Overview
The Intelligence and Data Management (iData) research group is a subgroup of the NUS Database Research Laboratory. Currently, our group consists of two faculty members, thirteen Phd. students, one research assistant and one intern.
Research Interests
Our research interest
span across the whole process of converting data into intelligence.
iData-ers view data as sources of intelligence and aim to extract
knowledge from data and information in an efficient and effective
manner so that the knowledge can be utilized to create intelligent
systems with applications in real life problem. The following
diagram summarized our research interests.
Data
This layer focused on the efficient indexing and query processing of data without too much emphasis on the semantic of the data. Information are abstracted as files, high dimensional data or generic structured data such as sequences, trees and graphs.
Information
Processing at the information layer will use more semantic meaning to the data. For example, a group of files can be seen as a relational databases while a digital data stream at the data layer can now be interpreted as an audio signal from an audio sensor. At this layer, techniques that are specific to each type of information (multimedia, software engineering data, biological data) will be studied with the support provided by the research being done at the data layer.
Knowledge
This layer deal with research on knowledge discovery techniques over both the data and information. While previous data mining techniques are mostly developed over generic data like tables, sequences and trees, we feel that introducing the semantic provided at the information layer will further enhance the result of mining. This will be the emphasis of our group at the knowledge mining layer.
Intelligence
Once knowledge are discovered, our aim is to utilize these knowledge to build intelligent systems that can help human users in their daily work. We envisioned that these systems will be a cross between expert systems that help to answer user's queries and monitoring systems that automatically detect events that are of interest to users. Challenges at this layer includes but is not limited to: ontology engineering, ontology managements, rules management and rule inferences.
Parallel/Distributed Processing using Modern Hardware
Our studies on all the four layers of processing above will be supported through the use of modern hardware architecture that facilitate the massive computation that is required to achieve our aim.
Latest News
We are happy to announce that our Gene Expression MINIng software Gemini II is available now!
This award represents the highest award that can be given in the database community for people who "make significant contributions to the field of database systems through research funding, education, and professional services".
1 research paper of our group is accepted by PVLDB!
1 research papers of our group is accepted by VLDB 2010!
1 research papers of our group is accepted by TKDE!
3 research papers of our group are accepted by SIGMOD 2010!
1 research papers of our group are accepted by ICDE 2010!