Data Science Institute (DSI)

Permanent URI for this community

https://udspace.udel.edu/handle/19716/29069

The Data Science Institute (DSI) aims to accelerate research in data science, serving as a nucleating effort to catalyze interdisciplinary research collaborations across fields impacting our society. Serving as a hub for interdisciplinary research, collaboration and excellence, the DSI brings together faculty and students from seven colleges across campus to work effectively with big data and address problems and opportunities facing society—from health sciences, physical sciences, environmental sciences, to behavioral and social sciences and public policy. The Institute will further involve partnerships with industry and other institutions in the region.

Visit the DSI website for more information.

Browse

Now showing 1 - 10 of 10

Proceedings of the 2020 DARWIN Computing Symposium
(Data Science Institute of the University of Delaware, 2020-02-12) Jayraman, Arthi; Bagozzi, Benjamin E.; Eigenmann, Rudolf; Totten, William; Wu, Cathy H.
The DARWIN Computing Symposium 2020—sponsored by the Data Science Institute of the University of Delaware—was held on February 12th, 2020. It represented the first event in a series of Symposia motivated by a National Science Foundation (NSF) MRI Award, also known as the Delaware Advanced Research Workforce and Innovation Network (DARWIN). As part of an NSF Major Research Instrumentation award (OAC-1919839), DARWIN has the goal of catalyzing "research and education at the University of Delaware (UD) and partners by acquiring a big data and high-performance computing system and making this instrument available to the community." This first DARWIN Computing Symposium introduced the machine—being ordered at the time— to the community, showcased computational and data-enabled research that will take advantage of the instrument, and provided opportunities for forming collaborations among future users at UD and regional partners. The Symposium included presentations detailing research involving UD faculty and members of DARWIN partner institutions that spanned the chemical and material sciences, engineering, the biological sciences, the environmental sciences, business, the social sciences, and education. Alongside this, an informational session on the DARWIN machine, a panel, and a student poster session provided an equally diverse range of additional viewpoints on computational- and data-intensive research, training, and education across the Delaware region and beyond. In addition to the NSF and Data Science Institute, the 2020 DARWIN Computing Symposium was sponsored by Atipa Technologies, DELL and CompassRed. Dr. Arthi Jayaraman, UD Professor and DARWIN Co-PI, served as chair of the 2020 DARWIN Computing Symposium.
DARWIN - A Resource for Computational and Data-intensive Research at the University of Delaware and in the Delaware Region
(Data Science Institute [DSI], University of Delaware, Newark, DE, 2021) Eigenmann, Rudolf; Bagozzi, Benjamin E.; Jayaraman, Arthi; Totten, William; Wu, Cathy H.
Proceedings of the 2021 DARWIN Computing Symposium
(Data Science Institute of the University of Delaware, 2021-02-12) Bagozzi, Benjamin E.; Eigenmann, Rudolf; Jayaraman, Arthi; Totten, William; Wu, Cathy H.
The DARWIN Computing Symposium 2021—sponsored by the Data Science Institute of the University of Delaware—was held on February 12, 2021. It represented the second event in a series of Symposia motivated by a National Science Foundation (NSF) MRI Award, also known as the Delaware Advanced Research Workforce and Innovation Network (DARWIN). As part of an NSF Major Research Instrumentation award (OAC-1919839), DARWIN has the goal of catalyzing "research and education at the University of Delaware (UD) and partners by acquiring a big data and high-performance computing system and making this instrument available to the community." This particular Symposium showcased recent computational and data-enabled research across the Delaware region, offered perspectives on broadening participation in computational and data-intensive research, and facilitated opportunities for forming collaborations among future DARWIN users at UD and regional partners. It also provided an overview of the newly operational DARWIN big data and high-performance computing machine via a panel on “early user mode” experiences. The 2021 DARWIN Computing Symposium was supported by the NSF and UD’s Data Science Institute. Dr. Benjamin E. Bagozzi, UD Associate Professor and DARWIN Co-PI, served as chair of the 2021 Symposium.
Measuring the impact of Automatic Program Parallelization Techniques in Cetus v2.0
(Data Science Institute [DSI], University of Delaware, Newark, DE, 2021-11-17) Bhosale, Akshay
Cetus is a source-to-source translator for programs written in the C language. The primary use is as a parallelizing compiler, translating C programs to equivalent C code annotated with OpenMP parallel directives. Cetus is a research platform to study parallelization techniques and related program transformations. Cetus was created out of a need for a state-of-the-art automatic parallelizer for multicores, written in a modern language and capable of performing analyses and transformations for today’s architectures. This poster presents an in-depth evaluation of the existing and newly added analysis and transformation techniques in Cetus on a set of benchmark applications.
Proceedings of the 2022 DARWIN Computing Symposium
(Data Science Institute of the University of Delaware, 2022-03-24) Hadden-Perilla, Jodi A.; Perilla, Juan R.; Bagozzi, Benjamin E.; Eigenmann, Rudolf; Jayaraman, Arthi; Totten, William; Wu, Cathy H.
The DARWIN Computing Symposium 2022—sponsored by the Data Science Institute of the University of Delaware—was held on March 24, 2022. It represented the third event in a series of Symposia motivated by a National Science Foundation (NSF) MRI Award, also known as the Delaware Advanced Research Workforce and Innovation Network (DARWIN). As part of an NSF Major Research Instrumentation award (OAC-1919839), DARWIN has the goal of catalyzing "research and education at the University of Delaware (UD) and partners by acquiring a big data and high-performance computing system and making this instrument available to the community." This third DARWIN Computing Symposium presented a wide variety of research enabled by the DARWIN machine to the Delaware community. Alongside this, it showcased additional computational and dataenabled research, provided details on accessing DARWIN for University of Delaware (UD) and partner institutions, and facilitated opportunities for forming collaborations among future users at UD and regional partners. In addition to the NSF and the Data Science Institute, the 2022 DARWIN Computing Symposium was sponsored by DELL and Nemours Children's Health. Drs. Jodi Haden-Perilla and Juan Perilla, both of the University of Delaware, served as co-chairs of the 2022 DARWIN Computing Symposium.
Proceedings of the 2023 DARWIN Computing Symposium
(Data Science Institute of the University of Delaware, 2023-02-23) Safronova, Marianna S.; Bagozzi, Benjamin E.; Eigenmann, Rudolf; Jayaraman, Arthi; Totten, William; Wu, Cathy H.
The DARWIN Computing Symposium 2023—sponsored by the Data Science Institute of the University of Delaware—was held on February 23, 2023. It represented the fourth event in a series of Symposia motivated by a National Science Foundation (NSF) MRI Award, also known as the Delaware Advanced Research Workforce and Innovation Network (DARWIN). As part of an NSF Major Research Instrumentation award (OAC-1919839), DARWIN has the goal of catalyzing "research and education at the University of Delaware (UD) and partners by acquiring a big data and high-performance computing system and making this instrument available to the community." This fourth DARWIN Computing Symposium presented a wide variety of research enabled by the DARWIN machine to the Delaware community. It also showcased additional computational and data-enabled research, provided perspectives on broadening participation in computational and data-intensive research, and facilitated opportunities for forming collaborations among future users at UD and regional partners. In addition to the NSF and the Data Science Institute, the 2023 DARWIN Computing Symposium was sponsored by AMD, BioCurie, Chemours, and Tech Impact. Dr. Marianna Safronova, Professor of Physics at the Department of Physics and Astronomy, University of Delaware, served as chair of the 2023 DARWIN Computing Symposium.
Proceedings of the 2023 Delaware Data Science Symposium
(Data Science Institute of the University of Delaware, 2023-09-22) Bagozzi, Benjamin E.; Abou Ali, Hanan; Blaustein, Michael; Blinova, Daria; Buler, Jeffrey; Carney, Lynette; Chandrasekaran, Sunita; Davey, Adam; Fleischhacker, Adam; Ostovari, Mina; Peart, Daniel; Smith, Sam; Tawiah, Nii Adjetey; Wu, Cathy H.
The 2023 Delaware Data Science Symposium was held on September 22nd with a primary focus on the role of data science in financial technology (FinTech) and health equity. The Symposium was organized by the University of Delaware’s (UD’s) Data Science Institute (DSI) with support from Tech Impact, Dupont, Kendal Corporation, Intellitec Solutions, UD’s Library, Museums, & Press, the UD Career Center, the UD Graduate College, the UD Master of Science in Data Science Program, UD’s Artificial Intelligence Center of Excellence (AICOE), and the DSI. It represented the fourth Delaware Data Science Symposium hosted at the University of Delaware, and the third such Symposium since the DSI’s inception. Altogether, the Symposium saw over 280 registered attendees from the University of Delaware and partner institutions across the Mid-Atlantic and beyond. The 2023 Delaware Data Science Symposium included multiple keynote speakers, a series of initiative & lightning talks, a poster session, a panel on data science-driven equity from healthcare, FinTech, community, and educational perspectives, and a session on UD’s summer 2023 Data Science (DS) + Artificial Intelligence (AI) Hackathon. Alongside these sessions, the Symposium also facilitated two associated satellite events. The first was a September 21st Data Science and Analytics Open House for UD graduate programs focused on data science and analytics. The second was a September 25th workshop on the use of MATLAB for low-code AI.
Proceedings of the 2024 DARWIN Computing Symposium
(Data Science Institute of the University of Delaware, 2024-02-12) Hsu, Tian-Jian; Bagozzi, Benjamin E.; Eigenmann, Rudolf; Jayaraman, Arthi; Totten, William; Wu, Cathy H.; Blaustein, Michael; Blinova, Daria; Carney, Lynette; Huffman, John; Smith, Samantha; Zhang, Jiaye
The DARWIN Computing Symposium 2024—sponsored by the Data Science Institute (DSI) of the University of Delaware—was held on February 12, 2024. It represented the fifth event in a series of Symposia motivated by a National Science Foundation (NSF) MRI Award, also known as the Delaware Advanced Research Workforce and Innovation Network (DARWIN). As part of an NSF Major Research Instrumentation award (OAC-1919839), DARWIN focuses on catalyzing "research and education at the University of Delaware (UD) and partners by acquiring a big data and high-performance computing system and making this instrument available to the community." In an effort to identify and advance future computing needs for artificial intelligence, to reduce the overhead for domain scientists utilizing HPC, and to develop regional partnerships, this fifth DARWIN Computing Symposium more specifically featured a panel and a keynote talk, as well as a series of research talks on DARWIN-enabled research, on computational and data-intensive (CDI) research/training needs, and on AI-focused CDI research more generally. These talks highlighted the use of AI in HPC to advance sciences and predictive capabilities with societal relevance across a wide range of domains. A panel discussion then facilitated interactions between research software engineers and domain scientists with an eye towards advancing scientific progress in different disciplines. In addition, 30 poster presentations by students and postdocs highlighted a number of relevant CDI research projects. Alongside the NSF and the Data Science Institute, the 2023 DARWIN Computing Symposium was sponsored by Tech Impact, UD’s Delaware Environmental Institute, UD’s Center for Applied Coastal Research, UD Information Technologies, and the University of Delaware Faculty Senate. Dr. Tian-Jian Hsu, University of Delaware Professor of Civil & Environmental Engineering and Director of the Center for Applied Coastal Research served as chair of the 2024 DARWIN Computing Symposium.
High-Resolution Modeling and Projecting Local Dynamics of Differential Vulnerability to Urban Heat Stress
(Earth's Future, 2024-10-06) Marginean, I.; Cuaresma, J. Crespo; Hoffmann, R.; Muttarak, R.; Gao, J.; Daloz, Anne Sophie
Climate change-induced heat stress has significant effects on human health, and is influenced by a wide variety of factors. Most assessments of future heat-related risks however are based on coarse resolution projections of heat hazards and overlook the contribution of relevant factors other than climate change to the negative impacts on health. Research highlights sociodemographic disparities related to heat stress vulnerability, especially among older adults, women and individuals with low socioeconomic status, leading to higher morbidity and mortality rates. There is thus an urgent need for detailed, local information on demographic characteristics underlying vulnerability with refined spatial resolution. This study aims to address the research gaps by presenting a new population projection exercise at high-resolution based on the Bayesian modeling framework for the case study of Madrid, using demographic data under the scenarios compatible with the Shared Socioeconomic Pathways. We examine the spatial and temporal distribution of population subgroups at the intra-urban level within Madrid. Our findings reveal a concentration of vulnerable populations, as measured by their age, sex and educational attainment level in some of the city's most disadvantaged neighborhoods. These vulnerable clusters are projected to widen in the future unless a sustainable trajectory is realized, driving vulnerability dynamics toward a more uniform and resilient change. These results can guide local adaptation efforts and support climate justice initiatives to protect vulnerable communities in urban environments. Key Points - Population projections by age, sex and education at small-area levels allow for high-resolution heat vulnerability modeling - Vulnerability to heat stress can vary widely between different areas in a city, and even within a single neighborhood - Areas that are vulnerable today are projected to become even more vulnerable in all Shared Socioeconomic Pathway scenarios except for that assuming a sustainable development narrative Plain Language Summary Heat stress is a major risk factor for human health, especially in cities where more people are exposed to increasingly higher temperatures in summer. Cities are usually hotter than their surrounding rural areas due to the predominance of dark, impervious surfaces which absorb more heat. Assessing heat risks for public health requires measurements of the hazard, such as a prolonged period with high temperatures, the population exposed to the hazard and characteristics of populations that make them more vulnerable to heat related diseases or even death. Various approaches and tools for risk assessment have been developed, but most of them focus on the hazard and exposure components. In this paper, we measure and project vulnerability to heat stress in alternative scenarios, using different population characteristics, such as age, sex and education. Our results show that there are compelling differences between areas within the city of Madrid and that areas that are vulnerable today will become even more vulnerable unless we follow a path of sustainable development. Detailed assessments of the spatial distribution of vulnerability within a city are relevant for developing adaptation solutions that target vulnerable populations and are thus more effective in reducing heat-related risks.
Mice employ a bait-and-switch escape mechanism to de-escalate social conflict
(PLoS Biology, 2024-10-15) Clein, Rachel S.; Warren, Megan R.; Neunuebel, Joshua P.
Intraspecies aggression has profound ecological and evolutionary consequences, as recipients can suffer injuries, decreases in fitness, and become outcasts from social groups. Although animals implement diverse strategies to avoid hostile confrontations, the extent to which social influences affect escape tactics is unclear. Here, we used computational and machine-learning approaches to analyze complex behavioral interactions as mixed-sex groups of mice, Mus musculus, freely interacted. Mice displayed a rich repertoire of behaviors marked by changes in behavioral state, aggressive encounters, and mixed-sex interactions. A distinctive behavioral sequence consistently occurred after aggressive encounters, where males in submissive states quickly approached and transiently interacted with females immediately before the aggressor engaged with the same female. The behavioral sequences were also associated with substantially fewer physical altercations. Furthermore, the male’s behavioral state could be predicted by distinct features of the behavioral sequence, such as kinematics and the latency to and duration of male–female interactions. More broadly, our work revealed an ethologically relevant escape strategy influenced by the presence of females that may serve as a mechanism for de-escalating social conflict and preventing consequential reductions in fitness.

Browse

Browsing Data Science Institute (DSI) by Issue Date

Results Per Page

Sort Options