Srijita Das

By |

My research is about building sample-efficient machine learning models. My long term goal is to develop collaborative systems that can actively seek advice from humans and make faster decisions, resulting in reliable and practical systems. I specifically focus on design of sequential decision-making models to make them learn faster. We leverage advice from humans in various forms (implicit and explicit) to encourage favorable decisions and avoid decisions having catastrophic consequences. We also focus on minimizing the cost of seeking advice by building suitable machine learning models from historical advice data and reusing them when required. Our research also develops ways to solve complex tasks in Reinforcement Learning by leveraging various kinds of knowledge transfer mechanisms, curriculum learning, teacher-student framework etc. Advances in these directions would make decision-making models sample-efficient and better suited for solving real-world problems. Along the supervised machine learning spectrum, we also focus on problems related to learning with less data, traditionally known as Active Learning, semi-supervised learning, and learning from multiple experts.

Mohamed Abouelenien

By |

Mohamed Abouelenien’s areas of interest broadly cover data science topics, including applied machine learning, computer vision, and natural language processing. He established the Affective Computing and Multimodal Systems Lab (ACMS) which focuses on modeling human behavior and developing multimodal approaches for different applications. He has worked on a number of projects in these areas, including multimodal deception detection, multimodal sensing of drivers’ alertness levels and thermal discomfort, distraction detection, circadian rhythm modeling, emotion and stress analysis, automated scoring of students’ progression, sentiment analysis, ensemble learning, and image processing, among others. His research is funded by Ford Motor Company (Ford), Educational Testing Service (ETS), Toyota Research institute (TRI), and Procter & Gamble (P&G). Abouelenien has published in several top venues in IEEE, ACM, Springer, and SPIE. He also served as a reviewer for IEEE transactions and Elsevier journals and served as a program committee member for multiple international conferences.

VAN HAI BUI

Van Hai Bui

By |

Dr. Bui’s research focuses on the operation and control of power and energy systems. We develop energy management systems aimed at optimizing the entire system’s operation to minimize operation costs, enhance system reliability, and improve system resiliency in both normal and emergency operation modes. Recently, the high penetration of distributed energy resources (DERs), including photovoltaics, wind turbines, and controllable distributed generators, in modern power systems has introduced numerous sources of uncertainty, making the operation and control of power systems significantly challenging. Conventional optimization methods often struggle to handle the high uncertainty of DER outputs. With the rapid development of AI/ML algorithms and their wide applications in the engineering domain, these techniques offer potential solutions for operating and controlling power systems. Our research group also investigates the state-of-the-art models in ML, such as deep learning, deep reinforcement learning, and physics-informed graph neural networks, and their applications in power and energy systems.

Tian An Wong

By |

Analysis of policing technology and police data, including impact assessment of surveillance technology, media sentiment analysis, and fatal police violence. Methods include topological data analysis, natural language processing, multivariate time series analysis, difference-in-differences, and complex networks.

 


Research Highlights

Picture of Besa Xhabija

Besa Xhabija

By |

Dr. Xhabija joined the Department of Natural Sciences in September 2022 as an Assistant Professor of Biochemistry. Her laboratory aims to understand the effects of toxins on early embryonic development utilizing embryonic stem cells because they provide a new tool and opportunity to investigate the impact of environmental exposures and their interactions with genetic factors on human development and health. To fully realize these potentials, she believes that it is important to understand the molecular basis of the defining characteristic of the stem cells. More specifically, she is interested in investigating how stem cells play a role in shaping the expression program during development and how mechanisms of self-renewal and differentiation during mammalian development regulate cellular fate decisions.

Feng Zhou

By |

For human-machine systems, I first collect data from human users, whether it’s an individual, a team, or even a society. Different kinds of methods can be used, including self-report, interview, focus groups, physiological and behavioral data, as well as user-generated data from the Internet.

Based on the data collected, I attempt to understand human contexts, including different aspects of the human users, such as emotion, cognition, needs, preferences, locations and activities. Such understanding can then be applied to different human-machine systems, including healthcare systems, automated driving systems, and product-service systems.

Based on the different design theory and methodology, from the perspective of the machine dimension, I apply knowledge of computing and communication as well as practical and theoretical knowledge of social and behavior to design various systems for human users. From the human dimension, I seek to understand human needs and decision making processes, and then build mathematical models and design tools that facilitate integration of subjective experiences, social contexts, and engineering principles into the design process of human-machine systems.

Zhixin (Jason) Liu

By |

My research focuses on quantitative modeling approaches that help business or nonprofit institutions make efficient operational decisions. My research addresses decisions that are made: 1) on either a single independent operation or multiple integrated operations, and 2) by either a single party or multiple parties, most likely different supply chain members. I am specifically interested in the allocation of resources over time and/or among different parties, which often involve scheduling, i.e., the allocation of resources over time to optimize certain objectives, capacity allocation, i.e., the allocation of production capacity from supplier to retailers in a supply chain setting, and pricing, i.e., the determination of selling price of certain products. When multiple parties are involved, decisions can be made either cooperatively or non-cooperatively. The methodologies used in my work include game theory, real analysis, optimization, approximation, simulation, and statistics.

Jaerock Kwon

By |

My research interests are in the areas of brain-inspired machine intelligence and its applications such as mobile robots and autonomous vehicles. To achieve true machine intelligence, I have taken two different approaches: bottom-up data-driven and top-down theory-driven approach. For the bottom-up data-driven approach, I have investigated the neuronal structure of the brain to understand its function. The development of a high-throughput and high-resolution 3D tissue scanner was a keystone of this approach. This tissue scanner has a 3D virtual microscope that allows us to investigate the neuronal structure of a whole mammalian brain in a high resolution. The top-down theory-driven approach is to study what true machine intelligence is and how it can be implemented. True intelligence cannot be investigated without embracing the theory-driven approach such as self-awareness, embodiment, consciousness, and computational modeling. I have studied the internal dynamics of a neural system to investigate the self-awareness of a machine and model neural signal delay compensation. These two meet in the middle where machine intelligence is implemented for mechanical systems such as mobile robots and autonomous vehicles. I have a strong desire to bridge the bottom-up and top-down approaches that lead me to conduct research focusing on mobile robotics and autonomous vehicles to combine the data-driven and theory-driven approaches.

9.9.2020 MIDAS Faculty Research Pitch Video.

High-Throughput and High-Resolution Tissue Scanner – NSF Funded

Niccolò Meneghetti

Niccolò Meneghetti

By |

Dr. Niccolò Meneghetti is an Assistant Professor of Computer and Information Science at the University of Michigan-Dearborn.
His major research interests are in the broad area of database systems, with primary focus on probabilistic databases, statistical relational learning and uncertain data management.

Lei Chen

Lei Chen

By |

Lei Chen’s group focus on applying data science tools to advanced manufacturing. Chen’s research expertise and interests are to integrate the physics-based computational and experimental methods and data-driven approaches, to exploit the fundamental phenomena emerged in advanced manufacturing and to establish the design protocol for optimizing the materials and process parameters of as-fabricated parts for quality control. Current research can be summarized by:
1 One of significant challenges in additive manufacturing (AM) is the presence of heterogeneous sources of uncertainty involved in the complex layer-wise processes under non-equilibrium conditions that lead to variability in the microstructure and properties of as-built components. Consequently, it is extremely challenging to repeat the manufacturing of a high-quality product in mass production, and current practice usually reverts to trial-and-error techniques that are very time-consuming and costly. This research aims to develop an uncertainty quantification framework by bringing together physical modeling, machine-learning (ML), and experiments.
2 Computational microstructure optimization of piezocomposites involves iterative searches to achieve the desired combination of properties demanded by a selected application. Traditional analytical-based optimization methods suffer from the searching efficiency and result optimality due to high dimensionality of microstructure space, complicated electrical and mechanical coupling and non-uniqueness of solutions. Moreover, AM process inherently poses several manufacturing constraints e.g., the minimum feature size and the porosity in the piezoelectric ceramics as well as at the ceramics-polymer interface. It is challenging to include such manufacturing constraints since they are not explicitly available. This research aims to develop a novel data-driven framework for microstructure optimization of AM piezoelectric composites by leveraging extensive physics-based simulation data as well as limited amount of measurement data from AM process.
3 Lithium (Li) and other alkali metals (e.g., sodium and potassium) are very attractive electrode candidates for the next-generation rechargeable batteries that promise several times higher energy density at lower cost. However, Li-dendrite formation severely limits the commercialization of Li-metal batteries, either because dendrite pieces lose electrical contact with the rest of the Li-electrode or because growing dendrites can penetrate the separator and lead to short circuits. This research aims to develop a computational model to accelerate the design of dendrite-free Li-metal batteries.

9.9.2020 MIDAS Faculty Research Pitch Video.

Blueprint for the research: data-driven modelling of additive manufacturing. Stereolithography-based and laser melting-based additive manufacturing processes are used to fabricate the powder-based piezoelectric ceramics and metals respectively, with controllable complex microstructures and/or architectures to tune material properties. Physics-based numerical simulations are performed in an “in-house” multiscale computational framework, which includes macroscopic finite-element based manufacturing process modelling, mesoscopic phase-field modelling of microstructure evolution and design, and first principles/CALPHAD calculation of thermodynamics and kinetics. Data-driven approaches include machine learning and uncertainty quantification with surrogate models, such as polynomial chaos expansion, Gaussian process, radial basis functions, etc.