Jian Tao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jian Tao has a total of 196 co-authors. Here are the top co-authors by number of shared publications:
- Fang Huang
School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, China
15 shared publications Xicheng Tan
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
5 shared publicationsLi Li
School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, China
4 shared publicationsNaoki Mizusawa
Kogakuin University,Tokyo,Japan
4 shared publicationsSaneyasu Yamaguchi
Kogakuin University,Tokyo,Japan
4 shared publications- Xicheng Tan
Wuhan University
4 shared publications
Latest Publications
- Open Access
- 27 July 2026
- Published by MDPI AG in AI in Medicine
- Vol. 1 (3) , 20
Data Stewardship Barriers to Building Digital Twin Technology for Precision Medicine
Digital twins (DTs) are dynamic, virtual representations of individual patients that could support predictive diagnostics and personalized therapeutic optimization. Their development depends on patient-level data from real-world data (RWD) sources and electronic medical record (EMR) data, but major barriers in data-stewardship, interoperability, provenance, and governance persist. This review examines critical bottlenecks within the current healthcare ecosystem, with particular attention to fragmented EMRs, limited longitudinal data continuity, and missing, incomplete, or inaccurate information. We address data availability, stewardship, and provenance rather than model construction itself. We also explore ethical imperatives of mitigating representational bias, where over-representation of European ancestry amplifies existing health inequalities. We evaluate blockchain technology as a decentralized trust anchor to ensure provenance, automate consent, and incentivize longitudinal data stewardship. In parallel, we acknowledge that clinically useful DTs also depend on substantial advances in model specification, calibration, and validation, especially for biologically complex diseases. By synthesizing computational, regulatory, and ethical challenges, we provide a roadmap for developing robust, equitable, and interoperable ecosystems for precision medicine.
- 27 July 2026
- Published by MDPI AG in AI in Medicine
- Vol. 1 (3) , 20
Open AccessData Stewardship Barriers to Building Digital Twin Technology for Precision Medicine
Digital twins (DTs) are dynamic, virtual representations of individual patients that could support predictive diagnostics and personalized therapeutic optimization. Their development depends on patient-level data from real-world data (RWD) sources and electronic medical record (EMR) data, but major barriers in data-stewardship, interoperability, provenance, and governance persist. This review examines critical bottlenecks within the current healthcare ecosystem, with particular attention to fragmented EMRs, limited longitudinal data continuity, and missing, incomplete, or inaccurate information. We address data availability, stewardship, and provenance rather than model construction itself. We also explore ethical imperatives of mitigating representational bias, where over-representation of European ancestry amplifies existing health inequalities. We evaluate blockchain technology as a decentralized trust anchor to ensure provenance, automate consent, and incentivize longitudinal data stewardship. In parallel, we acknowledge that clinically useful DTs also depend on substantial advances in model specification, calibration, and validation, especially for biologically complex diseases. By synthesizing computational, regulatory, and ethical challenges, we provide a roadmap for developing robust, equitable, and interoperable ecosystems for precision medicine.
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
From State Reconstruction to State Interpretation: S2VMO, an Agentic Voxel-Based Digital Twin for Space Habitat Structural Monitoring
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessFrom State Reconstruction to State Interpretation: S2VMO, an Agentic Voxel-Based Digital Twin for Space Habitat Structural Monitoring
- 20 April 2026
- Published by Taylor & Francis in Annals of the American Association of Geographers
- Vol. 116 (6) , 1-17
Sustainable Blue: A Participatory Spatial Decision Support System for Fishery Management
The global fishery market is widely recognized for its immense economic value and critical role in meeting human protein needs. According to the Food and Agriculture Organization of the United Nati...
- 20 April 2026
- Published by Taylor & Francis in Annals of the American Association of Geographers
- Vol. 116 (6) , 1-17
Sustainable Blue: A Participatory Spatial Decision Support System for Fishery Management
The global fishery market is widely recognized for its immense economic value and critical role in meeting human protein needs. According to the Food and Agriculture Organization of the United Nati...
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Machine Learning in Communications and Networking
- Vol. 4, 265-281
Signal Whisperers: Enhancing Wireless Reception Using DRL-Guided Reflector Arrays
This paper presents a multi-agent reinforcement learning (MARL) approach for controlling adjustable metallic reflector arrays to enhance wireless signal reception in non-line-of-sight (NLOS) scenarios. Unlike conventional reconfigurable intelligent surfaces (RIS) that require complex channel estimation, our system employs a centralized training with decentralized execution (CTDE) paradigm where individual agents corresponding to reflector segments autonomously optimize reflector element orientation in three-dimensional space using spatial intelligence based on user location information. Through extensive ray-tracing simulations with dynamic user mobility, the proposed multi-agent beam-focusing framework demonstrates substantial performance improvements over single-agent reinforcement learning baselines, while maintaining rapid adaptation to user movement within one simulation step. Comprehensive evaluation across varying user densities and reflector configurations validates system scalability and robustness. The results demonstrate the potential of learning-based approaches for adaptive wireless propagation control.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Machine Learning in Communications and Networking
- Vol. 4, 265-281
Open AccessSignal Whisperers: Enhancing Wireless Reception Using DRL-Guided Reflector Arrays
This paper presents a multi-agent reinforcement learning (MARL) approach for controlling adjustable metallic reflector arrays to enhance wireless signal reception in non-line-of-sight (NLOS) scenarios. Unlike conventional reconfigurable intelligent surfaces (RIS) that require complex channel estimation, our system employs a centralized training with decentralized execution (CTDE) paradigm where individual agents corresponding to reflector segments autonomously optimize reflector element orientation in three-dimensional space using spatial intelligence based on user location information. Through extensive ray-tracing simulations with dynamic user mobility, the proposed multi-agent beam-focusing framework demonstrates substantial performance improvements over single-agent reinforcement learning baselines, while maintaining rapid adaptation to user movement within one simulation step. Comprehensive evaluation across varying user densities and reflector configurations validates system scalability and robustness. The results demonstrate the potential of learning-based approaches for adaptive wireless propagation control.
- Open Access
- 21 November 2025
- Published by MDPI AG in Pharmacoepidemiology
- Vol. 4 (4) , 26
Idealized Framework for Assisting Pharmacovigilance Reporting in an Ambulatory Primary Care and Chronic Disease Management Clinic
Pharmacovigilance approaches have conventionally focused on the use of epidemiological data to detect emergent adverse drug reactions (ADRs). Recent advances in the use and availability of real-world data have expanded opportunities to detect ADR signals in medical records. We provide a limited review of pharmacovigilance practices and tools we have specifically considered implementing into our comprehensive medication management clinic and associated research programs. Use of pharmacogenomic variants has proven useful only on a limited scale as such data are reliant on low-dimensional approaches matching variants to drugs, often with small effect sizes. As such, most ADRs go unrecognized, undocumented, and unactionable. We posit that an idealized pharmacovigilance framework that relies on artificial-intelligence-assisted reporting with adjudication by pharmacovigilance experts and new models of ambulatory pharmaceutical practice would establish the following attributes: (1) all metadata relating to medication use would be available in the medical record in computable and interoperable data models, (2) digital surveillance tools would detect most ADR events with attributed pharmacological contributions, (3) all events would be characterized using standard adjudication rubrics, and (4) all events would iteratively inform an ADR knowledgebase and improve models to advance detection and prediction of ADR during the course of patient care with a focus on having the necessary tools for clinicians to prevent ADRs. This review provides a limited and focused framework for more systematic documentation of ADRs and tactics to mitigate the idiopathic nature of most ADRs.
- 21 November 2025
- Published by MDPI AG in Pharmacoepidemiology
- Vol. 4 (4) , 26
Open AccessIdealized Framework for Assisting Pharmacovigilance Reporting in an Ambulatory Primary Care and Chronic Disease Management Clinic
Pharmacovigilance approaches have conventionally focused on the use of epidemiological data to detect emergent adverse drug reactions (ADRs). Recent advances in the use and availability of real-world data have expanded opportunities to detect ADR signals in medical records. We provide a limited review of pharmacovigilance practices and tools we have specifically considered implementing into our comprehensive medication management clinic and associated research programs. Use of pharmacogenomic variants has proven useful only on a limited scale as such data are reliant on low-dimensional approaches matching variants to drugs, often with small effect sizes. As such, most ADRs go unrecognized, undocumented, and unactionable. We posit that an idealized pharmacovigilance framework that relies on artificial-intelligence-assisted reporting with adjudication by pharmacovigilance experts and new models of ambulatory pharmaceutical practice would establish the following attributes: (1) all metadata relating to medication use would be available in the medical record in computable and interoperable data models, (2) digital surveillance tools would detect most ADR events with attributed pharmacological contributions, (3) all events would be characterized using standard adjudication rubrics, and (4) all events would iteratively inform an ADR knowledgebase and improve models to advance detection and prediction of ADR during the course of patient care with a focus on having the necessary tools for clinicians to prevent ADRs. This review provides a limited and focused framework for more systematic documentation of ADRs and tactics to mitigate the idiopathic nature of most ADRs.
- 26 August 2025
- Published by Springer Nature
- p. 100-107
Dynamic Data-Driven Digital Twin Testbed for Enhanced First Responder Training and Communication
- 26 August 2025
- Published by Springer Nature
- p. 100-107
Dynamic Data-Driven Digital Twin Testbed for Enhanced First Responder Training and Communication
- Open Access
ThinkTank: A Framework for Generalizing Domain-Specific AI Agent Systems into Universal Collaborative Intelligence Platforms
This paper presents ThinkTank, a comprehensive and scalable framework designed to transform specialized AI agent systems into versatile collaborative intelligence platforms capable of supporting complex problem-solving across diverse domains. ThinkTank systematically generalizes agent roles, meeting structures, and knowledge integration mechanisms by adapting proven scientific collaboration methodologies. Through role abstraction, generalization of meeting types for iterative collaboration, and the integration of Retrieval-Augmented Generation with advanced knowledge storage, the framework facilitates expertise creation and robust knowledge sharing. ThinkTank enables organizations to leverage collaborative AI for knowledge-intensive tasks while ensuring data privacy and security through local deployment, utilizing frameworks like Ollama with models such as Llama3.1. The ThinkTank framework is designed to deliver significant advantages in cost-effectiveness, data security, scalability, and competitive positioning compared to cloud-based alternatives, establishing it as a universal platform for AI-driven collaborative problem-solving. The ThinkTank code is available at https://github.com/taugroup/ThinkTank
Open AccessThinkTank: A Framework for Generalizing Domain-Specific AI Agent Systems into Universal Collaborative Intelligence Platforms
This paper presents ThinkTank, a comprehensive and scalable framework designed to transform specialized AI agent systems into versatile collaborative intelligence platforms capable of supporting complex problem-solving across diverse domains. ThinkTank systematically generalizes agent roles, meeting structures, and knowledge integration mechanisms by adapting proven scientific collaboration methodologies. Through role abstraction, generalization of meeting types for iterative collaboration, and the integration of Retrieval-Augmented Generation with advanced knowledge storage, the framework facilitates expertise creation and robust knowledge sharing. ThinkTank enables organizations to leverage collaborative AI for knowledge-intensive tasks while ensuring data privacy and security through local deployment, utilizing frameworks like Ollama with models such as Llama3.1. The ThinkTank framework is designed to deliver significant advantages in cost-effectiveness, data security, scalability, and competitive positioning compared to cloud-based alternatives, establishing it as a universal platform for AI-driven collaborative problem-solving. The ThinkTank code is available at https://github.com/taugroup/ThinkTank
- Open Access
- 13 June 2024
- Published by Scifiniti Publishing in Computing&AI Connect
- Vol. 1 (1) , 1-10
Hierarchical Autoencoder-Based Lossy Compression for Large-Scale High-Resolution Scientific Data
Lossy compression has become an essential technique to reduce data size in many domains. This type of compression is especially valuable for large-scale scientific data, whose size ranges up to several petabytes. Although Autoencoder-based models have been successfully leveraged to compress images and videos, such neural networks have not widely gained attention in the scientific data domain. Our work presents a neural network that not only significantly compresses large-scale scientific data, but also maintains high reconstruction quality. The proposed model is tested with scientific benchmark data available publicly and applied to a large-scale high-resolution climate modeling data set. Our model achieves a compression ratio of 140 on several benchmark data sets without compromising the reconstruction quality. 2D simulation data from the High-Resolution Community Earth System Model (CESM) Version 1.3 over 500 years are also being compressed with a compression ratio of 200 while the reconstruction error is negligible for scientific analysis.
- 13 June 2024
- Published by Scifiniti Publishing in Computing&AI Connect
- Vol. 1 (1) , 1-10
Open AccessHierarchical Autoencoder-Based Lossy Compression for Large-Scale High-Resolution Scientific Data
Lossy compression has become an essential technique to reduce data size in many domains. This type of compression is especially valuable for large-scale scientific data, whose size ranges up to several petabytes. Although Autoencoder-based models have been successfully leveraged to compress images and videos, such neural networks have not widely gained attention in the scientific data domain. Our work presents a neural network that not only significantly compresses large-scale scientific data, but also maintains high reconstruction quality. The proposed model is tested with scientific benchmark data available publicly and applied to a large-scale high-resolution climate modeling data set. Our model achieves a compression ratio of 140 on several benchmark data sets without compromising the reconstruction quality. 2D simulation data from the High-Resolution Community Earth System Model (CESM) Version 1.3 over 500 years are also being compressed with a compression ratio of 200 while the reconstruction error is negligible for scientific analysis.
- Open Access
- 23 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 231-236
Porting AI/ML Models to Intelligence Processing Units (IPUs)
- 23 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 231-236
Open AccessPorting AI/ML Models to Intelligence Processing Units (IPUs)
- Open Access
- 11 July 2023
- Published by MDPI AG in Preprints.org
Technical Note: Using Computer Vision’s Pixel Segmentation to Detect Beef Cattle Feeding Behavior
There is a need for cost-effective and non-invasive methods of monitoring feeding behavior in livestock operations, considering the significant impact of feed costs on economic efficiency and assisting in detecting health issues of group-fed animals. This paper proposes using deep learning-based computer vision techniques to detect pen-fed beef cattle feeding behavior using Mask Region-based Convolutional Neural Network (RCNN). A deep learning model was pre-trained on the Common Objects in Context (COCO) dataset to generate cattle instance segmentation. Manually defined feed bunk polygons are compared with these segmentation masks to derive feeding time for each bunk. A full day’s worth of video data and the corresponding physical sensor data are collected for the experiment. By benchmarking the computer vision detected data with physical ground truth over random time segments from morning to evening (thus various lighting conditions), the optimal thresholds for Mask RCNN are determined to be 0.7 for bounding boxes and 0.1 for masks. Using these parameters. The reports suggest that the computer vision system achieved a precision of 87.2% and a recall of 89.1%, signifying precise detection of feeding events. Our study, to the best of our knowledge, was one of the first investigations of instance segmentation on feeding time sense, which combines deep learning methods with traditional computer vision logistics, reporting on feeding time data collection and processing, camera testing and adjustment, and performance evaluation. Future research directions include computer vision applied in feed grading and animal re-identification for individual production analysis.
- 11 July 2023
- Published by MDPI AG in Preprints.org
Open AccessTechnical Note: Using Computer Vision’s Pixel Segmentation to Detect Beef Cattle Feeding Behavior
There is a need for cost-effective and non-invasive methods of monitoring feeding behavior in livestock operations, considering the significant impact of feed costs on economic efficiency and assisting in detecting health issues of group-fed animals. This paper proposes using deep learning-based computer vision techniques to detect pen-fed beef cattle feeding behavior using Mask Region-based Convolutional Neural Network (RCNN). A deep learning model was pre-trained on the Common Objects in Context (COCO) dataset to generate cattle instance segmentation. Manually defined feed bunk polygons are compared with these segmentation masks to derive feeding time for each bunk. A full day’s worth of video data and the corresponding physical sensor data are collected for the experiment. By benchmarking the computer vision detected data with physical ground truth over random time segments from morning to evening (thus various lighting conditions), the optimal thresholds for Mask RCNN are determined to be 0.7 for bounding boxes and 0.1 for masks. Using these parameters. The reports suggest that the computer vision system achieved a precision of 87.2% and a recall of 89.1%, signifying precise detection of feeding events. Our study, to the best of our knowledge, was one of the first investigations of instance segmentation on feeding time sense, which combines deep learning methods with traditional computer vision logistics, reporting on feeding time data collection and processing, camera testing and adjustment, and performance evaluation. Future research directions include computer vision applied in feed grading and animal re-identification for individual production analysis.