2026
EyeFlow: A Self-Evolving Multi-Agent Framework for Knowledge-Grounded Ophthalmic Diagnosis
Bingjie YAN, Xiaolan CHEN, Mingguang HE, Danli SHI
11th Asia Pacific Tele-Ophthalmology Society (APTOS) Symposium 2026, Free Paper Abstract (2026)
EyeFlow coordinates specialized agents for ophthalmic diagnosis, combining image analysis, specialist debate, and knowledge retrieval. The APTOS free paper abstract reports evaluation on 169 semi-synthetic cases.
EyeFlow: A Self-Evolving Multi-Agent Framework for Knowledge-Grounded Ophthalmic Diagnosis
Bingjie YAN, Xiaolan CHEN, Mingguang HE, Danli SHI
11th Asia Pacific Tele-Ophthalmology Society (APTOS) Symposium 2026, Free Paper Abstract (2026)
EyeFlow coordinates specialized agents for ophthalmic diagnosis, combining image analysis, specialist debate, and knowledge retrieval. The APTOS free paper abstract reports evaluation on 169 semi-synthetic cases.
EyeWorld: A Generative World Model of Ocular State and Dynamics
Ziyu GAO, Xinyuan WU, Xiaolan CHEN, Zhuoran LIU, Ruoyu CHEN, Bowen LIU, Bingjie YAN, Zhenhan WANG, Kai JIN, Jiancheng YANG, Yih Chung THAM, Mingguang HE, Danli SHI
arXiv preprint, arXiv:2603.14039 (2026)
EyeWorld models the eye as a partially observed dynamic system. It learns a shared ocular state across imaging modalities and uses longitudinal data to model state changes, enabling cross-modal interpretation and forecasting of clinically relevant progression.
EyeWorld: A Generative World Model of Ocular State and Dynamics
Ziyu GAO, Xinyuan WU, Xiaolan CHEN, Zhuoran LIU, Ruoyu CHEN, Bowen LIU, Bingjie YAN, Zhenhan WANG, Kai JIN, Jiancheng YANG, Yih Chung THAM, Mingguang HE, Danli SHI
arXiv preprint, arXiv:2603.14039 (2026)
EyeWorld models the eye as a partially observed dynamic system. It learns a shared ocular state across imaging modalities and uses longitudinal data to model state changes, enabling cross-modal interpretation and forecasting of clinically relevant progression.
Empowering Locally Deployable Medical Agent via State Enhanced Logical Skills for FHIR-based Clinical Tasks
Wanrong YANG, Zhengliang LIU, Yuan LI, Bingjie YAN, Lingfang LI, Mingguang HE, Dominik WOJTCZAK, Yalin ZHENG, Danli SHI
arXiv preprint, arXiv:2603.06902 (2026)
This work introduces SELSM, a training-free memory framework that distills simulated clinical workflows into reusable, entity-agnostic skills. A query-anchored retrieval method uses those skills to guide locally deployable agents through FHIR-based electronic health record tasks.
Empowering Locally Deployable Medical Agent via State Enhanced Logical Skills for FHIR-based Clinical Tasks
Wanrong YANG, Zhengliang LIU, Yuan LI, Bingjie YAN, Lingfang LI, Mingguang HE, Dominik WOJTCZAK, Yalin ZHENG, Danli SHI
arXiv preprint, arXiv:2603.06902 (2026)
This work introduces SELSM, a training-free memory framework that distills simulated clinical workflows into reusable, entity-agnostic skills. A query-anchored retrieval method uses those skills to guide locally deployable agents through FHIR-based electronic health record tasks.
Benchmarking large multimodal models for ophthalmic visual question answering with OphthalWeChat
Pusheng XU, Xia GONG, Xiaolan CHEN, Weiyi ZHANG, Jiancheng YANG, Bingjie YAN, Meng YUAN, Yalin ZHENG, Mingguang HE, Danli SHI
Advances in Ophthalmology Practice and Research, 6(1), 33–41 (2026)
This study introduces OphthalWeChat, a bilingual visual question-answering benchmark built from real-world ophthalmic image posts. It contains 3,469 images and 30,120 question-answer pairs spanning nine ophthalmic subspecialties and supports evaluation of multimodal models in realistic eye-care scenarios.
Benchmarking large multimodal models for ophthalmic visual question answering with OphthalWeChat
Pusheng XU, Xia GONG, Xiaolan CHEN, Weiyi ZHANG, Jiancheng YANG, Bingjie YAN, Meng YUAN, Yalin ZHENG, Mingguang HE, Danli SHI
Advances in Ophthalmology Practice and Research, 6(1), 33–41 (2026)
This study introduces OphthalWeChat, a bilingual visual question-answering benchmark built from real-world ophthalmic image posts. It contains 3,469 images and 30,120 question-answer pairs spanning nine ophthalmic subspecialties and supports evaluation of multimodal models in realistic eye-care scenarios.
2025
From visual question answering to intelligent AI agents in ophthalmology
Xiaolan CHEN, Ruoyu CHEN, Pusheng XU, Xiaojie WAN, Weiyi ZHANG, Bingjie YAN, Xianwen SHANG, Mingguang HE, Danli SHI
British Journal of Ophthalmology, 110(1), 1–7 (2026)
This review traces the development of ophthalmic AI from visual question answering to multimodal agents for conversational and context-aware clinical support. It surveys recent approaches and discusses gaps in multimodal data, evaluation standards, and clinical integration.
From visual question answering to intelligent AI agents in ophthalmology
Xiaolan CHEN, Ruoyu CHEN, Pusheng XU, Xiaojie WAN, Weiyi ZHANG, Bingjie YAN, Xianwen SHANG, Mingguang HE, Danli SHI
British Journal of Ophthalmology, 110(1), 1–7 (2026)
This review traces the development of ophthalmic AI from visual question answering to multimodal agents for conversational and context-aware clinical support. It surveys recent approaches and discusses gaps in multimodal data, evaluation standards, and clinical integration.
Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application
Chuanpeng YANG, Yao ZHU, Wang LU, Yidong WANG, Qian CHEN, Chenlong GAO, Bingjie YAN, Yiqiang CHEN
ACM Transactions on Intelligent Systems and Technology, 16(6), Article 143 (2025)
This survey organizes knowledge distillation for large language models into white-box and black-box approaches, reviews how methods are evaluated and applied, and outlines open research directions for compressing models while retaining their capabilities.
Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application
Chuanpeng YANG, Yao ZHU, Wang LU, Yidong WANG, Qian CHEN, Chenlong GAO, Bingjie YAN, Yiqiang CHEN
ACM Transactions on Intelligent Systems and Technology, 16(6), Article 143 (2025)
This survey organizes knowledge distillation for large language models into white-box and black-box approaches, reviews how methods are evaluated and applied, and outlines open research directions for compressing models while retaining their capabilities.
EyeAgent: An Agentic AI System for Multimodal Clinical Decision Support in Ophthalmology
Danli SHI*, Xiaolan CHEN*, Bingjie YAN*, Weiyi ZHANG, Pusheng XU, Jiancheng YANG, Ruoyu CHEN, Siyu HUANG, Bowen LIU, Xinyuan WU, Meng XIE, Ziyu GAO, Yue WU, Senlin LIN, Kai JIN, Xia GONG, Yih Chung THAM, Xiujuan ZHANG, Li DONG, Yuzhou ZHANG, Jason YAM, Guangming JIN, Xiaohu DING, Haidong ZOU, Yalin ZHENG, Zongyuan GE, Mingguang HE (* equal contribution)
arXiv preprint, arXiv:2511.09394 (2025) Co-first author
EyeAgent uses a large language model to coordinate 53 ophthalmic tools across 23 imaging modalities for clinical decision support. The preprint evaluates the system through tool ablations, expert assessment, and a human–AI reader study.
EyeAgent: An Agentic AI System for Multimodal Clinical Decision Support in Ophthalmology
Danli SHI*, Xiaolan CHEN*, Bingjie YAN*, Weiyi ZHANG, Pusheng XU, Jiancheng YANG, Ruoyu CHEN, Siyu HUANG, Bowen LIU, Xinyuan WU, Meng XIE, Ziyu GAO, Yue WU, Senlin LIN, Kai JIN, Xia GONG, Yih Chung THAM, Xiujuan ZHANG, Li DONG, Yuzhou ZHANG, Jason YAM, Guangming JIN, Xiaohu DING, Haidong ZOU, Yalin ZHENG, Zongyuan GE, Mingguang HE (* equal contribution)
arXiv preprint, arXiv:2511.09394 (2025) Co-first author
EyeAgent uses a large language model to coordinate 53 ophthalmic tools across 23 imaging modalities for clinical decision support. The preprint evaluates the system through tool ablations, expert assessment, and a human–AI reader study.
FairFHTL: Achieving Task-Agnostic Fairness in Federated Hetero-Task Learning
Teng ZHANG, Yiqiang CHEN, Xinlong JIANG, Wuliang HUANG, Qian CHEN, Chenlong GAO, Zhirui WANG, Bingjie YAN
IEEE International Conference on Multimedia and Expo (ICME 2025), pp. 1–6 (2025)
This work addresses performance fairness when federated clients train heterogeneous tasks. FairFHTL combines task-independent shared representations with fair resource allocation to balance the global model's updates across tasks.
FairFHTL: Achieving Task-Agnostic Fairness in Federated Hetero-Task Learning
Teng ZHANG, Yiqiang CHEN, Xinlong JIANG, Wuliang HUANG, Qian CHEN, Chenlong GAO, Zhirui WANG, Bingjie YAN
IEEE International Conference on Multimedia and Expo (ICME 2025), pp. 1–6 (2025)
This work addresses performance fairness when federated clients train heterogeneous tasks. FairFHTL combines task-independent shared representations with fair resource allocation to balance the global model's updates across tasks.
Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks
Yang LIU, Bingjie YAN, Tianyuan ZOU, Jianqing ZHANG, Zixuan GU, Jianbing DING, Xidong WANG, Jingyi LI, Xiaozhou YE, Ye OUYANG, Qiang YANG, Ya-Qin ZHANG
arXiv preprint, arXiv:2504.17421 (2025)
This position paper examines how large and small language models can work together to adapt AI to private-domain tasks. It maps collaboration strategies and open challenges around privacy, model security, and resource constraints, and calls for benchmarks grounded in real-world applications.
Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks
Yang LIU, Bingjie YAN, Tianyuan ZOU, Jianqing ZHANG, Zixuan GU, Jianbing DING, Xidong WANG, Jingyi LI, Xiaozhou YE, Ye OUYANG, Qiang YANG, Ya-Qin ZHANG
arXiv preprint, arXiv:2504.17421 (2025)
This position paper examines how large and small language models can work together to adapt AI to private-domain tasks. It maps collaboration strategies and open challenges around privacy, model security, and resource constraints, and calls for benchmarks grounded in real-world applications.
Doubly-Bounded Queue for Constrained Online Learning: Keeping Pace with Dynamics of Both Loss and Constraint
Juncheng WANG, Bingjie YAN, Yituo LIU
Proceedings of the AAAI Conference on Artificial Intelligence, 39(20), 21135–21143 (2025)
This work studies online convex optimization with changing losses and constraints. It introduces COLDQ, a method that uses a bounded virtual queue to control hard constraint violations while providing dynamic-regret guarantees without requiring the Slater condition.
Doubly-Bounded Queue for Constrained Online Learning: Keeping Pace with Dynamics of Both Loss and Constraint
Juncheng WANG, Bingjie YAN, Yituo LIU
Proceedings of the AAAI Conference on Artificial Intelligence, 39(20), 21135–21143 (2025)
This work studies online convex optimization with changing losses and constraints. It introduces COLDQ, a method that uses a bounded virtual queue to control hard constraint violations while providing dynamic-regret guarantees without requiring the Slater condition.
2024
Buffalo: Biomedical Vision-Language Understanding with Cross-Modal Prototype and Federated Foundation Model Collaboration
Bingjie YAN, Qian CHEN, Yiqiang CHEN†, Xinlong JIANG, Wuliang HUANG, Bingyu WANG, Zhirui WANG, Chenlong GAO, Teng ZHANG († corresponding author )
ACM CIKM'24, CCF-B, CORE-A (Acceptance Rate: 22.7%) (2024) Oral
Buffalo addresses missing and heterogeneous modalities in collaborative biomedical learning with federated foundation models. Its cross-modal prototype imputation method improves downstream medical report generation and visual question answering without sharing raw client data.
Buffalo: Biomedical Vision-Language Understanding with Cross-Modal Prototype and Federated Foundation Model Collaboration
Bingjie YAN, Qian CHEN, Yiqiang CHEN†, Xinlong JIANG, Wuliang HUANG, Bingyu WANG, Zhirui WANG, Chenlong GAO, Teng ZHANG († corresponding author )
ACM CIKM'24, CCF-B, CORE-A (Acceptance Rate: 22.7%) (2024) Oral
Buffalo addresses missing and heterogeneous modalities in collaborative biomedical learning with federated foundation models. Its cross-modal prototype imputation method improves downstream medical report generation and visual question answering without sharing raw client data.
EyeGraphGPT: Knowledge Graph Enhanced Multimodal Large Language Model for Ophthalmic Report Generation
Zhirui WANG, Xinlong JIANG†, Chenlong GAO, Fan DONG, Weiwei DAI, Bingyu WANG, Bingjie YAN, Qian CHEN, Wuliang HUANG, Teng ZHANG, Yiqiang CHEN († corresponding author )
IEEE BIBM'24, CCF-B (2024) Oral
EyeGraphGPT combines a knowledge graph with a multimodal language model to generate ophthalmic reports from limited image-text data. It uses relation-aware visual alignment and instruction fine-tuning to handle specialized ophthalmic terminology.
EyeGraphGPT: Knowledge Graph Enhanced Multimodal Large Language Model for Ophthalmic Report Generation
Zhirui WANG, Xinlong JIANG†, Chenlong GAO, Fan DONG, Weiwei DAI, Bingyu WANG, Bingjie YAN, Qian CHEN, Wuliang HUANG, Teng ZHANG, Yiqiang CHEN († corresponding author )
IEEE BIBM'24, CCF-B (2024) Oral
EyeGraphGPT combines a knowledge graph with a multimodal language model to generate ophthalmic reports from limited image-text data. It uses relation-aware visual alignment and instruction fine-tuning to handle specialized ophthalmic terminology.
PrivFusion: Privacy-Preserving Model Fusion via Decentralized Federated Graph Matching
Qian CHEN, Yiqiang CHEN†, Xinlong JIANG, Weiwei DAI, Wuliang HUANG, Bingjie YAN, Zhen YAN, Lu WANG, Bo YE († corresponding author )
IEEE Transactions on Knowledge and Data Engineering (TKDE), CCF-A, CORE-A* (2024)
PrivFusion combines decentralized graph matching with local differential privacy to fuse models without additional training. A perturbation-filter adapter helps retain model utility while protecting activations and weights.
PrivFusion: Privacy-Preserving Model Fusion via Decentralized Federated Graph Matching
Qian CHEN, Yiqiang CHEN†, Xinlong JIANG, Weiwei DAI, Wuliang HUANG, Bingjie YAN, Zhen YAN, Lu WANG, Bo YE († corresponding author )
IEEE Transactions on Knowledge and Data Engineering (TKDE), CCF-A, CORE-A* (2024)
PrivFusion combines decentralized graph matching with local differential privacy to fuse models without additional training. A perturbation-filter adapter helps retain model utility while protecting activations and weights.
Im2col-Winograd: An Efficient and Flexible Fused-Winograd Convolution for NHWC Format on GPUs
Zhiyi ZHANG, Pengfei ZHANG, Zhuopin XU, Bingjie YAN, Qi WANG† († corresponding author )
ICPP'24, CCF-B (2024) Oral
Im2col-Winograd decomposes multidimensional convolution into 1D Winograd operations to accelerate NHWC-format convolution on GPUs with less workspace. The implementation supports filter widths 2–9 and reports speedups over cuDNN baselines.
Im2col-Winograd: An Efficient and Flexible Fused-Winograd Convolution for NHWC Format on GPUs
Zhiyi ZHANG, Pengfei ZHANG, Zhuopin XU, Bingjie YAN, Qi WANG† († corresponding author )
ICPP'24, CCF-B (2024) Oral
Im2col-Winograd decomposes multidimensional convolution into 1D Winograd operations to accelerate NHWC-format convolution on GPUs with less workspace. The implementation supports filter widths 2–9 and reports speedups over cuDNN baselines.
Correlation-Driven Multi-Modality Graph Decomposition for Cross-Subject Emotion Recognition
Wuliang HUANG, Yiqiang CHEN†, Xinlong JIANG, Chenlong GAO, Qian CHEN, Teng ZHANG, Bingjie YAN, Yifan WANG, Jianrong YANG († corresponding author )
ACM MM'24, CCF-A, CORE-A* (2024) Poster
CMMGD uses cross-modal correlation graphs and graph decomposition to learn subject-generalizable representations for physiological-signal emotion recognition. It reports improvements on the DEAP and MAHNOB-HCI datasets under leave-one-subject-out evaluation.
Correlation-Driven Multi-Modality Graph Decomposition for Cross-Subject Emotion Recognition
Wuliang HUANG, Yiqiang CHEN†, Xinlong JIANG, Chenlong GAO, Qian CHEN, Teng ZHANG, Bingjie YAN, Yifan WANG, Jianrong YANG († corresponding author )
ACM MM'24, CCF-A, CORE-A* (2024) Poster
CMMGD uses cross-modal correlation graphs and graph decomposition to learn subject-generalizable representations for physiological-signal emotion recognition. It reports improvements on the DEAP and MAHNOB-HCI datasets under leave-one-subject-out evaluation.
Model Trip: Enhancing Privacy and Fairness in Model Fusion across Multi-Federations for Trustworthy Global Healthcare
Qian CHEN, Yiqiang CHEN†, Bingjie YAN, Xinlong JIANG, Xiaojin ZHANG, Yan KANG, Teng ZHANG, Wuliang HUANG, Chenlong GAO, Lixin FAN, Qiang YANG († corresponding author )
ICDE'24, CCF-A (2024) Oral
This work introduces FairFusion, a cross-federation model-fusion method that optimizes utility, privacy, and fairness without additional training. Experiments on three healthcare datasets evaluate its performance across model structures and subgroups.
Model Trip: Enhancing Privacy and Fairness in Model Fusion across Multi-Federations for Trustworthy Global Healthcare
Qian CHEN, Yiqiang CHEN†, Bingjie YAN, Xinlong JIANG, Xiaojin ZHANG, Yan KANG, Teng ZHANG, Wuliang HUANG, Chenlong GAO, Lixin FAN, Qiang YANG († corresponding author )
ICDE'24, CCF-A (2024) Oral
This work introduces FairFusion, a cross-federation model-fusion method that optimizes utility, privacy, and fairness without additional training. Experiments on three healthcare datasets evaluate its performance across model structures and subgroups.
FedEYE: A Scalable and Flexible End-to-end Federated Learning Platform for Ophthalmology
Bingjie YAN*, Danmin CAO*, Xinlong JIANG, Yiqiang CHEN†, Weiwei DAI†, Fan DONG, Wuliang HUANG, Teng ZHANG, Chenlong GAO, Qian CHEN, Zhen YAN, Zhirui WANG (* equal contribution, † corresponding author )
Patterns, Cell Press, JCR-Q1, IF=6.7 (2024)
FedEYE is an end-to-end federated-learning platform that lets ophthalmologists create and deploy collaborative machine-learning projects without programming. It supports flexible deployment while keeping clinical data decentralized.
FedEYE: A Scalable and Flexible End-to-end Federated Learning Platform for Ophthalmology
Bingjie YAN*, Danmin CAO*, Xinlong JIANG, Yiqiang CHEN†, Weiwei DAI†, Fan DONG, Wuliang HUANG, Teng ZHANG, Chenlong GAO, Qian CHEN, Zhen YAN, Zhirui WANG (* equal contribution, † corresponding author )
Patterns, Cell Press, JCR-Q1, IF=6.7 (2024)
FedEYE is an end-to-end federated-learning platform that lets ophthalmologists create and deploy collaborative machine-learning projects without programming. It supports flexible deployment while keeping clinical data decentralized.
2023
UbiMeta: A Ubiquitous Operating System Model for Metaverse
Yiqiang CHEN†, Wuliang HUANG, Xinlong JIANG, Teng ZHANG, Yi WANG, Bingjie YAN, Zhirui WANG, Qian CHEN, Yunbing XING, Dong LI, Guodong LONG († corresponding author )
International Journal of Crowd Science (IJCS), (2023)
UbiMeta is a four-layer operating-system model for metaverse applications, designed to manage ubiquitous resources, process information with privacy safeguards, and provide AI capabilities. The paper discusses its use across healthcare, industry, education, and agriculture.
UbiMeta: A Ubiquitous Operating System Model for Metaverse
Yiqiang CHEN†, Wuliang HUANG, Xinlong JIANG, Teng ZHANG, Yi WANG, Bingjie YAN, Zhirui WANG, Qian CHEN, Yunbing XING, Dong LI, Guodong LONG († corresponding author )
International Journal of Crowd Science (IJCS), (2023)
UbiMeta is a four-layer operating-system model for metaverse applications, designed to manage ubiquitous resources, process information with privacy safeguards, and provide AI capabilities. The paper discusses its use across healthcare, industry, education, and agriculture.
AFL-CS: Asynchronous Federated Learning with Cosine Similarity-based Penalty Term and Aggregation
Bingjie YAN, Xinlong JIANG†, Yiqiang CHEN†, Chenlong GAO, Xuequn LIU († corresponding author )
IEEE ICPADS, CCF-C (2023) Oral
AFL-CS combines cosine-similarity-based layer penalties with asynchronous model aggregation to improve convergence in heterogeneous federated learning. Experiments show faster, more stable training, particularly with non-IID data.
AFL-CS: Asynchronous Federated Learning with Cosine Similarity-based Penalty Term and Aggregation
Bingjie YAN, Xinlong JIANG†, Yiqiang CHEN†, Chenlong GAO, Xuequn LIU († corresponding author )
IEEE ICPADS, CCF-C (2023) Oral
AFL-CS combines cosine-similarity-based layer penalties with asynchronous model aggregation to improve convergence in heterogeneous federated learning. Experiments show faster, more stable training, particularly with non-IID data.
FedTAM: Decentralized Federated Learning with a Feature Attention Based Multi-teacher Knowledge Distillation for Healthcare
Tingting MOU, Xinlong JIANG†, Jie LI, Bingjie YAN, Qian CHEN, Teng ZHANG, Wuliang HUANG, Chenlong GAO, Yiqiang CHEN († corresponding author )
IEEE ICPADS, CCF-C (2023) Oral
FedTAM uses cyclic model transfer and feature-attention-based multi-teacher distillation to train personalized models in decentralized federated learning with non-IID data. Experiments on healthcare and image benchmarks show gains over comparison methods.
FedTAM: Decentralized Federated Learning with a Feature Attention Based Multi-teacher Knowledge Distillation for Healthcare
Tingting MOU, Xinlong JIANG†, Jie LI, Bingjie YAN, Qian CHEN, Teng ZHANG, Wuliang HUANG, Chenlong GAO, Yiqiang CHEN († corresponding author )
IEEE ICPADS, CCF-C (2023) Oral
FedTAM uses cyclic model transfer and feature-attention-based multi-teacher distillation to train personalized models in decentralized federated learning with non-IID data. Experiments on healthcare and image benchmarks show gains over comparison methods.
2021
FedCM: A Real-time Contribution Measurement Method for Participants in Federated Learning
Bingjie YAN, Boyi LIU†, Lujia WANG, Yize ZHOU, Zhixuan LIANG, Ming LIU, Cheng-Zhong XU († corresponding author )
IJCNN, CCF-C (2021)
FedCM measures each participant's contribution during federated training by combining current- and previous-round signals, allowing per-round updates for fair credit and resource allocation. Experiments show that it reflects both data quantity and quality.
FedCM: A Real-time Contribution Measurement Method for Participants in Federated Learning
Bingjie YAN, Boyi LIU†, Lujia WANG, Yize ZHOU, Zhixuan LIANG, Ming LIU, Cheng-Zhong XU († corresponding author )
IJCNN, CCF-C (2021)
FedCM measures each participant's contribution during federated training by combining current- and previous-round signals, allowing per-round updates for fair credit and resource allocation. Experiments show that it reflects both data quantity and quality.
Experiments of Federated Learning for COVID-19 Chest X-ray Images
Bingjie YAN, Jun WANG, Jieren CHENG†, Yize ZHOU, Yixin ZHANG, Yifan YANG, Li LIU, Haojiang ZHAO, Chunjuan WANG, Boyi LIU († corresponding author )
ICAIS, EI (2021)
This study evaluates federated learning for COVID-19 detection from chest X-rays, comparing image classifiers while keeping hospital data local.
Experiments of Federated Learning for COVID-19 Chest X-ray Images
Bingjie YAN, Jun WANG, Jieren CHENG†, Yize ZHOU, Yixin ZHANG, Yifan YANG, Li LIU, Haojiang ZHAO, Chunjuan WANG, Boyi LIU († corresponding author )
ICAIS, EI (2021)
This study evaluates federated learning for COVID-19 detection from chest X-rays, comparing image classifiers while keeping hospital data local.
2020
An Improved Method for the Fitting and Prediction of the Number of COVID-19 Confirmed Cases Based on LSTM
Bingjie YAN, Jun WANG, Zhen ZHANG, Xiangyan TANG†, Yize ZHOU, Guopeng ZHENG, Qi ZOU, Yao LU, Boyi LIU, Wenxuan TU, Neal XIONG († corresponding author )
Computers, Materials and Continua, SCI (2020)
This paper presents an improved LSTM-based method for fitting and predicting confirmed COVID-19 case counts, and evaluates its forecasting performance on pandemic data.
An Improved Method for the Fitting and Prediction of the Number of COVID-19 Confirmed Cases Based on LSTM
Bingjie YAN, Jun WANG, Zhen ZHANG, Xiangyan TANG†, Yize ZHOU, Guopeng ZHENG, Qi ZOU, Yao LU, Boyi LIU, Wenxuan TU, Neal XIONG († corresponding author )
Computers, Materials and Continua, SCI (2020)
This paper presents an improved LSTM-based method for fitting and predicting confirmed COVID-19 case counts, and evaluates its forecasting performance on pandemic data.