Category: Research

ACSHF Forum: Grad Student Presentations

The Department of Cognitive and Learning Sciences will host ACSHF PhD Students Tauseef Ibne Mamun and Brittany Nelson at the next Applied Cognitive Science and Human Factors forum. Their presentations will be from 2:00 to 3:00 p.m. Monday (April 18) in Meese 109 and via Zoom.

Tauseef Ibne Mamun
Connected Vehicle Field Study: Outcomes and Challenges
Abstract: Poor driver decision-making continues to be a challenge at Highway-Rail Grade Crossings (HRGC). One way to improve safety has been to introduce a new, in-vehicle warning system that communicates with the external HRGC warning systems. The system gives drivers different rail-crossing-related warnings (e.g., approaching crossing, train presence) depending on the vehicle location. In a rare field study, 15 experienced drivers drove a connected vehicle (Chevy Volt) and used the warning system on a 12-mile loop, then completed a semi-structured interview and usability survey. Results from the post-drive survey and interview are reported and provide a template for future usability assessments for field studies involving new technologies.

Brittany Nelson
Identifying Healthy Lifestyle Knowledge Gaps Among Medical and Non-medical Students
Abstract: Across the US, chronic illnesses including cancer and cardiovascular disease are a result of poor lifestyle decisions such as diet, tobacco/alcohol use, and physical inactivity. Data suggests that previous interventions lack effectiveness for impacting lifestyle decisions, particularly long term. One reason why individuals continue to engage in unhealthy behaviors may be due to gaps in understanding that are not currently filled by previously developed interventions. To the extent individuals are informed of the risks/benefits of key health behaviors and the tools valuable for overcoming challenges associated with engaging/quitting those behaviors then people are more equipped to make decisions that are in-line with their goals and values. Little information exists on what informational gaps people hold. Therefore, the objective of this study was two-fold. First, it was designed to measure how calibrated medical and non-medical students are on the relation between lifestyle behaviors and their risk of major diseases. Second, this study was designed to identify informational gaps that impact perceived challenges of engaging in healthier lifestyle behaviors. Data from medical (N = 128) and non-medical (N = 24) students suggests they hold insufficient knowledge regarding the relation between lifestyle behaviors and risk of health outcomes. The most commonly reported barriers across non-dietary behaviors were time 39%, lack of motivation 15%, and weather 9%. The most commonly reported barriers specific to eating behaviors were cost 26%, taste 21%, and food spoiling too quickly 10%. The results from this study have implications for future intervention design.

Shruti Amre receives “Best Poster” in first Computing[MTU] Showcase

Michigan Tech’s College of Computing and the Institute of Computing and Cybersystems (ICC) co-hosted the first Computing[MTU] Showcase on April 4-6, 2022. Organizers say the showcase was intended to be a connection-maker on many levels, including undergraduate and graduate students presenting their most exciting innovations and current research.

The Department of Cognitive and Learning Sciences (CLS) was proud to have nine of the 40 entries in the Showcase’s research poster competition come from CLS students. With “Best Poster” going to Shruti Amre, ACSHF PhD student, for “Keep your hands on the wheel: the effect of driver engagement strategy on change detection, mind wandering, and gaze behavior”. Shruti is advised by Dr. Kelly Steelman.

Amre’s winning research poster

A few details on the research

Advanced driver-assist systems (ADAS) have revolutionized traditional driving by enabling drivers to relinquish operational control of the vehicle to automation for part of the total drive. These features only work under certain pre-defined conditions and require drivers to be attentive of their surroundings. While the features are engaged, there is an increased risk associated with drivers losing awareness of their environment. Popular manufacturers like Tesla requires drivers to have their hands-on-the-wheel while Cadillac’s ADAS requires drivers to keep their eyes-on-the road. We utilized a low-fidelity simulation and eye tracking to examine the effects of hands-on-the wheel and eyes-on-the road driver engagement strategies on change detection, mind wandering, and gaze behavior in a semi-autonomous driving task.


The showcase also hosted more than 20 speakers, including counterterrorism, health informatics, machine learning and security experts from companies and institutions ranging from Adobe, Amazon and Microsoft to the National Counterterrorism Center, the National Science Foundation and the U.S. Department of Defense.

Faculty Research Talk by Kevin Trewartha

Cognitive Neuroscience of Aging

Research talk by Dr. Kevin Trewartha

Dr. Kevin Trewartha, associate professor in the Department of Cognitive and Learning Sciences (CLS) and Department of Kinesiology and Integrative Physiology (KIP), will present a talk on cognitive neuroscience of aging, Friday, April 15, 2022, at 3:00 pm, in Rekhi Hall Room G005. The lecture can also be attended virtually on Zoom. For more information on Dr. Trewartha’s research, visit his Aging Cognition Action Lab.

Dr. Hongyu An, assistant professor in the Department of Electrical and Computer Engineering, will also present. Dr. An’s research interests include neuromorphic engineering/computing, energy-efficient neuromorphic electronic circuit design for Artificial Intelligence, emerging nanoscale device design, and spiking neural networks. Visit Dr. An’s faculty webpage.

The lecture is sponsored by the Department of Computer Science.

ACSHF Forum: Grad Student Presentation

The Department of Cognitive and Learning Sciences will host ACSHF PhD Student Shruti Amre at the next Applied Cognitive Science and Human Factors forum. The presentation, “Keep Your Hands on the Wheel: The Effect of Driver Engagement Strategies on Change Detection, Mind Wandering, and Gaze Behavior”, will be from 2:00 to 3:00 p.m. Monday (April 4) in Meese 109.

Abstract: Advanced driver-assist systems (ADAS) have revolutionized traditional driving by enabling drivers to relinquish operational control of the vehicle to automation for part of the total drive. These features only work under certain pre-defined conditions and require drivers to be attentive to their surroundings. While the features are engaged, there is an increased risk associated with drivers losing awareness of their environment. Popular manufacturers like Tesla requires drivers to have their hands-on-the-wheel while Cadillac’s ADAS requires drivers to keep their eyes-on-the road. We utilized a low-fidelity simulation and eye-tracking to examine the effects of hands-on-the-wheel and eyes-on-the-road driver engagement strategies on change detection, mind wandering, and gaze behavior in a semi-autonomous driving task.

Graduate Research Colloquium, 2022

Each spring, Michigan Tech’s Graduate Student Government sponsors the Graduate Research Colloquium (GRC) Poster & Presentation Competition. The GRC is a unique opportunity for current graduate students to share their research with the University community and to gain experience in presenting that research to colleagues. During this year’s GRC a virtual mock conference will be set-up where presenters are broken down into various technical sessions, ranging from Advances in Modern Medicine and Health to Power and Energy, and everything in between.

Five Applied Cognitive Science and Human Factors (ACSHF) students will be competing in this year’s event on March 29-30.

Lamia Alam

Assessing Cognitive Empathy Elements within the Context of Diagnostic AI Chatbots

Empathy is an important element for any social relationship and it is also very important in patient-physician communication for ensuring the quality of care. There are many aspects and dimensions of empathy applicable in such communication. As Artificial Intelligence is being heavily deployed in healthcare, it is critical that there is a shared understanding between patients and the AI systems if patients are directly interacting with those systems. But many of the emotional aspects of empathy may not be achievable by AI systems at present and cognitive empathy is the one that can genuinely be implemented through artificial intelligence in healthcare. We need a better understanding of the elements of cognitive empathy and how these elements can be utilized effectively. In this research, the goal was to investigate whether empathy elements actually make a difference to improve user perception of AI empathy. We developed a scale “AI Cognitive Empathy Scale (AICES)” for that purpose and conducted a study where the experimental condition had both emotional and cognitive empathy elements together. The AICES scale demonstrated reasonable consistency, reliability, and validity, and overall, empathy elements improve the perceived empathy concern within diagnostic AI chatbots.

Betsy Lehman

Easy Does It: Ease of Generating Alternative Explanations As A Mediator Of Counterfactual Reasoning In Ambiguous Social Judgments

According to sensemaking theory (Klein et al., 2007), people must first question their theory of a situation before they can shift their perspective. Questioning one’s perspective may be critical in many situations, such as taking action against climate change, improving diversity and equity at work, or promoting vaccine adoption. However, research on how people question their theories is limited. Using counterfactual theory (Roese & Olson, 1995), we examined several factors and strategies affecting this part of the sensemaking process. Eighty participants generated explanations and predicted outcomes in five ambiguous social situations. Likelihood of an alternative outcome was the measure for questioning one’s frame. Two models of the data were created. Using path analysis, we compared fit between a base model (i.e., ease, malleable factors, and missing information) and a model based on counterfactual generation theory with ease as a mediator. Results indicated that the counterfactual theory model fit was better, indicating that ease of generation may be a critical mediator in the sensemaking process. This work contributes to research focused on understanding of the mechanisms of perspective shifts to support applications for system design and training, such as programs to reduce implicit bias.

Anne Linja

Examining Explicit Rule Learning in Cognitive Tutorials: Training learners to predict machine classification

Artificial Intelligence (AI)/Machine Learning (ML) systems are becoming more commonplace and relied upon in our daily lives. Decisions made by AI/ML systems guide our lives. For example, these systems might decide whether we get a loan, and the full-self driving car we’re sharing the road with even makes decisions. However, we may not be able to predict, or even know whether, or when these systems might make a mistake. Many Explainable AI (XAI) approaches have developed algorithms to give users a glimpse of the logic a system uses to come up with its output. However, increasing the transparency alone may not help users to predict the system’s decisions even though users are aware of the underlying mechanisms. One possible approach is Cognitive Tutorials for AI (CTAI; Mueller et al., 2021), which is an experiential method used to teach conditions under which the AI/ML system will succeed or fail. One specific CTAI technique involved teaching simple rules that could be used to predict performance; this was referred to as Rule Learning. This technique aims to identify rules that can help the user learn when the AI/ML system succeeds, the system’s boundary conditions, and what types of differences change the output of the AI system. To evaluate this method, I will report on a series of experiments in which we compared different rule learning approaches to find the most effective way to train users on these systems. Using the MNIST data set, this includes showing positive and negative examples in comparison to providing explicit descriptions of rules that can be used to predict the system’s output. Results suggest that although examples help people learn the rules, tutorials that provided explicit rule learning and provided direct example-based practice with feedback led people to best predict correct and incorrect classifications of an AI/ML system.

Tauseef Ibne Mamun

Connected Crossings: Examining Human Factors in a Field Study

Poor driver decision-making continues to be a challenge at Highway-Rail Grade Crossings (HRGC). One way to improve safety has been to introduce a new, in-vehicle warning system that communicates with the external HRGC warning systems. The system gives drivers different rail-crossing-related warnings (e.g., approaching crossing, train presence) depending on the vehicle location. In a rare field study, 15 experienced drivers drove a connected vehicle (Chevy Volt) and used the warning system on a 12-mile loop, then completed a semi-structured interview and usability survey. Results from the post-drive survey and interview are reported and provide a template for future usability assessments for field studies involving new technologies.

Lauren Monroe

Don’t throw a tempo tantrum: the effects of varying music tempo on vigilance performance and effective state

Vigilance tasks, or sustained attention tasks, involve an operator monitoring an environment for infrequent and random critical signals buried among more frequent neutral signals for an extended period of time. In addition to an observable decline in task engagement, task performance, and arousal over time, these tasks are also related to an increased subjective workload. Previously, music has been shown to have a positive impact on operator engagement and reaction times during sustained attention, however the differences between fast and slow tempo music on vigilance performance and subjective mood measures have not been studied. The present study (N=50) examined the effects of music played at different tempos on a selection of performance metrics and subjective measures of mood, engagement, and workload. Results indicated that varying the tempo of music did not have an effect on the decline in the correct detection of critical signals. There also was not a significant impact on measures of arousal and stress, but the fast tempo condition had a slightly positive impact on worry and engagement from pre to post task subjective measures.

For more information on our student and faculty research see: https://www.mtu.edu/cls/research/

Undergraduate Research Symposium, 2022

Emilie Jacques


Hunter Malinowski

The tenth annual Undergraduate Research Symposium (URS) took place on Friday, March 25, 2022, in the Rozsa Lobby. The Symposium highlighted the cutting-edge research conducted on Michigan Tech’s campus by some of our best and brightest undergraduates. The students represented a wide array of scientific and engineering disciplines from across campus and highlighted the diversity of research areas being explored.

UG psychology students Hunter Malinowski (CS dual major) and Emilie Jacques were among this year’s URS participants. Hunter presented her research with advisor Dr. Shane Mueller in “Assessing the Effectiveness of the XAI Discovery Platform and Visual Explanations on User Understanding of AI Systems”. Emilie presented her research with advisor Dr. Susie Amato-Henderson in “The Immediate Effects of Mindfulness on Test Anxiety”. Both students were recipients of a Summer Undergraduate Research Fellowship (SURF).

Congratulations to all participants!

Human Factors in Healthcare Keynote: Dr. Rupa Valdez presents “Creating Systems That Promote Equity: A Journey Across Disciplines”

Please join us Friday (Mar 25) in ATDC conference room 101 (and via Zoom); talk from 3:30-4:30, with interactive discussion to follow from 4:30-5:00.

Dr. Rupa Valdez is an associate professor at the University of Virginia with joint appointments in the School of Medicine and the School of Engineering and Applied Sciences. She is also a core faculty member of Global Studies and the Disability Studies Initiative. Dr. Valdez merges the disciplines of human factors engineering, health informatics, and cultural anthropology to understand and support the ways in which people manage health at home and in the community.

We encourage faculty and graduate students with any overlap in research, interest in collaboration, or just interest in learning more about Dr. Valdez’s work/journey/activism to join us!

This event is co-sponsored by CLS, KIP, and CSA, and is sponsored in part by the Michigan Tech Visiting Professor Program, which is funded by a grant to the Office of the Provost from the State of Michigan’s King-Chavez-Parks Initiative. Michigan Technological University is an Equal Opportunity Educational Institution/Equal Opportunity Employer that provides equal opportunity for all, including protected veterans and individuals with disabilities.

Abstract:
Catalyzed by the pandemic and by the killings of George Floyd, Breonna Taylor, and many
others, there is rapidly growing interest in determining how we can create sociotechnical
systems that promote equity rather than perpetuate disparity and injustice. In this talk, I share
and critically reflect on my journey toward this goal over the last decade. I begin with earlier
efforts to merge approaches from cultural anthropology and engineering to inform the design
of patient-facing health information technologies. I end with more recent community-based
participatory research and policy-based efforts to reimagine public health education, accessible
healthcare, and the role of community in shaping the research process.  My engagement with
historically marginalized communities has pushed my efforts from a primary focus on creating
technologies aligned with the contexts in which such communities are embedded to a broader
focus on working with communities to shift these contexts. In concluding remarks, I reflect on
how encouraging such work requires, at minimum, embracing a broader conceptualization of
engineering and, more ambitiously, work that may be considered a-disciplinary.

BIOGRAPHY
Dr. Rupa Valdez is an associate professor at the University of Virginia with
joint appointments in the School of Medicine and the School of Engineering
and Applied Sciences. She is also a core faculty member of Global Studies and the Disability
Studies Initiative. Dr. Valdez merges the disciplines of human factors engineering, health
informatics, and cultural anthropology to understand and support the ways in which people
manage health at home and in the community. Her research and teaching focuses on
underserved populations, including populations that are racial/ethnic minorities, are of low
socioeconomic status, or are living with physical, sensory, or cognitive disabilities. Her work
draws heavily on community engagement and has been supported by the National Institutes of
Health (NIH), Agency for Healthcare Research and Quality (AHRQ), the National Science
Foundation (NSF), and the US Department of Agriculture (USDA), among others. She recently
testified before Congress on the topic of health equity for the disability community and
received the Jack A. Kraft Innovator Award from the Human Factors and Ergonomics Society
(HFES) for her pioneering work in creating and developing the subdiscipline of patient
ergonomics.
Dr. Valdez currently serves as an Associate Editor for Ergonomics, the Journal of American
Medical Informatics Association (JAMIA) Open, and Human Factors in Healthcare. Among other
appointments, she serves on the Board of Directors for the American Association of People with
Disabilities and on PCORI’s Patient Engagement Advisory Panel. She is further the
founder and president of Blue Trunk Foundation, a nonprofit dedicated to
making it easier for people with chronic health conditions, disabilities, and
age-related conditions to travel. Dr. Valdez herself lives with multiple chronic health
conditions and disabilities, which have and continue to influence her work and advocacy.

ACSHF Forum: Kyle Wilson, Seeing Machines

The Applied Cognitive Science and Human Factors (ACSHF) Forum will be held from 2-3 p.m. Monday (Feb 21) virtually via Zoom. Our speaker is Kyle Wilson, Ph.D. Kyle is a Human Factors Senior Scientist and Team Lead at the company Seeing Machines in Canberra, Australia.

Title: Driver behaviors and safety risks surrounding new in-cabin technology: Three case studies from human factors research in automotive and rail environments. 
Brief Description: Dr. Wilson will discuss three human factors studies he was involved with in the transport space – each with a focus on how people experience new technology and related implications on safety and performance. He’ll cover:

  • One of the world’s first on-road automated vehicle studies with a primary focus on driver behaviour
  • Field research involving 10+ hour night shifts in the cramped cabin of a coal train
  • An on-road study evaluating safety and usability of an app that tells drivers when the traffic light is going to change

For each study he’ll discuss the goals, approach taken, findings and outcomes. Throughout, he also intends to highlight challenges and lessons learned, in what was sometimes ‘messy’ applied research.

ACSHF Forum: Grad Student Presentations

The Applied Cognitive Science and Human Factors (ACSHF) Forum will be held from 2-3 p.m. Monday (Feb 7) virtually via Zoom. There will be two speakers: Anne Linja and Lauren Monroe, both ACSHF graduate students.

Linja will present “Examining Explicit Rule Learning in Cognitive Tutorials: Training learners to predict machine classification“.

Abstract:
Artificial Intelligence (AI)/Machine Learning (ML) systems are becoming more commonplace and relied upon in our daily lives. Decisions made by AI/ML systems guide our lives. For example, these systems might decide whether we get a loan, what our medical diagnoses are, and the full-self driving car we’re sharing the road with even makes decisions. However, we may not be able to predict, or even know whether, or when these systems might make a mistake.

Many Explainable AI (XAI) approaches have developed algorithms to give users a glimpse of the logic a system uses to come up with its output. However, increasing the transparency alone may not help users to predict the system’s decisions even though users are aware of the underlying mechanisms.

One possible approach is Cognitive Tutorials for AI (CTAI; Mueller, Tan, Linja et al., 2021), which is an experiential method used to teach conditions under which the AI/ML system will succeed or fail. One specific CTAI technique that was proposed involved teaching simple rules that could be used to predict performance; this was referred to as Rule Learning. This technique aims to identify rules that can help the user learn when the AI/ML system succeeds, fails, the system’s boundary conditions, and what types of differences change the output of the AI system. To evaluate this method, I will report on a series of experiments in which we compared different rule learning approaches to find the most effective way to train users on these AI/ML systems. Using the MNIST data set, this includes showing positive and negative examples in comparison to providing explicit descriptions of rules that can be used to predict the system’s output. Results suggest that although examples help people learn the rules (especially examples of errors), tutorials that provided explicit rule learning and provided direct example-based practice with feedback led people to best predict correct and incorrect classifications of an AI/ML system. I will discuss approaches to developing these tutorials for image classifiers and autonomous driving systems.


Monroe will present “Don’t throw a tempo tantrum: the effects of varying music tempo on vigilance performance and affective state“.

Abstract:
Vigilance tasks, or sustained attention tasks, involve an operator monitoring an environment for infrequent and random critical signals buried among more frequent neutral signals for an extended period of time. In addition to an observable decline in task engagement, task performance, and arousal over time, these tasks are also related to an increased subjective workload. Previously, music has been shown to have a positive impact on operator engagement and reaction times during sustained attention. The present study (N=50) examined the effects of music played at different tempos on a selection of performance metrics and subjective measures of mood, engagement, and workload. Results indicated that varying the tempo of music did not have an effect on the decline in the correct detection of critical signals. There also was not an observable impact on measures of engagement and stress but the fast tempo condition had a slightly significant positive impact on worry from pre to post task subjective measures. 

ACSHF Forum: Grad Student Presentations

The Applied Cognitive Science and Human Factors (ACSHF) Forum will be held from 2-3 p.m. Monday (Jan. 24) virtually via Zoom.

There will be two speakers: Pomm Khaewratana and Alex Watral, both ACSHF graduate students.

Pomm Khaewratana:
Title: Learning with word game: Effects of crossword and elaboration on learning scientific vocabulary
Abstract: Crosswords have been used in a variety of science classrooms as a supplementary tool to help students learn technical vocabulary and to improve scientific thinking. However, the majority of crossword studies showed positive findings only for the former and almost none for the latter. We currently lack evidence for the usefulness of crossword in learning anything beyond the vocabulary and their definition or associated context provided as crossword hints. In this presentation, I will describe a continuation of the series of my experiments that evaluate the effect of crossword with an add-on elaboration task. The task supposedly enhances learning and retention of learned vocabulary by having learners generate sentences from technical words that depict an application-based use of the words. Fifty undergraduate students were recruited as participants in the aforementioned within-subject-design experiment. Results indicated significant improvement on memory level but not on the higher level of application.

Alex Watral:
Title: Online Assessment of Motor Learning in Younger and Older Adults
Abstract: Motor learning is a specific type of learning that occurs through repetition of a movement following the law of practice wherein rapid improvements in performance occur initially, followed by more gradual improvements as practice continues. In this sense, we can think of motor skill learning as unfolding in two phases that may rely on different cognitive mechanisms. Evidence has shown that motor learning abilities change with healthy aging such that older adults are slower to learn novel motor tasks initially while ultimately they are still able to learn to the same degree as young adults. One of the gold-standard approaches to studying motor learning is called the visuomotor rotation (VMR) paradigm. Motor learning tasks like the VMR paradigm are typically implemented in our lab using a robotic device called a Kinarm. As our understanding of motor learning evolves, we need to focus on options for testing that are more accessible than laboratory limited approaches. We have created a web-based application to assess visuomotor adaptation in a remote setting. No application downloads are required on the part of the participant. The only requirement is for them to have a computer (laptop or desktop) and an internet connection. This makes the application far more accessible than current laboratory and portable platforms. The overarching goal of this project is to validate the web-based application in younger adults as well as healthy older adults. We are also interested in verifying that previously identified correlations between the early and late stages of motor learning and implicit memory, spatial working memory, and visual-spatial abilities can be observed with this online app. Healthy younger adults (n=21) and healthy older adults (n=17) participated in this study. Each participant met with a researcher via Zoom and shared their screen while performing the VMR task and cognitive battery so that the researcher could troubleshoot as needed. Preliminary results suggest that the online application produced results similar to the laboratory task. Further analyses will be conducted to determine if there were significant differences between the two collection methods (app vs laboratory) and to see how cognitive constructs correlate with performance on the VMR app.