About

Dr. Yan Jin is a Professor of Aerospace and Mechanical Engineering at the University of Southern California and serves as the Director of the USC IMPACT Laboratory. He received his doctoral degree in Naval Engineering from The University of Tokyo and completed postdoctoral research at Stanford University. His research encompasses AI/ML in design and manufacturing, design theory and methodology, multiagent and self-organizing systems, organization modeling, project management, and collaborative engineering. Prior to joining USC in the fall of 1996, he worked as a Senior Research Scientist at Stanford University and has also served as a Senior Engineer (adjunct) at RAND Corporation and a Guest Professor at Shanghai Jiaotong University. Dr. Jin's current research interests include systems engineering with a focus on AI/ML, design cognition and methods, and the study of complexity and complex systems. Throughout his career, he has received numerous awards, including the ASME DTM Award in 2025, NSF CAREER Award in 1998, and the Northrop Grumman Excellence in Teaching Award in 2001. He has held editorial roles in prominent journals such as AIEDAM, Design Science, and the Journal of Mechanical Design, and has served as program and conference chair for the ASME DTM Conference. Dr. Jin is a Fellow of ASME since 2010 and has been recognized for his contributions to engineering research and education.

Research topics

• Optoelectronics
• Materials science
• Computer Science
• Engineering
• Nanotechnology
• Internal medicine
• Computer hardware
• Endocrinology
• Medicine
• Chemistry
• Crystallography
• Electronic engineering
• Telecommunications

Selected publications

• A simulation-based design methodology for service business processes in uncertainty (Case study of IT support business processes to examine the validity of the methodology)

  Transactions of the JSME (in Japanese) · 2026-01-01

  articleOpen accessSenior author

  To realize the target business process in the assumed business environment, it is essential to have the ability to understand the process design elements and their settings that are effective in achieving the goal, and the ability to select the most appropriate one among multiple alternatives derived from the combinations of those design elements and settings. In service businesses such as IT support services and factory maintenance services, which provide intangible products such as actions, it is necessary to take into account the effects of two types of uncertainty: uncertainty caused by the external environment, which is the probabilistic generation of demands due to demand that is difficult to predict, and uncertainty caused by the internal environment, which is the generation of processing costs other than planned processing such as exceptions and communications for coordination that occur probabilistically in the processing process. Therefore, this study proposes a business process design methodology based on discrete event simulation through a case study of a business process in the IT department of one company that processes for both predictable and unpredictable demand. In the proposed design method, service business process design is classified into two categories, static structure design and operational guideline design, and Design Variables are selected from each category. By changing the settings of the selected Design Variables, various combinations of alternative processes were created, and process designs that satisfy the goals were identified through simulation predictions. The case study results showed that the proposed method can efficiently explore optimal business process designs by identifying Design Variables and their settings that are effective in achieving goals. The case study quantitatively showed the effect of a change in the method of selecting the next request to be processed on improving the reliability of the process.

  PublisherOA PDFDOI

• Why are you? Exploring patients’ behavior in selecting physicians in online health communities

  Information & Management · 2025-05-11 · 7 citations

  article
  PublisherDOI

• An effective method for prospective scheduling of tasks in cloud-fog computing with an energy consumption management approach based on Q-learning

  Engineering Applications of Artificial Intelligence · 2025-04-03 · 4 citations

  article1st authorCorresponding
  PublisherDOI

• Association between lactate dehydrogenase to albumin ratio and ICU mortality in patients with acute kidney injury: a retrospective cohort study

  Frontiers in Nephrology · 2025-06-02 · 1 citations

  articleOpen accessSenior author

  Background: Acute kidney injury (AKI) is a prevalent and severe medical condition that is frequently observed in the intensive care unit (ICU). Although numerous biomarkers have been identified to predict the prognosis of AKI, the lactate dehydrogenase to albumin ratio [LDH/ALB ratio (LAR)] has not been extensively investigated. The principal objective of this study was to assess the relationship between LAR and all-cause mortality in patients with AKI. Methods: A total of 6,831 AKI patients were included in this study, divided into survival (n = 5,152) and non-survival groups (n = 1,679). The association between LAR and mortality was examined through restricted cubic spline (RCS) analysis and Cox regression analysis. Subgroup analysis was used to search for interactive factors. Additionally, the prognostic capability of LAR was further evaluated using receiver operating characteristic (ROC) curve analysis. Results: for non-linearity < 0.001). A LAR of 10.4 was used as the cutoff point to generate the high-LAR and low-LAR subgroups, and the Kaplan-Meier curves revealed that the ICU cumulative survival rate for patients with AKI was significantly lower in the high-LAR group (log-rank p < 0.001). The LAR's prediction of ICU mortality in AKI patients yielded an area under the ROC curve of 0.65. Conclusion: Our research suggests that LAR monitoring may be promising as a prognostic marker among patients with AKI. Higher LAR is associated with greater ICU mortality.

  PublisherOA PDFDOI

• Natural fracture opening pressure in the ultra-deep reservoir considering friction resistance along the hydraulic fracture

  2025-06-08

  article

  ABSTRACT: In the process of hydraulic fracturing, hydraulic fractures can activate natural fractures and form a complex fracture network, but the opening of natural fractures needs to reach a certain threshold pressure (i.e., opening pressure). In ultra-deep reservoirs, the width of hydraulic fractures is small. If the flow friction of fracturing fluid in hydraulic fractures is ignored, the calculation of opening pressure will bring large errors. In this study, the opening pressure was calculated considering the combined effect of the friction along the hydraulic fractures and the local in-situ stress of the natural fracture. A mathematical model of natural fracture opening pressure considering the flow friction is proposed. Through the example calculation and analysis, it is found that the opening pressure of ultra-deep natural fractures is most affected by the width of hydraulic fractures, and due to the high stress difference, natural fractures are easier to be opened by shear slip. The longer the hydraulic fracture and the narrower its width, the greater the friction of the fracturing fluid along its path, which leads to a higher opening pressure for natural fractures. The high viscosity of the fracturing fluid and the large flow rate also increase the opening pressure of the natural fracture.

  PublisherDOI

• Taxonomic classification of 80 near-Earth asteroids

  Earth and Planetary Physics · 2025-06-22 · 1 citations

  articleOpen access

  The near-Earth objects are not only important for studying the early formation of the Solar System, but also pose a serious hazard to humanity since they can make close approaches to the Earth. The study of their physical properties can provide useful information on their origin, evolution and hazard to human being. However, it is still challenging to investigate the newly discovered small near-Earth objects because of their limited observational window. We aim to derive the visible colors of near-Earth asteroids and perform an initial taxonomic classification to analyze their relationship with size or orbital parameters. Observations were performed using the Yaoan High Precision Telescope and the 1.88m telescope at the Kottamia Astronomical Observatory in broadband BVRI Johnson-Cousins photometric system. We present new photometric observations for 84 near-earth asteroids, and taxonomical classification of 80 of them based on their photometric colors. Our results show that nearly half (46.3%) of the objects in our sample are classified as S-complex members, 26.3% as C-complex, 6% as D-complex and 15.0% as X-complex; the remaining belong to the A- or V-type. Additionally, we identified three P-type NEAs in our sample according to the Tholen scheme. The fractional abundances of the C/X-complex members with H ≥ 17.0 were more than twice as large as those with H < 17.0. However, the fractions of C- and S-complex members with D ≤ 1km and D > 1km remains nearly the same, while X-complex members tend to have sub-kilometer diameters. In our sample, the C/D-complex objects are predominant among those with a Jovian Tisserand parameter of TJ < 3.1. These bodies could have a cometary origin. C- and S-complex members account for a considerable proportion of potentially hazardous asteroids.

  PublisherOA PDFDOI

• Digital Representation and Mechanical Simulation of Rock Microstructures

  2025-06-08

  article

  ABSTRACT: The lack of well logging data and formation core samples in non-target complex intervals poses a challenge to traditional rock mechanics evaluation methods that rely on conducting laboratory experiments using core samples. In this study, we first characterize the microstructure of drilling cuttings and utilize image processing algorithms for denoising, boundary extraction, and boundary fitting of the microscopic images, achieving the digital representation of formation rocks. Finally, by assigning mechanical parameters to the digital model of formation rocks, the equivalent stress-strain curves of rocks are simulated using finite element analysis, enabling the rock mechanics evaluation of formation rocks based on drilling cuttings. The method established in this study overcomes the limitations of traditional rock mechanics evaluation methods that rely on formation core samples. It achieves the digital representation of formation rocks, enriches the methods for rock mechanics evaluation, and can serve as the basis for conducting research on engineering problems related to rock mechanics, such as formation fracturing, hydraulic fracturing, and wellbore stability, using digital twin technology.

  PublisherDOI

• Liquid Injected Seal to Reduce Leakage Flow in a Refrigerant Compressor

  2025-06-16

  articleSenior author

  Abstract The leakage flow through a traditional labyrinth seal reduces the compressor capacity of an oil-free magnetic bearing centrifugal compressor. Also, the super-heated leakage flow pollutes the downstream coolant flow, affecting motor cooling. A novel design is introduced to utilize the pressure loss across the seal by injecting liquid refrigerant near the seal inlet. The liquid-injected seal also functions as an expansion valve, producing low-temperature wet vapor at the seal exit. The wet vapor is projected to be utilized for motor cooling. A multiphase numerical simulation is performed to quantify the compressor performance of the liquid-injected seal and traditional seal under adiabatic conditions. The numerical simulation utilizes a Eulerian-Eulerian approach with an equilibrium phase change model. This study evaluates the compressor performance at three-speed lines: N1, N2, and N3. The base case results are validated with the experimental findings, with a maximum error of 3% in compressor efficiency. The local distribution of vapor mass fraction, pressure, and temperature are analyzed. The numerical results show that the leakage flow in the liquid-injected seal is reduced by 95%, and the compressor capacity is increased by 2.9%.

  PublisherDOI

• The Origin of Surface Energy of Calcite and Its Wettability

  Langmuir · 2025-12-22

  articleSenior authorCorresponding

  The microstructure and anisotropy of the solid–liquid interface hold significant importance in a wide range of fields, such as rock mechanics, mineral processing, and powder technology. Despite the prevalence of anisotropic properties in calcite, the underlying physical mechanisms remain poorly understood. Focusing on surface energy, we established a quantitative relationship for surface broken bonds density (Db) and interlayer spacing (d) on surface energy: γdry = 0.021Db – 1.036d + 0.77, which provided a novel approach to evaluating surface stability and reactivity of calcite. Examination of anisotropic surface properties revealed the (104) calcite surface as the most common cleavage surface owing to its lower surface energies, smaller Db, and larger d. Furthermore, the effects of water coverage and salinity on surface energy were explored, indicating a negative relationship between water coverage and surface energy of (104) calcite. The interaction of water with calcite was observed to affect surface energy, with water adsorption sites being occupied by salt ions. By incorporating contact angle measurements and charge transfer analyses, we elucidated the interaction mechanisms governing surface wettability and offered new insights into the adsorption behavior of water on calcite surfaces, which contributed to advancing the field of mineral surface science and the interaction processes at solid–liquid interfaces.

  PublisherDOI

• Designing Robotic Manipulation: Exploring Knowledge Transfer in CausalWorld

  Journal of Computing and Information Science in Engineering · 2025-04-17

  articleSenior author

  Abstract This study explores the design issues of a learning-based approach to solving a tri-finger robotic arm manipulating task, which requires complex movements and coordination among the fingers. We train an agent to acquire the necessary skills for proficient manipulation by employing reinforcement learning. To enhance the learning efficiency, effectiveness, and robustness, two knowledge transfer strategies, fine-tuning and curriculum learning, are utilized and compared within the soft actor-critic architecture. Fine-tuning allows the agent to leverage pre-trained knowledge and adapt it to new tasks. Several tasks and learning-related factors are investigated and evaluated, such as model versus policy transfer and within- versus across-task transfer. To eliminate the need for pretraining, curriculum learning decomposes the advanced task into simpler and progressive stages, mirroring how humans learn. The number of learning stages, the context of the subtasks, and the transition timing are examined as critical design parameters. The key design parameters of two learning strategies and their corresponding effects are explored in context-aware and context-unaware scenarios, allowing us to identify the scenarios where the methods demonstrate optimal performance, derive conclusive insights, and contribute to a broader range of learning-based engineering applications.

  PublisherDOI

Recent grants

• Collaborative Research: A Framework for Modeling and Measuring Collaborative Creativity in Early Stage Engineering Design Teams

  NSF · $217k · 2011–2015

• Collaborative Research: A Unified Cellular Self-Organizing Approach to Design Automation and Operation of Complex Systems

  NSF · $240k · 2012–2015

• EAGER: A DNA-Based, Cellar and Self-Organizing Approach to Adaptive System Development

  NSF · $75k · 2009–2011

Frequent coauthors

• Ashok K. Goel

  Georgia Institute of Technology

  1538 shared

• Amaresh Chakrabarti

  1538 shared

• Mary Lou Maher

  1538 shared

• Kristina Shea

  1408 shared

• Clive L. Dym

  Harvey Mudd College

  769 shared

• Harvey Mudd

  Indian Institute of Science Bangalore

  768 shared

• Kristina Shea

  ETH Zurich

  128 shared

• Kemper Lewis

  128 shared

Education

• Ph.D., Aerospace Engineering

  University of Southern California

  2005

• M.S., Aerospace Engineering

  University of Southern California

  2002

• B.S., Aerospace Engineering

  University of Southern California

  2000

Awards & honors

• ASME DTM Award (2025)
• NSF CAREER Award (1998)
• Northrop Grumman Excellence in Teaching Award (2001)
• Best Paper in Human Information Systems (5th World Multi-Con…
• ASME DTM Best Paper Awards (2021 & 2002)