Yaxin Mei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yaxin Mei has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Tian Wang
Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China
5 shared publications - Huiling Qin
Beijing Normal University, Zhuhai, China
2 shared publications - Yu Zheng
Southwest Jiaotong University, Chengdu, Sichuan, China
2 shared publications - Yuzhu Liang
Beijing Normal University
2 shared publications - Changfu Xu
Jiangxi University of Finance and Economics
1 shared publication - Chenhao Wang
Beijing Normal University, Zhuhai, China
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 3715-3726
PG-DyRA: Potential-Game Guided Multi-Agent Collaboration for Dynamic Urban Resource Allocation
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 3715-3726
Open AccessPG-DyRA: Potential-Game Guided Multi-Agent Collaboration for Dynamic Urban Resource Allocation
- 28 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-15
ST-CoSense: Spatio-Temporal Cooperative Sensing for Resource-Constrained Urban Applications
Urban sensing is a critical infrastructure for smart cities, yet dense sensor deployments remain prohibitively costly, and sensor data quality degrades severely under real-world interference (e.g., signal occlusion, extreme weather) that results in data gaps. Existing approaches treat sampling and imputation as two independent stages: sampling strategies select locations based on heuristics or optimization criteria without considering the downstream reconstruction objective, while imputation models passively adapt to whatever observations are provided, with no mechanism to inform the sampler which locations would most effectively reduce reconstruction error. We propose ST-CoSense, a unified framework that bridges this gap through end-to-end joint optimization of active sparse sampling and spatio-temporal imputation. A mask-guided encoder dynamically selects informative sensing locations by integrating historical sampling patterns with learned spatio-temporal representations, while an attention-based imputation module reconstructs complete urban data from sparse observations. Imputed results in turn refine subsequent sampling decisions, allowing continuous adaptation under sampling budget constraints. Experimental results show that ST-CoSense outperforms state-of-the-art methods, achieving up to 9.07% MAE and 10.53% RMSE improvement at a 50% sampling rate. Furthermore, ST-CoSense demonstrates superior robustness in large-scale urban networks, achieving a 4.95% RMSE improvement over the best-performing baseline. These results underscore ST-CoSense's effectiveness and its practical potential in resource-constrained urban sensing applications.
- 28 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-15
ST-CoSense: Spatio-Temporal Cooperative Sensing for Resource-Constrained Urban Applications
Urban sensing is a critical infrastructure for smart cities, yet dense sensor deployments remain prohibitively costly, and sensor data quality degrades severely under real-world interference (e.g., signal occlusion, extreme weather) that results in data gaps. Existing approaches treat sampling and imputation as two independent stages: sampling strategies select locations based on heuristics or optimization criteria without considering the downstream reconstruction objective, while imputation models passively adapt to whatever observations are provided, with no mechanism to inform the sampler which locations would most effectively reduce reconstruction error. We propose ST-CoSense, a unified framework that bridges this gap through end-to-end joint optimization of active sparse sampling and spatio-temporal imputation. A mask-guided encoder dynamically selects informative sensing locations by integrating historical sampling patterns with learned spatio-temporal representations, while an attention-based imputation module reconstructs complete urban data from sparse observations. Imputed results in turn refine subsequent sampling decisions, allowing continuous adaptation under sampling budget constraints. Experimental results show that ST-CoSense outperforms state-of-the-art methods, achieving up to 9.07% MAE and 10.53% RMSE improvement at a 50% sampling rate. Furthermore, ST-CoSense demonstrates superior robustness in large-scale urban networks, achieving a 4.95% RMSE improvement over the best-performing baseline. These results underscore ST-CoSense's effectiveness and its practical potential in resource-constrained urban sensing applications.
- Top Cited Papers
- 19 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (10) , 20583-20599
A Comprehensive Survey on Large Language Model Compression for Artificial Intelligence Applications in Edge Systems
Large language models (LLMs) have achieved remarkable performance across various artificial intelligence (AI) applications. However, current LLMs cannot be deployed directly on edge nodes due to their large number of parameters. Fortunately, model compression technology has been proposed to reduce the computational workload and memory usage of LLMs, enabling further edge-based LLM services. However, existing research typically concentrates on isolated compression algorithms and lacks a comprehensive perspective on how to leverage these techniques for practical, end-to-end LLM deployment in edge environments. In this survey, we review edge-oriented LLM compression techniques and software–hardware codesign strategies to enable efficient LLM deployment on resource-constrained edge systems and guide future research in this area. First, we analyze techniques for LLM compression from the perspective of cloud–edge collaborative intelligence, including model quantization, parameter pruning, and knowledge distillation (KD). Second, we present several hybrid model frameworks tailored to dynamic, heterogeneous edge environments, based on model architecture, application scenarios, and combination selection. Third, we further refine a four-layer software–hardware codesign and an overhead-aware LLM deployment optimization. Finally, we discuss the challenges of current model compression approaches and offer insights into future research directions, with a focus on edge-based LLM services.
- 19 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (10) , 20583-20599
Top Cited PapersA Comprehensive Survey on Large Language Model Compression for Artificial Intelligence Applications in Edge Systems
Large language models (LLMs) have achieved remarkable performance across various artificial intelligence (AI) applications. However, current LLMs cannot be deployed directly on edge nodes due to their large number of parameters. Fortunately, model compression technology has been proposed to reduce the computational workload and memory usage of LLMs, enabling further edge-based LLM services. However, existing research typically concentrates on isolated compression algorithms and lacks a comprehensive perspective on how to leverage these techniques for practical, end-to-end LLM deployment in edge environments. In this survey, we review edge-oriented LLM compression techniques and software–hardware codesign strategies to enable efficient LLM deployment on resource-constrained edge systems and guide future research in this area. First, we analyze techniques for LLM compression from the perspective of cloud–edge collaborative intelligence, including model quantization, parameter pruning, and knowledge distillation (KD). Second, we present several hybrid model frameworks tailored to dynamic, heterogeneous edge environments, based on model architecture, application scenarios, and combination selection. Third, we further refine a four-layer software–hardware codesign and an overhead-aware LLM deployment optimization. Finally, we discuss the challenges of current model compression approaches and offer insights into future research directions, with a focus on edge-based LLM services.
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 20 (4) , 1-19
Privacy-Enhanced Cooperative Storage Scheme for Contact-Free Sensory Data in AIoT with Efficient Synchronization
The growing popularity of contact-free smart sensing has contributed to the development of the Artificial Intelligence of Things (AIoT). The contact-free sensory data has great potential to mine and analyze the hidden information for AIoT-enabled applications. However, due to the limited storage resource of contact-free smart sensing devices, data is naturally stored in the cloud, which is at risk of privacy leakage. Cloud storage is generally considered insecure. On one hand, the openness of the cloud environment makes the data easy to be attacked, and the complex AIoT environment also makes the data transmission process vulnerable to the third party. On the other hand, the Cloud Service Provider (CSP) is untrusted. In this article, to ensure the security of data from contact-free smart sensing devices, a Cloud-Edge-End cooperative storage scheme is proposed, which takes full advantage of the differences in the cloud, edge, and end. Firstly, the processed sensory data is stored separately in the three layers by utilizing well-designed data partitioning strategy. This scheme can increase the difficulty of privacy leakage in the transmission process and avoid internal and external attacks. Besides, the contact-free sensory data is highly time-dependent. Therefore, combined with the Cloud-Edge-End cooperation model, this article proposes a delta-based data update method and extends it into a hybrid update mode to improve the synchronization efficiency. Theoretical analysis and experimental results show that the proposed cooperative storage method can resist various security threats in bad situations and outperform other update methods in synchronization efficiency, significantly reducing the synchronization overhead in AIoT.
- 11 May 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 20 (4) , 1-19
Open AccessPrivacy-Enhanced Cooperative Storage Scheme for Contact-Free Sensory Data in AIoT with Efficient Synchronization
The growing popularity of contact-free smart sensing has contributed to the development of the Artificial Intelligence of Things (AIoT). The contact-free sensory data has great potential to mine and analyze the hidden information for AIoT-enabled applications. However, due to the limited storage resource of contact-free smart sensing devices, data is naturally stored in the cloud, which is at risk of privacy leakage. Cloud storage is generally considered insecure. On one hand, the openness of the cloud environment makes the data easy to be attacked, and the complex AIoT environment also makes the data transmission process vulnerable to the third party. On the other hand, the Cloud Service Provider (CSP) is untrusted. In this article, to ensure the security of data from contact-free smart sensing devices, a Cloud-Edge-End cooperative storage scheme is proposed, which takes full advantage of the differences in the cloud, edge, and end. Firstly, the processed sensory data is stored separately in the three layers by utilizing well-designed data partitioning strategy. This scheme can increase the difficulty of privacy leakage in the transmission process and avoid internal and external attacks. Besides, the contact-free sensory data is highly time-dependent. Therefore, combined with the Cloud-Edge-End cooperation model, this article proposes a delta-based data update method and extends it into a hybrid update mode to improve the synchronization efficiency. Theoretical analysis and experimental results show that the proposed cooperative storage method can resist various security threats in bad situations and outperform other update methods in synchronization efficiency, significantly reducing the synchronization overhead in AIoT.
- 1 March 2021
- Published by Elsevier in Journal of Systems Architecture
- Vol. 114
Edge-based auditing method for data security in resource-constrained Internet of Things
- 1 March 2021
- Published by Elsevier in Journal of Systems Architecture
- Vol. 114
Edge-based auditing method for data security in resource-constrained Internet of Things