Hybrid Artificial Intelligence Lab (HAI LAB) is primarily engaged in theoretical and applied research in artificial intelligence (AI) and data science. Its core objective is to achieve the implementation of AI in basic industries. The research direction focuses on the interdisciplinary integration of computer science, mathematics, communication science, and other fields. Specifically, it includes:

• Wireless Intelligence. Applying machine learning to wireless communication and networks to address the non-ideal and high-complexity challenges in traditional wireless communication and networking.

• Machine Learning Theory. Focusing on knowledge-driven machine learning theory and federated learning theory, and researching lightweight implementations of machine learning models and algorithms.

• Integrated Circuit Process Optimization. Based on data science theory and artificial intelligence technology, studying the process optimization challenges of large-scale integrated circuits to improve yield.

Journal Article

Physics-Informed Machine Learning based Edge Detection for SEM Images

Yi Fang, Chun Wang, Sihai Zhang. in IEEE Transactions on Semiconductor Manufacturing, 2025.

WAE: An evaluation metric for attribution-based XAI on time series forecasting

Yueshan Chen, Sihai Zhang, Neurocomputing, 2025, 622: 129379.

Why Contour Averaging Works for SEM Metrology: Analysis and Validation

Jingxian Wei, Chenyu Xu, Sihai Zhang, IEEE Transactions on Semiconductor Manufacturing, DOI: 10.1109/TSM.2024.3471635.

The Quantitative evaluation of carbon reduction enabled by mobile communication in other industries: indicators, methods, and cases

Sihai Zhang, Chan Cui, Hongyu Sun, Yongmei Zeng, Jiang Zhu, Jinkang Zhu, SCIENTIA SINICA Informationis, 2024, 54(4): 777–787. DOI: 10.1360/SSI-2023-0295

Optimal Two-Timescale Configuration of Mobile Edge Computing with Mixed Energy Supply

Xiaojing Chen, Si Chen, Wei Ni, Xin Wang, Sihai Zhang, Shunqing Zhang, Yanzan Sun, Shugong Xu, Abbas Jamalipour, IEEE Transactions on Smart Grid, doi: 10.1109/TSG.2024.3390772.

The Predictability of Stock Price: Empirical Study on Tick Data in Chinese Stock Market

Yueshan Chen, Xingyu Xu, Tian Lan,  Sihai Zhang, Big Data Research, 2024, 35: 100414.

DGL: Device Generic Latency Model for Neural Architecture Search on Mobile Devices

Qinsi Wang, Sihai Zhang, IEEE Transactions on Mobile Computing, 2023, 23(2): 1954-1967.

FedSeq: A Hybrid Federated Learning Framework Based on Sequential In-Cluster Training

Zhikun Chen, Daofeng Li, Rui Ni, Jinkang Zhu, Sihai Zhang, IEEE Systems Journal, 2023, 17(3): 4038-4049.

Wireless knowledge driven channel estimation in massive MIMO

Sihai Zhang, Jiashu Lin, Yamei Xu, Ming Zhao, Jinkang Zhu, SCIENTIA SINICA Informationis, Volume 53, Issue 4, 2023, Pages 758-, ISSN 1674-7267.

Conference Paper

Knowledge-enhanced N2N: Learning SEM Images Denoising with No Clean Data

Yi Fang, Chun Wang, Tian Lan and Sihai Zhang, 2025 International Joint Conference on Neural Networks, Rome, Italy, 2025.

LoS Identifcation Based Transmit Power Minimization in Cell-free ISAC System

Jingwen Wu, Chao Hu, Sihai Zhang , Ling Qiu, 2025 IEEE 101st Vehicular Technology Conference (VTC2025-Spring), Oslo, Norway, 2025.

Two-timescale Transmit Power Minimization in Semi-Passive IRS-Aided ISAC Systems

Jingwen Wu, Qilue Huang, Sihai Zhang and Ling Qiu, 2024 the 10th International Conference on Computer and Communications (ICCC), Chengdu, China, 2024.

A User-driven Sleep and wake-up Technology for Energy-Efficient 5G-Advanced Base Stations

Xiangzhi Guo, Xiaohui Chen, Weidong Wang, Sihai Zhang, 2024 16th International Conference on Wireless Communications and Signal Processing, Hefei, China, 2024.

Performance Analysis of Machine Learning on Homomorphically Encrypted Data

Morogo Freshina Mahatho, Yueshan Chen, Sihai Zhang, 2024 16th International Conference on Wireless Communications and Signal Processing, Hefei, China, 2024.

Multi-Point Channel Charting Aided Resource Management in Cell-Free Networks

Yuanqing Ye, Chenyu Xu, Zhen Wang, Lie Shan, Sihai Zhang, International Conference on Future Communications and Networks, Valletta, Malta, November, 2024.

Feature Fusion based HotspotDetection with R-EfficientNet

Chun Wang, Yi Fang, and Sihai Zhang, InProceedings of Great Lakes Symposiumon VLSI (GLSVLSI ’24).

MathNAS: If Blocks Have a Role in Mathematical Architecture Design

Qinsi Wang, Jinghan Ke, Zhi Liang and Sihai Zhang, NeurIPS, 2023

Energy Consumption Constrained Resource Cell Optimization Based on Multipoint Channel Charting

Yuanqing Ye, Zhikun Chen, Ming Zhao, and Sihai Zhang, 2023 15th International Conference on Wireless Communications and Signal Processing, Hangzhou, China,2023.

Data Collaborative Federated Learning for Non-I.i.d Data in Wireless Networks

Jiaqi Pan, Zhikun Chen, Sihai Zhang, and Ming Zhao, International Conference on Future Communications and Networks, Queenstown, New Zealand, December, 2023.

Adaptive User Selection and Bandwidth Allocation for Fast Convergence of Federated Learning in Wireless Networks

Jiaqi Pan, Zhikun Chen, Ming Zhao, Sihai Zhang, and Jinkang Zhu, International Conference on Future Communications and Networks, Queenstown, New Zealand, December, 2023.

Complete Paper Compilation: 论文汇总.pdf

• Zhan Wang, Fang Yi, Zhang Sihai. A Noise Model-Based Denoising Method for Scanning Electron Microscope (SEM) Images: China, CN202510219767.1 [P]. 2025-02-26.

• Zhang Sihai, Fang Yi, Wang Chun. A Physics-Informed Edge Detection Method for SEM Images: China, CN202510338237.9 [P]. 2025-03-21.

• Zhang Sihai, Sun Hongyu. A Sleep Control-Based Energy-Saving Method and Device for Off-Grid Photovoltaic-Powered Base Stations: China, CN202510242414.3 [P]. 2025-05-30.

• Zhao Wei, Lu Zhiqiang, Zhang Sihai, He Haihui, Wu Xu, Luo Zhaofeng, Hu Bing. An Experimental Equipment Reservation Management System. 201610331323.8.

• Zhang Sihai, Zhou Wuyang. A Method for Detecting Taxi Refusal Behaviors Based on Large-Scale Real-Time Trajectory Analysis. 201610032750.6.

• Zhao Ming, Jia Yulin, Wei Haichao, Zhang Sihai, Zhou Wuyang. A Max-Min Fairness Resource Allocation Method Based on Interference Coordination in Heterogeneous Networks. 201511025987.3.

• Zhang Sihai, Qian Cen, Qin Xiaowei, Zhou Wuyang. A Dynamic Adjustment Method for Satellite Beam Coverage Based on Beam Traffic Volume. 201310626926.7.

• Zhang Sihai, Qian Cen, Qin Xiaowei, Zhou Wuyang. A Method for Modeling Opportunity Routing Behaviors Based on the Social Characteristics of Nodes in Mobile Social Networks. 201310626892.1.

• Fang Bin, Fan Juan, Zhang Sihai, Zhou Wuyang, Li Lei. An Access Control Method for the Integration of Cellular Networks and Wireless Local Area Networks. 201310134084.3.

• Fang Bin, Fan Juan, Zhang Sihai, Zhou Wuyang, Li Lei. A Distributed Vertical Handover and Resource Allocation Method. 201310133836.4.

• Yang Fei, Zhao Ming, Zhang Sihai, Zhou Wuyang. A Multi-Channel Blind Known Interference Cancellation Method. 201310010968.8.

• Liu Chang, Qin Xiaowei, Zhang Sihai, Zhou Wuyang. A User Fair Resource Allocation Method for Orthogonal Frequency Division Multiple Access Relay Systems. 201010266609.5.

• Wang Xufa, Cao Xianbin, Luo Wenjian, Ma Jianhui, Zhang Sihai. A Hierarchical Collaborative Method for Identifying Network Viruses and Malicious Code. 200310106551.8.

Wireless Big Data - Enlightenment for Operator Transformation
Yiping Yin, Sihai Zhang, Zhen Wang, People's Posts and Telecommunications Press, 1st Edition (October 2018)

Data Analysis at Work
Thomas Davenport (Author), Jeanne Harris (Author), Robert Morrison (Author), Translated by Yang Qi, Sihai Zhang, Zhejiang People's Publishing House, 1st Edition (March 1, 2018)

White Paper on Wireless Big Data and Smart 5G

Sihai Zhang et al., Future Mobile Communications Forum, 1st Edition (November 2017)

Computer Programming (C Language Edition)
Boqi Jia, Weibing Gu, Shihua Su, Sihai Zhang, Kedong He, China Machine Press, 1st Edition (July 2011)

AI-Driven 6G Wireless Intelligent Air Interface Transmission Technology

• Project Source: Ministry of Science and Technology

• Project Duration: October 2022 – October 2025
  Research Objective: Address the complex network environment of 6G by studying an efficient and ordered wireless access system based on network-native intelligence.

Theoretical Research, Architecture, and Methods for Native Green Communication Networking with Sensing-Communication-Computing Integration

• Project Source: Ministry of Science and Technology

• Project Duration: October 2022 – October 2026
  Research Objective: Reveal the energy consumption evolution laws of networking architectures and methods; study native green network architectures and intelligent and simplified resource scheduling technologies to achieve low-energy intelligent matching of energy, sensing-communication-computing resources, and personalized services.

Basic Theoretical Research on Low-Energy Personalized Federated Learning in Future Mobile Communication Systems

• Project Source: Anhui Provincial Natural Science Foundation

• Project Duration: January 2022 – December 2024
  Research Objective: Design low-energy federated learning schemes to reduce system communication power consumption; develop personalized federated learning schemes to alleviate user data heterogeneity issues.

Theoretical Research on New Federated Learning for Human-Computer-Things Integration

• Project Source: University of Science and Technology of China

• Project Duration: January 2022 – December 2024
  Research Objective: Study centerless federated learning theory based on dynamic consensus averaging; investigate user grouping federated learning theory with low network overhead.

OPC Intelligent Optimization

• Project Source: CXMT (CX Storage)

• Project Duration: June 2022 – June 2024
  Research Objective: Use machine learning methods to analyze SEM images generated during integrated circuit R&D and production, extract key process information such as contours and semantics, and improve production yield.

Huawei Wireless Enablement

• Project Source: Huawei Technologies

• Project Duration: July 2022 – July 2023
  Research Objective: Propose enablement coefficients based on energy-saving capabilities across industries, and complete verification and analysis; use big data statistical analysis methods to evaluate enablement coefficients for several key industries and conduct distributed carbon reduction 总量 (total volume) assessments that protect data privacy across parties.