The application of augmented reality-based building defect inspection (AR-BDI) has become increasingly common in construction practice. Visual fatigue and related discomfort remain practical ergonomic concerns during prolonged AR head-mounted display (AR-HMD) use, which may negatively affect worker performance and safety. To address this ergonomic challenge, this study proposes an integrated method that combines human–computer interaction (HCI) interface optimization with work–rest scheduling based on eye tracking data. A total objective function, developed from visual attention mechanisms, is optimized through a genetic algorithm (GA) with a penalty mechanism to improve interface layout efficiency. In addition, an LSTM-based model is used to monitor visual fatigue levels in real-time and dynamically adjust rest intervals. Field experiments with AR-HMDs indicate that the optimized HCI interface enhances information recognition efficiency and reduces eye movement load. The proposed scheduling system further supports visual fatigue management by enabling timely rest interventions. By integrating ergonomic interface design with sequential visual fatigue prediction and fatigue-aware work–rest scheduling in AR-BDI tasks, this study offers a structured method to enhance user experience and long-term system usability in construction settings.

Video analytics (VA) has become essential in applications, yet it poses significant challenges related to privacy preservation, network bandwidth, and computational resources. With the increasing deployment of high-definition cameras, privacy concerns and resource constraints are becoming critical barriers to the widespread adoption of VA systems. Existing privacy-preserving techniques are often static, inefficient, and fail to adapt to dynamic, real-time scenarios. In this paper, we propose Parachute, a dynamic, resource-aware and privacy-preserving video analytics system that adaptively switches between a local mode and a collaborative mode in response to traffic conditions. The system uses local reinforcement learning to enable each individual camera to operate independently, and switches to multi-agent reinforcement learning for coordinated optimization when local resources become limited. Experiments on real-world datasets demonstrate that Parachute effectively balances detection accuracy and privacy protection, outperforming baseline methods under bandwidth constraints.

As a core contribution merge mechanism in distributed collaborative development, pull requests contain valuable knowledge of code evolution and issue resolution. With the co-evolution of multiple projects in a software ecosystem, relevant and similar issues can arise across different projects. Leveraging existing solutions in pull requests (PRs) through cross-project pull request recommendation (CPR) can enrich context knowledge and improve the efficiency of issue resolution. However, the characteristics of CPR and its effectiveness in the process of issue resolution still remain unclear. To bridge this gap, we conduct an empirical study of the CPR on GitHub. We first extract 4,445 CPRs from 2,500 open source projects and quantitatively analyze the characteristics of CPR. Then we conduct a qualitative analysis of sampled CPR cases to understand the influence of CPR. We also use a regression model to explore the impact of CPRs on issue resolution. Our main findings are as follows: (1) Experienced contributors in target projects make most of the CPRs and their CPRs are more timely than inexperienced contributors; (2) In CPR dataset, bugs constitute the largest proportion of target issue types, followed by enhancements, features and questions; (3) Nearly half of the CPRs are accepted by issue participants; (4) A greater number of the CPRs contribute indirectly to solving the target issue by offering solutions and contextual information, rather than providing appropriate code that can be directly applied to the issue; (5) Most of CPR-related factors have a significant impact on issue resolution delay. Among these, recommendation latency has the most significant impact, followed by the type of recommender. Our work has important insights into CPR and offers important guidance for developers on recommending cross-project PRs to resolve the mushrooming issues.

More and more users are uploading their data to the cloud without storing any copies locally. Under the premise that cloud users cannot fully trust cloud service providers, how to ensure the integrity of users’ shared data in the cloud storage environment is one of the current research hotspots. In this paper, we propose a secure and effective data sharing scheme for dynamic user groups. (1) In order to realize the user identity tracking and the addition and deletion of dynamic group users, we add a new role called Rights Distribution Center (RDC) in our scheme. (2) To protect the privacy of user identity, when performing third party audit to verify data integrity, it is not possible to determine which user is a specific user. Therefore, the fairness of the audit can be promoted. (3) Define a new integrity audit model for shared cloud data. In this scheme, the user sends the encrypted data to the cloud and the data tag to the Rights Distribution Center (RDC) by using data blindness technology. Finally, we prove the security of the scheme through provable security theory. In addition, the experimental data shows that our proposed scheme is more efficient and scalable than the state-of-the-art solution.

Traffic congestion has become a worldwide problem, seriously restricting the performance of transport network. Association of congested links is an essential factor in the formation of traffic congestion, while it lacks enough research. In this paper, a methodology ARM-K combining K-means clustering and association rules mining is proposed to discover the relations of congested links. Specifically, the method digs out the association of two congested links and further extends the 2-tuple relations into a relation graph. As a result, the relation graph and its topological-order profile the associations of congested links. The experiments including congestion prediction and congestion dispersion are devised for the proposed method based on mobile data derived from the traffic simulator VISSIM. The results show relatively high prediction accuracy (above 0.75) and obvious improvement of network performance after dispersion (more than 12.5 percentage-point drop of travel time index), indicating that ARM-K can effectively explores the associations of congested links and provide valuable information for congestion management.