At Kno.e.sis, we take pride in working on multidisciplinary research in which new advances result by working on complex real world problems of significant social and economic significance. These team projects involve real world data, cutting edge technologies, and close collaboration with researchers in different domains. Some examples that give you a glimpse are:
Reducing hospital readmission for chronic heart patients using low cost sensors and mobile application supported semantic computing: 50% of chronic heart patients are readmitted within 6 months of initial hospitalization, costing the US health care industry 17 billion dollars a year. A multidisciplinary team involving a top practicing surgeon in cardiology, a medical informatician and Kno.e.sis’ computer scientists are developing a system involving non-invasive low cost sensors and mobile application based system to address this challenging problem.
PI: Amit Sheth.
Co-PIs: T. K. Prasad.
Keywords: chronic heart failure, cardiology, semantic perception, semantic sensor web, Health 2.0, machine perception – explanation and discrimination, mobile health.
Semantic Platform for Open Materials Science and Engineering: Innovations in materials play an essential role in our progress towards a better life - from improving laptop battery life to developing protective gears that prevent life threatening injuries and making aircraft more efficient. However, it often takes 20 years from the time of discovery to when a new material is put into practical applications. The Whitehouse’s Materials Genome Initiative (MGI) seeks to improve the US’ competitiveness in the 21st Century by discovering, manufacturing, and deploying advanced materials twice as fast, at a fraction of the cost. Kno.e.sis’ Federated Semantic Services Platform for Open Materials Science and Engineering project, involving a collaboration between computer and material scientists, will allow it to play a central role in developing the Digital Data component of MGI’s Materials Innovation Infrastructure.
Funding: AFRL (Rome and WPAFB) $740,000,
PI: Amit Sheth.
Co-PIs: T.K. Prasad and Raghu Srinivasan.
Keywords: structural materials, functional materials, materials ontologies, materials database knowledge discovery and data mining, semantic annotation,semantic search, access control, linked material data, semantic interoperability.
SoCS: Social Media Enhanced Organizational Sensemaking in Emergency Response: Online social networks and always-connected mobile devices have created an immense opportunity that empowers citizens and organizations to communicate and coordinate effectively in the wake of critical events. Specifically, there have been many isolated examples of using Twitter to provide timely and situational information about emergencies to relief organizations, and to conduct ad-hoc coordination. This research involving cognitive scientists and computer scientists at Kno.e.sis, in collaboration with Ohio State University, seeks to understand the full ramifications of using social networks in a more concerted manner for effective organizational sensemaking in such contexts.
Funding: NSF $480,000.
PI: Amit Sheth.
Co-PIs: John Flach and Valerie Shalin Keywords: Social Networking, Emergency Response, Content Analysis, Network Analysis, Organizational Sensemaking, Collaborative Decision Making.
Diffuse Coronary Artery Disease Detection: Coronary heart diseases remain one of the leading causes of death in most western societies. Improved diagnostic tools are needed that can detect these diseases at an early stage and determine the severity of the disease at that stage. Thus, the general objective of this project is to develop a novel rationale for diagnosis of diffuse coronary artery disease (DCAD) using clinical non-invasive imaging of the coronary arteries. The indices of diagnosis will be validated in studies of an atherosclerotic porcine model with DCAD. Our unique algorithms for accurately extracting morphometric data from computerized tomography angiography (CTA) images of normal and disease patients along with our quantitative approach uniquely position us to undertake this research.
Funding: NIH $385,423.
PI: Thomas Wischgoll.
Keywords: medical imaging, image processing, visualization.
PREscription Drug abuse Online-Surveillance and Epidemiology (PREDOSE): The non-medical use of pharmaceutical opioids has been identified as one of the fastest growing forms of drug abuse in the U.S. This NIH sponsored interdisciplinary project between the Center for Interventions, Treatment and Addictions Research (CITAR) and Kno.e.sis provides an alternative to traditional interview of subjects with the study of Web 2.0 empowered social platforms, including Web forums for detecting patterns and changes in the non-medical use of pharmaceutical and other illicit drugs.
Funding: NIH $401,500.
PIs: Raminta Daniulaityte (CITAR), Amit Sheth (Kno.e.sis).
Keywords: prescription drug abuse, drug abuse ontology, semantic entity extraction, relationship extraction, semantic web.
Scientific Knowledge Exploration using Semiautomatically created Background Knowledge: Life science researchers currently search and sift through a growing amount of scientific literature to gain insights and elicit knowledge. This research creates and applies contextually relevant background knowledge to ease the challenging tasks of information extraction, search and exploration. A detailed background knowledge is created using DOOZER, a tool to create an initial domain model by mining relevant Wikipedia content, followed by a focused knowledge (entity-relationship) extraction from relevant scientific literature using shallow NLP techniques. Life scientists then use SCOONER, a tool that supports knowledge exploration. This research is evaluated and used by biologists at the Air Force Research Lab in the area of human performance and cognition.
Funding: Henry Jackson Foundation ($400,000); Hewlett Packard ($70,000)
PI: Amit Sheth.
Keywords: automatic domain model extraction, focused knowledge extraction, semantic knowledge exploration, knowledge elicitation, human performance and cognition, DOOZER, SCOONER.
Integrated -Omics - Understanding Human Biology by Studying Whole Systems : The study of biology is undergoing a transformation that is changing the way scientists look at living systems. Traditional studies have tended to focus on just one gene or one protein, ignoring the complex interactions between genes, proteins, and metabolites that give rise to cells, tissues and organisms. In recent years, technologies such as genomics, transcriptomics, and metabolomics have allowed a broader and more holistic study of life. Working together with the Nuclear Magnetic Resonance lab at Wright State University and the Air Force Research Lab, we are developing web-based analysis platforms that allow scientists to integrate information from different -omics technologies to obtain a clearer understanding of the marvelous complexity of interactions in all living things.
PI: Michael Raymer.
Keywords: bioinformatics, genomics, metabolomics, transcriptomics, eScience.
High Confidence Protein Structure Prediction: Understanding protein structure and the forces that drive protein folding is one of the most fundamental and challenging problems in biochemistry. Finding computer-based methods for predicting the structure of proteins has remained a challenging task, even as computing power and algorithm sophistication has grown. In collaboration with Dr. Jerry Alter's lab, (Department of Biochemistry and Molecular Biology, Wright State University) we have developed a technique that improves the reliability of protein structure prediction algorithms by including experimental information in the model selection process. MRAN - Modification Reactivity Analysis combines experimental data from proteolysis or residue modification reactions with computational modeling of protein structure to yield highly-reliable predictions of protein structures. The resulting models are of suitable quality to serve as targets for pharmaceutical drug design.
PI: Michael Raymer.
Keywords: protein folding, protein structure, drug design.
Semantic Problem-Solving environment (PSE) for T. cruzi (SPSE): Approximately 18 million people are infected with the T. cruzi parasite. As many as 40% of these suffer from Chagas disease, characterized by some as the new AIDS of the Americas. In this NIH sponsored collaboration with University of Georgia, Athens’ Center for Tropical and Emerging Global Diseases and the National Center for Biomedical Ontologies, we have developed a number of semantic web tools with advanced capabilities such as provenance and access control to help scientists analyze experimental data and scientific literature in their effort to find potential vaccine targets.
Funding: NIH/NHLBI $1,515,656.
PI: Amit Sheth.
Keywords: Trypanosoma cruzi, Semantic Web, Semantic Web Service, semantic provenance, RDF access control, Ontology of Parasite Life Cycle, Parasite Experiment Ontology.