Robert K. L. Gay

Nanyang Technological University, Tumasik, Singapore

Are you Robert K. L. Gay?

Claim your profile

Publications (75)30.38 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: 3D visualisation plays an important role in understanding abstract and complex concepts. In this paper, we move one step further by proposing a 3D multiuser collaborative virtual environment (CVE) system for e-learning. It provides an engaging learning environment, where the students and lecturers can collaboratively interact with the 3D e-learning contents, which will response based on law of physics or simulation rules. This would be particularly useful for those subjects that require multiuser collaboration. It also bridges the gap between lecturers and students by providing virtual real-time interactions, thus overcoming the limitations resulted from the distance issue in the Distance Learning.
    No preview · Article · Jul 2010 · International Journal of Applied Systemic Studies
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: One of the open problems in neural network research is how to automatically determine network architectures for given applications. In this brief, we propose a simple and efficient approach to automatically determine the number of hidden nodes in generalized single-hidden-layer feedforward networks (SLFNs) which need not be neural alike. This approach referred to as error minimized extreme learning machine (EM-ELM) can add random hidden nodes to SLFNs one by one or group by group (with varying group size). During the growth of the networks, the output weights are updated incrementally. The convergence of this approach is proved in this brief as well. Simulation results demonstrate and verify that our new approach is much faster than other sequential/incremental/growing algorithms with good generalization performance.
    Preview · Article · Sep 2009 · IEEE Transactions on Neural Networks
  • Guorui Feng · Guang-Bin Huang · Qingping Lin · Robert Kheng Leng Gay

    No preview · Article · Jan 2009
  • Source
    Guopeng Zhao · Zhiqi Shen · Chunyan Miao · Robert Gay
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper first reviews extreme learning machine (ELM) in light of coverpsilas theorem and interpolation for a comparative study with radial-basis function (RBF) networks. To improve generalization performance, a novel method of combining a set of single ELM networks using stacked generalization is proposed. Comparisons and experiment results show that the proposed stacking ELM outperforms a single ELM network for both regression and classification problems.
    Full-text · Conference Paper · Jul 2008
  • [Show abstract] [Hide abstract]
    ABSTRACT: Service orientation has emerged as a new promising paradigm for enterprise integration in the manufacturing sector. In this article, we focus on the approach and technologies for constructing a service oriented manufacturing environment. The service orientation is achieved via virtualization in which everything, including machines, equipments, devices, various data sources, applications, and processes are virtualized as standard-based Web services. The virtualization approach is based on the emerging Web Services Resource Framework (WS-RF). A case study of virtualizing an AGV system using WS-RF is described. The use of Semantic Web Services technologies to enhance manufacturing Web services for a semantic-rich environment is discussed, focusing on OWL-S for semantic markup of manufacturing Web services and OWL for the development of ontologies in the manufacturing domain. An enterprise integration architecture enabled by Semantic Web service composition is also discussed.
    No preview · Article · Jul 2007

  • No preview · Conference Paper · Jan 2007
  • Qingping Lin · Hoon Kang Neo · Liang Zhang · Guangbin Huang · Robert K. L. Gay
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a grid-based large-scale web3D collaborative virtual environment that has the capability of scaling across multiple geographically dispersed resources. The architecture consists of distributed mobile agents working cooperatively in supporting and managing the web3D collaborative virtual environments. The mobile agents' tasks include managing persistency and consistency of the virtual worlds, maintaining reliability and efficiency of user interactions, ensuring security and integrity of data and systems. The mobile agents are autonomous and have the ability of migrating among hosts to maximize resource utilizations. Grid technologies allow the mobile agents to execute and communicate securely in multiple administrative domains. Grid-based scheduling components and polices are integrated to provide intelligent resource optimizations. Furthermore, a better load-balancing can be achieved by utilizing additional or more accurate information like data-user proximity and hosts' workload. The result will be a more scalable and robust architecture for supporting large-scale web3D collaborative virtual environment.
    No preview · Conference Paper · Jan 2007
  • Source
    Hui Mien Lee · Wen Feng Lu · Bin Song · Zhiqi Shen · Zhonghua Yang · Robert Kheng Leng Gay
    [Show abstract] [Hide abstract]
    ABSTRACT: The manufacturing industry is facing unprecedented challenges in this dynamic economy and social environment. Factors like incorporation of quality services, environmental sustainability and the successful effective leveraging of industrial informatics for virtual enterprises are new determinants for a manufacturing enterprise to stay competitive. Among these, the environmental problems related to electronic waste have prompted the electronic products manufacturers to innovate and adopt new initiatives such as take back system and after‐sales service network. A concept with a holistic approach to integrate manufacturing and services with the considerations for environmental sustainability is being introduced here. Based on this, the service stage is discussed and a software infrastructure framework for this stage will be proposed. Finally, a case scenario for the use of computer in manufacturing environment is elaborated.
    Full-text · Article · Jan 2007 · International Journal of Services Operations and Informatics
  • [Show abstract] [Hide abstract]
    ABSTRACT: The existing Collaborative Virtual Environment (CVE) systems have limited scalability due to the constraints in computer processing power and network bandwidth of participating hosts. In this paper, we propose a grid-based large-scale collaborative virtual environment architecture to scale across multiple geographically dispersed resources. Tire architecture consists of distributed mobile agents working cooperatively in supporting and managing the collaborative virtual environments. The mobile agents are autonomous and have the ability of migrating among hosts to maximize resource utilizations. Grid technologies allow the mobile agents to execute and communicate securely in multiple administrative domains. Grid-based scheduling components and polices can be integrated to provide intelligent; resource optimizations. The result will be a more scalable architecture for supporting large-scale collaborative virtual environment.
    No preview · Conference Paper · Jan 2007
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A key issue in pedagogy is individualization, i.e., adapting the teaching to the needs of various learners. In many cases, however, current e-learning systems have so far focused most on porting existing courses with traditional teaching methods onto the web/virtual environments without any fine-tuning and adaptation to the learner needs, just making non-individualized teaching even more widely available. The intelligent agent technology has potential regarding the creation of more intelligent, personalized, adaptive and interactive e-learning applications, providing individualization and therefore enhancing the effects of learning. In this paper, an intelligent virtual teacher is presented to provide personalized content management, learner model, and adaptive instant interaction in virtual learning environment. Mentor provides information for the student, and rises to help whenever the student has lost the clues. The mind model of the mentor agent is proposed on top of the Dempster-Shafer Goal-Net architecture. User-awareness and context-awareness are both achieved by reasoning student activities and context evolvement. Proposed architecture is validated by applying on Singapore River City, an agent augmented virtual environment designed to engage and motivate students at the lower secondary level in Singapore. Extensive experiments illustrate the effectiveness of the proposed intelligent mentor where students have found the mentor agent as believable as a virtual teacher.
    Full-text · Article · Jan 2007
  • Source
    Zhiqi Shen · Chunyan Miao · Robert Gay · Chor Ping Low
    [Show abstract] [Hide abstract]
    ABSTRACT: A major drawback of current e-learning systems is that they are too disconnected from learner's learning preferences and learning goals. There has been a high demanding for learner centric e-learning systems. Research on personalized e-learning is emerging in recent years. However, most of the current research is focused on user profile modeling, and learning styles research, etc. In this paper, we propose a novel goal oriented approach towards learner centric and personalized e-Learning. With this approach, learning goals are immersed into the courses or learning objects to bridge the gap between the individual learner's goal and the learning objects. Personalized learning path which satisfies the learner's goals can be generated for individual learners. A prototype system is demonstrated as the proof of concept.
    Full-text · Article · Jan 2007
  • Hui Mien Lee · Robert Gay · Wen Feng Lu · Bin Song
    [Show abstract] [Hide abstract]
    ABSTRACT: Driven by the international pressure, various legislations such the WEEE and RoHS by the EU and the deteriorating environmental conditions, sustainable product development will take the centre stage for manufacturers in particularly the electrical and electronic manufacturers. One of the factors that is impeding sustainable product development currently is the deficiency of knowledge and lack of total management for the product life cycle from cradle to grave. In this paper, the objective is to develop a conceptual framework for managing the end-of-life information and design information in assistance of designing product with better environmental performance from a system perspective. The end-of-life stage which is formally being incorporated in an earlier work for Integrated Manufacturing and Product Service System (IMPSS) to close the product life cycle management loop will be formalized and structured for easier information sharing with design stage. Ontology will be employed for implementing the concept.
    No preview · Conference Paper · Sep 2006
  • Q.Z. Yang · C.Y. Miao · Y. Zhang · R. Gay
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an ontology modeling and engineering approach to semantic description and integration of product development processes. Using OWL and OWL-S, the proposed method formalizes the underlying semantic representations of the product development process in domain object ontologies and the generic problem solving structures in domain task ontologies. Both the domain object and task ontologies are incorporated in the OWL-S based application service ontologies to facilitate the semantic process description and semantic service discovery, composition in the integration of product development processes. The approach has been applied to the development of ontological models for the consumer product development process in a pilot project of a national research program in Singapore namely the Integrated Manufacturing and Service Systems (IMSS).
    No preview · Conference Paper · Sep 2006
  • Source
    Bing Duan · Habib Mir Mohamad Hosseini · Keck Voon Ling · Robert Kheng Leng Gay
    [Show abstract] [Hide abstract]
    ABSTRACT: Internet-based learning systems, or e-learning, are widely available in institutes, universities, and industrial companies, hosting regular or continuous education programs. The dream of teaching and learning from anywhere and at anytime becomes a reality due to the construction of e-learning infrastructure. Traditional teaching materials and methods are shifting to the new paradigm. In higher education, laboratory work is playing an important role in the area of training students and helping students to absorb more knowledge. With the goal of bringing e-learning to the traditional laboratory experiment, in this chapter, we present an architecture for an online laboratory e-learning system to facilitate the design and deployment of lab-based courses for e-education. The chapter provides an overall view of the system design and implementation so the Internet-based laboratory can be easily integrated with the e-learning infrastructure.
    Full-text · Article · Apr 2006 · International Journal of Distance Education Technologies
  • Source
    Chao Boon Teo · Robert Kheng Leng Gay
    [Show abstract] [Hide abstract]
    ABSTRACT: This article highlights basic issues that have hindered e-learning systems from becoming the revolutionary force it could be for education. While current systems aim to foster significant improvements in learning, this article argues that most systems are still limited to just being online repositories. This and the lack of learning personalization has become a topic for research. A knowledge-driven model to personalize e-learning is proposed in this article. A novel methodology for eliciting and personalizing tacit knowledge is presented. We focus on describing the complex information processing in terms of knowledge, rather than the details of its implementation.
    Preview · Article · Mar 2006 · Journal on Educational Resources in Computing
  • Source
    Jianshu Weng · Chunyan Miao · Angela Goh · Zhiqi Shen · Robert K. L. Gay
    [Show abstract] [Hide abstract]
    ABSTRACT: There exist a number of similarity-based recommendation communities, within which similar users' opinions are collected by users' agents to make predictions of their opinions on a new item. Similarity-based recommendation communities suffer from some significant limitations, such as scalability and susceptibility to the noise. In this paper, we propose a trust-based community to overcome these limitations. The trust-based recommendation community incorporates trust into the domain of item recommendation. Experimental results based on a real dataset show that trust-based community manages to outperform its similarity-based counterpart in terms of prediction accuracy, coverage, and robustness in the presence of noise.
    Full-text · Conference Paper · Jan 2006
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Recently there has been a great demand for extending high throughput life science research to bio-manufacturing. However, there is a gap from life science research to bio-manufacturing. Most existing bio-workflow tools/grid computing systems only provide an isolated solution to help bio-scientist to orchestrate bio-R&D operations such as bio-database query, bio-computation and analysis for biological problems in specific verticals. They are static and lack the ability to adapt in a dynamic changing environment. Manufacturing of biological materials such as diagnostics, therapeutics and prophylactics, or bio-manufacturing, typically involves many bioprocesses, each of which requires a set of bio-workflows to be choreographed. This is currently achieved by manually defining and managing the workflows for bioprocesses through different workflow tools. This paper proposes a novel goal-oriented approach to modeling bioprocesses, choreographing bio-workflows from different workflow tools, and to integrating agents, web services and workflows for automated execution. It demonstrates how a multi-agent system on a grid infrastructure can be further derived to adapt and automate complex bio-manufacturing workflow/processes in a dynamic changing environment. In this way, database access in a large data grids, high performance computing in a computational grid, and remote device control in a manufacturing grid, can be coupled to a supply chain management system to form a broad scale bio-manufacturing grid that streamlines the entire value chain from R&D, productisation and design of biological products.
    Full-text · Article · Jan 2006
  • Alireza Kashian · Robert Kheng Leng Gay · Abdul Halim Abdul Karim
    [Show abstract] [Hide abstract]
    ABSTRACT: Without textual descriptions or label information of images, searching semantic concepts in image databases is a very challenging task. Automatic annotation techniques for images are aimed to detect objects which are located visually inside images, like a tiger in grass. One challenge which remains to be solved is “Understanding”. Image understanding is something beyond automatic annotation scope. The second issue is manual annotation of images. In manual annotation, user contribution is important. In this demo, we have developed an online tool which simulates a collaborative environment to help users to generate several facts for selected images. Ontological thinking led us to devise a method for a simple user interface. We are also studying the construction of synergies out of generated facts for our future work.
    No preview · Conference Paper · Jan 2006
  • Q. Z. Yang · C. Y. Miao · Y. Zhang · R. Gay
    [Show abstract] [Hide abstract]
    ABSTRACT: Product sustainability approaches, such as life cycle assessment (LCA) and life cycle costing (LCC), are becoming increasingly critical to influence product decisions for all lifecycle stages. However, LCA and LCC methods must be integrated into the product lifecycle processes for sharing their data semantics with other applications in order to support decisions in the technical, ecological and economic aspects of products. Semantics sharing has raised big challenges in understanding and interpreting the intended meaning of LCA, LCC and other product data. This paper presents an ontology-driven, standard-based approach to the explicit capture and reuse of product data semantics for heterogeneous information sharing across lifecycle processes in computer aided design, quality assurance, LCA and LCC analysis, and product development process management. The approach incorporates object-based product data modeling, interoperability standardization, and ontology engineering to address the product data semantics sharing issues. A software implementation of the approach with a use scenario is also discussed in the paper.
    No preview · Conference Paper · Jan 2006
  • Source
    Zhiqi Shen · Chunyan Miao · Yuan Miao · Xuehong Tao · Robert Gay
    [Show abstract] [Hide abstract]
    ABSTRACT: Goal selection and action selection are important topics in agent research. This paper first describes an agent model, Goal Net, which supports multiple goal selection methods and action selection mechanisms for an agent. Then a goal selection algorithm and action selection mechanisms supported by Goal Net are presented. Examples from real system development are also given to illustrate the algorithm and mechanisms.
    Full-text · Conference Paper · Jan 2006

Publication Stats

799 Citations
30.38 Total Impact Points

Institutions

  • 1992-2010
    • Nanyang Technological University
      • • School of Electrical and Electronic Engineering
      • • School of Computer Engineering
      Tumasik, Singapore
  • 2005
    • University of Vic
      Vic, Catalonia, Spain
    • Peking University
      Peping, Beijing, China
  • 2004
    • Universitat Oberta de Catalunya
      Barcino, Catalonia, Spain
  • 1994-2004
    • Nanyang Normal University
      Nan-yang-shih, Henan Sheng, China