Undergraduate researchers enthusiastic about applying artificial intelligence and machine learning (AI/ML) algorithms for a wide variety of data science and engineering-based tasks within industry including data masking, synthetic data generation, cybersecurity, additive manufacturing, software security, and intrusion detection.

Big Data/Machine Learning, Deep Learning, Internet of Things (IoT)

• No Major Restriction

- Basic programming experience in Python/MATLAB - enthusiasm for practical applications of linear algebra, statistics, and computer science-based application is preferred. - strong background in physics and mathematics

Nuclear Engineering

Hany Abdel-Khalik

The student will work with a group of researchers at Purdue, Harvard and Tuskegee University on an NSF Future Manufacturing project focused on internet of things (IoT) edge devices and artificial intelligence (AI) for manufacturing applications. The IoT devices will be deployed at local manufacturing companies and their data will be used to improve operations.

Big Data/Machine Learning, Deep Learning, Internet of Things (IoT)

• Electrical Engineering
• Mechanical Engineering
• Industrial Engineering
• Computer Science
• Computer Engineering

Electrical and Computer Engineering

Ali Shakouri

Embedded systems provide control and operational intelligence for high-value cyber-physical systems such as smart cars, smart tractors, and smart city components. These systems must be secured from adversarial interactions. Vulnerabilities in embedded systems primarily occur in the external-facing components, especially in networking protocol stacks. One vulnerability detection technique that is widely used for IT software, such as web services, is called dynamic analysis (“fuzz testing”). We believe fuzzing will also find vulnerabilities in embedded systems. However, there are many challenges in adapting fuzzers to embedded systems software.

This project will develop new techniques to enable dynamic security analysis of embedded systems. The student will express research ideas in computer software, especially C/C++/Python code. The student will conduct experiments to identify and analyze discovered security vulnerabilities.

Cybersecurity, Internet of Things (IoT)

• No Major Restriction

Strong C/C++ programming skills, Python, familiarity with Linux programming environment (e.g. you are comfortable on the terminal), some knowledge of cybersecurity exploits (e.g. buffer overflows). Knowledge of embedded systems context is a plus. Successful applicants are likely EE, CompEng, or CS majors.

Electrical & Computer Engineering

James Davis

The goal of the project is to design low-cost and user-friendly paper-based point-of-care (POC) diagnostics tests for the detection of a panel of infectious diseases.
These student will be involved directly in the research related to the fabrication and testing of these point-of-care technologies, designed to allow for sensitive, rapid, and repeatable multiplexed detection of a variety of food and waterborne pathogens with high precision and accuracy and minimal sample handling. Target pathogens include parasites such as P. falciparum, (malaria), and Cyclospora Cayetanensis (found in agricultural water that severely lacks detection technologies), along with bacteria-induced foodborne and waterborne infectious diseases such as E. Coli O157:H7, S. Typhimurium, Listeria spp. and Campylobacter Jejuni. These will be aptamer-enabled biosensors, which will be further amenable for the rapid and low cost detection of other diseases, such as inflammation marker panels for Troponin, CRP, IL-6, and TNF-α. Aptamers are DNA molecules with high stability, high affinity for both small molecules and whole-cell pathogens, and are robust when exposed to harsh environments.

The main biorecognition element for the detection of these whole-cell pathogens, responsible for infectious diseases of interest, will be aptamers, which will allow for whole-cell pathogen detection, without amplification or cell lysis. Blood serum samples will be loaded in the sample well, and will diffuse to the four testing areas, each labeled for one individual pathogen. The initially negative testing areas will display a pink color. A positive test for one of the pathogens will be recognized by a change of color from pink to purple. A 3D printed portable imaging box, equipped with an image capture system and embedded color recognition and analysis software will allow for images of the test strips to be taken at constant illumination, on site, at primary care clinics or anywhere at the patient’s home, regardless of time of the day and natural illumination conditions. The portable imaging device will be able to display the test results on the screen. Thus, the detection limit of the diagnostic devices will be pushed down to levels beyond the ones possible with the naked eye, considering the limitation of human vision performance, especially at low illumination levels. A negative test for one pathogen will display an unchanged pink color of the corresponding testing area. We will optimize the device that has already been demonstrated in preliminary work in Stanciu’s group for food samples for E. Coli O157:H7, Listeria monocytogenesis and Salmonella typhimurium, to serum samples for the four pathogens of interests. Ultimately, the project's objective is to establish device performance (detection limit, linear range) .

Chemical Catalysis and Synthesis, Internet of Things (IoT), Medical Science and Technology, Nanotechnology, System-on-a-Chip

• No Major Restriction

General chemistry or biochemistry laboratory training.

Materials Engineering

Lia Stanciu

Internship opportunities:
1. Data analytics: Instrument and perform analysis of scientific application workloads on the Anvil system
2. High Performance Computing (HPC): Extend the Anvil system to burst scientific workflows into the Microsoft Azure cloud
3. Kubernetes: To support science gateways applications, extend Anvil’s Kubernetes-based composable subsystem to use cloud-based Kubernetes clusters
4. Containers to Support Education: Enable the use of large-scale notebook deployments to provide interactive access to Anvil in support of education

Applicants must be U.S. citizens. Open to undergrad students from all backgrounds.

Big Data/Machine Learning, Computer Architecture, Internet of Things (IoT), Other

• No Major Restriction

Linux command line experience preferred. However, programming experience is not a requirement for our REU. We seek students with a range of computational backgrounds and will provide research opportunities appropriate for beginner to advanced levels in computing. Our REU is designed to help you develop these computational skills.

RCAC

Amanda Hassenplug