Eugene's research spans the areas of information retrieval, natural language processing, data mining, and human computer interaction. Eugene is a Sloan Research Fellow, a past member of the DARPA Computer Science Study Group, recipient of best paper awards from SIGMOD, SIGIR, and WSDM conferences. and of the 2013 Karen Spark Jones award from the British Computer Society.

Extremely large (aka high-performance) computing systems have become critical instruments in theorlds grandest scientific and engineering challenges. Designed, built and managed by computer scientists and engineers, these systems' principal users are experts from other domains. Dorian studies the theory and practice of system software that makes large, complex computer systems accessible to computer systems non=experts - in particular the performance, scalability and reliability issues that abound in large scale computer environments.

Dr. Choi has been active in the field of Natural Language Processing (NLP). He has presented many state-of-the-art NLP models that automatically derive various linguistic patterns from unstructured text. These models are publicly available through the cloud-based NLP platform called ELIT that Dr. Choi has created to promote academic and industrial research. He has also introduced novel machine comprehension models to identify personal entities and infer explicit and implicit contexts in multiparty dialogue, which can be used to build question answering systems on daily conversion. For medical informatics, Dr. Choi has developed innovative models to classify severity levels on radiology reports using deep neural networks and detect early stages of Alzheimer’s disease using meta-semantic analysis, which show similar accuracy as human experts in those domains.

Signal processing, machine learning and physiological modeling to reduce costs, increase accuracy, and improve access in healthcare using high frequency multivariate data streams. Theoretical developments focus on building confidence intervals and trust metrics for fusing predictive algorithms and scaling analysis of medical data beyond conventional clinical capacity. Application areas include critical care, sleep & circadian rhythms, perinatal monitoring, and resource-constrained mHealth in the US & LMICs.

I research and develop innovative technology based on Artificial Intelligence, Data Mining, and Natural Language Processing to support teaching and improve learning.

My research focuses on the development of novel data mining and machine learning algorithms for healthcare applications. In particular, I am interested in building interpretable models using dimensionality reduction and modern time series analysis.

Dr. Li's research interests include multidimensional biomedical signal processing, advanced patient monitoring, artifact and noise analysis, machine learning, and large physiological database analysis.

My recent focus has been on applying artificial intelligence and language processing techniques to develop interactive tools for researchers in the health sciences. I am also interested in tools to assist in the composition process. ​

Dr. Mahmoudi's research is at the interface of machine learning, artificial intelligence and neuroscience my research is to better understand the information processing in the brain and restore normal function after injures or neuropsychiatric diseases by developing intelligent neural interface systems that continuously sense the dynamics of brain states and learn to optimally modulate those states to achieve a desired therapeutic or behavioral outcome.

My research focuses on tools to enhance visibility, debugging and performance in system programs and operating systems.

Dr. Nagy's research expertise is in scientific computation, numerical linear algebra, and ill-posed inverse problems. He has done a substantial amount of work on the development of algorithms and software for image processing, including reconstruction, deblurring, and enhancement. His research has been funded by grants from the National Science Foundation (NSF), Air Force Office of Scientific Research (AFOSR) and the National Institutes of Health (NIH).

I have extensive experience in statistical modeling and computing with applications to statistical genetics and genomics. My recent research is focused on developing Bayesian model-based methods to analyze data generated from applications of next-generation sequencing technologies such as ChIP-seq, RNA-seq, Hi-C, WGBS, resequencing, and on developing software so that the methods can be easily adopted by the research community.. I am also actively collaborating with biomedical scientists and clinicians on projects that utilize next-generation sequencing technologies to better understand genomics and epigenomics.

My general field of interest is computational methods for inverse problems arising in medical and geophysical imaging. My research is interdisciplinary in nature and covers a variety of topics ranging from mathematical theory via design of numerical algorithms and efficient computational methods towards solving problems arising in real-world applications.

Our lab focuses on developing novel systems that are used to manage, explore, integrate and process large (>1TB) biomedical, clinical, and imaging datasets, particularly those related to cancer. This is a highly collaborative effort and involves researchers from multiple disciplines and institutions. In the coming years, the research will make extensive use of Big Data systems such as Spark and Drill; multi-modal fusion of data; and novel systems to visualize and explore such diverse datasets.

Dr. Sun's research focuses on the personalized and preventive health measures of chronic diseases across ethnic groups, to better understand the disease etiology and to improve the predictive modeling of the development, treatment and prevention of diseases. His research interests include novel study designs and applications using high-dimensional multi-omic analysis and phenomics approach.

Vaidy's research interests are in high performance and cloud computing, collaborative frameworks, and data science, with a focus on privacy and security. He is the principal architect of several software systems for metacomputing and collaboration, and his work is supported by grants from the National Science Foundation and the Air Force Office of Scientific Research.

Mathematical and numerical modeling of problems of real interest, with particular emphasis on cardiovascular diseases. Computational mechanics on real problems demands the most advanced numerical methods and parallel architectures. We work on image processing applied to cardiovascular sciences to perform massive simulations of patient-specific geometries for a fast and effective computation of quantities of medical interest and for the creation of decision-support tools.

Ymir's research focuses on creating, improving and understanding the large-scale systems that organize and process information and help us communicate. He is particularly interested in socially motivated real-world problems that embody deep trade-offs within distributed data replication -- caching, live streaming and multicast -- and in security.
Ymir co-founded Syndis in 2013, a company that simulates sophisticated cyberattacks against large companies. His TEDx talk on "Why I teach people how to hack"has received over 1,000,000 views on YouTube. Ymir's software has been used in cloud products at IBM, databases at Yahoo! and at other major companies. He holds four patents.

Professor Waller's research involves the development and application of statistical methods for spatially referenced data including applications in environmental justice, neurology, epidemiology, disease surveillance, conservation biology, and disease ecology. He has published in a variety of biostatistical, statistical, environmental health, and ecology journals and is co-author with Carol Gotway of the text Applied Spatial Statistics for Public Health Data (2004, Wiley).

Whereas computer scientists have defined how to arrange storage to meet specific metrics such as fault tolerance and access speed, in neuroscience the metrics are observable but the system unknown. I am working to model information in the brain as a storage problem to better learn how we collect and interpret signals from our world, working towards a robust fault tolerance model for the brain.

My research is focused on bioinformatics.

The Cancer Data Science lab explores how learning algorithms can be used to improve basic cancer research and clinical care. We develop machine learning and image analysis methods to analyze and integrate imaging, genomic and clinical data with the aims of improving the precision of medical interventions and gaining insights into disease mechanisms.

Dr. Kong's research interests include biomedical image analysis, computer-aid diagnosis, machine learning, 2D/3D whole-slide microscopy image processing, computer vision, bioimaging informatics, and signal processing for large-scale biomedical translational research. He has established multiple Computer-aided Diagnosis systems and quantitative data integration methods for different cancer diseases.

My research brings together concepts and tools across signal processing, information theory, control theory, optimization, and machine learning (ML) to design physiologically-inspired models and predictive analytic algorithms. A major focus of my ongoing research is in the intensive care unit (ICU) where my team is developing advanced ML algorithms capable of summarizing large volumes of continuously measured patient data, with the goal of prediction of life threatening clinical events and risk assessment.