About

Yin Li is an Associate Professor in the Department of Biostatistics and Medical Informatics at the University of Wisconsin–Madison. His research interests include computer vision and its applications in healthcare, as well as Mobile Health and wearable Computing. He is affiliated as a faculty member with the Department of Computer Sciences, the College of Letters and Science, and the Department of Data & Information Sciences at UW–Madison. His work focuses on leveraging computer vision techniques to improve healthcare outcomes and developing innovative solutions in Mobile Health and wearable technology to advance medical informatics.

Research topics

• Computer Science
• Artificial Intelligence
• Engineering
• Chemistry
• Surgery
• Physics
• Medicine
• Computer vision
• Electronic engineering
• Structural engineering
• Telecommunications
• Mechanical engineering
• Electrical engineering

Selected publications

• Application and Discussion of Airbag in Salvage

  Lecture notes in civil engineering · 2025-10-08 · 1 citations

  book-chapterOpen access

  The environment of wrecks and sunken objects in the sea is ever-changing, and the salvage methods are varied. Because of its unique performance and advantages, air bag has shown great potential and value in wrecks salvage and water transportation. Air bags have always been used as buoyancy AIDS in the field of salvage, usually tied to the two sides of the wreck or placed in the wreck cabin, and then combined with internal buoyancy or other large machinery to complete salvage. In some complex narrow waters, when large machinery cannot play a role, air bag buoyancy has become the best choice. This paper introduces the development and application scenarios of air bag salvage technology, summarizes the basic principle and technical characteristics of air bag salvage, and summarizes the key technologies of air bag salvage through the research of the construction technology of air bag salvage, and discusses the limitations and prospects of its application.

  PublisherOA PDFDOI

• Multi-time-scale carbon emission assessment and low-carbon scheduling optimization for energy-intensive enterprises

  AIP Advances · 2025-11-01 · 1 citations

  articleOpen access1st authorCorresponding

  Energy-intensive enterprises are major contributors to global carbon emissions and face dual pressures from time-of-use electricity pricing and dynamic carbon factors. This study develops a multi-time-scale low-carbon scheduling framework that integrates daily and weekly horizons within an improved multi-objective particle swarm optimization algorithm. The method combines constraint repair, Pareto archiving, and a weight-guided decision mechanism to ensure feasibility and balanced trade-offs between cost and emissions. Daily optimization enhances short-term responsiveness to fluctuating price and emission signals, while weekly optimization captures representative operating patterns and improves long-term stability. Time-series aggregation and clustering are employed to reduce computational complexity without compromising fidelity. Case studies on representative energy-intensive enterprises verify that the proposed framework consistently achieves effective cost-emission trade-offs, with enterprise-specific differences in sensitivity to optimization weights. The results demonstrate that the framework provides a practical and scalable tool for guiding energy-intensive industries toward sustainable and low-carbon operations under the dual-carbon strategy.

  PublisherDOI

• Design and Implementation of Permanent Magnet Synchronous Motor Drive System Based on Model Predictive Control

  2025-08-29

  article1st authorCorresponding

  High-performance permanent magnet synchronous motor (PMSM) drive systems impose stringent requirements on the real-time and accuracy of control strategies. Aiming at the shortcomings of traditional control methods in terms of dynamic performance and robustness, this study proposes a drive system design scheme based on model predictive control. By optimizing the weight configuration of the cost function and the selection of the prediction step size, the dynamic response characteristics of the system are significantly improved. The hardware implementation scheme based on DSP+FPGA dual-core architecture overcomes the problem of large computational volume of the predictive control algorithm. The experimental results verify the superior performance of the proposed control strategy under the working conditions of motor starting and sudden load change.

  PublisherDOI

• Quantifying Weather’s Share in Dynamic Grid Emission Factors via SHAP: A Multi-Timescale Attribution Framework

  Processes · 2025-10-23

  articleOpen access

  Accurately quantifying the impact of weather on dynamic grid carbon intensity is crucial for power system decarbonization. This study proposes a novel, interpretable machine learning framework integrating tree-based models with SHapley Additive exPlanations (SHAP) to quantify this impact across multiple timescales via a standardized “Weather Share” metric. Applied to city-level hourly data from China, the analysis reveals that meteorological variables collectively explain 21.64% of the hourly variation in carbon intensity, with air temperature and solar irradiance being the dominant drivers. Significant temporal variations are observed: the weather share is higher in summer (29.8%) and winter (23.5%) than in transition seasons and increases markedly to 32.7% during extreme high-temperature events. The proposed framework provides a robust, quantitative tool for grid operators, offering actionable insights for weather-aware carbon reduction strategies and highlighting critical time windows for targeted interventions.

  PublisherOA PDFDOI

• Correction: Carbon reduction analysis of power system based on carbon emission flow theory: a case study of Shenzhen power grid

  Discover Applied Sciences · 2025-09-04

  articleOpen access1st authorCorresponding
  PublisherOA PDFDOI

• Carbon reduction analysis of power system based on carbon emission flow theory: a case study of Shenzhen power grid

  Discover Applied Sciences · 2025-08-01 · 1 citations

  articleOpen access1st authorCorresponding

  As the largest contributor to carbon emissions in China’s industrial sector, the power industry accounts for over 40% of the nation’s total carbon emissions. Establishing an accurate carbon measurement system has become a critical prerequisite for achieving emission reduction targets in electricity systems. Current carbon measurement methodologies exhibit notable limitations, particularly in addressing the spatiotemporal heterogeneity of carbon emission factors. To address these challenges, this study proposes an integrated framework combining carbon emission flow theory with a low carbon demand response mechanism, accompanied by corresponding computational algorithms. Utilizing operational data from the Shenzhen power grid, we conducted a comprehensive empirical study featuring three key innovations. First, developing dynamic carbon accounting models reflecting temporal and spatial variations. Second, proposing demand-side management strategies for emission mitigation. Third, quantifying potential emission reductions through scenario simulations. The results demonstrate that the carbon emission flow methodology effectively captures the spatial-temporal disparities in carbon intensity across different districts and load periods within the Shenzhen power grid. Furthermore, the low carbon emission response mechanism is shown to offer operational guidance for grid decarbonization while quantifying emission reduction benefits. This research provides both methodological advancements and practical insights for implementing precision carbon management in urban power systems.

  PublisherOA PDFDOI

• An Improved Particle Swarm Optimization Algorithm for Automated Test Resource Allocation

  Journal of Physics Conference Series · 2024-03-01 · 1 citations

  articleOpen access

  Abstract With the rapid increase of software complexity, automated testing has become the mainstream of software testing. However, the current automated test tools adopt a large number of common test equipment resource. At the beginning of the test, for specific test scenarios, the testers need to plan the test equipment resources according to the requirements of the software under test. An automatic test equipment resource planning and optimization algorithm based on group optimization is proposed IPSO (Improved Particle Swarm Optimization) to solve this problem. This method maps the requirement description to the equipment description to obtain the matching matrix, and then establishes a multi-objective constrained optimization model for test equipment resource planning. The solution is obtained through improved particle swarm optimization algorithm to achieve the optimal planning of test equipment resources. Compared with traditional manual planning methods, this algorithm reduces the workload of testers, and improves the automation and efficiency of testing. Experimental results demonstrate that the optimal solutions found by the algorithm proposed in this paper is superior to those of the PSO (Particle Swarm Optimization)) and Linearly Decreasing Inertia Weight Particle Swarm Optimization (LWPSO) algorithms.

  PublisherOA PDFDOI

• Integrating Reinforcement Learning for Behavioral Analysis in Interconnected Electricity and Carbon Markets

  2024-12-13

  article

  The integration of electricity and carbon markets plays a crucial role in promoting renewable energy adoption and achieving global carbon reduction targets. However, the interconnection of these markets introduces significant challenges due to their inherent complexity and dynamic nature. This paper proposes a hybrid experimental learning framework, combining realworld experimentation and reinforcement learning-based generative models, to analyze participant behavior and market dynamics in coupled electricity and carbon markets.The framework simulates trading processes by modeling strategic bidding behaviors using a reinforcement learning approach, formulated as a Markov Decision Process (MDP). Leveraging both historical and experimental data, the model generates bidding strategies that adapt to market conditions while balancing economic and environmental objectives. A case study based on the Guangdong electricity market, incorporating modified IEEE 6-bus systems and realworld carbon trading scenarios, demonstrates the effectiveness of this approach in capturing market complexities and uncovering distinct behavioral patterns among participants. Results highlight the ability of reinforcement learning-based generative models to replicate human decision-making and optimize bidding strategies in interconnected markets. The findings provide insights into market behaviors, regulatory impacts, and potential strategies for improving efficiency and sustainability in the energy sector. This study underscores the value of hybrid experimental learning as a tool for exploring coupled market dynamics and guiding the transition to low-carbon energy systems.

  PublisherDOI

• Machine-Learning-Driven Lifecycle Carbon Footprint Assessment in Electric Vehicle Batteries

  2024-11-29

  articleSenior author

  In response to the European Union’s Carbon Border Adjustment Mechanism (CBAM), which mandates stringent carbon footprint standards for imported Electric Vehicle (EV) batteries, accurate and high-resolution carbon accounting across its lifecycle has become essential. This paper presents a Machine-Learning(ML)-driven methodology for comprehensive carbon footprint accounting designed to precisely capture emissions across material extraction, assembly, logistics, and recycling phases in EV battery production. By employing advanced machine learning techniques, our approach enhances the granularity and accuracy of emissions data, aligning with regulatory requirements and supporting sustainable practices in EV battery manufacturing. The model is validated through empirical analysis, demonstrating its capability to support compliance with evolving global carbon policies.

  PublisherDOI

• Interpretable Deep Learning for Strategic Behavior Analysis in Joint Electricity and Carbon Markets

  2024-11-29

  article

  The integration of carbon markets with the electricity sector represents a crucial development in aligning economic activities with environmental goals, particularly in China. Generation companies (GenCos) navigate these coupled markets through strategic bidding behaviors influenced by various carbon emission allowance (CEA) allocation methods. This study explores how different market conditions and regulatory policies shape GenCo bidding strategies, employing deep learning models like GAN to model these behaviors. To enhance interpretability, we utilize Local Interpretable Model-agnostic Explanations (LIME) and introduce a Bayesian extension (BayLIME), which leverages empirical data and prior knowledge for a more robust analysis. The results demonstrate significant correlations between operational features and strategic dimensions, providing insights that could aid in optimizing market performance and ensuring compliance. The application of BayLIME particularly enhances the reliability and consistency of model explanations, offering a clearer understanding of market dynamics for stakeholders. The findings contribute to both strategic planning and policy-making efforts aimed at fostering a sustainable energy market.

  PublisherDOI

Frequent coauthors

• Bulent Sarlioglu

  University of Wisconsin–Madison

  60 shared

• Dheeraj Bobba

  23 shared

• Ju Hyung Kim

  University of Wisconsin–Madison

  11 shared

• Hao Ding

  First Automotive Works (China)

  11 shared

• Mingda Liu

  Lucid Motors (United States)

  10 shared

• Silong Li

  University of Shanghai for Science and Technology

  10 shared

• Bocheng Chen

  Michigan State University

  9 shared

• Erik Schubert

  9 shared

Labs

• Yin Li's LabPI

  members of my group

Education

• Ph.D., Biostatistics

  University of Wisconsin-Madison

  2008

• M.S., Biostatistics

  University of Wisconsin-Madison

  2004

• B.S., Mathematics

  University of Wisconsin-Madison

  2002