Concurrency and Computation-Practice & Experience最新文献_第8页

Research on Privacy Protection Video Behavior Recognition Method Based on Improved SlowFast 基于改进SlowFast的隐私保护视频行为识别方法研究

IF 1.5 4区计算机科学

Concurrency and Computation-Practice & Experience Pub Date : 2025-08-21 DOI: 10.1002/cpe.70225

Yunxue Shao, Min Li, Lingfeng Wang

{"title":"Research on Privacy Protection Video Behavior Recognition Method Based on Improved SlowFast","authors":"Yunxue Shao, Min Li, Lingfeng Wang","doi":"10.1002/cpe.70225","DOIUrl":"https://doi.org/10.1002/cpe.70225","url":null,"abstract":"<div>\u0000 \u0000 <p>Surveillance cameras in public areas have had a positive impact on reducing violence, but have also raised concerns about privacy invasion. With these factors in mind, the Bullying10K neuromorphic dataset utilizes dynamic vision sensor (DVS) cameras to detect instances of violent behavior while protecting individual privacy. This dataset collects a variety of complex, fast violent actions from real-life scenarios as well as potentially occluded individuals. In this paper, for the characteristics of this dataset, the representative SlowFast neural network in behavior recognition is selected for research and improvement. First, a linear interpolation is applied to the Slow pathway to account for the absence of background influence in the Bullying10K dataset. Second, for the complex and fast action features and noise effects in the dataset, the interframe difference method is applied to the input of Fast pathway, which can effectively amplify the real dynamic signals and recognize the motion information in the video. Finally, it is difficult to prevent leakage of nonfacial information, such as gait data, against this dataset. The spatiotemporal attention fusion module (STAFM) is introduced, which not only better protects the privacy of nonfacial information but also improves the security and accuracy of the model when dealing with sensitive data, as well as enhances the generalization ability of the model. Experiments on Bullying10K show that the improved SlowFast exhibits significant advantages, including higher recognition accuracy, better protection of personal privacy, and better generalization capabilities. In addition, this paper is also validated on the UCF101 dataset, and the experimental results demonstrate the generalization of the improved method. The code of this paper is open-sourced at: https://github.com/MinL0128/STAFM-SlowFast.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 21-22","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Performance Forecast and Analytic for Sports Dance Athletes Using a Hybrid Method 基于混合方法的体育舞蹈运动员成绩预测与分析

IF 1.5 4区计算机科学

Concurrency and Computation-Practice & Experience Pub Date : 2025-08-20 DOI: 10.1002/cpe.70248

Qiaohui Wang, Xiaowei Wang, Liqing Zhang, Jian Zheng

{"title":"Performance Forecast and Analytic for Sports Dance Athletes Using a Hybrid Method","authors":"Qiaohui Wang, Xiaowei Wang, Liqing Zhang, Jian Zheng","doi":"10.1002/cpe.70248","DOIUrl":"https://doi.org/10.1002/cpe.70248","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper proposed a forecast method consisting of Long Short-Term Memory (LSTM) network with Markov transition matrix aiming for the forecast of training performance for dance athletes. Firstly, using the Event-Group theory to design five training indicators affecting the training performance of dance athletes. The role of the five training indicators is the construction of a training dataset. Thereafter, we put Markov transition matrix into LSTM network; meanwhile, we established the mapping of Markov transition matrix to LSTM network through writing the <i>m</i>-step Markov status matrix into the forget gate weight of LSTM network. Finally, using the experiments to verify the proposed method, and results show that the proposed method obtains 0.972 accuracy in forecasting the training performance of dance athletes and significantly outperformed the comparative methods in forecast capabilities. Results also show that the running efficiency of the proposed method defeated most comparative methods. Moreover, we find that the five training metrics can be used separately in the training of dance athletes, thus significantly improving their training performance, due to they exist weak dependency relationship. We also find that basic posture training has more positive effects than speed training in the improvement of the training performance for dance athletes.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 21-22","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Risk-Based Adaptive Authentication in Mobile Network System Using Dynamic Elliptic Curve Digital Signature Algorithm 基于动态椭圆曲线数字签名算法的移动网络系统风险自适应认证

IF 1.5 4区计算机科学

Concurrency and Computation-Practice & Experience Pub Date : 2025-08-19 DOI: 10.1002/cpe.70208

Qureshi Imran M. Hussain, Vijay Kale

{"title":"Risk-Based Adaptive Authentication in Mobile Network System Using Dynamic Elliptic Curve Digital Signature Algorithm","authors":"Qureshi Imran M. Hussain, Vijay Kale","doi":"10.1002/cpe.70208","DOIUrl":"https://doi.org/10.1002/cpe.70208","url":null,"abstract":"<div>\u0000 \u0000 <p>The Risk-based Adaptive Authentication (RBAA) in mobile networks is to ensure a dynamic nature of authentication requirements, as per the real-time risk factors, taking into account the users' behavior and status of the device, and geographical location. It is argued to increase the system's security by always authenticating users according to the risk of the attempted access. Current models have limitations because they are static, and they have to use unified strategies that either undermine security or cause users' discomfort. Thus, to overcome those existing challenges, this research proposed the Adaptive PKI Authentication System (APAS) and the Dynamic Elliptic Curve Digital Signature Algorithm (DECDSA) to enhance the security and efficiency of mobile network systems. Specifically, the APAS incorporates innovative risk-based mechanisms with the flexible risk adjustment of the authentication process to respond to reliable threat assessments, which enhances the resistance to unauthorized access and the provision of highly secure protection adjusted for different levels of risk. The proposed DECDSA model attains less decryption time of 0.70 ms, less encrypted time of 0.58 ms, a genuine user rate of 0.96, less memory of 122.42 KB, a responsiveness of 0.86 ms, and less time complexity of 0.37 ms.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 21-22","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144869958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Intrusion Detection in Cloud Environment via Soft-Max Deep Spectral Recurrent Neural Network 基于Soft-Max深度频谱递归神经网络的云环境入侵检测

IF 1.5 4区计算机科学

Concurrency and Computation-Practice & Experience Pub Date : 2025-08-18 DOI: 10.1002/cpe.70161

Sandanakaruppan Ammavasai, Hariharan Subramani, Manjunathan Alagarsamy, Sanmugavalli Palanisamy, Menaga Devendran, Sharon Priya Surendran

{"title":"Intrusion Detection in Cloud Environment via Soft-Max Deep Spectral Recurrent Neural Network","authors":"Sandanakaruppan Ammavasai, Hariharan Subramani, Manjunathan Alagarsamy, Sanmugavalli Palanisamy, Menaga Devendran, Sharon Priya Surendran","doi":"10.1002/cpe.70161","DOIUrl":"https://doi.org/10.1002/cpe.70161","url":null,"abstract":"<div>\u0000 \u0000 <p>Cloud computing is one of the most promising technologies for effectively storing data and offering internet services. There are several benefits to using this quickly evolving technology instead of more conventional defenses to shield computer-based systems from cyberattacks. In this paper, a novel Intrusion Detection in Cloud Environment via Soft-max Deep Spectral Recurrent Neural Network has been proposed to improve the security in cloud computing. Initially, Data preprocessing using IoT-23 dataset values reduces null or inappropriate feature values. Feature extraction utilizes Principal Component Analysis (PCA) to reduce dimensionality while retaining significant information. Feature selection is optimized using the Reptile Search algorithm (RSO) to prioritize relevant features by evaluating their relational weights. A Soft-max Deep Spectral Recurrent Neural Network (SDSRN<sup>2</sup>) classifies data into intrusion or non-intrusion categories. Detected intrusions undergo further analysis using a Recursive Multi-Perception Neural Classifier (RMNC) to assess risk levels. To evaluate the effectiveness of the proposed model, several metrics are utilized, namely accuracy, precision, F1 score, and recall. The performance analysis of accuracy attained by the proposed technique is 99.5%, which is higher than the existing technique. The proposed approach compared to existing methods such as SSAFS-DLID, SeArch, Improved-IDs, and the proposed model improves detection accuracy by 5.18%, 3.7%, and 1.77%, respectively.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 21-22","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144869317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 Segmented Activation Function-Based Zeroing Neural Network Model for Dynamic Sylvester Equation Solving and Robotic Manipulator Control 基于分段激活函数的归零神经网络模型在动态Sylvester方程求解和机械臂控制中的应用

IF 1.5 4区计算机科学

Concurrency and Computation-Practice & Experience Pub Date : 2025-08-17 DOI: 10.1002/cpe.70243

Rui Li, Jie Jin, Daobing Zhang, Chaoyang Chen

{"title":"A Segmented Activation Function-Based Zeroing Neural Network Model for Dynamic Sylvester Equation Solving and Robotic Manipulator Control","authors":"Rui Li, Jie Jin, Daobing Zhang, Chaoyang Chen","doi":"10.1002/cpe.70243","DOIUrl":"https://doi.org/10.1002/cpe.70243","url":null,"abstract":"<div>\u0000 \u0000 <p>Traditional methods for solving the dynamic Sylvester equations suffer from challenges such as unsatisfactory convergence and sensitivity to noise. To address these limitations, a segmented activation function-based Zeroing neural network (SAF-ZNN) model is proposed in this paper. The segmented activation function consists of the power function, hyperbolic tangent function, and exponential function, and the SAF-ZNN model can effectively deal with various system errors of various sizes and types. Specifically, the SAF-ZNN model with power function is used to handle large errors, the SAF-ZNN model with hyperbolic tangent function is used to handle medium errors, and the SAF-ZNN model with exponential function is used to handle small errors. The whole proposed SAF-ZNN model achieves rapid convergence and strong robustness adaptively during the dynamic Sylvester equation solving. Theoretical analysis proves that the proposed SAF-ZNN model possesses global stability, finite-time convergence, and noise tolerance. Furthermore, both the simulation experiments and their application in robotic manipulator control validate the superior performance of the proposed SAF-ZNN model.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 21-22","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144861883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Research on Robot Target Classification and Localization Based on Improved Mask R-CNN 基于改进掩模R-CNN的机器人目标分类与定位研究

IF 1.5 4区计算机科学

Concurrency and Computation-Practice & Experience Pub Date : 2025-08-16 DOI: 10.1002/cpe.70247

Xinghua Wang, Yuting Tang, Xiaolong Liu, Jie Wang, Jiawen Cao, Ruijin Sun

{"title":"Research on Robot Target Classification and Localization Based on Improved Mask R-CNN","authors":"Xinghua Wang, Yuting Tang, Xiaolong Liu, Jie Wang, Jiawen Cao, Ruijin Sun","doi":"10.1002/cpe.70247","DOIUrl":"https://doi.org/10.1002/cpe.70247","url":null,"abstract":"<div>\u0000 \u0000 <p>The small workpieces are easily missed during detection, and the irregular workpieces are difficult to recognize and segment effectively by traditional detection algorithms in the industrial field. The traditional target detection algorithms have problems such as low accuracy and poor generalization performance. This paper proposes a robot target recognition and positioning method based on the improved Mask R-CNN. First, the network structure is designed to add a Convolutional Block Attention Module (CBAM) in the backbone, replace the Feature Pyramid Network (FPN) structure used in the original model of Mask R-CNN with a Path Aggregation Network (PAN) structure, and increase the receptive field to enhance the recognition of small target objects and the segmentation of multi-objects. Second, after classification is completed, according to the segmentation information, the output is augmented with center coordinates and rotation angle information. Finally, comparative experiments are conducted in the COCO dataset and the industrial part dataset to verify the effectiveness and practicality of the proposed algorithm. The experimental results show that the improved model achieves an AP<sub>50</sub> of 60.6 in the COCO dataset and 99.4 in the industrial parts dataset. Additionally, in single-object and multi-object grasping experiments, the grasping accuracy is 91.5% and 85.3%, respectively.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 21-22","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144853813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Cloudhive: A Cloud-Based Framework for Smart Grid Co-Simulation, Data, and Communication Cloudhive：基于云的智能电网协同仿真、数据和通信框架

IF 1.5 4区计算机科学

Concurrency and Computation-Practice & Experience Pub Date : 2025-08-16 DOI: 10.1002/cpe.70238

Kenneth B. Kent, Mengbing Zhou, Gabriel Adeyemo, Yang Wang

{"title":"Cloudhive: A Cloud-Based Framework for Smart Grid Co-Simulation, Data, and Communication","authors":"Kenneth B. Kent, Mengbing Zhou, Gabriel Adeyemo, Yang Wang","doi":"10.1002/cpe.70238","DOIUrl":"https://doi.org/10.1002/cpe.70238","url":null,"abstract":"<div>\u0000 \u0000 <p>The integration of renewable energy has driven the need for smart grid frameworks that enable efficient co-simulation, data management, and secure communication. This paper introduces CloudHive, a cloud-native framework designed to address these challenges by unifying large-scale power-network co-simulation, real-time data communication, and big data analytics in a single modular architecture. Unlike existing co-simulation tools or data platforms that operate in isolation, CloudHive uniquely enables bidirectional interaction between simulation environments (e.g., OpenDSS for power systems, OMNeT++ for communication networks) and real-world smart grids, supported by message-oriented middleware (RabbitMQ, Apache Kafka) for low-latency data exchange and Kubernetes for dynamic scalability. We evaluate CloudHive's accuracy, scalability, and usability through three representative case studies. The results show that CloudHive achieves high accuracy, performs well in real-world scenarios, and scales efficiently with growing workloads in cloud environments.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 21-22","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144853823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Privacy-Preserving Genetic Matching Diagnosis on Lightweight Devices 轻量级设备上保护隐私的遗传匹配诊断

IF 1.5 4区计算机科学

Concurrency and Computation-Practice & Experience Pub Date : 2025-08-16 DOI: 10.1002/cpe.70235

Xianning Tang, Jichao Xiong, Jiageng Chen, Hui Liu, Heng Xu

{"title":"Privacy-Preserving Genetic Matching Diagnosis on Lightweight Devices","authors":"Xianning Tang, Jichao Xiong, Jiageng Chen, Hui Liu, Heng Xu","doi":"10.1002/cpe.70235","DOIUrl":"https://doi.org/10.1002/cpe.70235","url":null,"abstract":"<div>\u0000 \u0000 <p>Next-generation sequencing (NGS) technology has revolutionized human genome research, significantly advancing the field of genetics. NGS provides unmatched abilities to analyze DNA and RNA molecules efficiently and cost-effectively, transforming genomics research. This technology detects specific alleles within tissues, allowing for accurate diagnoses of genetic mutation-related diseases. However, the sensitivity of genetic information necessitates careful protection across different usage scenarios. In this paper, we introduce an efficient protocol for privacy-preserving genetic matching based on the Private Set Intersection (PSI) technique. Our protocol allows genetic diagnoses without disclosing individual genetic data, offering greater security than previous methods that required external server storage or processing of genetic data. By keeping the data on the individuals local device, we reduce the risks associated with cloud storage. The protocol uses a collision-resistant cuckoo hash table and symmetric encryption methods, ensuring data accuracy and error-free genetic matching diagnoses. Moreover, our protocol is lightweight, utilizing minimal encryption components to maintain security while minimizing computational complexity and client-side load. Experimental results demonstrate that our protocol enhances performance by approximately 31.135% compared to similar protocols on average. These attributes make our PSI-based protocol a robust solution for privacy-preserving genetic matching, safeguarding sensitive genetic information while meeting the efficiency needs of practical applications.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 21-22","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144853824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

CRU-Net: An Innovative Network for Building Extraction From Remote Sensing Images Based on Channel Enhancement and Multiscale Spatial Attention With ResNet 基于通道增强和多尺度空间关注的遥感影像建筑提取网络CRU-Net

IF 1.5 4区计算机科学

Concurrency and Computation-Practice & Experience Pub Date : 2025-08-14 DOI: 10.1002/cpe.70249

Zhuozhao Chen, Wenbo Chen, Jiao Zheng, Yuanyuan Ding

{"title":"CRU-Net: An Innovative Network for Building Extraction From Remote Sensing Images Based on Channel Enhancement and Multiscale Spatial Attention With ResNet","authors":"Zhuozhao Chen, Wenbo Chen, Jiao Zheng, Yuanyuan Ding","doi":"10.1002/cpe.70249","DOIUrl":"https://doi.org/10.1002/cpe.70249","url":null,"abstract":"<div>\u0000 \u0000 <p>Building extraction from high-resolution remote sensing images enables systematic quantification of urban form evolution, supports critical decision-making in infrastructure development and land-use optimization, and facilitates disaster resilience and risk assessment. However, the characteristics of urban landscapes, such as high-density building distribution and heterogeneous building geometries, pose significant challenges in achieving pixel-level accuracy. To address these challenges, we proposed an innovative network for building extraction based on channel enhancement and multiscale spatial attention with ResNet (CRU-Net). First, CRU-Net employed U-Net as the core architecture, with ResNet34 as the encoder component. Second, to fully exploit the ability of convolutional neural networks to extract features at multiple scales, a new dilated residual block (DRB) was designed by combining a residual block with dilated convolution. Replacing the residual blocks in ResNet34 with DRB enhances the ability of CRU-Net to extract semantic information at different scales for building extraction. Next, the channel enhancement and multiscale spatial attention (CEMS) module was proposed and added to the skip connection of the network. CEMS is capable of learning more important features both spatially and channel-wise, enhancing the network's feature representation ability. Finally, a joint loss function combining normalized cross-correlation loss and binary cross-entropy loss was introduced to train the network, enabling it to focus on learning both global and local features of the building. The experiments show that CRU-Net achieves high accuracy and intersection over union (IoU) values on the Massachusetts building dataset, Inria aerial image labeling dataset, and WHU building dataset.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 21-22","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144843282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Hiding Patterns With Gaps in Sequential Data 隐藏序列数据中有间隙的模式

IF 1.5 4区计算机科学

Concurrency and Computation-Practice & Experience Pub Date : 2025-08-14 DOI: 10.1002/cpe.70187

Guiyuan Zhao, Dequan Chen, Meng Zhang

引用次数: 0