Concurrency and Computation-Practice & Experience最新文献

{"title":"Analysis and Performance Measure of Dynamic Cluster Based Hierarchical Real Time Scheduling for Distributed Systems","authors":"Girish Talmale,&nbsp;Urmila Shrawankar","doi":"10.1002/cpe.70038","DOIUrl":"https://doi.org/10.1002/cpe.70038","url":null,"abstract":"<div>\u0000 \u0000 <p>Efficient scheduling is critical for real-time systems, which are ubiquitous in daily life, as they demand high computational performance while minimizing power consumption and thermal inefficiencies. Multi-core platforms address these requirements but present challenges in task scheduling. Existing scheduling strategies include partitioned scheduling, which statically assigns tasks to processors to eliminate migration costs but suffers from NP-hard task allocation and low CPU utilization, and global scheduling, which allows task migration across processors to improve system utilization but incurs significant migration and preemption overheads. Neither strategy alone is sufficient to handle all real-time task sets effectively, highlighting the need for a hybrid solution for multi-core platforms. To address these challenges, this manuscript proposes a dynamic, cluster-based hybrid real-time scheduling algorithm that employs a hierarchical approach. By grouping cores into clusters, this method balances the trade-offs between partitioned and global scheduling. It minimizes migration and preemption overheads while improving resource utilization and system reliability. Dynamic cluster resizing and task assignment strategies further enhance efficiency by tailoring the scheduling process to workload demands. Simulation results demonstrate the proposed scheduler's superiority over partitioned and global scheduling approaches. It achieves higher resource utilization, better job acceptance rates, and reduced response times while lowering migration, preemption, and scheduling overheads. This work introduces an innovative scheduling framework that combines task assignment and scheduling in a two-step process: (1) Task Assignment: Allocates tasks to cores with controlled migration based on workload. (2) Task Scheduling: Sequences the execution of allocated tasks within clusters to ensure efficiency. The proposed approach offers a scalable and reliable solution for managing real-time tasks on multi-core systems, addressing limitations of traditional scheduling methods.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 6-8","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143602719","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}

{"title":"Quantitative Risk Assessment for Cloud-Based Software Migration Processes","authors":"Wen Zeng,&nbsp;Wenjing Yan,&nbsp;Emily Simpson,&nbsp;Carlos Molina–Jimenez","doi":"10.1002/cpe.70009","DOIUrl":"https://doi.org/10.1002/cpe.70009","url":null,"abstract":"<div>\u0000 \u0000 <p>Cloud migration is the process of moving data, files, and applications to a cloud computing environment. With the success of cloud computing, cloud migration is becoming fashionable. However, different cloud service providers have their own migration processes as currently, no standard cloud-based software migration procedure exists to guide how to move digital resources to the cloud. Moreover, there are serious security risks associated with cloud migration processes that threaten business processes that have not been systematically analyzed. In addition, no formal models and security metrics exist to evaluate and analyze these risks. Therefore, it is necessary to develop a generic approach with real customer use cases. In this study, firstly, we will develop a general cloud-based software migration procedure to help organizations migrate their digital resources to cloud platforms. Secondly, we will develop a risk assessment model for analyzing migration processes. Thirdly, on the basis of this risk assessment model, we use stochastic colored Petri nets to describe the dynamic behavior of the model, thus the concurrency, synchronization, mutual exclusion, and conflicts can be analyzed to assess the risks of migration automatically. Fourthly, security metrics will be defined to quantitatively evaluate the risks and vulnerabilities of the organizations. We believe that this study can help chief information officers identify which risk will have more opportunity to occur during the migration processes and make informed decisions about software migration and security.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 6-8","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143602812","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}

{"title":"S2C-HAR: A Semi-Supervised Human Activity Recognition Framework Based on Contrastive Learning","authors":"Xue Li,&nbsp;Mingxing Liu,&nbsp;Lanshun Nie,&nbsp;Wenxiao Cheng,&nbsp;Xiaohe Wu,&nbsp;Dechen Zhan","doi":"10.1002/cpe.70027","DOIUrl":"https://doi.org/10.1002/cpe.70027","url":null,"abstract":"<div>\u0000 \u0000 <p>Human activity recognition (HAR) has emerged as a critical element in various domains, such as smart healthcare, smart homes, and intelligent transportation, owing to the rapid advancements in wearable sensing technology and mobile computing. Nevertheless, existing HAR methods predominantly rely on deep supervised learning algorithms, necessitating a substantial supply of high-quality labeled data, which significantly impacts their accuracy and reliability. Considering the diversity of mobile devices and usage environments, the quest for optimizing recognition performance in deep models while minimizing labeled data usage has become a prominent research area. In this paper, we propose a novel semi-supervised HAR framework based on contrastive learning named <i>S</i>²C-HAR, which is capable of generating accurate pseudo-labels for unlabeled data, thus achieving comparable performance with supervised learning with only a few labels applied. First, a contrastive learning model for HAR (CLHAR) is designed for more general feature representations, which contains a contrastive augmentation transformer pre-trained exclusively on unlabeled data and fine-tuned in conjunction with a model-agnostic classification network. Furthermore, based on the FixMatch technique, unlabeled data with two different perturbations imposed are fed into the CLHAR to produce pseudo-labels and prediction results, which effectively provides a robust self-training strategy and improves the quality of pseudo-labels. To validate the efficacy of our proposed model, we conducted extensive experiments, yielding compelling results. Remarkably, even with only 1% labeled data, our model achieves satisfactory recognition performance, outperforming state-of-the-art methods by approximately 5%.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 6-8","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143602813","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}

{"title":"Two-Step Estimation Strategy for Predicting Petroleum Reservoir Simulation Jobs Runtime on an HPC Cluster","authors":"Alan L. Nunes,&nbsp;Bernardo Gallo,&nbsp;Bruno Lopes,&nbsp;Felipe A. Portella,&nbsp;José Viterbo,&nbsp;Lúcia M. A. Drummond,&nbsp;Luciano Andrade,&nbsp;Miguel de Lima,&nbsp;Paulo J. B. Estrela,&nbsp;Renzo Q. Malini","doi":"10.1002/cpe.70026","DOIUrl":"https://doi.org/10.1002/cpe.70026","url":null,"abstract":"<div>\u0000 \u0000 <p>Modeling petroleum field behavior provides crucial knowledge for risk quantification regarding extraction prospects. Since their processing requires significant computational and storage capabilities, oil companies run reservoir simulation jobs on high-performance computing clusters managed by job managers, for example, Slurm. In this scenario, efficiently using machine learning algorithms to predict the runtime of incoming jobs can improve the effectiveness of cluster resources, such as enhancing the resource usage rate and reducing the jobs queue time. This work analyses diverse machine learning-based predictors built from a real-world Slurm jobs log from Petrobras, a globally renowned Brazilian energy company. Furthermore, a two-step estimation strategy that predicts the duration time interval of reservoir simulation jobs is proposed and assessed, indicating that such estimated runtimes, when employed by job managers in their scheduling decisions, can positively impact the throughput of a real-world batch system.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 4-5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143554683","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}

{"title":"Scaling Up Optuna: P2P Distributed Hyperparameters Optimization","authors":"Loïc Cudennec","doi":"10.1002/cpe.70008","DOIUrl":"https://doi.org/10.1002/cpe.70008","url":null,"abstract":"<div>\u0000 \u0000 <p>In machine learning (ML), hyperparameter optimization (HPO) is the process of choosing a tuple of values that ensures an efficient deployment and training of an AI model. In practice, HPO not only applies to ML tuning but can also be used to tune complex numerical simulations. In this context, a numerical model of a given object is created to be used in realistic simulations. This model is defined by a set of values describing properties such as the geometry of the object or other unknown parameters related to physical quantities. While HPO for ML usually requires finding a few parameters, a numerical model can involve the tuning of more than a hundred parameters. As a consequence, a large number of tuples have to be explored and evaluated before finding a relevant solution, offering new challenges in high-performance computing for efficiently driving the optimization. In this work we rely on the Optuna HPO framework, primarily designed for ML tasks and including state-of-the-art sampling and pruning algorithms. We report on its use to optimize a complex numerical model onto a 1024-core machine. We suggest 1.5M tuples and evaluate 5M simulations using different Optuna-distributed layouts to build several tradeoffs between performance and energy consumption metrics. In order to further scale up the optimization process onto resources, we introduce OptunaP2P, an extension of Optuna based on the peer-to-peer paradigm. This allows to remove any bottleneck in the management of the shared knowledge between optimization processes. With OptunaP2P, we were able to compute up to 3 times faster compared to the regular Optuna-distributed implementation and to obtain close-to-similar results in terms of quality in this reduced time-frame.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 4-5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143534051","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}

{"title":"A Multidimensional Virtual Resource Allocation Framework With Energy-Aware Physical Resource Mapping for Green Cloud Computing","authors":"Ayşenur Uslu,&nbsp;Ali Haydar Özer","doi":"10.1002/cpe.70039","DOIUrl":"https://doi.org/10.1002/cpe.70039","url":null,"abstract":"<p>Cloud computing has seen a surge in demand, driven by its scalability and cost efficiency. However, the growing energy consumption of data centers poses significant environmental challenges. This study introduces a multidimensional resource allocation model designed to allocate and place virtual resources in an energy-efficient manner using a combinatorial auction approach. Unlike current approaches, which rely on predefined virtual resources, this model allows users to request virtual resources with specific features and capacities tailored to their workflows. Furthermore, it incorporates a flexible bidding language that supports simultaneous requests for multiple resources using logical AND/OR relations. The model accommodates various data centers, allowing users to indicate their preferred locations. Through a combinatorial optimization problem, the model identifies the most resource-efficient allocations and the most energy-efficient placements. This study provides the mathematical definition of the model and the formulation of its optimization problem. Given the complexity of this problem, it explores several heuristic methods, including ant colony optimization and genetic algorithms. A test case generator is developed to simulate real-life scenarios. The effectiveness of the model and the proposed heuristic solutions is assessed through various experiments, demonstrating that these methods can achieve near-optimal solutions within reasonable timeframes.</p>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 4-5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cpe.70039","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved SVM-Recursive Feature Elimination (ISVM-RFE) Based Feature Selection for Bigdata Classification Under Map Reduce Framework","authors":"J. C. Miraclin Joyce Pamila,&nbsp;R. Senthamil Selvi","doi":"10.1002/cpe.70037","DOIUrl":"https://doi.org/10.1002/cpe.70037","url":null,"abstract":"<div>\u0000 \u0000 <p>Big data is widely recognized for its methodical collection and analysis of massive, particularly complex datasets. But handling the speed of the irregularity of information in the massive datasets requires a dependable system, which is difficult to achieve with big data processing. This paper proposes a new big data classification under a map-reduce framework under Improved Support Vector Machine- Recursive Feature Elimination (SVM-RFE) based feature selection. At first, inconsistent data values are eliminated by preprocessing the dataset, in which the data normalization technique is employed. Then the pre-processed data is processed via a map-reduce framework to handle the bigdata, wherein the mapper phase, selects the features by the ISVM-RFE approach. The reducer phase merges all the features and selects the appropriate features. In the end, the hybrid classification model, which combines an enhanced LSTM and CNN, receives the chosen features. Particularly, the LSTM model is improved in its loss calculation, where the hybrid loss function is introduced containing inverse dice loss function and inverse binary cross entropy loss function. The improved score level fusion method, which uses this method to produce a double sigmoid normalization mechanism for enhanced classification, determines the final classification results.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 4-5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143481390","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}

{"title":"MapReduce-Enhanced Fuzzy K-Least Medians for Qualitative Clustering of Document Big Data","authors":"Tanvir Habib Sardar,&nbsp;Zahid Ahmed Ansari,&nbsp;Prasannavenkatesan Theerthagiri,&nbsp;P. Karthikeyan,&nbsp;Vadivel Ayyasamy,&nbsp;Dilip Kumar Jang Bahadur Saini","doi":"10.1002/cpe.70035","DOIUrl":"https://doi.org/10.1002/cpe.70035","url":null,"abstract":"<div>\u0000 \u0000 <p>Researchers design MapReduce-enhanced versions of traditional clustering algorithms to obtain the time performance benefit in big data clustering. However, the current literature shows that only a handful of partitioning clustering algorithms are enhanced using the MapReduce model. This work proposes a MapReduce-enhanced design of the Fuzzy K-Least Medians algorithm (MRFK-LstMdns) and its two novel variations. The purpose is to determine the best-performing MapReduce-enhanced partitioning clustering algorithms among the proposed and existing ones in terms of time performance and cluster quality. The work first preprocesses different self-crawled document datasets. Then, an optimal noise removal process is employed to make the dataset optimally noise-free. The proposed MRFK-LstMdns and its two novel variations are designed using three MapReduce job chaining. Each of the jobs performs the staged and suitable algorithmic parts. The proposed algorithms' time performance and cluster quality are compared against the existing MapReduce-enhanced partitioning algorithms. Although the proposed algorithm's time complexity is higher than that of existing algorithms as KLeast median is well known to execute in more time than other algorithms such as KMeans, KMedoids and its fuzzy versions, its efficient design, incorporating a chained MapReduce job execution, ensures that the actual execution time remains comparable to that of the existing algorithms. A majority voting technique using seven cluster quality measures shows that the MRFK-LstMdns generates better quality clusters than existing algorithms.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 4-5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143489973","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}

{"title":"Surface Defect Detector Based on Deformable Convolution and Lightweight Multi-Scale Attention","authors":"Zilin Xia,&nbsp;Zedong Huang,&nbsp;Jinan Gu,&nbsp;Wenbo Wang","doi":"10.1002/cpe.70003","DOIUrl":"https://doi.org/10.1002/cpe.70003","url":null,"abstract":"<div>\u0000 \u0000 <p>The detection of defects on industrial surfaces is essential for guaranteeing the quality and safety of products. Deep learning-based object detection methods have demonstrated impressive efficacy in industrial applications in recent years. However, due to the complex and variable shape of defects, the similarity between defects and background, large intra-class differences, and small inter-class differences lead to low classification accuracy, it is a great challenge to achieve accurate defect detection. To overcome these challenges, this research proposed a novel network specifically designed for defect detection. First, a feature extraction network, ResDCA-Net, is constructed based on deformable convolution and lightweight multi-scale attention, where deformable convolution can adaptively adjust to extract features of defects with complex and variable shapes. Second, the lightweight multi-scale attention module is constructed, which uses multi-branch and cross-space fusion to obtain the complete feature space attention map, thereby improving the defect feature attention and reducing the background feature attention. Third, to enhance the classification and localization accuracy, an attention-based decoupled prediction module is proposed to ensure that the classification and regression branches of the model can focus on their required features. Finally, extensive comparative experiments indicate that the proposed approach performs best, achieving 83.7% and 83.4% mean Average Precision (mAP) on the GC10-DET and NEU-DET datasets, respectively. The effectiveness of the proposed individual modules is further validated in ablation experiments, which demonstrate the excellent performance and potential in defect detection tasks.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 4-5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143481504","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}

{"title":"ARTransformer: An Architecture of Resolution Representation Learning for Cross-Resolution Person Re-Identification","authors":"Xing Lu,&nbsp;Fengshan Lai,&nbsp;Zhixiang Cao,&nbsp;Daoxun Xia","doi":"10.1002/cpe.8348","DOIUrl":"https://doi.org/10.1002/cpe.8348","url":null,"abstract":"<div>\u0000 \u0000 <p>Cross-resolution person re-identification (CR-ReID) seeks to overcome the challenge of retrieving and matching specific person images across cameras with varying resolutions. Numerous existing studies utilize established CNNs and ViTs to resize captured low-resolution (LR) images and align them with high-resolution (HR) image features or construct common feature spaces to match between images of different resolutions. However, these methods ignore the potential feature connection between the LR and HR images of the same pedestrian identity. Besides, the CNNs or ViTs usually obtain outliers within the attention maps of LR images; this inclination to excessively concentrate on anomalous information may obscure the genuine and anticipated characteristics between images, which makes it challenging to extract meaningful information from the images. In this work, we propose the abnormal feature elimination and reconfiguration Transformer (ARTransformer), a novel network architecture for robust cross-resolution person re-identification tasks. This method uses a resolution feature discriminator to learn resolution-invariant features and output feature matrices of images with different resolutions. It then calculates the potential feature relationships between images of pedestrians with the same identity but different resolutions through a new cross-resolution landmark agent attention (CR-LAA) mechanism. Conclusively, it utilizes output feature matrices to model LR and HR image interactions by mitigating abnormal image features and prioritizing attention on the target person by learning representations from input images of various resolutions. Experimental results show that ARTransformer performs well in matching images with different resolutions, even with unseen resolution, and extensive evaluations on four real-world datasets confirm the excellent results of our approach.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 4-5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143481505","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}