A UTA computer scientist is using machine learning to develop a novel deep learning technique that uses algorithms that mimic the structure and function of neural networks in the brain to create a deep learning pipeline that can lead to a new convolution neural network for graph classification.

Making big data more accessible

A UTA computer science professor and his team are working to develop a process by which data points in multiple graph layers of a very large dataset can be connected in a way that is both highly scalable and will allow analysts to look at it in greater depth.

Balancing supply and demand in the electricity market

Researchers at UTA are working to determine how to meet the demands of an extremely dynamic and uncertain energy market by developing machine-learning models that predict real-time market prices and manage large-scale participation of residential demand-response programs.

Customized treatment for lung cancer patients

A UTA researcher is developing algorithms for predicting clinical outcomes using automated pathological image analyses of biopsy images that will help pinpoint care for lung cancer patients.

A better experience for mobile users

A UTA computer scientist is developing a framework for wireless carriers and internet providers to incorporate data obtained through context-aware sensing that factors in user location, the type of applications being accessed and even a user’s emotional state that would allow companies to make adjustments to optimize the user experience.

Ensuring quality and credibility of information in knowledge networks

A UTA computer scientist has been developing an electronic fact-checking system called ClaimBuster for several years, and recently led a multi-institution, multi-disciplinary team in the first phase of a National Science Foundation Convergence Accelerator Pilot program to deliver a system that will enable verifiably credible, open-knowledge networks.

Making raw data more useful

A team of researchers led by UTA is working to increase the role of humans in the data-science pipeline to address the shortcoming of computers’ inability to understand nuance and mitigating factors that could make raw data more usable.

Resources

Database Exploration Lab

The DBX Lab investigates fundamental research issues arising in Big Data. Research encompasses diverse areas such as data mining, information retrieval, data uncertainty and probabilistic methods, approximate query processing, data summarization, data analytics and data exploration of hidden web databases, social and collaborative media.

Human-Centered Computing Lab

The Human-Centered Computing Lab specializes in human-computer interaction, including human-robot collaboration systems, medical imaging, bioinformatics, multimodal sensing, vocational computing, virtual reality, rehabilitation, and games.

Innovative Data Intelligence Research Lab

Research focuses on building large-scale human-assisting and human-assisted data and information systems with high usability, low cost and applications for social good.

Machine Learning and Computer Vision for Clinical Applications Lab

Research focuses on developing machine learning/deep learning methods for fundamental computer vision problems including object motion tracking, segmentation, 3D reconstruction, classification and image captioning in 2D/3D images including RGBD images, remote sensing data, 3D CT/MRI medical images and biomedical text.

Mobile Computing and Security Lab

Research includes mobile computing, Internet of things, security, and privacy-preserving computing.

Vision-Learning-Mining Research Lab

The VLM Lab conducts research in the areas of computer vision, machine learning and data mining. Current areas of focus include human motion analysis, gesture and sign language recognition, and hand pose estimation.

COSMOS Center

The Center on Stochastic Modeling, Optimization, and Statistics (COSMOS) researches the design and modeling of complex real-world systems, in particular, to develop new methods for making sound decisions. COSMOS methods seek to integrate statistics, optimization, and simulation/stochastic modeling to achieve better solutions more efficiently, and COSMOS applications customize approaches to match the needs of the decision-maker.

ACTION Lab

Conducts exploratory research in urban traffic management and provides engineering services and product-grade traffic management solutions and software packages to transportation agencies and industry partners.