UMBC Information Systems Department
Browse by
Recent Submissions
-
Spatio-Temporal Climate Data Causality Analytics – An Analysis of ENSO’s Global Impacts
Numerous studies have indicated that El Niño and the Southern Oscillation (ENSO) could have determinant impacts on remote weather and climate using the conventional correlation-based methods, which however cannot identify ... -
Mineral Dust Detection Using Satellite Data
Mineral dust, defined as aerosol originating from the soil, can have various harmful effects to the environment and human health. The detection of dust, and particularly incoming dust storms, may help prevent some of these ... -
Benchmarking parallel implementations of cloud type clustering from satellite data
The study of clouds, i.e., where they occur and what are their characteristics, plays a key role in the understanding of climate change. The aim of this project is to use machine learning in conjunction with parallel ... -
Analysis and Prediction of 911 Calls based on Location using Spark Big Data Platform
(UMBC, 2019)Proper management of critical resources like Police Force and Ambulance Services is the key to establish peace quickly in times of crisis. When a police district receives a 911 call, quick response can be the difference ... -
Subgrid variations of the cloud water and droplet number concentration over the tropical ocean: satellite observations and implications for warm rain simulations in climate models
(Copernicus Publications, 2019-01-28)One of the challenges in representing warm rain processes in global climate models (GCMs) is related to the representation of the subgrid variability of cloud properties, such as cloud water and cloud droplet number ... -
Deep Learning Based Mineral Dust Detection and Feature Selection
Dust storm affects human health and the environment. In this study, we develop deep learning models to identify dust from cloud and surface using MODIS observations and CALIPSO data. We also identified the best subset of ... -
Stochastic Precipitation Generation for the Potomac River Basin Using Hidden Markov Models
A daily precipitation generator based on hidden Markov models (HMM) using satellite precipitation estimates is studied for the Potomac river basin in Eastern USA over the wet season months of July to September. GPM-IMERG ... -
Performance Benchmarking of Parallel Hyperparameter Tuning for Deep Learning based Tornado Predictions
(UMBC, 2020-05-31)Predicting violent storms and dangerous weather conditions with current models can take a long time due to the immense complexity associated with weather simulation. Machine learning has the potential to classify tornadic ... -
Early Detection of Cybersecurity Threats Using Collaborative Cognition
(IEEE, 2018-11-19)The early detection of cybersecurity events such as attacks is challenging given the constantly evolving threat landscape. Even with advanced monitoring, sophisticated attackers can spend more than 100 days in a system ... -
Situation-Aware Access Control in Federated Data-as-a-Service for Maritime Search and Rescue
(IEEE, 2019-08-29)Maritime Search and Rescue missions involve complex operations in which multiple entities, playing different roles in dynamic situations, benefit from sharing mission-dependent data. We propose an approach to support ... -
Affinity Propagation Initialisation Based Proximity Clustering For Labeling in Natural Language Based Big Data Systems
(IEEE, 2020-06-23)A key challenge for natural language based large text data is automatically extracting knowledge, in terms of entities and relations, embedded in it. State of the art relation extraction systems requires large amounts of ... -
Automating GDPR Compliance using Policy Integrated Blockchain
Data Protection regulations, like GDPR, mandate security controls to secure Personal Identifiable Information (PII) of the users which they share with service providers. With the volume of shared data reaching exascale ... -
Tornado Storm Data Synthesization using Deep Convolutional Generative Adversarial Network: Related Works and Implementation Details
Predicting violent storms and dangerous weather conditions with current models can take a long time due to the immense complexity associated with weather simulation. Machine learning has the potential to classify tornadic ... -
An Adaptive DPPM for Efficient and Robust Visible Light Communication Across the Air-Water Interface
(IEEE, 2020-05-02)The scarcity of the optical power is the main challenge for underwater visible light communication. It becomes worst for communication across the air-water interface because of the reflection of light from the air-water ... -
Chasing Lions: Co-Designing Human-Drone Interaction in Sub-Saharan Africa
(2020-05-17)Drones are an exciting technology that is quickly being adopted in the global consumer market. Africa has become a center of deployment with the first drone airport established in Rwanda and drones currently being used for ... -
Towards More Universal Wayfinding Technologies: Navigation Preferences Across Disabilities
Accessibility researchers have been studying wayfinding technologies for people with disabilities for decades, typically focusing on solutions within disability populations - for example, technologies to support blind ... -
A User Study on a De-biased Career Recommender System
AI is increasingly being used in making consequential decisions such as determining whether someone is granted parole or not (Angwin et al., 2016). Unfortunately, there have been a wide range of recent discoveries of biased ... -
Privacy and Power: Acknowledging the Importance of Privacy Research and Design for Vulnerable Populations
(ACM, 2020-04)Privacy researchers and designers must take into consideration the unique needs and challenges of vulnerable populations. Normative and privileged lenses can impair conceptualizations of identities and privacy needs, as ... -
Mitigating Socio-lingustic Bias in Job Recommendation
With increasing diversity in the job market as well as the workforce, employers receive resumes from an increasingly diverse population. Many employers have started using automated resume screening to filter the many ...
RSS 1.0