UMBC Information Systems Department
Browse by
Recent Submissions
-
RadSense: Enabling one hand and no hands interaction for sterile manipulation of medical images using Doppler radar
(Elsevier, 2019-11-15)In this paper, we show how surgeons can interact with medical images using finger and hand gestures in two situations: one hand-free and no hands-free interaction. We explain how interaction with only one hand or a couple ... -
Blockchains for Government: Use Cases and Challenges
Blockchain is the technology used by developers of cryptocurrencies, like Bitcoin, to enable exchange of financial “coins” between participants in the absence of a trusted third party to ensure the transaction, such as is ... -
IDIOMS: Infectious Disease Imaging Outbreak Monitoring System
(ACM, 2020-11)In this commentary, we propose a framework for convergence accelerator research leveraging AI models with medical images for effective diagnosis, monitoring, and treatment of diseases with pandemic potential. The goal is ... -
Supporting Instructors to Provide Emotional and Instructional Scaffolding for English Language Learners through Biosensor-based Feedback
(ACM, 2020-10)Delivering a presentation has been reported as one of the most anxiety-provoking tasks faced by English Language Learners. Researchers suggest that instructors should be more aware of the learners' emotional states to ... -
The role of virtual reality in preparing graduate students for community engagement
(2020-10-22)Community engagement (CE) experiences in higher education have been shown to lead to greater student engagement and graduation rates. Students also develop learning, personal, and social competencies in the affective domain ... -
LASO: Exploiting Locomotive and Acoustic Signatures over the Edge to Annotate IMU Data for Human Activity Recognition
Annotated IMU sensor data from smart devices and wearables are essential for developing supervised models for fine-grained human activity recognition, albeit generating sufficient annotated data for diverse human activities ... -
Deep multi-scale learning for automatic tracking of internal layers of ice in radar data
(Cambridge University Press, 2020-10-12)In this study, our goal is to track internal ice layers on the Snow Radar data collected by NASA Operation IceBridge. We examine the application of deep learning methods on radar data gathered from polar regions. Artificial ... -
Scalable Aggregation Service for Satellite Remote Sensing Data
(Springer, Cham, 2020-09-29)With the advances of satellite remote sensing techniques, we are receiving huge amount of satellite observation data for the Earth. While the data greatly helps Earth scientists on their research, conducting data processing ... -
Generating Realistic COVID19 X-rays with a Mean Teacher + Transfer Learning GAN
(2020-09-26)COVID-19 is a novel infectious disease responsible for over 800K deaths worldwide as of August 2020. The need for rapid testing is a high priority and alternative testing strategies including X-ray image classification are ... -
Mining sensor datasets with spatiotemporal neighborhoods
(2013-11-06)Many spatiotemporal data mining methods are dependent on how relationships between a spatiotemporal unit and its neighbors are defined. These relationships are often termed the neighborhood of a spatiotemporal object. The ... -
Hypertext: from Text to Expertext
Efforts to exploit technology so as to add extra dimensions to text have occurred throughout history, but the electronic computer has opened new vistas. The modern history of hypertext begins with the text `As We May Think' ... -
Characterizing Search Spaces
A heuristic is good on a search space to the extent that it llows the prediction of which states are near to the goal. In this paper heuristics are investigated on several different search spaces. A measure is proposed for ... -
Organizational roles and communication modes in team work
(IEEE, 2001-01-06)We have surveyed ten collaborators' perceptions on the value of nine communication modes: email, telephone, pen-and-paper, computer conferencing, telephone conferencing, face-to-face, fax, post, and whiteboard. Eight roles ... -
Forecasting Exchange Rates: A Neuro-Fuzzy Approach
This paper presents an adaptive neuro-fuzzy inference system (ANFIS) for USD/JPY exchange rates forecasting. Previous work often used time series techniques and neural networks (NN). ANFIS can be used to better explain ... -
A Top-k Analysis Using Multi-level Association Rule Mining for Autism Treatments
Association rule mining is based on associations of attribute values in a database. To facilitate finding meaningful rules, we segment the database by a categorization of database records based on a taxonomy on one of the ... -
Estimation Metrics for Courseware Maintenance Effort
Software engineering methods and metrics to estimate development time for the development and maintenance of computer-based training (CBT) differ from methods and metrics used to develop large information systems. The ... -
Modeling the Dynamics of Using a Collaborative Hypertext
(Walter de Gruyter GmbH, 2000-12-01)The dynamics of using a collaborative hypertext system is analyzed and modeled, based on time series data from the real users. First, we studied how users access a shared workspace simultaneously. Traditional time series ... -
Hypertext to Knowledge to Workflow
The engineering hypothesis is that a hypertext-like, collaborative authoring system can provide an appropriate infrastructure for a knowledge and workflow management system. A hierarchical, hypertext infrastructure with ... -
Applying Information Technology to Financial Statement Analysis for Market Capitalization Prediction
(Scientific Research Publishing, 2013-01)Determining which attributes may be employed for predicting the market capitalization of a business firm is a challenging task which may benefit from research intersecting principles of accounting and finance with information ... -
Filtering the piotroski portfolio: the roles of economic sector, small cap, and technical momentum
Background and Objective: In one of the most cited, value-investing results, a portfolio of approximately 100 stocks is selected based on value and fundamental factors. If an investor wants to select 10 of those recommended ...
RSS 1.0