consistently outperforms state-of-the-art baselines across several standard evaluation metrics, including recall, normalized discounted cumulative gain, and hit ratio. These results confirm the robustness and effectiveness of the proposed framework, highlighting its potential to support more accurate, diverse, and user-centric recommendation services in real-world applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110970"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927372","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 real-time smart energy management system for greenhouses using a hybrid optimization algorithm: Experimental implementation for efficient and sustainable operation 基于混合优化算法的温室实时智能能源管理系统：高效可持续运行的实验实现

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-03-01 Epub Date: 2026-01-12 DOI: 10.1016/j.compeleceng.2026.110948

Mohamed W. Haggag , Asmaa H. Rabie , Islam Ismael , Waleed Shaaban

The increasing global demand for food and energy, along with climate change and resource scarcity, causes potential challenges to sustainable agriculture. Smart greenhouses create controlled environments that optimize crop production and minimize resource use, especially in arid regions. This paper introduces a Real-Time Smart Greenhouse Energy Management (SGEM) system that combines IoT-based sensing, renewable energy sources, and a Hybrid Optimization Algorithm (HOA). The HOA combines Particle Swarm Optimization (PSO) for global exploration with the Coati Optimization Algorithm (COA) for local exploitation. To optimize operating costs, battery State of Charge (SoC), and the use of renewable energy, the HOA dynamically gathers energy from photovoltaic panels (PV), battery storage, and the electrical grid. The system is designed as a hybrid PV-battery-grid configuration, validated through both simulation and experimental implementation, guaranteeing a steady supply of energy while minimizing grid dependency. Experimental validation shows that the SGEM system reduces costs by 49.98%, lowers daily grid consumption by 50.24%, cuts CO₂ emissions by 50.5%, and extends battery life by 14.7%. The results obtained demonstrate the system’s capability for adaptive, efficient, and sustainable greenhouse energy management, providing a scalable solution for modern smart agriculture.

全球对粮食和能源的需求不断增加，加上气候变化和资源短缺，对可持续农业构成了潜在挑战。智能温室创造可控环境，优化作物生产，最大限度地减少资源使用，特别是在干旱地区。本文介绍了一种结合物联网传感、可再生能源和混合优化算法（HOA）的实时智能温室能源管理（SGEM）系统。该算法将粒子群优化算法（PSO）与Coati优化算法（COA）相结合，进行全局勘探和局部开发。为了优化运营成本、电池充电状态（SoC）和可再生能源的使用，HOA动态地从光伏板（PV）、电池存储和电网收集能量。该系统被设计为混合pv -电池-电网配置，通过仿真和实验实施验证，保证稳定的能源供应，同时最大限度地减少对电网的依赖。实验验证表明，SGEM系统降低了49.98%的成本，降低了50.24%的日电网消耗，减少了50.5%的二氧化碳排放量，延长了14.7%的电池寿命。所获得的结果证明了该系统具有适应性、高效和可持续的温室能源管理能力，为现代智能农业提供了可扩展的解决方案。

{"title":"A real-time smart energy management system for greenhouses using a hybrid optimization algorithm: Experimental implementation for efficient and sustainable operation","authors":"Mohamed W. Haggag , Asmaa H. Rabie , Islam Ismael , Waleed Shaaban","doi":"10.1016/j.compeleceng.2026.110948","DOIUrl":"10.1016/j.compeleceng.2026.110948","url":null,"abstract":"<div><div>The increasing global demand for food and energy, along with climate change and resource scarcity, causes potential challenges to sustainable agriculture. Smart greenhouses create controlled environments that optimize crop production and minimize resource use, especially in arid regions. This paper introduces a Real-Time Smart Greenhouse Energy Management (SGEM) system that combines IoT-based sensing, renewable energy sources, and a Hybrid Optimization Algorithm (HOA). The HOA combines Particle Swarm Optimization (PSO) for global exploration with the Coati Optimization Algorithm (COA) for local exploitation. To optimize operating costs, battery State of Charge (SoC), and the use of renewable energy, the HOA dynamically gathers energy from photovoltaic panels (PV), battery storage, and the electrical grid. The system is designed as a hybrid PV-battery-grid configuration, validated through both simulation and experimental implementation, guaranteeing a steady supply of energy while minimizing grid dependency. Experimental validation shows that the SGEM system reduces costs by 49.98%, lowers daily grid consumption by 50.24%, cuts CO₂ emissions by 50.5%, and extends battery life by 14.7%. The results obtained demonstrate the system’s capability for adaptive, efficient, and sustainable greenhouse energy management, providing a scalable solution for modern smart agriculture.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110948"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978314","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 comprehensive review of computational techniques for obscenity detection: Past, present, and future 淫秽检测的计算技术的全面回顾：过去，现在和未来

IF 4.9 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2026-03-01 Epub Date: 2026-01-12 DOI: 10.1016/j.compeleceng.2026.110960

Pundreekaksha Sharma , Dr. Vijay Kumar , Dr. Neeraj Kumar

With the rapid proliferation of obscene content over the internet, detecting and preventing obscenity has become the most prominent way of maintaining a safe digital environment. The accessibility of obscene content has significant psychological, social, ethical, and technological impacts. To overcome these challenges, it is essential to develop an obscenity detection system using advanced artificial intelligence techniques, including social and ethical considerations that prevent the spread of obscenity. This research has presented a comprehensive literature analysis covering traditional to advanced computational techniques for obscenity detection. It also serves as a valuable resource for researchers improving obscenity detection techniques. Analyse computer vision techniques for obscenity detection, featuring hybrid deep learning methods including Transformers, vision transformers, diffusion models, and other techniques. Additionally, this research discusses the strengths and limitations of these techniques. Examines the mathematical formulations and equations of the models, and the impact of input and additional parameters. Compare the performance of models on various datasets and discuss how to develop a diverse dataset. A significant overview of social and ethical considerations included in obscenity detection. The research paper also highlights challenges and potential future research directions in obscenity detection. In conclusion, this research provides a gap analysis that helps researchers enhance computational techniques for obscenity detection.

随着互联网上淫秽内容的迅速扩散，检测和防止淫秽内容已成为维护安全数字环境的最重要方式。淫秽内容的可及性具有显著的心理、社会、伦理和技术影响。为了克服这些挑战，必须开发一种使用先进人工智能技术的淫秽内容检测系统，包括防止淫秽内容传播的社会和伦理考虑。本研究提出了一个全面的文献分析，涵盖传统到先进的计算技术的淫秽检测。它也为研究人员改进淫秽检测技术提供了宝贵的资源。分析用于淫秽内容检测的计算机视觉技术，包括混合深度学习方法，包括变形金刚、视觉变形金刚、扩散模型和其他技术。此外，本研究还讨论了这些技术的优点和局限性。检查模型的数学公式和方程，以及输入和附加参数的影响。比较模型在不同数据集上的性能，并讨论如何开发不同的数据集。一个重要的社会和道德考虑的概述，包括在淫秽检测。研究论文还强调了淫秽物检测面临的挑战和潜在的未来研究方向。总之，这项研究提供了一个差距分析，帮助研究人员提高淫秽检测的计算技术。

{"title":"A comprehensive review of computational techniques for obscenity detection: Past, present, and future","authors":"Pundreekaksha Sharma , Dr. Vijay Kumar , Dr. Neeraj Kumar","doi":"10.1016/j.compeleceng.2026.110960","DOIUrl":"10.1016/j.compeleceng.2026.110960","url":null,"abstract":"<div><div>With the rapid proliferation of obscene content over the internet, detecting and preventing obscenity has become the most prominent way of maintaining a safe digital environment. The accessibility of obscene content has significant psychological, social, ethical, and technological impacts. To overcome these challenges, it is essential to develop an obscenity detection system using advanced artificial intelligence techniques, including social and ethical considerations that prevent the spread of obscenity. This research has presented a comprehensive literature analysis covering traditional to advanced computational techniques for obscenity detection. It also serves as a valuable resource for researchers improving obscenity detection techniques. Analyse computer vision techniques for obscenity detection, featuring hybrid deep learning methods including Transformers, vision transformers, diffusion models, and other techniques. Additionally, this research discusses the strengths and limitations of these techniques. Examines the mathematical formulations and equations of the models, and the impact of input and additional parameters. Compare the performance of models on various datasets and discuss how to develop a diverse dataset. A significant overview of social and ethical considerations included in obscenity detection. The research paper also highlights challenges and potential future research directions in obscenity detection. In conclusion, this research provides a gap analysis that helps researchers enhance computational techniques for obscenity detection.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110960"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978310","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