 |
Research
Research Summary:
Social bots for Healthcare: Community, Conversational and Cognitive Information Agents
We are developing a system called Cobot (for Community/Conversational bot) that consists of active agents participating in an online community of health information seekers. These agents monitor user conversations with other users in the community and provide personalized as well as community based responses and recommendations to users. One of the goals is to develop an innovative approach to delivering relevant healthcare information using a combination of Web 2.0 social networking and Artificial Intelligence information aggregation techniques as my thesis research. My long-term objective is to facilitate end users efficiently find personalized health-care and biomedical information using collaborative computing techniques.
Keywords: Agent Learning, Recommendation Systems, Case based Reasoning, Natural Language Processing, User Modeling
Knowledge Representation and Reasoning
The rapidly increasing volume of unstructured biomedical information poses the challenge of knowledge integration so as to build autonomic computing systems that can acquire, represent and learn such knowledge, and efficiently reason from it to aid in knowledge discovery and re-use. The construction of these automated systems to assist biomedical decision making is impeded by difficulties in formalizing knowledge and in encoding that knowledge for use by computer systems. My research focuses on developing efficient methods of information retrieval and extraction and build a semantic intelligence infrastructure using techniques of language processing, learning and reasoning. This requires automatic construction of knowledge models and ontologies for representing biological objects and processes, as well as methods for expressing hypotheses and 'biological inference rules' that will facilitate their evaluation against what is already known.
Keywords: Ontology Learning, Information Retrieval and Extraction, Applied Machine Learning, Natural Language Processing
Textual Case based Reasoning
Effective encoding of information is one of the keys to qualitative problem solving. My aim is to explore Knowledge representation
techniques that capture meaningful word associations occurring in documents. We have developed iReMedI, a TCBR based problem solving system. For representation we have used a combination of NLP and graph based techniques which we call as Shallow Syntactic Triples, Dependency Parses and Semantic Word Chains. To test their effectiveness we have developed retrieval techniques based on PageRank, Shortest Distance and Spreading Activation methods. The various algorithms developed and the comparative
analysis of their results provides us with useful insight for creating an effective problem solving and reasoning system.
Keywords: Knowledge Representation, Language Parsing, Knowledge Re-use and adaptation, Spreading Activation
|
