IS Department Research Seminar Series

 

 

 

Please join us as we bring you a series of talks highlighting department research and topical issues in our field.

 

Upcoming Seminars

 

Past Seminars

Title: Prototype Nation: China & the Contested Promise of Innovation
Time: Monday, April 19th, 3pm
Speaker: Dr. Silvia Lindtner, Associate Professor at the University of Michigan

Abstract:
How did China’s mass manufacturing and “copycat” production become transformed, in the global tech imagination, from something holding the nation back to one of its key assets? Prototype Nation offers a transnational analysis of how the promise of democratized innovation and entrepreneurial life has shaped China’s governance and global image. Lindtner reveals how a growing distrust in Western models of progress and development, including Silicon Valley and the tech industry after the financial crisis of 2007–8, shaped the rise of the global maker movement and the vision of China as a “new frontier” of innovation. Lindtner’s investigations draw on more than a decade of research in makerspaces, tech incubators, corporate offices, and factories. She examines how the ideals of the maker movement, to intervene in social and economic structures, served the technopolitical project of prototyping a “new” optimistic, assertive, and global China. In doing so, Lindtner demonstrates that entrepreneurial living influences governance, education, policy, investment, and urban redesign in ways that normalize the persistence of sexism, racism, colonialism, and labor exploitation. Prototype Nation shows that by attending to the bodies and sites that nurture entrepreneurial life, technology can be extricated from the seemingly endless cycle of promise and violence.

**Get Prototype Nation now for 30% off with code P234 from the Princeton U Press website**

Bio:
Silvia Lindtner (she/her) is Associate Professor at the University of Michigan in the School of Information and Associate Director of the Center for Ethics, Society, and Computing (ESC). She is a founding member of Precarity Lab, a research collective working on various forms of insecurity, vulnerability, and social and cultural exclusion that digital platforms produce, and mediate. Lindtner’s research interests include cultures and politics of technology innovation and entrepreneurship, with a particular focus on the gendered and racialized forms of labor necessary to incubate entrepreneurial life and sustain technological promise. Lindtner draws from more than ten years of multi-sited ethnographic research, with a particular focus on China’s shifting position in the global political economy of technology production, economic development, and science and technology policy. Lindtner’s work contributes to the fields of STS (science and technology studies), cultural and feminist anthropology, China studies, HCI (human computer interaction), global communication studies, science and technology policy, and design. Her research has been awarded support from the US National Science Foundation, IMLS, Intel Labs, Google Anita Borg, and the Chinese National Natural Science Foundation.

 

Title: Towards Accounting for the Human in Emotion Recognition/AI Technologies
Time: Monday, March 29, 3pm
Speaker: Dr. Nazanin Andalibi, Assistant Professor at the University of Michigan School of Information

Abstract:
Emotions are powerful, mediate humans’ experiences with their surroundings, and impact decision-making and attention online and off. Sharing and signaling one’s emotions to other humans can be beneficial, but involves privacy calculations and complex decision-making processes. Despite the deeply personal nature of human emotion, artificial intelligence (AI) algorithms are being built to recognize and infer emotions using data sources such as social media behavior, streaming service use, voice, facial expressions, biometrics, and body language in ways often unknown to users.
A key perspective missing from debates in emotion AI/recognition is that of the humans who produce the data that make emotion recognition possible, and whose experiences are shaped by these technologies. In this talk I will share insights from my recent work around data subjects’ attitudes toward and conceptions of emotion recognition technologies, factors informing these attitudes, as well as anticipated risks and benefits. I focus on social media as a technological context and discuss data subjects’ attitudes towards emotion recognition on social media broadly, as well as emotion AI’s use in wellbeing and advertising domains. I then complicate accuracy and transparency notions in emotion recognition through an analysis of data subjects’ attitudes towards these notions and related folk theories. I conclude with a discussion of my research group’s ongoing and future research in this space.

Bio:
Dr. Nazanin Andalibi is an assistant professor at the University of Michigan School of Information. She is also affiliated with the Center for Social Media Responsibility, the Center for Ethics, Society, and Computing, and the Digital Studies Institute. Her research interests are in social computing, computer-mediated communication, and human-computer interaction, including examining relationships between emotions, identity, and technologies in contexts ranging from social media to artificial intelligence. Through this research agenda, Dr. Andalibi seeks to inform theory, design, activism, and policy for socio-technical futures that foreground the values and needs of marginalized individuals to support qualities such as wellbeing, safety, privacy, ethics, and equity. Dr. Andalibi’s work is published in venues such as ACM CHI, CSCW, TOCHI, JMIR, and New Media and Society, and featured by media outlets such as CNN, Fast Company, and Huffington Post. Her publications have received several Best Paper Honorable Mention Awards at ACM CHI and CSCW and her work is sponsored by the National Science Foundation.

 

Title: Machine Learning for Malware: Challenges and Progress
Time: Wednesday, February 17, 12-1pm ET.
Location: WebEx, meeting link: https://umbc.webex.com/umbc/j.php?MTID=m87807fcfe1c446dd14e68ef9371aa494 .  Meeting number: 120 701 4260 . Password: ugUaz6rH

Speaker: Dr. Edward Raff, Booz Allen Hamilton. Visiting Professor, UMBC Dept. of Computer Science

Abstract: Malware is an ever growing problem, single malware families have caused billions in damages and the first direct death attributed to malware taking down a hospital has occurred. To detect new malware, machine learning is a naturally attractive approach. However, malware poses a number of unique challenges that have slowed the progress of ML based solutions. In this talk we will look at the task of malware detection from byte based analysis, why is poses many challenging ML research problems, and progress we have made on these tasks by taking some non-standard approaches to machine learning: building shallow and wide networks instead of deep, handicapping the features of our model to make it robust, and using literal compression algorithms (LZMA) to find similar content.

BioEdward Raff leads Booz Allen’s machine learning research group and supports clients developing new ML solutions. His research includes cyber security, adversarial machine learning, fairness and ethics, fingerprint biometrics, and high-performance computing. In his spare time, he is the author of the JSAT machine learning library. He received his BS and MS in Computer Science from Purdue University, and his PhD in CS from UMBC. Dr. Raff is a Nvidia Deep Learning certified instructor, and Visiting Professor at UMBC.

 

Title: Advancing the Frontiers of Computer and Information Science and Engineering – and Translation, Innovation, and Partnerships at the National Science Foundation
Time: Wednesday, February 10, 12-1pm ET
Location: WebEx, meeting link: https://umbc.webex.com/umbc/j.php?MTID=maab130f0f58303f510b74b3730513562 . Meeting number: 120 550 9311 . Password: ywFBX23R
Speaker:  Dr. Erwin Gianchandani

Abstract: Since its founding in 1950, the National Science Foundation has sought “to promote the progress of science; to advance the national health, prosperity, and welfare; and to secure the national defense.” NSF-funded research has advanced foundational, exploratory research, like the detection of gravitational waves validating Einstein’s general theory of relativity, as well as use-inspired, translational research, like the page-rank algorithm that became the basis for Google.

In this two-part talk, I will first describe NSF’s leadership of computer and information science and engineering (CISE) discovery and innovation through its support of research, education, and research infrastructure. Then I will more generally explore the opportunity to enhance the synergies between exploratory and translational research to meet today’s societal grand challenges, thereby improving the critical services that communities deliver to their residents, transforming higher education to meet the needs of tomorrow’s workforce, and advancing public policies.

Bio:  Dr. Erwin Gianchandani currently serves as the National Science Foundation’s (NSF) Senior Advisor for Translation, Innovation, and Partnerships, reporting to the NSF Director. For the last five and one-half years, he has been the NSF Deputy Assistant Director for Computer and Information Science and Engineering (CISE), twice serving as NSF Acting Assistant Director for CISE. In this role, he has contributed to the leadership and management of NSF’s CISE directorate, including formulation and implementation of the directorate’s $1 billion annual budget, strategic and human capital planning, and oversight of day-to-day operations. In recent years, he has led the development and launch of several new NSF investments, including Smart & Connected Communities, Platforms for Advanced Wireless Research, and the National Artificial Intelligence Research Institutes. Before joining NSF in 2012, Dr. Gianchandani was the inaugural Director of the Computing Community Consortium, providing leadership to the computing research community in identifying and pursuing audacious, high-impact research directions. He has published extensively and presented at international conferences on computational systems biology. He holds a B.S. in computer science and M.S. and Ph.D. in biomedical engineering from the University of Virginia.

Title: Community-based Participatory Design: Creating, Learning and Innovating Together
Time: Wednesday, December 2, 12-1pm
Location: Google Meet – https://meet.google.com/ghj-ycbk-swg . Phone in: ‪(US) +1 802-440-0910‬ PIN: ‪447 647 617‬#
Speakers: Dr. Foad Hamidi

Abstract:
Community-based Participatory Design (PD) is a research and design practice that highlights the social constructs and relations of groups that include but go beyond formal workplace organizational structures. Thus, in addition to democratizing the workplace, community-based PD is concerned with working with community-based organizations, activist and hobbyist groups, and employing design methods in cultural production to understand and improve on current practices and create future ones. In this talk, I will describe three ongoing community-based PD projects in Baltimore City. First, I will present research with community labs that provide opportunities for the public to engage with biology and art in an informal setting. Next, I will outline an equity-based framework for empowering community educators to implement localized technology-rich informal learning programs for youth. Finally, I will describe a study on using community resources to provide free broadband Internet access to low-income families in Baltimore City. I will conclude with reflections on the strengths and challenges of the community-based PD approach.

Bio:
Foad Hamidi is an Assistant Professor in Information Systems at UMBC. His research interests include Human-Computer Interaction (HCI), Participatory Design, Living Media Interfaces and DIY Assistive Technology. He conducts interdisciplinary community-engaged research and collaborates regularly with diverse community partners. He has a PhD in Computer Science from York University, Toronto.

Title: Information Systems Research on Pandemic Preparedness at UMBC
Time: Friday, November 13th, 12-1:30pm
Location: Webex (virtual)
Speakers: Drs. Foad Hamidi, Nirmalya Roy, Drs. Aryya Gangopadhyay, Shimei Pan

Abstract:
The unprecedented global pandemic caused by the spread of the COVID-19 virus comes at a time also marked by historically unparalleled levels of network connectivity, information production, collection and analysis, and increases in community-engaged research across the world. The Information Systems (IS) research community is particularly well-positioned in exploring groundbreaking ways to leverage digital technologies, interdisciplinary approaches, and community resources to develop effective responses to the pandemic and its aftermath. NSF RAPID funded projects in the UMBC IS department include, Deep Learning Models for Early Screening of COVID-19 using CT Images, Influences of the COVID-19 Outbreak on Racial Discrimination, Identity Development and Socialization, and Responding to COVID-19 using High-speed Mesh Wireless Community Internet. Other research efforts, such as USM’s Maryland Institute for Pandemic Preparedness, have initiated to leverage the potential of interdisciplinary efforts in this area.

Bio:
In recognition of the innovative research being conducted by the IS faculty and with the goal of increasing research visibility and crosscutting collaborations, the IS research committee organized a virtual showcase on Friday, November 13th on Pandemic Preparedness Research. The event consisted of a panel and a series of lightning talks. Below, we include brief summaries of the projects that were shared.

 

Title: What is the impact of the affective behaviors and rendering fidelity of virtual humans on users’ emotions and visual attention?
Time: Friday, March 6th, 10 am (lecture), 11-11:30 am (discussion)
Location: ITE 459
Speaker: Matias Volonte

Abstract:
Anthropomorphic virtual characters are digital entities that mimic humans’ behavior and appearance. Currently, virtual humans have the potential to revolutionize human-computer interaction since they could be used as interfaces for social or collaborative scenarios. Present technology advancements provide the means to create virtual humans with an animation and an appearance fidelity that will make them almost indistinguishable from humans. Understanding the emotional impact on users during interaction with digital humans is primordial, specifically in training systems, since emotion influences learning results. Furthermore, users’ gaze mechanisms during interaction with conversational virtual agents can provide useful behavioral data since studies report that humans are mostly visual learners. Despite these technological breakthroughs, it is important to answer, what is the impact of the affective behaviors and rendering fidelity of virtual humans on users’ emotions and visual attention?

This presentation describes the result from studies focused on understanding the impact that animation, rendering fidelity and affective behaviors of virtual characters have on users’ emotions and visual attention. In a series of studies, users interacted with virtual humans that exhibit different emotional verbal and non-verbal behaviors and animation fidelities. Overall results show that users’ emotion, visual attention and behavior varies depending on the appearance, animation and affective disposition of the virtual entities.

Bio:
Matias Volonte is a PhD candidate in Human Centered Computing at Clemson University, South Carolina. His doctoral research investigates the effect that rendering style and animation of virtual humans have on users’ emotions and visual attention in interactive medical training simulator. Matias holds a master’s degree in Digital Production Arts oriented to Visual Effects from Clemson University, South Carolina and a bachelor’s degree in Audiovisual Communication from Universidad Blas Pascal, Argentina. Prior to starting her doctorate, Matias worked in the film industry as an artist and technical developer for feature films and television commercials

 

 

Title: Risk and Resilience: A Teen-centered Perspective on Teens and Technology Use
Time: Tuesday, March 3rd, 10-11 am (lecture), 11-11:30 am (discussion)
Location: ITE 459
Speaker: Dr. Pamela Wisniewski

Abstract:
We often equate keeping teens safe online to shielding them from experiencing online risks – such as information breaches, cyberbullying, sexual solicitations, and exposure to explicit content. However, this abstinence-only approach tends to be very parent-centric and does not take into account the developmental needs and experiences of our youth. For instance, parental control apps operate by monitoring and restricting teens’ mobile activities, instead of helping teens self-regulate their online behavior. On one hand, we tell teens they need to care about their online privacy in order to stay safe, and on the other, we are taking their privacy away. On all accounts, we assume teens have no personal agency when it comes to their own online safety, and that they cannot effectively manage online risks by themselves. Meanwhile, developmental psychologists have shown that some level of autonomy and risk-seeking behaviors are a natural and necessary part of adolescent developmental growth. In fact, shielding teens from any and all online risks may be detrimental to this process. Therefore, Dr. Wisniewski’s research takes a more teen-centric approach to understanding adolescent online risk experiences, how teens cope with these risks, and ultimately challenges the assumptions that have been made about how to protect teens online. Further, her research shows that parents are often not authoritative figures when it comes to the risks their teens are experiencing online; thus, an over-reliance on parental mediation to ensure teen online safety may be problematic. Thus, her research suggests new approaches that empower teens online by enhancing their risk-coping, resilience, and self-regulatory behaviors, so that they can learn to more effectively protect themselves from online risks.

Bio:
Dr. Wisniewski is an Assistant Professor in the Department of Computer Science at the University of Central Florida. She is a Human-Computer Interaction scholar whose research lies at the intersection of Social Computing and Privacy. She is an expert in the interplay between social media, privacy, and online safety for adolescents. She was one of the first researchers to recognize the need for a resilience-based approach, rather than an abstinence-based approach to adolescent online safety, and to back this stance up with empirical data. She has authored over 65 peer-reviewed publications and has won multiple best papers (top 1%) and best paper honorable mentions (top 5%) at top conferences in her field. She has been awarded over $2.85 million in external grant funding, and her research has been featured by popular news media outlets, including ABC News, NPR, Psychology Today, and U.S. News and World Report. She is an inaugural member of the ACM Future Computing Academy and the first computer scientist to ever be selected as a William T. Grant Scholar. She is also the recipient of the National Science Foundation’s prestigious CAREER Award for her innovative, teen-centric approach to adolescent online safety, “Safety by Design: Protecting Adolescents from Online Risks,”

 

 

Title: Mental Models and User Experiences of the Tor Browser
Time: Friday, February 28th, 10-11 am
Location: ITE 459
Speaker: Dr. Sameer Patil

Abstract:
With the exponential increase in government and corporate surveillance of online activities, there is an increasingly important need for usable tools that help individuals maintain privacy. While the Tor Browser is a popular anonymity tool, it has yet to achieve notable levels of mainstream usage by non-expert users. Making the Tor Browser appealing to the general population would require greater attention to usability and user experience aspects. To this end, we carried out two studies to examine user understanding of Tor operation and user experience of browsing the Web using the Tor Browser, respectively. The first study found significant differences in the mental models of experts and non-experts regarding Tor operation and threat model. The second study uncovered a number of significant challenges users encounter when using the Tor Browser for everyday online activities. Based on these findings, we offer a number of suggestions for making the Tor Browser more usable, thus helping boost privacy and anonymity for everyone.

Bio:
Sameer Patil is an Assistant Professor in the School of Informatics, Computing, and Engineering at Indiana University Bloomington. He also holds an affiliate appointment as an Assistant Research Professor in the Department of Computer Science and Engineering at New York University (NYU) Tandon School of Engineering. Previously, he has held several appointments in academia and industry, including Vienna University of Economics and Business (Austria), Helsinki Institute for Information Technology (Finland), University of Siegen (Germany), and Yahoo Labs (USA).

Sameer’s research interests cover the fields of Human Computer Interaction (HCI), Computer Supported Collaborative Work (CSCW), and social computing, with a focus on privacy and security aspects. His research has been funded by the National Science Foundation (NSF), Department of Homeland Security (DHS), and Google. Sameer’s work has been published in top-tier conferences and journals, and he holds eight US patents related to mobile technologies. Sameer obtained a Ph.D. in Computer and Information Science from the University of California, Irvine and holds Master’s degrees in Computer Science & Engineering and Information from the University of Michigan, Ann Arbor.

 

 

Title: Simulating human behavior: psychology envisioned as engineering.
Time: Thursday February 20th, 1-2 pm
Location: ITE 459
Speaker: Stacy Marsella

Abstract:
In this talk, I will first give a brief overview of my group’s work in social simulation and virtual humans. Then I will provide my perspective on the synergy between psychology and the engineering of these artifacts as well as illustrate this perspective using our work on the computational modeling of emotion. Computational models of human behavior are used in a wide range of artifacts. At a large scale, social simulations are being used, for example, to model people’s response to a natural disaster. At a medium-scale, models of human decision-makers are being used to study social technical systems such as the pharmaceutical drug supply network. At the highly detailed individual scale, virtual replicas of humans are being crafted. These virtual humans are facsimiles of people that can engage people in face-to-face interactions using the same verbal and nonverbal behavior people use. The designs of these various models heavily leverage psychological theories and data. Psychology and the social sciences, in turn, are increasingly using these computational artifacts as means to formulate, test and explore theories about human behavior.

Bio:
Stacy Marsella is a professor in the Institute of Neuroscience and Psychology at University of Glasgow, where he is the director of the Centre for Social, Cognitive and Affective Neuroscience. He is also a co-Director of SOCIAL, Glasgow’s UKRI Centre for Doctoral Training in Socially Intelligent Artificial Agents.

 

 

Title: The Frontiers of Computer and Information Science and Engineering
Time: Monday, February 17th, 9:30 am (discussion) 10 am (lecture)
Location: ITE 459
Speaker: Dr. Erwin Gianchandani

Abstract:
The National Science Foundation’s (NSF) Directorate for Computer and Information Science and Engineering (CISE) seeks to expand the frontiers of computing, communication, and information technologies; support advanced data and computing capabilities across all fields of science and engineering; and help prepare a workforce with the skills and competencies necessary for the 21st-century digital economy. This talk will present an overview of CISE and its programs and investments, along with a vision for evolving programs and priorities to support the frontiers of the field, and of science and engineering more broadly.

Bio:
Dr. Erwin Gianchandani is the National Science Foundation’s (NSF) Acting Assistant Director for Computer and Information Science and Engineering (CISE). In this role, he guides the CISE directorate in supporting fundamental and transformative research, the development and use of cyberinfrastructure across the science and engineering enterprise, and the education of a diverse workforce of researchers and practitioners. He oversees strategic and human capital planning, formulation and implementation of the directorate’s nearly $1 billion annual budget, and day-to-day operations. He has served as the NSF/CISE Deputy Assistant Director since 2015, and has led the development, launch, and implementation of several new NSF investments, including Smart & Connected Communities, Platforms for Advanced Wireless Research, and the National Artificial Intelligence Research Institutes. Before joining NSF in 2012, Dr. Gianchandani was the inaugural Director of the Computing Community Consortium (CCC), providing leadership to the computing research community in identifying and pursuing audacious, high-impact research directions. Prior to that, he was the Director of Innovation Networking at the University of Virginia, reporting to the university’s Vice President for Research. Dr. Gianchandani has authored or co-authored numerous publications in computational systems modeling of biological networks, with the goal of understanding disease mechanisms and identifying therapeutic targets. He earned his Ph.D. and M.S. in biomedical engineering and his B.S. in computer science from the University of Virginia.

 

 

Title: Bayesian Modeling of Intersectional Fairness: The Variance of Bias
Time: Thursday, September 19, 12-1 pm
Location: ITE 459
Speaker: Jimmy Foulds
RSVP on Facebook

Abstract:
With the rising influence of machine learning algorithms on many important aspects of our daily lives, there are growing concerns that biases inherent in data can lead the behavior of these algorithms to discriminate against certain populations. Informed by the framework of intersectionality from the Humanities literature, we propose mathematical definitions of AI fairness that aim to ensure protection along overlapping dimensions including gender, race, sexual orientation, class, and disability. We prove that our fairness criteria behave sensibly for any subset of the set of protected attributes, and we illustrate links to differential privacy. Finally, we present a Bayesian probabilistic modeling approach for the reliable, data-efficient estimation of fairness with multi-dimensional protected attributes. Experimental results on criminal justice, census, and synthetic data demonstrate the utility of our methodology, and show that Bayesian methods are valuable for the modeling and measurement of fairness in an intersectional context.

Bio:
Dr. James Foulds (Jimmy) is an Assistant Professor in the Department of Information Systems at UMBC. His research interests are in both applied and foundational machine learning, focusing on probabilistic latent variable models and the inference algorithms to learn them from data. His work aims to promote the practice of probabilistic modeling for computational social science, and to improve AI’s role in society regarding privacy and fairness. He earned his Ph.D. in computer science at the University of California, Irvine, and was a postdoctoral scholar at the University of California, Santa Cruz, followed by the University of California, San Diego. His master’s and bachelor’s degrees were earned with first class honours at the University of Waikato, New Zealand, where he also contributed to the Weka data mining system.

 

 

Title: Center for Accelerated Real Time Analytics (CARTA): Next Generation Research
Time: Thursday, September 26, 10-11 am
Location: ITE 459
Speaker: Karuna Joshi
Speaker’s website: http://karuna.informationsystems.umbc.edu
RSVP on Facebook

Abstract:
CARTA is an NSF sponsored Industry-University Cooperative Research Center (IUCRC) in UMBC focused on cutting edge inter-disciplinary research in real time analytics using next generation accelerated hardware. This center, lead by UMBC, also includes Rutgers University, New Brunswick, North Carolina State University (NCSU) and Rutgers University, Newark. Our international partner is Tel Aviv University. The overall Center Director is Dr. Yelena Yesha and the UMBC Site Director is Dr. Karuna P Joshi. This interactive talk will cover information about CARTA’s resources and research projects.

Bio:
Karuna Pande Joshi is an Assistant Professor of Information Systems at UMBC and UMBC Site Director of CARTA. She also directs the Knowledge Analytics Cognitive and Cloud (KnACC) Lab. Her research focus is in the areas of Data Science, Cloud Computing, Data Security and Privacy and Healthcare IT systems. She has published over 50 papers and her research is supported by ONR, NSF, DoD, GE Research and Cisco. She teaches courses in Big Data, Database Systems Design and Software Engineering. She received her MS and PhD in Computer Science from UMBC, where she was twice awarded the IBM PhD Fellowship, and her Bachelors in Computer Engineering from the University of Mumbai, India. Dr. Joshi also has extensive experience of working in the industry primarily as an IT Program/Project Manager at the International Monetary Fund.

 

 

Title: Information Extraction: From General Domain to Specific Domain
Time: Thursday, October 10, 12-1 pm
Location: ITE 459
Speaker: Arpita Roy
RSVP on Facebook

Abstract:
Information extraction (IE) is the task of automatically extracting structured information from unstructured text. IE is an important NLP task with many practical applications including business intelligence, scientific research, healthcare records management, financial investigation and social media analysis. Due to the difficulty and diversity of the problem, we divide IE into two different categories; general domain IE and domain specific IE. As each of these domains has its’ own unique characteristics, we propose two different noble IE approaches for each domain. For general domain we focus on leveraging knowledge from existing IE systems and build a superior IE model. For specific domain like cyber security we propose using structured domain knowledge for better IE. In both domain we use machine learning based IE techniques.

Bio:
Arpita Roy is a PhD student at the Department of Information Systems at University of Maryland, Baltimore County, working with Dr. Shimei Pan in the Text Mining and Social Media Analytics Lab. Her research interests include Natural Language Processing, Machine Learning and Text Mining. Her current research focus is developing machine based Information Extractions models for different domains.

 

 

Title: Deep Learning Models for Healthcare and Oncology
Time: Thursday, October 17, 12-1 pm
Location: ITE 459
Speaker: Sanjay Purushotham
RSVP on Facebook

Abstract:
It is widely believed that machine learning and artificial intelligence techniques will substantially change healthcare industries. Even though recent developments in machine learning, particularly deep learning, has achieved success in many applications, such as computer vision, natural language processing, speech recognition, and so on, healthcare applications pose many significantly different challenges to existing deep learning models. Examples include but are not limited to interpretations for prediction, heterogeneity in data, missing values, multi-rate multi-resolution data, big and small data, and privacy issues. In this talk, I will discuss a series of problems in healthcare that can benefit from deep learning models, the challenges as well as recent advances in addressing those. I will also present the findings from our recent foray of applying deep learning models to oncology research.

Bio:
Sanjay Purushotham is an Assistant Professor in the Department of Information Systems at the University of Maryland, Baltimore County (UMBC). Before joining UMBC, he was a Postdoctoral Scholar Research Associate in the Department of Computer Science at the University of Southern California (USC). He obtained his M.S and Ph.D. in Electrical Engineering from USC. His research interests are in machine learning, data mining, optimization theory, statistics, computer vision, and its applications to healthcare & bioinformatics, oncology, and multimedia data analytics. Recently, he has been developing deep learning frameworks to model healthcare data and to predict survival outcomes for cancer patients. He has produced more than 30 publications and has won the best paper and best poster awards at international conferences.

 

 

Title: A Surprise Behind Every Door: Research and reflections on making healthcare safer for older adults coming home from the hospital
Time: Wednesday, November 13, 10-11:30 am
Location: ITE 459
Speaker: Alicia Arbaje, Division of Geriatric Medicine and Gerontology, Johns Hopkins University
RSVP of Facebook

Abstract:
Define and describe national patterns of older adults’ care transitions in the U.S. Describe a multi-site, qualitative study to investigate information management during the hospital-to-home care transition. Present challenges healthcare providers, older adults, and caregivers face during care transitions. Discuss practical approaches to implement best practices and improve care transitions supported by informatics.

Bio:
Dr. Arbaje is an internist, geriatric medicine specialist, and health services researcher at Johns Hopkins University School of Medicine. She is Associate Professor of Medicine and Director of Transitional Care Research at the Center for Transformative Geriatrics Research. Dr. Arbaje is interested in the problems older adults face as they navigate through the healthcare system. She is leading several studies that aim to develop performance measures, define best practices, and ultimately improve the quality of care of older adults as they leave the hospital. The focus of her research has been on identifying patient populations at risk of experiencing suboptimal care transitions, identifying care processes and hospital characteristics related to readmissions, and developing clinical interventions to improve care transitions and reduce hospital readmissions. For the past 15 years, she has been investigating risks to older adults’ safety as they receive skilled home healthcare services after hospital discharge.

 

 

Title: Crimes of Omission: The Trouble with Siloing Datasets and Defining Data Narrowly
Time: Thursday, November 21, 12-1 pm
Location: ITE 459
Speaker: Lee Boot, Imaging Research Center (Director), Visual Arts and Computer Science and Engineering (Affiliate Associate Professor), UMBC
RSVP on Facebook

Abstract:
Concerns about data ethics are gaining traction as researchers, policymakers, news organizations, and the general public realize that quantitative data are becoming a virtual proxy for human beings and our world. Embedded in data are biases and facile assumptions; data are decontextualized as they migrate to serve purposes beyond those for which they were intended. Less discussed is the practice overall and what it means when we isolate datasets from one another and from important factors that are not quantified, but could determine outcomes. Lee Boot will discuss the Imaging Research Center’s efforts to envision tools and practices that will allow all relevant stakeholders addressing a challenge to contextualize data in dynamic, collaborative environments.

Bio:
Lee Boot is Director of the Imaging Research Center, and Affiliate Associate Professor of Visual Arts and Computer Science and Engineering at UMBC. Informed by his background in painting and filmmaking, his work of the past two decades is transdisciplinary research to develop novel digital media technologies, forms, and content to improve the capacity of the digital media and datasphere to address longstanding societal problems including health, education, and urban challenges. Currently, he is developing human interfaces for visualizing and interacting with complex problems that emerge from myriad interrelated factors and also observing and measuring human behavior in simulated virtual reality environments. The work has been sponsored by federal agencies such as the National Institutes of Health, foundations including Surdna, and the Robert W. Deutsch Foundation, and has been commissioned by the National Academy of Sciences. His work has been broadcast, screened, and exhibited nationally and internationally at venues including the Johannesburg Biennial in South Africa. His feature film, Euphoria, received the Gold Award for documentary at the Houston International Film Festival in 2005. His findings have been published in journals and presented at conferences on art, education, new media and digital communications.

 

 

Title: Scalable and Reliable Practical Design: A Bayesian Perspective
Time: Monday, November 25, 12:30-1:30pm
Location: ITE 459
Speaker: Seyede Fatemeh Ghoreishi, Institute for Systems Research (ISR), University of Maryland College Park (postdoctoral research fellow)

Abstract:
Design problems are pervasive in scientific and industrial endeavors: scientists design experiments to gain insights into physical and social phenomena, engineers design machines to execute tasks more efficiently, pharmaceutical researchers design new drugs to fight disease, and companies design websites to enhance user experience and increase advertising revenue. All these design problems are fraught with choices, choices that are often complex and high-dimensional, with interactions that make them difficult for individuals to reason about. Despite several advances made in design and decision making in recent years, lack of reliability and lack of scalability have limited their applications to a wide range of practical problems. This talk will focus on Bayesian optimization, in particular, a new Bayesian formulation of model-based and data-driven experimental design for large-scale and reliable design and decision-making.

Bio:
Seyede Fatemeh Ghoreishi is a postdoctoral research fellow at the Institute for Systems Research (ISR) at the University of Maryland. She received her Ph.D. and M.Sc. degrees both in Mechanical Engineering from Texas A&M University in 2019 and 2016 respectively. She holds a minor in Applied Statistics from the department of Statistics at Texas A&M University. She also received a M.Sc. degree in Biomedical Engineering from Iran University of Science and Technology in 2014 and a B.Sc. degree in Mechanical Engineering from the University of Tehran in 2012. Her research interests include Machine Learning, Bayesian Statistics and Design under Uncertainty with a wide range of applications. She is the recipient of several awards including being selected as Rising Stars in Computational and Data Sciences at the Oden Institute for Computational Engineering and Sciences at the University of Texas at Austin in 2019.

 

 

Title: Shaping the Collaborative View of Health Information
Time: Thursday, December 5, 12-1 pm
Location: ITE 459
Speaker: Helena Mentis, Associate Dean of Academic Programs and Learning, College of Engineering and Information Technology; Associate Professor, Department of Information Systems, UMBC
RSVP on Facebook

Abstract:
In the design of health information systems, there is an implicit belief that if everyone can simply see the same information they can easily engage in shared decision-making. However, in practice clinicians and patients engage in effortful presentation of information in order to convey their perspective. With this talk I take a step back to show the productive and cross-referential nature of health information use in the specific case of minimally invasive surgery. I discuss how it is not simply a case of displaying visual information, but rather a new practice is instantiated in shaping a view of that information for the collaborative team. I use these findings to motivate design directions for imaging interaction in the operating room to support surgeon collaboration and education as well as the design of sensor systems for Parkinson’s patients and their clinicians to see and discuss movement ability.

Bio:
As an HCI expert, Helena Mentis investigates how collaboration and coordination are achieved and better supported, primarily with regards to information sharing and decision making in healthcare contexts. In turn, she develops interactive systems to investigate the effects of new mechanisms for collaboratively sensing, presenting, and interacting with information. She has primarily been addressing this problem space in surgical environments and patient-physician interactions.