Embedded Files
NCKU CPS Lab 成立於2011年8月，（原名為ISA Lab）。
由蔡佩璇教授帶領，實驗室成員約10~12位，包含碩博士及大學專題生。
CPSLAB 長期致力於發展 數位分身（Digital Twin）技術，著重於感測、建模與智能決策之深度整合，並應用於即時監控、模擬與最佳化。研究範疇涵蓋 個人健康照護、消防防災、智慧製造 等領域，強調高度可靠的資訊系統、AI 驅動建模、以及邊緣–雲端協同運算。
本實驗室的數位分身研究包含 理論方法、AI 模型創新、系統實作、與跨領域實證合作，並持續在實務場域（如醫療機構、消防單位、工廠）推展應用。
歡迎有興趣的同學們一起加入實驗室!
NCKU CPS Lab, (a.k.a ISA Lab), has been established since 2011 and led by Prof. Pei-Hsuan Tsai. There are about 10 to 12 members in the lab, including master students and Ph.D students.
CPSLAB focuses on advancing Digital Twin technologies that tightly integrate sensing, modeling, and intelligent decision-making to enable real-time monitoring, simulation, and optimization across multiple domains. Our research spans personal healthcare, fire safety, and smart manufacturing, with particular emphasis on high-reliability cyber-physical systems, AI-driven modeling, and edge–cloud computing.
Our contributions include theoretical frameworks, AI modeling innovations, and real-world deployments in collaboration with hospitals, fire departments, and industrial partners.
主要應用場域 Main Application Field
智慧醫院
Smart Hospital智慧消防
Smart Fire Protection智慧工廠
Smart factory智慧建築
Smart Building智慧城市
Smart City智慧交通
Smart Transportation
研究方向 Research Direction
路徑規劃演算法
Path Planning Algorithm基於影像之AI流程驗證
AI Video-based SOP Verification自動化消防逃生輔助系統
Automation of Fire Response System物件與動作辨識
AI Video-based Object and Action recognition定位與導航系統
Localization and Positioning System即時工作排程與分配
Real-time Job Scheduling and Dispatching資料融合與決策分析
Data Fusion and Decision Analysis感測器網路
Sensor Network
Digital Twin in Smart Healthcare Systems
Digital Twin in Smart Healthcare Systems
Research Mission
致力於建構生理與心理的數位分身。CPS Lab 發展具備臨床應用價值的機器學習技術，特別專注於解決醫療數據稀缺的難題，並透過個人化時序分析來優化醫療決策。
Engineering physiological and psychological digital twins. The CPS Lab develops clinically actionable machine learning frameworks, specializing in data-constrained environments and the optimization of clinical decision-making through personalized temporal analysis.
Our research spans
研究主題包含利用輕量化模型進行跨模態資料生成、心理狀態的量化建模，以及基於病患動態作息的智慧用藥排程演算法。
Our research encompasses cross-modal synthesis via lightweight architectures, quantitative modeling of psychological states, and algorithmic medication scheduling optimized for longitudinal patient routines.
Selected Publications
Ying-Chun Lin and Pei-Hsuan Tsai*, "A Multi-Objective Resource Allocation Strategy for Personal Healthcare Digital Twins in Dynamic Edge Environments", accepted and to be published in IEEE Internet of Things Journal. doi: 10.1109/JIOT.2025.3614647 [SCI, Q1, 11/258(COMPUTER SCIENCE, INFORMATION SYSTEMS)]
Pei-Hsuan Tsai*, J. W. S. Liu, "Intelligent Tools for Minimizing Medication Dispensing and Administration Errors," Foundations of Health Information Engineering and Systems, Lecture Notes in Computer Science, vol. 8315, January 2014.
Pei-Hsuan Tsai*, T. Y. Chen, C. Y. Yu, C. S. Shih and J. W. S. Liu, "Smart Medication Dispenser: Design, Architecture and Implementation," IEEE Systems Journal, Volume: 5, Issue: 1, March 2011. [SCI,Q1]
Pei-Hsuan Tsai*, C. S. Shih, J. W. S. Liu, "Algorithms for Scheduling Interactive Medications," Foundations of Computing and Decision Science, vol. 34, no. 4, 2009.
P. H. Tsai, C. S. Shih, and J. W. S. Liu, "Mobile Reminder for Flexible and Safe Medication Schedule for Home Users," Proc. of HCI International (HCII 2011), (July 9-14, 2011, Orlando, Florida, USA.
P. H. Tsai, C. Y. Yu, W. Y. Wang, J. K. Zao, H. C. Yeh, C. S. Shih, and J. W. S. Liu, "iMAT: Intelligent Medication Administration Tools," Proc. of IEEE Healthcom, (July 1-3, 2010, Lyon, France).
M. Y. Wang , P. H. Tsai, J. K. Zao, and J. W. S. Liu, "Smart Phone Based Medicine In-take Scheduler, Reminder and Monitor," Proc. of IEEE HealthCom, (July 1-3, 2010, Lyon, France).
P. H. Tsai, Y. T. Chuang, T. S. Chou, C. S. Shih and J. W. S. Liu, "iNuC: An Intelligent Mobile Medication Cart," Proc. of the 2nd International Conference on Biomedical Engineering and Informatics (BMEI 2009), (October 17-19, 2009, Tianjin, China).
M. Y. Wang, J. K. Zao, P. H. Tsai, and J. W. S. Liu, "Wedjat: A Mobile Phone Based Medication Reminder and Monitor," Proc. of the 9th IEEE International Conference on Bioinformatics and Bioengineering (BIBE 2009), IEEE CS Press, (June 22-24, 2009, Taichung, Taiwan).
T. Y. Chen, P. H. Tsai, T. S. Chou, C. S. Shih, T. W. Kuo, and J. W. S. Liu, "Component Model and Architecture of Smart Devices for the Elderly," Proc. of the 7th Working IEEE/IFIP Conference on Software Architecture (WICSA 2008), pp. 51–60, (February 18-21, 2008, Vancouver, BC, Canada). (Oral, Acceptance rate 26%)
J. W. S. Liu, C. S. Shih, P. H. Tsai, H. C. Yeh, P. C. Hsiu, C. Y. Yu, and W. H. Chang, "End-User Support for Error Free Medication Process," Proc. of High-Confidence Medication Device Software and Systems and Universal Plug-and-Play Workshop (HCMDSS/MD PnP 2007), pp. 34-45, (June 25-27, 2007, Cambridge, Massachusetts).
P. H. Tsai, H. C. Yeh, C. Y. Yu, P. C. Hsiu, C. S. Shih and J. W. S. Liu, "Compliance Enforcement of Temporal and Dosage Constraints," Proc. of the 27th IEEE Real-Time Systems Symposium (RTSS 2006), pp. 359-368, (December 5-8, 2006, Rio de Janerio, Brazil). (Oral, Acceptance rate 21%, Top Conference)
H. C. Yeh, P. C. Hsiu, C. S. Shih, P. H. Tsai and J. W. S. Liu, "APAMAT: A Prescription Algebra for Medication Authoring Tool," Proc. of IEEE International Conference on Systems, Man and Cybernetics (SMC 2006), vol. 5, pp. 4284-4291, (Octobert 8-11, 2006, Taipei, Taiwan).
Digital Twin for Disaster Prevention and Response
Digital Twin for Disaster Prevention and Response
Research Mission
專注於極端環境下的動態模擬與人機協作。CPS Lab 結合物理建模與演算法，目標為提升災難現場的場景感知能力，並透過計算智能保障人類與自動化設備在危急時刻的安全。
Advancing dynamic simulation and human-robot collaboration (HRC) in extreme environments. The CPS Lab integrates physics-informed modeling with algorithmic frameworks to augment situational awareness in disaster scenarios, leveraging computational intelligence to ensure the safety of human-agent collectives during mission-critical operations.
Our research spans
研究主題包含室內火災的即時預測與視覺化、災難現場的環境建模，以及人類與機器設備的協同路徑規劃，開發能即時避開動態危險區域的最佳化救援策略。
Our work encompasses real-time indoor fire forecasting and visualization, environmental reconstruction for disaster response, and collaborative path planning for human-machine teams, specializing in optimized rescue strategies for dynamic hazard avoidance.
Selected Publications
Guan-Rong Shih and Pei-Hsuan Tsai*, "A Self-Evacuation Approach For Robots in Fire Disasters", IEEE Systems Journal, volume 18, issue 1, page 392-402, March 2024. [SCI, Q1, 64/258(COMPUTER SCIENCE, INFORMATION SYSTEMS)]
Zheng-Ting Lin and Pei-Hsuan Tsai*, "A Method to Accelerate the Rescue of Fire-stricken Victims", Expert Systems With Applications, volume 238, Part E, 15 March 2024, 122186. [SCI, Q1, 28/204(COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE)]
Guan-Rong Shih and Pei-Hsuan Tsai*, "Safest-path Planning Approach for Indoor Fire Evacuation", International Journal of Disaster Risk Reduction, Volume 93, July 2023, 103760 . [SCI,Q1, 38/258 (GEOSCIENCES, MULTIDISCIPLINARY)]
A.F. Lee and Pei-Hsuan Tsai*, "Online Indoor Fire Evacuation System", IEEE Systems Journal, Page: 3584 - 3592, Volume:17, Issue: 3, September 2023. [SCI,Q1,62/250 (COMPUTER SCIENCE, INFORMATION SYSTEMS)]
Guan-Rong Shih and Pei-Hsuan Tsai*, "A Resource-saving Shelter Selection Approach for Large-scale Area Emergency", IEEE Systems Journal, Page: 2836 - 2846, Volume: 17, Issue: 2, June 2023. [SCI,Q1, 62/250 (COMPUTER SCIENCE, INFORMATION SYSTEMS)]
Rong-Guei Tsai, Pei-Hsuan Tsai*, Guan-Rong Shih, Jingxuan Tu. “RPL based Emergency Routing Protocol for Smart Buildings”. IEEE Access, vol. 10, pp. 18445-18455, 2022. [SCI, Q2]
Rong-Guei Tsai, Yi-Yuan Tsai, Pei-Hsuan Tsai*, "Automation Tool for Home Fire Safety Check". IEEE Sensors Letters, Volume: 5, Issue: 12, December 2021. [SCI]
Pei-Hsuan Tsai*, R.G. Tsai, S.S. Wang, "Hybrid Localization Approach for Underwater Sensor Networks," Journal of Sensors, vol. 2017, Article ID 5768651, 13 pages, 2017. [SCI]
Pei-Hsuan Tsai*, C. L. Lin, J. N. Liu, "On-the-Fly Nearest-Shelter Computation in Event-Dependent Spatial Networks in Disaster," IEEE Transactions on Vehicular Technology, vol. 65, no. 3, pp. 1109-1120, March 2016. [SCI,Q1]
E. T. H. Chu, C. Y. Lin, Pei-Hsuan Tsai*, J. W. S. Liu, "Design and Implementation of Participant Selection for Crowdsourcing Disaster Information," International Journal on Safety and Security Engineering, WIT Press, vol. 5, no. 1, pp. 48-62, March 2015.
Pei-Hsuan Tsai*, Y. C. Lin, Y. Z. Ou, E. T. H. Chu, J. W. S. Liu, "A Framework for Fusion of Human Sensor and Physical Sensor Data," IEEE Transactions on Systems Man and Cybernetics: Systems, vol. 44, no. 9, pp. 1248-1261, September 2014. [SCI,Q1]
C. Y. Lin, E. T. H. Chu, Pei-Hsuan Tsai*, J. W. S. Liu, "Participant Selection for Crowdsourcing Disaster Information," WIT Transactions on the Built Environment, vol. 133, pp. 205-215, July 2013.
Digital Twin for Smart Manufacturing & Industrial Systems
Digital Twin for Smart Manufacturing & Industrial Systems
Research Mission
聚焦於建構能驅動工業 4.0 的適應性人機系統。CPS Lab 探討電腦視覺、物聯網與人類行為之間的連結，開發能理解人類動作並優化生產效率的智慧演算法，推動製造流程的自動化與標準化。
Engineering adaptive human-machine systems for Industry 4.0. The CPS Lab investigates the integration of computer vision, the Internet of Things (IoT), and human behavioral analysis to develop algorithms that interpret human actions, optimize operational efficiency, and advance the standardization of automated manufacturing workflows.
Our research spans
研究範疇涵蓋利用骨架辨識進行操作合規性評估、設計能依據組裝狀態動態調整的自適應教學系統，以及結合排程建模與工業物聯網數據，進行動態產線排程與生產資源的全局最佳化。
Our research spans skeletal-based operational compliance assessment, context-aware adaptive instructional systems for manual assembly, and the global optimization of production resources through dynamic scheduling integrated with Industrial IoT (IIoT) analytics.
Selected Publications
Fang-Yu Lin and Pei-Hsuan Tsai*, "A State-Diagram-Based Modeling Approach for Assembly Instructions", accepted and to be published in Journal of Information Science and Engineering. [SCI]
Guan-Rong Shih and Pei-Hsuan Tsai*, "A Self-Evacuation Approach For Robots in Fire Disasters", IEEE Systems Journal, volume 18, issue 1, page 392-402, March 2024. [SCI, Q1, 64/258(COMPUTER SCIENCE, INFORMATION SYSTEMS)]
Junbin Zhang, Pei-Hsuan Tsai* and Meng-Hsun Tsai, "Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos", Applied Intelligence, volume 54, page 2084-2099, 29 January 2024. [SCI, Q2, 84/204(COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE)]
S. H. Peng and Pei-Hsuan Tsai*, "An Efficient Graph Convolution Network for Skeleton-Based Dynamic Hand Gesture Recognition", IEEE Transactions on Cognitive and Developmental Systems, Page: 2179 - 2189, Volumn:15, Issue:4, December 2023. doi: 10.1109/TCDS.2023.3242988 [SCI, Q1, 45/197 (COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE)]
Rong-Guei Tsai, Xiaoyan Lv, Lin Shen, Pei-Hsuan Tsai*. 2022. "A High-Robust Sensor Activity Control Algorithm for Wireless Sensor Networks". Sensors, 22(5):2020, 2022. [SCI, Q2]
Pei-Hsuan Tsai*, Junbin Zhang, Meng-Hsun Tsai*. "An Efficient Probe-Based Routing for Content-Centric Networking". Sensors, 22(1):341, 2022. [SCI, Q2]
Pei-Hsuan Tsai*, G.R. Shih, W.D. Cheng and R.G. Tsai, "Σ-Scan: A Mobile Beacon-Assisted Localization Path-Planning Algorithm for Wireless Sensor Networks," IEEE Sensors Journal. Volume: 19, Issue: 23, 01 December 2019. [SCI,Q1]
R. G. Tsai, Pei-Hsuan Tsai*, "An Obstacle-Tolerant Path Planning Algorithm for Mobile-Anchor-Node-Assisted Localization," Sensors, 18(3), 2018. [SCI, Q2]
Pei-Hsuan Tsai*, "Building Coordinate System of Sensor Nodes Using Self-configurable Grid-based Approach," Journal of Information Science and Engineering, vol. 34 No. 2, pp. 451-468, Mar. 2018. [SCI]
Pei-Hsuan Tsai*, R.G. Tsai, S.S. Wang, "Hybrid Localization Approach for Underwater Sensor Networks," Journal of Sensors, vol. 2017, Article ID 5768651, 13 pages, 2017. [SCI]
Pei-Hsuan Tsai*, R.G. Tsai, J.F. Liaw, "Improvement in Human Error by Target Predication In TCP/IP-based Remote Control System," Advances in Mechanical Engineering, vol. 9, issue 10, Oct. 2017 [SCI]
Pei-Hsuan Tsai*, C. L. Lin, J. S. Wang, "Power saving algorithm for monitoring extreme values in sensor networks," Sensors & Transducers Journal, vol. 18, special issue, January 2013.
國際連結與校外合作
國際連結與校外合作
CPS Lab 同時和台灣大學資工系特聘教授張原豪博士、中央研究院資創中心研究員修丕承博士（資訊科技創新研究中心）合作，進入本實驗室的研究所新生在研究主題的選擇上，也能加入兩位研究員老師的研究主題。
國際連結方面:CPS Lab目前與美國伊利諾大學香檳分校 Computer Science CPS lab led by Professor Lui Sha，共同研究有關Medical Guidance System，有興趣的同學歡迎加入!
★ 張原豪博士（資訊科學研究所）
隨手雜記： 豪豪老實說
研究領域：非揮發性記憶體、記憶/儲存系統、作業系統、即時系統、嵌入式系統、電腦系統
研究簡介（節錄）:
My research area is mainly on computer systems and embedded systems, with a prime focus on improving the capability of memory and storage systems. The research results were published in top conferences (e.g., ACM/IEEE DAC, ACM/IEEE ICCAD, and ACM/IEEE CODES) and top journals (e.g., IEEE TC, IEEE TCAD, IEEE TVLSI, ACM TECS, ACM TODAES, and ACM TOS).
★ 修丕承博士（資訊科技創新研究中心）
實驗室網站： 嵌入式暨行動運算實驗室
研究領域：嵌入式系統 (Embedded Systems), 間歇性運算 (Intermittent Computing), 微型深度學習 (TinyML)
研究簡介：
Dr. Hsiu’s research goal is to realize Intermittent Artificial of Things (iAIoT), enabling battery-less IoT devices to intermittently execute deep neural networks (DNN) via ambient power. iAIoT is a novel research direction at the intersection of intermittent computing and deep learning. He has led a research team to release a suite of system runtime and libraries, facilitating AI and IoT application developers to easily build low cost, intermittent-aware inference systems. In particular, an intermittent operating system (TCAD’20), which was the first attempt to allow multitasking and task concurrency on intermittent systems, makes complicated intermittent applications increasingly possible. The HAWAII middleware (TCAD’20), which comprises an inference engine and API library, enables hardware accelerated intermittent DNN inference, while the iNAS framework (TECS’21) was the first framework that introduces intermittent execution behavior into neural architecture search to automatically find intermittently-executable DNN models. A solar-powered image classification system was developed with our intermittent system runtime and inference library as an example: https://youtu.be/n6lEAjmn0Ng .
Page updated
Google Sites
Report abuse