360 degree video streaming is a new form of video streaming where video is captured using a 360 degree video camera, and users may select which perspectives are of interest to them. Using traditional approaches to video streaming can result in 5X-6X bandwidth overhead. It is desirable to only show a user the portion of the video relevant to her, but user motion can lead to stalls, or degraded experience. We are developing new algorithms and solutions for 360 degree streaming with smooth user experience while achieving significant bandwidth savings.

In the summer project, we are looking to build a complete end to end prototype, where users can engage in 360 streaming from mobile devices and Oculus headsets. We would like to work with real content producers (e.g., Purdue commencement) to perform field trials of our 360 video streaming system. Doing so can also allow for A/B testing of different algorithms and provide data on how users engage with such content.

Human Factors, Mobile Computing, Other

• Computer Engineering

The main skillsets are: (i) strong Computer Engineering skills, especially in systems and software building; and (ii) an interest and passion in building working real-world research prototypes and evaluations among real users. Strong background in C++ is preferred, and an ability to develop code for mobile devices, and devices such as Oculus headsets will be required. Desired course work include: Operating Systems, and Computer Networking. Other requirements include C++/Java (ECE 30862/39595) and Data Structures (ECE 368).

Electrical and Computer Engineering

Sanjay Rao

The student will be studying the basic concepts of programming techniques, as well as Machine Learning and Human-Computer-Interaction techniques. Once the knowledge is well obtained, the student will be involved in a research project working on the topic of 3D reconstruction of Hand and Object interaction, utilizing the skill learned. The final stage of this project will be an academic publication and a detailed report on the topics being discussed over the semester. Three credit hours are to be registered, and the student is expected to work 10-12 hours per week on this project.

Deep Learning, Human Factors

• No Major Restriction

Electrical & Computer Engineering

Alex Quinn

This project will use deep learning models to analyze sequences of data (such as music). The analysis results will trigger a generative model to create visual art (image or video). Different styles of music (such as class, jazz, and rock) will be used as the input. The music will have different tempos. The computer models analyzes the style and tempo of the music and sets the parameters to generate the visual art. Faster music produces fast moving video. The SURF student will evaluate the existing (open source) computer models for music analysis and visual art generation, integrate them, and provide proof-of-concept demonstrations.

Big Data/Machine Learning, Deep Learning, Human Factors

• Computer Engineering
• Computer and Information Technology
• Computer Science
• Music
• Data Science

Required: At least one course on computer programming. Desired: Knowledge about machine learning and music.

Electrical and Computer Engineering

Yung-Hsiang Lu

Our project is funded by the U.S. Environmental Protection Agency (EPA) and involves an interdisciplinary collaboration between engineers, chemists, and psychologists at Purdue University and New York University (NYU). We will elucidate determinants of indoor dust ingestion in 6- to 24-month-old infants (age range for major postural and locomotor milestones). Specific objectives are to test: (1) whether the frequency and characteristics of indoor dust and non-dust mouthing events change with age and motor development stage for different micro-environments; (2) how home characteristics and demographic factors affect indoor dust mass loading and dust toxicant concentration; (3) how dust transfer between surfaces is influenced by dust properties, surface features, and contact dynamics; and (4) contributions of developmental, behavioral, and socio-environmental factors to dust and toxicant-resolved dust ingestion rates. In addition, the project will (5) create a shared corpus of video, dust, toxicant, and ingestion rate data to increase scientific transparency and speed progress through data reuse by the broader exposure science community.

Our transdisciplinary work will involve: (1) parent report questionnaires and detailed video coding of home observations of infant mouthing and hand-to-floor/object behaviors; (2) physical and chemical analyses of indoor dust collected through home visits and a citizen-science campaign; (3) surface-to-surface dust transfer experiments with a robotic platform; (4) dust mass balance modeling to determine distributions in and determinants of dust and toxicant-resolved dust ingestion rates; and (5) open sharing of curated research videos and processed data in the Databrary digital library and a public website with geographic and behavioral information for participating families.

The project will provide improved estimates of indoor dust ingestion rates in pre-sitting to independently walking infants and characterize inter-individual variability based on infant age, developmental stage, home environment, and parent behaviors. Dust transport experiments and modeling will provide new mechanistic insights into the factors that affect the migration of dust from the floor to mouthed objects to an infant’s mouth. The shared corpus will enable data reuse to inform future research on how dust ingestion contributes to infants’ total exposure to environmental toxicants.

U.S. EPA project overview: https://cfpub.epa.gov/ncer_abstracts/index.cfm/fuseaction/display.abstractDetail/abstract_id/11194

Biological Characterization and Imaging, Ecology and Sustainability, Engineering the Built Environment, Environmental Characterization, Human Factors

• No Major Restriction

We are seeking students passionate about studying environmental contaminants and infant exposure to chemicals in the indoor environment. Preferred skills: experience with MATLAB, Python, or R. Coursework: environmental science and chemistry, microbiology, physics, thermodynamics, heat/mass transfer, fluid mechanics, developmental psychology.

Lyles School of Civil Engineering

Brandon Boor

Effective human-automation interaction (HAI) holds great promise for improved safety, performance, and efficiency across a variety of domains, ranging from transportation to healthcare to manufacturing. These settings have in common a vision of shared autonomy between human and automation. However, realizing the promise of HAI rests on first addressing the fundamental challenge of enabling automation to be aware of, and responsive to, the human with whom it is interacting. Dr. Jain’s research group is thus trying to develop a mathematical control-oriented model for human cognitive states that include trust, self-confidence, mental workload and perceived risk that will allow level II autonomous vehicles to appropriately calibrate these states so that a human’s reliance behavior on the automation is consistent with the reliability of the automation. The goal of this SURF project will be to develop a level II self-driving car simulator using Unreal Engine 5 that will be used as an experimental testbed. The most important criteria for consideration for this position will be prior game development experience using Unreal Engine. Applicants will be presented with a detailed document outlining the functionality requirements of the simulator if their applications are under consideration for the position. Pending the student’s interest, there will be opportunities for the student to contribute the experiment ideation and data analysis.

Human Factors, Other

Exceptional programming skills, with experience in video game development (preferably) in Unreal Engine.

School of Mechanical Engineering

Neera Jain

This project involves the analysis of motion capture data and the development of human motor learning metrics to evaluate a wearable system developed by a company sponsor. Specifically, the undergraduate role is to assist in data collection and analysis. The student must take ethics courses and training to be approved for limited participation in human research and be comfortable interacting with healthy human subjects.

Project is co-advised by Dr Laura Blumenschein and Deva Chan

Biological Characterization and Imaging, Human Factors, Learning and Evaluation, Medical Science and Technology, Other

• Biomedical Engineering
• Mechanical Engineering
• Kinesiology
• Health Science PreProfessional
• Health and Disease
• Occupational Health Science
• Rehabilitation Engineering
• Pre-physical Therapy
• Applied Exercise and Health (Pre)

Human subjects, physiology, data analysis, statistics, motor learning

Mechanical Engineering

Laura Blumenschein

Accessible, on-demand transportation is unavailable to many persons with travel-limiting disabilities. Professors Duerstock and Brandon Pitts have led a team to look at inclusive design for autonomous transportation. They were recently awarded $1 million 1st prize for the DOT Inclusive Design Challenge to design autonomous vehicles (AV) for passengers with disabilities including those with motor and perceptual impairments. This internship will focus on the analysis of data collected through surveys and participant testing from this competition as well as future investigations of this problem from the standpoint of AV design and transportation infrastructure.

Engineering the Built Environment, Human Factors

• No Major Restriction

Understanding scientific methods of statistical analysis and data collection from both qualitative and quantitative data sets is a must. Some programming experience is preferred.

School of Industrial Engineering

Brad Duerstock

High physical and cognitive workload among surgeons and nurses are becoming more common. The purpose of this project is to examine the contributors to these and develop technology to understand and enhance their performance.

The SURF student will participate in data collection in the operating room at Indiana University School of Medicine, data analysis and interpretation, and write his/her results for a journal publication. The student will regularly communicate his/her progress and results with faculty, graduate mentors, and surgeon collaborators.
More information: https://engineering.purdue.edu/YuGroup

Human Factors

• Industrial Engineering
• Biomedical Engineering
• Computer Science

Desired experience: Human Factors, Machine Learning, Sensors, Programming

industrial engineering

Denny Yu

Automation is being applied to increasingly complex tasks in manufacturing, medical, military applications and more. There is a need for better human automation interaction to prevent the misuse, disuse and abuse of automation. Our main objective is to develop algorithms for cognitive control so that automated and autonomous systems can respond better to, and guide, human behavior such that task performance is maximized. During this SURF 2023 project, the researcher will help with developing experimental platforms involving human-automation interaction utilizing an online quadrotor simulator module. This may include (but is not limited to) control algorithm and heuristic design of automation assistance, development of human automation interaction contexts and tasks, and incorporating psychophysiological sensors for data collection. Previous and current experiments utilizing this and similar platforms have involved modeling trust, modeling self-confidence, modeling risk perception, and improving learning rates.

Big Data/Machine Learning, Human Factors, Learning and Evaluation

• No Major Restriction

Strong coding skills, including experience in HTML, Javascript, MATLAB, and/or Python.

School of Mechanical Engineering

Neera Jain

The project goal is to determine how manufacturing workers in the Midwest value different attributes of their jobs that may be impacted by a transition to decarbonized manufacturing. The undergraduate researcher would work with the research team to coordinate and process structured interviews with workers in the steel industry, assist with recruiting for a choice-based-conjoint survey, and conduct preliminary data analysis based on interview and survey data. Some overnight travel (Indiana, Ohio) may be required, and expenses would be covered by project funds.

Energy and Environment, Human Factors

• No Major Restriction

Prior experience conducting interviews or surveys is a plus, as is experience with Python.

Mechanical Engineering

Rebecca Ciez