Laboratories

AISE-CPS Lab is dedicated to advancing the intersection of Artificial Intelligence (AI) and Software Engineering for the development, verification, and optimization of Cyber-Physical Systems (CPS). The lab’s mission is to enhance the reliability, safety, and performance of CPS through cutting-edge research. By integrating innovative techniques such as search-based software engineering and machine learning, the lab addresses complex challenges in CPS across diverse domains, including autonomous systems, robotics, and industrial automation.

The Artificial Intelligence Research Lab (AIR) is an interdisciplinary group, hosted in the CIS department, connecting AI researchers across the University of Michigan - Dearborn. It provides interdisciplinary research environment in which faculty from various disciplines can cooperate and conduct research on sponsored projects involving core and applied Artificial Intelligence across the areas of computational intelligence, human-centered AI, robotics, safety, planning, intelligent software engineering, and improving human productivity.

With vast amounts of data being generated on a daily basis, advanced data analytics techniques are essential to understand and learn from this data. Research scientists relied mostly on a specific attribute of the data of interest to make inferences. However, most of the generated data is multimodal in nature. The ACMS lab focuses on human-centered modeling in particular. In order to improve different aspects of our life and develop enhanced, personalized technologies, we need to understand human behavior. However, human behaviors are complex, vary significantly, and are difficult to model and predict.

In our lab, we are developing multimodal frameworks that allow us to capture multiple diverse signals that are reflective of human behaviors, thereby enabling us to understand several human-centric phenomena such as deception, stress, discomfort, alertness, and affect. In order to build reliable systems, the modeling process encompasses multimodal inputs covering vision, language, physiological signals, and thermal maps in addition to demographic information, and aims at analyzing how these features interact, complement each other, and integrate to train our behavior detection systems.

Our lab focuses on cybersecurity and privacy in networked systems, AI/ML-powered wireless and mobile systems, RFID, 5G/6G networks, wireless/mobile sensing, dynamic spectrum sharing, Internet of Things (IoT), cyber-physical systems, edge computing, AI and machine learning, social networks.

The DSPLab conducts research in data-driven security, security & privacy in machine learning, and systems security. We take a data-driven approach for analysis, characterization, measurement, and defense of cybercrime on the Internet. Adversarial machine learning and privacy-preserving machine learning are studied in the context of techniques to harden machine learning models against adversarial inputs while ensuring privacy of subjects in training datasets. In systems security, DSPLab explores modeling, detection, and forensics of advanced and persistent threats. The contributions of research done in DSPLab are published in top-tier cybersecurity venues such as IEEE S&P, ACM CCS, USENIX Security, and NDSS.

The Data Science/Management Research Group in the Department of Computer and Information Science at the University of Michigan - Dearborn has strong faculty members who are active in the data science/management areas. They conduct innovative research in data science/management and related areas. Their research projects have been funded by various federal and industrial sponsors including the U.S. National Science Foundation (NSF), the U.S. National Institutes of Health (NIH), Michigan Life Science Corridor, IBM Corporation, and Ford Motor Company. The faculty members in the group have published research results in refereed quality journals and conference proceedings including IEEE Transactions on Data and Knowledge Engineering, IEEE Transactions on Big Data, IEEE Transactions on Services Computing, IEEE Transactions on Multimedia, ACM Transactions on Database Systems, ACM Transactions on Information Systems, ACM Transactions on Management Information Systems,  ACM Transactions on the Web, the VLDB Journal, Information Systems, Data and Knowledge Engineering, Distributed and Parallel Databases, Pattern Recognition, International Conference on Very Large Data Bases (VLDB), IEEE International Conference on Data Engineering (ICDE), and IEEE International Conference on Multimedia Computing and Systems (ICMCS). They actively participate in professional activities including serving on the editorial boards for various technical journals and serving as program/organizing committee members/chairs for numerous international conferences.

My lab focuses on building sample-efficient decision-making agents that can leverage multiple modalities of advice from single or multiple humans and cost-effectively interact with them.

This laboratory is a software development practice, which focuses on couching software engineering problems as optimization problems and utilizing meta-heuristic techniques to discover near-optimal
solutions to those problems.

We conduct research related to the application of computational search techniques to a wide variety of engineering problems, including requirements management, software testing, and capability management. ISE offers a productive and proven approach to software engineering through automated discovery of near-optimal solutions to problems, and has proven itself to be effective on a wide variety of problems.

The ISE lab has strong collaborations with industry, and includes a total of seven PhD students and several master and undergraduate students. The members of the ISE lab are very active in the software engineering community with a strong publications record in top software engineering journals and conferences such as TOSEM, TSE, and EMSE. The lab has also organized several software engineering conferences such as GECCO, SSBSE, and NasBASE.

The Learning and Uncertainty in Intelligent Systems Lab seeks to advance our fundamental knowledge about both the theory and practice of artificial intelligence (AI) and machine learning (ML) as they relate to (1) the design of intelligent systems for important problems of current practical interest and broad significance; (2) the future of these disciplines; and (3) the flexible implementation and effective use of intelligent systems in a wide range of real world domains, from the technological, to the social and
behavioral.

The emphasis falls mostly on the design and analysis of computational tools, such as frameworks, models, and algorithms that can handle the inherent uncertainty of complex systems and can also learn from huge collections of data on their behavior. The particular focus is on large, real-world systems whose complex global behavior is the result of simple local interactions among embedded entities forming the system (e.g., technological, social, financial, biological, political, and economic networks).

The Pervasive Computing Lab is a hub of advanced research in cloud, mobile, edge, and vehicular computing. Our work encompasses the creation of efficient systems and innovative applications within pervasive computing and IoT. Underpinning our efforts is a profound belief that technology must be harnessed not merely for its inherent fascination, but for its transformative potential to substantially elevate the quality of human life and societal well-being.

Our lab investigates novel approaches to use AI within a data management system. Our primary focus is on probabilistic databases, statistical relational learning and uncertain data management.

This laboratory conducts research in the areas of computer and network security, digital forensics, and applied cryptography. It aims at tackling real-world security challenges and at the same time provides security education for society.

The security and systems lab seeks to explore novel designs that can efficiently scale technology to meet the demands of emerging workloads while preserving the security and privacy of the end-user’s information. Members of our team aim to uncover side-channel vulnerabilities in state-of-the-art computer systems, investigate novel authentication mechanisms that can scale to meet the demands of the Internet of Things, enable oblivious mobile and cloud architectures that preserve the privacy of user information, as well as efficiently accelerate machine learning applications.

The Software Evolution and Maintenance (SEM) lab at the University of Michigan-Dearborn, founded and led by Dr. Foyzul Hassan, is dedicated to advancing research in Software Engineering. The lab focuses on developing innovative methods and techniques to assist software developers in addressing the challenges of creating and maintaining large software systems, including those involving Machine Learning (ML) and Virtual Reality (VR) applications.  

This is an NSF-sponsored research laboratory.

Due to the increasing energy consumption by computer systems and the thermal threat to computer systems, environmentally sustainable computing has received significant attention in industry and research. The goal of sustainable computing is to efficiently and effectively manage system resource to render the computing sustainable with minimal impact on the environment. The underlying systems are diverse, ranging from embedded systems to high-performance chip-multiprocessors to server clusters in data centers. Many applications on these systems demand timing requirements of their applications. One of our research goals is to study these timing-sensitive applications on diverse sustainable computing platforms.

On the other hand, many systems are highly vulnerable to faults or attacks, which can compromise the system performance, corrupt important data, or expose private information. Another major research goal is to design approaches to render systems more sustainable, secure, and trustworthy. Learn more research lab for Sustainable Systems.

The System Research Lab conducts research at the intersections of high-performance computing, program analysis, and runtime systems. With the increasing complexity of computational systems, the task of designing efficient software and hardware becomes more challenging. The efficiency of computing directly impacts user satisfaction, the success of user-facing applications or services, operational costs, and scientific discoveries. Under the leadership of Dr. Probir Roy, the lab is dedicated to developing practical tools and techniques for performance monitoring and program analysis. Their objective is to identify scalability bottlenecks, inefficient resource utilization, and optimization opportunities within software and runtime systems. The research aims to benefit both the software engineers in the tech industry and the scientific research community.

At Trustworthy AIoT Lab (TAI Lab), our research focuses on harnessing artificial intelligence (AI), security technologies, and cutting-edge wireless communication and mobile computing to build trustworthy AI-enabled Internet-of-Things (IoT) systems and networks. We are committed to developing intelligent systems that operate securely and transparently in dynamic and uncertain environments, while effectively integrating advanced technologies to ensure their reliability. Our research encompasses AI fairness and interpretability, IoT device security and privacy, and the optimization of wireless, network, and mobile technologies. We apply these innovations to a variety of real-world scenarios, including smart cities, smart agriculture, smart education, environmental protection, and Industry 4.0. Our goal is to advance the integration of AI and IoT technologies, ensuring that these systems are dependable and secure.

With emerging standards such as dedicated short-range communication (DSRC) designated for vehicle-to-vehicle communications and roadside-to-vehicle communications, cars will soon be able to communicate with each other. This enables a new class of communications applications that can support future transportation systems and needs. Located in Motown, we are working to rapidly adapt these technologies for the transportation industry. Several faculty members at the University of Michigan-Dearborn have teamed together to establish the Vehicular Networking Systems Research Laboratory. The goal of this laboratory is to provide a dedicated environment for interdisciplinary experimental research in wireless networking and mobile computing in order to develop expertise in both the theoretical and applied aspects of wireless networking and mobile computing within the context of automotive applications.

The Virtual Engineering Laboratory is an NSF-sponsored research lab that is equipped with state-of-the-art research facilities, including a high-energy and high-accuracy X-ray computer tomography system, a high-accuracy laser scanning system, a measurement microscope, a surface roughness profiler, a coordinate measurement machine, a portable robotic arm, an autostereo and geowall display, and high-end workstations. The research at VEL focuses on innovative computational methodologies for solving both fundamental and applied problems in engineering. Our work follows the principle of being unique, creative and explorative with a focus on critical unsolved problems in precision measurement, nondestructive evaluation, computational material science, and computer-aided design, modeling and simulation.