Agent-Augmented Co-Space: Growing Cognitive Autonomous Agents for Context-Aware Personalized Experience in Co-Space (2008-2011)

Supported by National Research Foundation - Interactive Digital Media (NRF-IDM) Programme

Team Members: Ah-Hwee Tan (PI), Yew-Soon Ong (co-PI), Chunyan Miao (co-PI), Budhitama Subagdja (Research Fellow), Chua Zin Yan (Project Officer), Xing Jiang (Project Officer); Collaborators: Una-May O'Reilly (MIT), Yuan Miao (Victoria University), Zhang Daqing (Institute TELECOM SudParis)

Co-Space is an initiative championed by MDA to develop interactive virtual worlds that are typically modeled after a real physical environment in terms of content, look-and-feel and functionalities. To enrich the experience of individual users in Co-Space, it is critical to incorporate knowledge and intelligent facilities to enhance the interactivity and playability within. To this end, this project proposes to develop and populate human-like cognitive agents in the form of autonomous avatars that roam in the landscape of Co-Space, develop an awareness of its surrounding and interact with users through their human avatars. With the autonomous avatars befriending and providing personalized context-aware services to human avatars, the content and services in Co-Space can then become active and readily available to the users.

A Co- Evolution Theory for Episodic and Semantic Memory  (2009-2011)

Supported by DSO National Laboratories, Singapore

Team Members: Ah-Hwee Tan (PI), Gee-Wah Ng (DSO), Di Wang (Project Officer)

This project aims to develop a co-evolution theory for the representation, learning, and processing of human declarative memory, comprising the episodic and semantic memory. By taking an interdisciplinary approach, we shall investigate the formation of episodic memory and how such representation may be translated into the more structured and permanent semantic memory store. Conversely, we shall study and model the role of semantic memory in making sense of one’s experience and guiding the formation of new episodic memory.

Completed Projects

Towards Integrated Neural Architectures for Memory Representation and Cognitive Information Processing (2007-2009)

Supported by DSO National Laboratories, Singapore

Team Members: Ah-Hwee Tan (PI), Gee-Wah Ng (DSO), Di Wang (Project Officer)

Cognitive information processing is a new and emerging research area with a great potential to leap-frog beyond the state-of-the-art intelligent systems. Under this collaborative project between NTU and DSO, we aim to develop a biologically inspired integrated neural architecture by tapping the rich know-how in the fields of neurobiology and cognitive science. Specifically we will develop a core set of high level cognitive capabilities, namely learning, reasoning, explaining, and robust coping with surprises, based on a myriad of memory constructs and their interactions.

Cognitive Information Systems for Situation Awareness Modelling, Context-Aware Presentation and Knowledge Discovery (2005-2008)

Supported by Intelligent Systems Centre and Singapore Technologies Engineering

Team Members: Ah-Hwee Tan (PI), Budhitama Subagdja (Research Fellow), Teng Teck Hou (PhD student, MOE Scholar), Dan Xiao (PhD student, part-time)

Situation awareness refers to the perception and understanding of one's environment for the purpose of planning and critical decision making. This project aims to develop a cognitive architecture for modelling situation awareness. Taking an adaptive learning approach, a self-organizing memory structure will be developed for modelling environment in terms of entities, their attributes with respect to space and time, events, trajectories, and missions. In contrast to traditional situation awareness models, the cognitive memory system will further incorporate a knowledge level for learning critical causal relationships between the actions of the entities, enabling one to perform scenario projection and hypothesis testing. The proposed research can be applied to a wide range of applications, including homeland security for tracking terrorist groups/activities as well as command and control in battlefield modelling and tactical warfare planning.

Intelligent Technologies for Multimedia Information Fusion and Analysis (2005-2008)

Supported in part by A*STAR Institute for Infocomm Research under I2R-SCE Joint Lab on Intelligent Media

Team Members: Ah-Hwee Tan (PI), Jamie Ng, Joo-Hwee Lim (co-PI, I²R), Tao Jiang (PhD student, MOE Scholar), Jiang Xing (PhD student, MOE Scholar), Nguyen Luong Dong (PhD Student, MOE Scholar, more members are listed under I2R-SCE Joint LabInformation in the ubiquitous media age is typically fragmented and appears in various unstructured and unlabelled forms as data, text, image, audio, and video.  This project aims to develop a framework for high-level level analysis and organization across mixed media information. For transforming raw information content into knowledge, the project will develop various cross-media and media-specific technologies for modeling and working with text, audio, images, and video data as well as their unification and association at the semantic conceptual level based on XML schema and MPEG7 standards. To deliver people-oriented rich media content and services to content producers and end users, we further study the issues of user modeling, and develop tools for user- and purpose-centric production, retrieval, organization and repurposing of media content from distributed sources.

Smart-Places: UWB-Enabled Context-Aware Service Environment (2004-2005)

Supported in part by A*STAR Pilot Programme on UWB and Pervasive Computing

Team Members: Ah-Hwee Tan (PI), Chuan-Heng Foh (co-PI), Hwee-Hwa Pang (co-PI, I²R), Ghim-Eng Yap (PhD student, A*Star Scholar)With the continual popularization of UWB technologies and mobile devices, users in the near future will be able to access applications and services from any location at any time. The benefits of UWB in high bandwidth transmission and precision localization create opportunities for developing smart places supported by context-aware mobile applications at locations of strategic importance in Singapore. This project proposes to develop an unified framework that integrates low level (physical) context information, such as locations, time, network condition, and device characteristics, as well as high level contextual information, such as the users' background, schedule, intention, and commitment. Based on the integrated framework, we will develop adaptive algorithms for learning and refining contextual knowledge in an online and interactive manner.

Completed Projects at A*Star Institute for Infocomm Research

Intelligent Cyber Agents (2001 - 2003)

Supported by A*STAR Core Research Funding

Principal investigator (PI) spearheading and managing multiple research projects. The Knowledge DMA project develops technologies for the extraction, discovery, management, and application of knowledge on the web. The other project Heterogeneous Agent-Based Research Platform (HARP) develops an agent-based platform to support the competitive intelligence activities of research scientists.

Image-Based Text Mining Research (2000 -2003)

Supported by A*STAR Research Funding

A collaboration project with the School of Computing at the National University of Singapore. I am a co-PI investigating new machine learning techniques and models for document classification and clustering. The project received a funding of half a million dollars over three years from A*STAR (formerly NSTB) and the Ministry of Education.

Text Mining (1999-2001)

Supported by A*STAR Core Research Funding

Principal investigator spearheading and managing multiple research projects for internet content mining, document categorization/clustering, personalization, and domain knowledge integration. Key technologies and systems delivered include

1.  Text Category eXpert (TCX): A document classification system that learns from examples as well as incorporate rule-based classification knowledge. The technology has been filed for patent application and licensed to a couple of companies for developing applications.

2.   User-Configurable Clustering (UCC): A new information management paradigm that integrates the flexibility of clustering systems and the predictability of categorization systems. UCC has been filed for patent application and integrated into Flexible Organizer for Competitive Intelligence (FOCI), a web-based tool for web based information integration, organization, tracking, and sharing.

Intelligent Fax Router (1996-1998)

Supported by National Computer Board, SingaporeProject manager of a national project funded by the Singapore National Computer Board (NCB) for developing an electronic document routing system that analyzed incoming facsimile documents and forwarded the documents automatically to their target recipients. The project funding for development and deployment was slightly more than half a million dollars. Technologies involved in this project include document image processing, printed/cursive character recognition, logical analysis, morphological name search, and semantic analysis. The system was deployed in many commercial and government organizations, including NCB, Singapore Polytechnic, National Library Board, MINDEF, Bank of Tokyo, and KRDL/LIT. The technology was successfully licensed and transferred to a local software firm WinSoft for commercialization in 1998.

Neural-Logic Networks (1994-1997)

Supported by Real World Computing Programme, Japan

A collaboration project under the Japan's Real World Computing partnership (RWCP, http://www.rwcp.or.jp) from which ISS/KRDL received a funding of 70 million Yens per year.  I was a project leader developing a new breed of knowledge systems that integrated the key strengths of neural network learning and symbolic knowledge inferencing. The technology was subsequently used to build a personalized information system that learned and incorporated user profile for news filtering.