UAB - The University of Alabama at Birmingham

Research

Combatting spam, phishing, and malware
Spam enables various types of criminal activities. A spam campaign is the set of emails sent by a spammer, all for the same purpose and using the same infrastructure. We cluster spam into spam campaigns, to enable antispam workers to understand and combat spam. Our work with phishing and malware is analogous.
The Lobbying Disclosure Project
Using Computer and Information Sciences to Understand Organizational Engagement
Consolidating Client Name in the Lobbying Disclosure Database Using Efficient Clustering Technique
Due to errors and inconsistencies in manual typing, the name of a client often has multiple representations including erroneously spelled names and sometimes shorthand forms, presenting difficulties in associating lobbying activities and interests with one single client.Therefore, there is a need to consolidate various forms of names
of the same client into one group/cluster.
Accurate 3D Body Construction from 2D-Photograph for Body Fat Prediction
3D body volume construction from 2D body profile images can be a low-cost, much more convenient and safer alternative to estimate the body volume. Density (Mass/Volume) calculated using this estimated volume could be used to accurately predict the body fat percentage.
Content Based Image Clustering and Image Retrieval (CBIR)
Content-based Image Retrieval (CBIR) is the application of computer vision to the problem of searching for digital images in large databases. The main objective of this project is to develop an object-based image retrieval system, which incorporates Relevance Feedback (RF) and semantic clustering techniques to improve the accuracy and efficiency of the retrieval.
Image Spam Mining
Image spam prevents text based spam filters from detecting and blocking spam messages. This project investigates image spam with image segmentation and image clustering techniques in order to reveal the common sources, i.e. the spammers, of unsolicited emails.
Spatio-temporal Event Mining for Surveillance Video Databases
The major objective of this project is to develop an event mining system for surveillance video databases that incorporates various techniques from computer vision and spatio-temporal data mining such as object tracking, classification, and abnormal event (e.g., accidents and illegal U-turns) detection.
imArray
imArray is a NSF funded project carried out in collaboration with the Department of Biostatistics at UAB. We propose to develop an automatic high-performance microarray scanner software, which is intended to provide a comprehensive data and information management environment for microarray image analysis and microarray data mining from multi-modalities.
SEQOPTICS: Protein Sequence Clustering with Optics
SEQOPTICS is a data mining tool that clusters protein sequences on the basis of OPTICS (Ordering Points To Identify the Clustering Structure). SEQOPTICS emphasizes the visualization of results and supports interactive work.
Outlier Detection
An outlier is an observation that is numerically distant from the rest of the data. We introduce a novel method to find the outliers and strong outlier groups, based on the Maximum Flow Minimum Cut theorem from graph theory, and evaluate the outliers by outlier degrees.
Profiling Online Auction Sellers Using
Image-Editing Styles
Product images serve an important role in online auction listings. To stand out from competitors, veteran sellers often edit product images to attract potential buyers. Over time, many sellers have developed their own editing styles that recurrently appear in their image pool and are mostly distinct from other sellers, indicating a promising feature for seller profiling. Seller profiling is fundamental for the detection of account anomalies, which are often related to fraudulent acts. Numerous online auction guides suggest that buyers watch for anomalies in a seller’s auction listings (such as sudden changes in product categories, auction templates, and text fonts), because such anomalies often indicate account takeovers. We developed an automatic algorithm that can extract image editing styles to establish seller profiles.
Co-Op: A Brain Training Game
This link was prepared to demonstrate the first of eight levels for the grant proposal:
A Pilot Test of Social Cognitive Remediation for Major Depressive Disorder.
PI: Charles Brendan Clark, Ph.D.
University of Alabama at Birmingham

The link contains a demo to explain the first level of the game.

Permanent link to this article: http://kddm.cis.uab.edu/research/