UMBC Information Systems Department

Permanent URI for this collectionhttp://hdl.handle.net/11603/51

Browse

Now showing 1 - 20 of 1113

MedReg-KG: KnowledgeGraph for Streamlining Medical Device Regulatory Compliance
(2024-12-15) Chattoraj, Subhankar; Joshi, Karuna
Healthcare providers are deploying a large number of AI-driven Medical devices to help monitor and medicate patients. For patients with chronic ailments, like diabetes or gastric diseases, usage of these devices becomes part of their daily lifestyle. These medical devices often capture personally identifiable information (PII) and hence are strictly regulated by the Food and Drug Administration (FDA) to ensure the safety and efficacy of the medical device. Medical device regulations are currently available as large textual documents, called Code of Federal Regulations (CFR) Title 21, that cross-reference other documents and so require substantial human effort and cost to parse and comprehend. We have developed a semantically rich framework MedReg-KG to extract the knowledge from the rules and policies for Medical devices and translate it into a machine-processable format that can be reasoned over. By applying Deontic Logic over the policies, we are able to identify the permissions and prohibitions in the regulation policies. This framework was developed using AI/Knowledge extraction techniques and Semantic Web technologies like OWL/RDF and SPARQL. This paper presents our Ontology/Knowledge graph and the Deontic rules integrated into the design. We include the results of our validation against the dataset of Gastroenterology Urology devices and demonstrate the efficiency gained by using our system.
Leveraging the Human Factors Discipline for Better Cybersecurity Outcomes: A Roundtable Discussion
(IEEE, 2024-11) Cunningham, Margaret; Nobles, Calvin; Robinson, Nikki; Haney, Julie
Three human factors experts get to the bottom of what the human factors discipline actually is, how the cybersecurity community and organizations can benefit from it, and how to create a pipeline of professionals with human factors and cybersecurity expertise.
Increasing Visual Literacy With Collaborative Foraging, Annotation, Curation, and Critique
(ACM, 2024-12-05) Williams, Rebecca M.; Syed, Afrin Unnisa; Kurumaddali, Krishna Vamsi
Students today are facing information overload, contamination, and bloat from dubious sources: AI-generated content, masqueraded influencer opinions, context-less listicles, and consumer manipulation - frequently heralded by graphs and charts to bolster the argument. Because this information firehose presents as technical visual communications, the overload is both cognitive and perceptual, potentially causing more insidious misperceptions than text alone. In addition to consuming such media, students in computing fields work with data to produce graphs and charts themselves, including assignments, academic research, and personal projects/blog posts/tweets. Depending on visual literacy (VL) and prior data analysis instruction, many students inadvertently code misleading, unethical, or biased visualizations, potentially contributing to the dark corpus already festering online. Prior research on misconceptions in visualization pedagogy suggests students benefit from repeated opportunities to forage, curate and critique examples, discussing and debating with peers and instructors. Inspired by these findings, we incorporated a visual curation + annotation platform into a Data Visualization Computer Science course, enabling students to participate in processes of searching for and curating found examples of misleading visualizations, collaborative annotation + critique of examples, and structured self-evaluation of misleading elements in their own work. We assess our interventions with pre-/post-course Visualization Literacy Assessment Tests, qualitative evaluation of student reflections, taxonomic evaluation of formative student-produced visualizations, and post-course exit surveys. Post-course, students' VL increased significantly, and the number and severity of misleading visualizations they created decreased. Students also reflected that they gained increased confidence in spotting visual disinformation online, and in avoiding its creation in software.
Improving Gamma Imaging in Proton Therapy by Sanitizing Compton Camera Simulated Patient Data using Neural Networks through the BRIDE Pipeline
(UMBC High Performance Computing Facility, 2024) Chen, Michael O.; Hodge, Julian; Jin, Peter L.; Protz, Ella; Wong, Elizabeth; Cham, Mostafa; Gobbert, Matthias; Barajas, Carlos A.
Precision medicine in cancer treatment increasingly relies on advanced radiotherapies, such as proton beam radiotherapy, to enhance efficacy of the treatment. When the proton beam in this treatment interacts with patient matter, the excited nuclei may emit prompt gamma ray interactions that can be captured by a Compton camera. The image reconstruction from this captured data faces the issue of mischaracterizing the sequences of incoming scattering events, leading to excessive background noise. To address this problem, several machine learning models such as Feedfoward Neural Networks (FNN) and Recurrent Neural Networks (RNN) were developed in PyTorch to properly characterize the scattering sequences on simulated datasets, including newly-created patient medium data, which were generated by using a pipeline comprised of the GEANT4 and Monte-Carlo Detector Effects (MCDE) softwares. These models were implemented using the novel ‘Big-data REU Integrated Development and Experimentation’ (BRIDE) platform, a modular pipeline that streamlines preprocessing, feature engineering, and model development and evaluation on parallelized GPU processors. Hyperparameter studies were done on the novel patient data as well as on water phantom datasets used during previous research. Patient data was more difficult than water phantom data to classify for both FNN and RNN models. FNN models had higher accuracy on patient medium data but lower accuracy on water phantom data when compared to RNN models. Previous results on several different datasets were reproduced on BRIDE and multiple new models achieved greater performance than in previous research.
Family Care Partners and Paid Caregivers: National Estimates of Role-Sharing in Home Care
(Oxford University Press, 2024-12-09) Fabius, Chanee D.; Gallo, Joseph J.; Burgdorf, Julia; Samus, Quincy M.; Skehan, Maureen; Stockwell, Ian; Wolff, Jennifer L.
We describe “role-sharing” in home care, defined as family care partners and paid caregivers assisting with the same task(s).We studied 440 participants in the 2015 National Health and Aging Trends Study (NHATS) receiving paid help with self-care, mobility, or medical care. We describe patterns in receiving paid help only, help from care partners only, and role-sharing. We examine whether sole reliance on paid help or role-sharing differs by Medicaid-enrollment and dementia status.Half (52.9%) of care networks involved role-sharing. Care networks involving role-sharing more often occurred among older adults with dementia (48.7% vs. 25.6%, p<0.001) and less often for those who were Medicaid-enrolled (32.1% vs. 49.4%, p<0.01). Those living with dementia more often experienced role-sharing in eating (OR 3.9 [95% CI 1.20, 8.50]), bathing (OR 2.7, [95% CI 1.50, 4.96]), dressing (OR 2.1 [95% CI 1.14, 3.86]), toileting (OR 2.9 [95% CI 1.23, 6.74]), and indoor mobility (OR 2.8 [95% CI 1.42, 5.56]), and less often received help solely from paid helpers with medication administration (OR 0.24, [95% CI 0.12, 0.46]). Medicaid-enrollees more often received paid help only in dressing (OR 2.0 [95% CI 1.12, 3.74]), outdoor (OR 2.4 [95% CI 1.28, 4.36]) and indoor mobility (OR 4.3 [95% CI 2.41, 7.62]), and with doctor visits (OR 2.8 [95% CI 1.29, 5.94]).Role-sharing is common, especially among older adults living with dementia who are not Medicaid-enrolled. Strategies supporting information sharing and collaboration in home-based care merit investigation.
Demand Modeling for Advanced Air Mobility
(2024-11-25) Acharya, Kamal; Lad, Mehul; Sun, Liang; Song, Houbing
In recent years, the rapid pace of urbanization has posed profound challenges globally, exacerbating environmental concerns and escalating traffic congestion in metropolitan areas. To mitigate these issues, Advanced Air Mobility (AAM) has emerged as a promising transportation alternative. However, the effective implementation of AAM requires robust demand modeling. This study delves into the demand dynamics of AAM by analyzing employment based trip data across Tennessee's census tracts, employing statistical techniques and machine learning models to enhance accuracy in demand forecasting. Drawing on datasets from the Bureau of Transportation Statistics (BTS), the Internal Revenue Service (IRS), the Federal Aviation Administration (FAA), and additional sources, we perform cost, time, and risk assessments to compute the Generalized Cost of Trip (GCT). Our findings indicate that trips are more likely to be viable for AAM if air transportation accounts for over 70\% of the GCT and the journey spans more than 250 miles. The study not only refines the understanding of AAM demand but also guides strategic planning and policy formulation for sustainable urban mobility solutions. The data and code can be accessed on GitHub.{https://github.com/lotussavy/IEEEBigData-2024.git }
Care Compare Star Ratings and Family Satisfaction in Maryland Nursing Facilities: A Comparison by Facility Structure
(2024-02-22) Millar, Roberto; Diehl, Christin; Kusmaul, Nancy; Stockwell, Ian
These findings were presented at the Gerontological Society of America’s (GSA) 2023 meeting in Tampa, Florida. Part of a Center and Institute Departmentally-Engaged Research (CIDER) award, this is part of several studies focused on examining quality of care in Maryland nursing facilities.
Regional Air Mobility Flight Demand Modeling in Tennessee State
(2024-12-11) Acharya, Kamal; Lad, Mehul; Song, Houbing; Sun, Liang
Advanced Air Mobility (AAM), encompassing Urban Air Mobility (UAM) and Regional Air Mobility (RAM), offers innovative solutions to mitigate the issues related to ground transportation like traffic congestion, environmental pollution etc. RAM addresses transportation inefficiencies over medium-distance trips (50-500 miles), which are often underserved by both traditional air and ground transportation systems. This study focuses on RAM in Tennessee, addressing the complexities of demand modeling as a critical aspect of effective RAM implementation. Leveraging datasets from the Bureau of Transportation Statistics (BTS), Internal Revenue Service (IRS), Federal Aviation Administration (FAA), and other sources, we assess trip data across Tennessee's Metropolitan Statistical Areas (MSAs) to develop a predictive framework for RAM demand. Through cost, time, and risk regression, we calculate a Generalized Travel Cost (GTC) that allows for comparative analysis between ground transportation and RAM, identifying factors that influence mode choice. When focusing on only five major airports (BNA, CHA, MEM, TRI, and TYS) as RAM hubs, the results reveal a mixed demand pattern due to varying travel distances to these central locations, which increases back-and-forth travel for some routes. However, by expanding the RAM network to include more regional airports, the GTC for RAM aligns more closely with traditional air travel, providing a smoother and more competitive option against ground transportation, particularly for trips exceeding 300 miles. The analysis shows that RAM demand is likely to be selected when air transportation accounts for more than 80\% of the total GTC, air travel time is more than 1 hour and when the ground GTC exceeds 300 for specific origin-destination pairs. The data and code can be accessed on GitHub. {https://github.com/lotussavy/AIAAScitecth-2025.git}
Psychological Ownership in Teleinstructive Augmented Reality Workspaces
(ACM, 2025-01-10) Mentis, Helena; Seo, Jwawon; Avellino, Ignacio
Psychological ownership over virtual and physical spaces in augmented reality can lead to tensions between collaborators, yet, there is still a significant challenge in understanding how psychological ownership manifests in shared AR and what that might mean for the inclusion of collaborative interaction mechanisms. Through an experimental instruction task with a teleAR system, we interviewed 16 participant pairs on their perceptions of ownership of virtual and physical spaces and how they thought their perceptions impacted their interaction within those spaces. Our findings indicate (1) how AR introduces new ideas around behavioral norms in spaces that are layered and (2) that the nature of the task itself, in this case one of instruction where collaborators have different levels of knowledge and the local worker is reliant on the remote expert, significantly affects the perceptions of ownership and therefore behavior norms.
Nurse Staffing in Nursing Facilities and Family Members' Appraisal of Resident Care
(2024-06-29) Millar, Roberto; Diehl, Christin; Cannon-Jones, Stephanie; Kusmaul, Nancy; Stockwell, Ian
Multiple Chronic Condition Patterns among Full-Benefit Maryland Medicaid Enrollees
(2024-06-29) Han, Fei; Gill, Christine; Blake, Elizabeth; Stockwell, Ian
Listening for Expert Identified Linguistic Features: Assessment of Audio Deepfake Discernment among Undergraduate Students
(2024-11-21) Bhalli, Noshaba Nasir; Naqvi, Nehal; Evered, Chloe; Mallinson, Christine; Janeja, Vandana
This paper evaluates the impact of training undergraduate students to improve their audio deepfake discernment ability by listening for expert-defined linguistic features. Such features have been shown to improve performance of AI algorithms; here, we ascertain whether this improvement in AI algorithms also translates to improvement of the perceptual awareness and discernment ability of listeners. With humans as the weakest link in any cybersecurity solution, we propose that listener discernment is a key factor for improving trustworthiness of audio content. In this study we determine whether training that familiarizes listeners with English language variation can improve their abilities to discern audio deepfakes. We focus on undergraduate students, as this demographic group is constantly exposed to social media and the potential for deception and misinformation online. To the best of our knowledge, our work is the first study to uniquely address English audio deepfake discernment through such techniques. Our research goes beyond informational training by introducing targeted linguistic cues to listeners as a deepfake discernment mechanism, via a training module. In a pre-/post- experimental design, we evaluated the impact of the training across 264 students as a representative cross section of all students at the University of Maryland, Baltimore County, and across experimental and control sections. Findings show that the experimental group showed a statistically significant decrease in their unsurety when evaluating audio clips and an improvement in their ability to correctly identify clips they were initially unsure about. While results are promising, future research will explore more robust and comprehensive trainings for greater impact.
Interactive Assessment of Variances of High-Resolution Model Features in Digital Twin Simulations
(ACM, 2024-11-22) Kulkarni, Chhaya; Privé, Nikki; Janeja, Vandana
Prior to the deployment of expensive instruments into orbit, spatio-temporal digital twin systems modeling the whole earth are used to study the efficacy of these instruments. However, we need to make sure that the simulated instruments have realistic characteristics (to reflect the physics of the atmosphere and limits of the instrument itself) in order for the results of the digital twin to be robust and usable. If these simulations are done accurately, the instrument can be deployed, leading to more accurate weather forecasts and climate research. This demonstration system validates the simulations, specifically the realism of remotely sensed observations. The digital twin system is a low-cost way to improve instrument design used in meteorological and climatological research. The primary goal is to show how atmospheric data can improve the development and validation of new observational systems for meteorology and climate science. We have developed an interactive variability study system that uses a dynamic platform to visualize, assess, and grasp complex atmospheric dynamics. The dashboard is built using Python for backend operations and integrates tools such as the Streamlit framework for quick web application development and the Folium library for advanced geospatial visualizations. This dashboard acts as a bridge between advanced atmospheric modeling and spatio-temporal digital twin applications, showcasing the substantial benefits of integrating comprehensive model outputs into the simulation of observational systems.
Making Enterprise Recorded Meetings Easy to Discover and Share
(IGI Global, 2015) Pan, Shimei; Topkara, Mercan; Boston, Jeff; Wood, Steve; Lai, Jennifer
The prevalence of social content sharing such as video and photo sharing has greatly enhanced information discovery and social interaction over the internet. This has inspired similar efforts within enterprise to encourage collaboration and expertise sharing. Moreover, enterprise web meeting tools increasingly become an important platform for knowledge workers to participate and collaborate remotely. Although these web meetings contain rich enterprise knowledge and are frequently recorded, they are rarely revisited and shared. To encourage enterprise knowledge sharing especially, to facilitate the discovery and sharing of enterprise meetings, we develop an end-to-end enterprise meeting service Agora that manages the full cycle of hosting and sharing recorded web meetings. Agora leverages the functionality of existing enterprise meeting hosting, video sharing and presentation sharing services to build a coherent meeting service. Agora was deployed as a cloud service in a global fortune 500 company which allows its customers to test new collaborative technologies.
User-directed Non-Disruptive Topic Model Update for Effective Exploration of Dynamic Content
(ACM, 2015-03-18) Yang, Yi; Pan, Shimei; Song, Yangqiu; Lu, Jie; Topkara, Mercan
Statistical topic models have become a useful and ubiquitous text analysis tool for large corpora. One common application of statistical topic models is to support topic-centric navigation and exploration of document collections at the user interface by automatically grouping documents into coherent topics. For today's constantly expanding document collections, topic models need to be updated when new documents become available. Existing work on topic model update focuses on how to best fit the model to the data, and ignores an important aspect that is closely related to the end user experience: topic model stability. When the model is updated with new documents, the topics previously assigned to old documents may change, which may result in a disruption of end users' mental maps between documents and topics, thus undermining the usability of the applications. In this paper, we describe a user-directed non-disruptive topic model update system, nTMU, that balances the tradeoff between finding the model that fits the data and maintaining the stability of the model from end users' perspective. It employs a novel constrained LDA algorithm (cLDA) to incorporate pair-wise document constraints, which are converted from user feedback about topics, to achieve topic model stability. Evaluation results demonstrate advantages of our approach over previous methods.
LDAExplore: Visualizing Topic Models Generated Using Latent Dirichlet Allocation
(2015-07-23) Ganesan, Ashwinkumar; Brantley, Kiante; Pan, Shimei; Chen, Jian
We present LDAExplore, a tool to visualize topic distributions in a given document corpus that are generated using Topic Modeling methods. Latent Dirichlet Allocation (LDA) is one of the basic methods that is predominantly used to generate topics. One of the problems with methods like LDA is that users who apply them may not understand the topics that are generated. Also, users may find it difficult to search correlated topics and correlated documents. LDAExplore, tries to alleviate these problems by visualizing topic and word distributions generated from the document corpus and allowing the user to interact with them. The system is designed for users, who have minimal knowledge of LDA or Topic Modelling methods. To evaluate our design, we run a pilot study which uses the abstracts of 322 Information Visualization papers, where every abstract is considered a document. The topics generated are then explored by users. The results show that users are able to find correlated documents and group them based on topics that are similar.
An Uncertainty-Aware Approach for Exploratory Microblog Retrieval
(IEEE, 2015-08-12) Liu, Mengchen; Liu, Shixia; Zhu, Xizhou; Liao, Qinying; Wei, Furu; Pan, Shimei
Although there has been a great deal of interest in analyzing customer opinions and breaking news in microblogs, progress has been hampered by the lack of an effective mechanism to discover and retrieve data of interest from microblogs. To address this problem, we have developed an uncertainty-aware visual analytics approach to retrieve salient posts, users, and hashtags. We extend an existing ranking technique to compute a multifaceted retrieval result: the mutual reinforcement rank of a graph node, the uncertainty of each rank, and the propagation of uncertainty among different graph nodes. To illustrate the three facets, we have also designed a composite visualization with three visual components: a graph visualization, an uncertainty glyph, and a flow map. The graph visualization with glyphs, the flow map, and the uncertainty analysis together enable analysts to effectively find the most uncertain results and interactively refine them. We have applied our approach to several Twitter datasets. Qualitative evaluation and two real-world case studies demonstrate the promise of our approach for retrieving high-quality microblog data.
Using Personal Traits For Brand Preference Prediction
(ACL, 2015-09) Yang, Chao; Pan, Shimei; Mahmud, Jalal; Yang, Huahai; Srinivasan, Padmini
In this paper, we present a comprehensive study of the relationship between an individual’s personal traits and his/her brand preferences. In our analysis, we included a large number of character traits such as personality, personal values and individual needs. These trait features were obtained from both a psychometric survey and automated social media analytics. We also included an extensive set of brand names from diverse product categories. From this analysis, we want to shed some light on (1) whether it is possible to use personal traits to infer an individual’s brand preferences (2) whether the trait features automatically inferred from social media are good proxies for the ground truth character traits in brand preference prediction.
Cross-Domain Error Correction in Personality Prediction
(IOS Press, 2016) Kılıç, Işıl Doğa Yakut; Pan, Shimei
In this paper, we analyze domain bias in automated textbased personality prediction, and proposes a novel method to correct domain bias. The proposed approach is very general since it requires neither retraining a personality prediction system using examples from a new domain, nor any knowledge of the original training data used to develop the system. We conduct several experiments to evaluate the effectiveness of the method, and the findings indicate a significant improvement of prediction accuracy.
An Empirical Study of the Effectiveness of using Sentiment Analysis Tools for Opinion Mining
(SciTePress, 2016) Ding, Tao; Pan, Shimei
Sentiment analysis is increasingly used as a tool to gauge people’s opinions on the internet. For example, sentiment analysis has been widely used in assessing people’s opinions on hotels, products (e.g., books and consumer electronics), public policies, and political candidates. However, due to the complexity in automated text analysis, today’s sentiment analysis tools are far from perfect. For example, many of them are good at detecting useful mood signals but inadequate in tracking and inferencing the relationships between different moods and different targets. As a result, if not used carefully, the results from sentiment analysis can be meaningless or even misleading. In this paper, we present an empirical analysis of the effectiveness of using existing sentiment analysis tools in assessing people’s opinions in five different domains. We also proposed several effectiveness indicators that can be computed automatically to help avoid the potential pitfalls in misusing a sentiment analysis tool.

Browse

Recent Submissions