Skip to content
Log in

Author

Jun Zhan

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Review Open access Aug 2026

Connected Environments: Advancing Monitoring and Decision Support through the Fusion of IoT Sensors and Intelligent Systems

Interrelated environments are also becoming the driving force behind how intricate physical, social, and cyber-physical systems are observed and handled. The key in this development is the incorporation of Internet of Things (IoT) sensing infrastructures and smart systems that have data analytics, learning, and decision support capabilities. The review is a well-organized account of the development of recent connected environments with a specific emphasis on the interactions of IoT sensors and intelligent systems to improve monitoring and decision-making. First, the article discusses IoT sensing infrastructures, which comprise architectural foundations, sensor technologies, communication mechanisms, and deployment considerations that facilitate the acquisition of large volumes of data. It then looks at intelligent systems data processing and analytics, with the contribution of machine learning, artificial intelligence, and edge-cloud design to the conversion of raw sensor information into insights. Based on these premises, the review examines frameworks and strategies of fusion that combine heterogeneous sensor data and intelligent analytics across multiple layers of systems. The application domains, such as smart cities, healthcare, industrial automation, and environmental monitoring, are mentioned as examples of the representative areas where the concept of intelligent connected environments has practical implications and issues. The Major technical, organizational, and societal issues—scalability, data heterogeneity, security, privacy, and trust—are discussed critically. Lastly, the article also describes the emerging trends and future research directions, such as distributed intelligence, privacy-preserving learning, and autonomous decision systems. With its holistic view of connected environments, this review is expected to help researchers and practitioners in developing robust, scalable, and trustworthy next-generation monitoring and decision support in connected environments.

Jun Zhan, Wei Yu · 0 citations
Open access Jul 2026

Privacy-preserving clustered federated learning via differential privacy and homomorphically encrypted prototypes.

Clustered federated learning (CFL) is an effective paradigm for handling statistical heterogeneity by grouping clients with similar data characteristics and learning cluster-specific models. However, existing CFL methods often expose sensitive clustering signals or cluster-specific updates to the server, which may reveal latent client similarity relations and weaken privacy protection. To address this issue, we propose Privacy-Preserving Clustered Federated Learning (PPCFL), a split-stream framework that integrates adaptive Gaussian perturbation with threshold Paillier encrypted aggregation. In PPCFL, backbone updates are protected by adaptive Gaussian perturbation before plaintext aggregation, while clustering signatures and cluster-head updates are first perturbed by stream-specific adaptive Gaussian mechanisms and then uploaded under threshold Paillier encryption. The server performs ciphertext-domain aggregation for clustering prototypes and cluster-head updates, whereas plaintext prototypes and cluster-level decrypted aggregates are recovered by a qualified threshold-decryption client subset without giving the server decryption capability. In addition, PPCFL adopts round-wise budget growth, utility-aware refinement, and adaptive clipping-threshold updates to improve the privacy-utility trade-off under dynamic Non-IID settings. Experiments on MNIST, Fashion-MNIST, and CIFAR-10 show that PPCFL achieves the highest final-round accuracy among the evaluated methods in the reported settings while providing enhanced protection for clustering-related information and cluster-specific updates. Under the representative Dirichlet setting [Formula: see text], PPCFL improves the final accuracy over DP-FedAvg by 0.33, 1.73, and 2.62 percentage points on MNIST, Fashion-MNIST, and CIFAR-10, respectively, and over IFCA by 0.98, 8.28, and 10.24 percentage points.

Jun Zhan, Zhenglong Jiang, Lang Liu · 0 citations