首页期刊导航|Concurrency and computation: practice and experience
期刊信息/Journal information
Concurrency and computation: practice and experience
John Wiley & Sons Ltd.
Concurrency and computation: practice and experience

John Wiley & Sons Ltd.

1532-0634

Concurrency and computation: practice and experience/Journal Concurrency and computation: practice and experience
正式出版
收录年代

    Weak–Strong Synergy Learning With Random Grayscale Substitution for Cross-Modality Person Re-Identification

    Zexin Zhang
    e70101.1-e70101.14页
    查看更多>>摘要：Visible-infrared person re-identification (VI-ReID) is a rapidly emerging cross-modality matching problem that aims to identify the same individual across daytime visible modality and nighttime thermal modality. Existing state-of-the-art methods predominantly focus on leveraging image generation techniques to create cross-modality images or on designing diverse feature-level constraints to align feature distributions between heterogeneous data. However, challenges arising from color variations caused by differences in the imaging processes of spectrum cameras remain unresolved, leading to suboptimal feature representations. In this paper, we propose a simple yet highly effective data augmentation technique called Random Grayscale Region Substitution (RGRS) for the cross-modality matching task. RGRS operates by randomly selecting a rectangular region within a training sample and converting it to grayscale. This process generates training images that integrate varying levels of visible and channel-independent information, thereby mitigating overfitting and enhancing the model’s robustness to color variations. In addition, we design a weighted regularized triplet loss function for cross-modality metric learning and a weak–strong synergy learning strategy to improve the performance of cross-modal matching.We validate the effectiveness of our approach through extensive experiments conducted on publicly available cross-modality Re-ID datasets, including SYSU-MM01 and RegDB. The experimental results demonstrate that our proposed method significantly improves accuracy, making it a valuable training trick for advancing VT-ReID research.
      原文链接:
    • NETL
    • NSTL
    • Wiley

    Multi-Modal Anomalous Driving Behavior Detection With Adaptive Masking

    Kun ZengZhonghua PengZuoyong LiYun Chen...
    e70110.1-e70110.12页
    查看更多>>摘要：Intelligent Transportation Systems are tasked with enhancing road safety, a crucial challenge given that approximately 1.35 million fatalities occur globally each year, with 15%–27% of these deaths attributed to Anomalous Driving Behaviors (ADBs). Detecting these behaviors in real time is vital for preventing accidents and improving traffic safety. However, the complexity of driving environments, characterized by diverse scenarios, drivers, and vehicle conditions, makes ADB detection a challenging task. This article proposes a novel approach for ADB detection, leveraging the advantages of multimodal data, adaptive masking, and multihead self-attention mechanisms. The proposed method first employs an adaptive masking technique based on the Softmax function to sparsify input features, effectively reducing the influence of irrelevant information. By focusing on key features, the model becomes more resilient to noise, such as background clutter or irrelevant driver actions, which might otherwise interfere with the detection of abnormal behaviors. To further enhance feature integration across different data modalities (e.g., visual, infrared, and depth data), a multihead self-attention mechanism is incorporated. This mechanism enables the model to prioritize important information from various sensor inputs, fostering more effective multimodal fusion and better decision-making for behavior classification. In addition, a supervised contrastive learning strategy is utilized to mitigate memory usage, a common challenge in real-time systems where computational resources are limited. This approach ensures efficient learning by emphasizing the distinction between normal and abnormal behaviors while minimizing the memory footprint of the model. Extensive experiments on two benchmark datasets, 3MDAD and DAD, demonstrate the proposed method’s superior performance in detecting ADBs. The results indicate a significant improvement in detection accuracy and robustness, highlighting the potential of this approach for deployment in real-world Intelligent Transportation Systems aimed at enhancing road safety. This research provides a promising step forward in the development of more effective and scalable solutions for ADB detection, offering a foundation for future advancements in traffic safety technologies.
      原文链接:
    • NETL
    • NSTL
    • Wiley

    Construction and Application of a Digital Platform for Charitable Cultural Resources Integrating VR Technology and BiGRU

    Huifang LiuHuilin YeYunfeng Ye
    e70123.1-e70123.13页
    查看更多>>摘要：As an important spiritual driving force to promote the development of public welfare undertakings, charity culture is currently facing challenges such as lack of professional talents and inefficient resource management. The purpose of this research is to build a digital platform of charity cultural resources that integrates virtual reality technology and bidirectional gated circulation unit network, so as to solve the problems of low efficiency of charity cultural information processing, insufficient interaction, and weak public cognition. By introducing a sentence-level attention mechanism and a relationship perception enhancement module, the bidirectional gated cyclic unit network model is improved, and the entity extraction and relationship mining capabilities of the charity culture knowledge map are optimized. Combine virtual reality technology to realize dynamic visual display of cultural resources to improve platform performance. In the initial stage of the pattern, the growth rate of F1 was very fast; then the growth rate slowed down, and finally stabilized, with good generalization performance. At 80% CPU occupancy, the response time of the system did not change by more than 0.18 s. With 500 and 1000 parallel users respectively, the communication efficiency of the platform reached 98.37%, demonstrating good signal transmission and communication performance. However, the hardware environment of the digital platform constructed in this study may limit its popularity, and the real-time update and maintenance of the knowledge graph are faced with challenges.
      原文链接:
    • NETL
    • NSTL
    • Wiley

    Prediction of Network Public Opinion Evolution Trends in Emergent Hot Events

    Xinyan ZhangJing Fang
    e70125.1-e70125.25页
    查看更多>>摘要：In recent years, there has been a notable increase in food safety incidents, which has raised considerable public concern. Optimizing food safety supervision and enhancing public trust have become urgent issues to be addressed. This study specifically examines the “tanker mixed with edible oil” incident and employs a variety of methodologies, including text analysis and time series modeling, to conduct a comprehensive analysis of public sentiment, The findings provide a scientific foundation for enhancing regulatory oversight. Relevant data were gathered via Python, public opinion trends were forecast via the ARIMA time series model, and an in-depth analysis of the thematic characteristics associated with each phase of public opinion development was conducted by integrating LDA topic modeling techniques. Meanwhile, this study employs social network analysis to construct an interactive network among users and identify key nodes and pathways involved in the dissemination of public opinion. Through simulation analysis, the following conclusions are drawn: (1) The “tanker mixed with cooking oil” incident exhibited a pronounced trend of negative sentiment that intensified over time. (2) The thematic analysis reveals public concern regarding disarray in food transportation and insufficient regulatory oversight, highlighting a shift in the public’s focus. (3) Social network analysis emphasizes the crucial roles played by official media and individual key opinion leaders (KOLs) in shaping public opinion, illustrating how these entities influence the direction of public sentiment through their interactive relationships. Through the empirical analysis of the “tanker mixed with edible oil” incident, this paper verifies the effectiveness of the adopted method, providing an important reference for the risk prevention and control of food safety public opinion and policy-making.
      原文链接:
    • NETL
    • NSTL
    • Wiley

    Predicting the Best Green Growth Performance With Integrated Intuitionistic Fuzzy and Metaheuristic Algorithms

    Mustafa Ozdemir
    e70089.1-e70089.21页
    查看更多>>摘要：Although various studies monitor and evaluate green growth performance, no heuristic-based hybrid studies test the reflection of green growth indicators. This study aims to identify the best green growth performance by using intuitionistic fuzzy and metaheuristic algorithms over green growth indicators, contributing to filling the gap in the field and providing inferences about green growth to decision-makers. For this purpose, the green growth levels of 31 selected countries were analyzed based on environmental and resource efficiency indicators, and the best result was predicted. The study was conducted in two phases. In the first phase, countries were ranked according to their green growth performance using intuitionistic fuzzy methods. In the second phase, the best performance value was estimated at different population levels using metaheuristic algorithms. The research results show that the renewable electricity generation variable is the most important criterion. Ireland (1.00), Switzerland (0.98), and Costa Rica (0.95) are the countries with the best green growth performance, respectively. In green growth performance estimation, the ANFIS-TLBO model (R2 =0.908; MAE=0.196; SMAPE=0.689; MSE=0.050; RMSE=0.223; MBE=0.188) demonstrated the closest estimation accuracy to the real values. In this study, for the first time, a hybrid model combining the intuitionistic fuzzy method and a metaheuristic algorithm was tested and proposed for green growth performance assessment. With this originality, it is expected that the results of this article will make a significant contribution to the literature gap and serve as a guide for policymakers and researchers.
      原文链接:
    • NETL
    • NSTL
    • Wiley

    SS-LDP: A Framework for Sparse Streaming Data Collection Based on Local Differential Privacy

    Hongjiao LiMing JinJiayi XuZhenya Shi...
    e70119.1-e70119.16页
    查看更多>>摘要：The continuous collection of streaming data in the Internet of Things (IoT) may compromise user privacy, as such data often originates from personal information. Local differential privacy (LDP) is a novel privacy notion that offers a strong privacy guarantee to all users without relying on a trusted data collector. However, existing LDP-based studies mainly focus on static scenarios or perturbation of data points at a single timestamp without sufficiently considering data sparsity, which adds excessive noise and leads to low utility. Therefore, we propose a Framework for Sparse Streaming Data Collection based on Local Differential Privacy (SS-LDP), which aims to provide high utility at each timestamp while satisfying ?-event LDP. One component is the introduction of an upper-bound optimization mechanism, which reduces the noise scale by combining error minimization with the gradient descent method. Another component of SS-LDP targets the efficient management of privacy resources through two specific strategies. First, significant changes in streaming data are captured by calculating differences between the latest few data points, thereby conserving the privacy budget. Second, an improved sparse privacy budget allocation mechanism quantifies data sparsity at each timestamp using the moving average method, enabling efficient allocation of the privacy budget for each timestamp. SS-LDP is evaluated using two real-world datasets and compared with four baseline methods that satisfy ?-event privacy. Extensive experiments and theoretical analyses are conducted to demonstrate the superiority of our framework.
      原文链接:
    • NETL
    • NSTL
    • Wiley

    Prediction of Carbon Emission Rights Trading Prices Based on the CNN–LSTMModel in the Context of Carbon Peak: Taking Guangdong Province as an Example

    Tinggui ChenJiawen YeYanping ZhouQing Yu...
    e70121.1-e70121.24页
    查看更多>>摘要：Carbon emissions are a significant contributor to global warming. As one of the largest carbon emitters in the world, China is committed to establishing a carbon emission trading market to address the challenges posed by climate change. The carbon price is a fundamental component of the carbon financial market. Accurately predicting it can improve environmental quality, reduce energy demand, and promote economic growth. This study uses price data from the Guangdong carbon market as a case study and employs a hybrid model that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks for carbon price forecasting. The findings indicate that: (1) the CNN–LSTMmodel exhibits optimal predictive performance when the sliding window is set to a size of 5 on the basis of previous carbon price data. (2) By incorporating significant indicator features from the Guangdong pilot carbon price dataset while maintaining a sliding window size of 5, the model achieves superior predictive accuracy, as evidenced by a Goodness of Fit (R2) of 0.8622 and a mean absolute error (MAE) of 0.0228, resulting in the most favorable comprehensive evaluation index. (3) The integration of one-dimensional convolutional layers with LSTM layers in the CNN–LSTM model effectively leverages the strengths of CNNs for local feature extraction and the capabilities of LSTMs for modeling time series data. This approach leads to a substantial improvement in predictive performance compared with alternative models such as Support Vector Machine (SVM), Recurrent Neural Network (RNN), and LSTM.
      原文链接:
    • NETL
    • NSTL
    • Wiley

    Blockchain-Based Ciphertext-Policy Attribute-Based Encryption for Controlled Multi-User Collaboration

    Zhaoqian ZhangDi WuQiang ZhuWei Qin...
    e70093.1-e70093.16页
    查看更多>>摘要：As cloud computing technology continues to advance and mature, the public cloud has emerged as a predominant method for data sharing. Ciphertext-policy attribute-based encryption (CP-ABE) is recognized as a highly promising cryptographic approach that safeguards data confidentiality while improving sharing efficiency. However, as the demand for collaborative access increases, the shortcomings of existing schemes in controlled multi-user collaboration scenarios have become increasingly evident. In this paper, we propose a blockchain-based CP-ABE scheme for controlled multi-user collaboration. We convert the regular policy to collaborative policy by the collaborative attribute bounding to a ciphertext, and we present a collaborative access structure with attribute reuse to avoid an increase in computation and storage overhead. Furthermore, we design a collaborative channel driven by smart contracts to efficiently control the collaboration within the same group. Security analysis demonstrates that our scheme achieves IND-CPA security, ensures controlled collaboration, and resists user collusion. Additionally, we analyze the impact of blockchain security on the scheme. Performance comparisons indicate that our scheme is competitive, achieving a moderate performance in encryption, a 15% reduction in decryption overhead, and a 5% reduction in key generation overhead compared to state-of-the-art approaches, while completely eliminating the need for any collaborative communication overhead. These results align with the initial purpose of the scheme and demonstrate its feasibility in multi-user collaborative scenarios.
      原文链接:
    • NETL
    • NSTL
    • Wiley

    A Unified Job Scheduler for Optimization of Different System Performance Metrics

    Jaishree MayankArijit Mondal
    e70111.1-e70111.17页
    查看更多>>摘要：Internet-of-Things-enabled frameworks have eased the development of complex systems, but they throw a significant challenge for efficient resource utilization, thereby improving the system performance. An intelligent scheduler is essential for managing the resources and allocating the same resources to different requests or tasks. This work proposes a generic methodology to optimize system performance metrics such as throughput, utilization, and reward achieved. We present an integer linear programming formulation of the problem to find an optimal solution.We present offline heuristic methods to quickly find reasonable solutions, given the intractable nature of the problem. These heuristics yield promising outcomes, with deviations from optimal solutions below 20% in scenarios with task overlap and high utilization. In scenarios with minimal overlap and utilization, deviations remain under 10%. However, as variables and constraints increase in ILP, the demand for time and memory resources rises substantially. We conduct a comparative analysis of heuristic performance across various scenarios and large test cases. Additionally, we extend our methods to handle resources in online mode, presenting an extensive comparative study with encouraging results.
      原文链接:
    • NETL
    • NSTL
    • Wiley

    Access Control Modeling and Validation for Ethereum Smart Contracts

    Insaf AchourHanen IdoudiSamiha Ayed
    e70108.1-e70108.15页
    查看更多>>摘要：Smart contracts are self-executing programs that operate on a blockchain network. They are designed to automate transaction execution without the need for intermediaries. Once deployed in the blockchain network, smart contracts cannot be altered. However, this immutability can also lead to security risks. If a smart contract contains a vulnerability upon deployment, it cannot be corrected, leaving the code vulnerable. Therefore, incorporating security considerations during the design phase of smart contract development is crucial.Access control is a key security concept that must be integrated into the design of smart contracts to prevent unauthorized access to critical functions or data. In this paper, we introduce a Model-Driven Architecture (MDA) approach to design access control for smart contracts, and we validate, using Ethereum, the proposed approach using Smart Contract Security Verification Standard (SCSVS) rules.
      原文链接:
    • NETL
    • NSTL
    • Wiley