COMPUTER-BASED INTELLIGENT SUPPORT FOR MODERATELY ILL-STRUCTURED PROBLEMS
Problems are often categorized into two types: ill-structured and well-structured, in the context of education/learning, cognitive science and artificial intelligence. Then, from an educational viewpoint, ill-structured problems are further more important because they are useful to promote a learner to think about learning target deeply and to master computational or logical thinking skills, including metacognition. This paper proposes an additional characterization of problems by using two factors, (1) well/ill-structured domain model and (2) well/ill-structured problem setting. Based on this characterization, "moderately ill-structured problems" are defined as a category of problems specified by "well-structured domain model" and "ill-structured problem setting". If a problem is set in well-structured domain model, it is possible to realize computer-based monitoring and diagnosis of learner's activities for the problem. If the problem setting is ill-structured, for example, open-ended, a learner is required to engage in the problem as ill-structured one. Therefore, moderately ill-structured problems are promising to realize computer-based intelligent support for solving ill-structured problems, while keeping educational advantages of ill-structured problems. In this paper, a definition of moderately ill-structured problems is described. Then, using the arithmetic word problems as an example of learning target domains, this paper describes (1) well-structured domain model of arithmetic word problems, and (2) design of moderately ill-structured problem as "problem-posing assignment" based on the domain model. Moreover, (3) implementation of an intelligent learning environment that requests a learner to solve ill-structured problems as problem-posing is introduced. The environment has functions to diagnose learner's behaviors and to give individual feedback.
BIG DATA: REDUCTION NOT COMPRESSION
To Be Announced (TBA)
INTEGRATED SMART NEIGHBOURHOOD APPLICATION TO SUSTAIN AN INNOVATIVE DIGITAL ECONOMY IN THE 4IR AND BIG DATA ERA
Malaysia is moving from a social paradigm shift of Agricultural through Digital era; from an industrial paradigm shift of 1st Industrial Revolution through 4th Industrial Revolution (4IR) in which Big data plays a significant role. This study involved the design of a smart neighbourhood application, to sustain an innovative economy in this 4IR Big Data era. This study involved a five-part study: Part 1 investigated on the appropriate drivers of the dimension of the innovative Digital Malaysia concept before theories of digital signal processing, visualisation and appropriate ambient computing could be applied into the design framework of the Integrated Smart Neighbourhood in a Smart City/Smart Village in Malaysia. The main drivers and dimensions of Digital Malaysia had to come from a knowledge-based society framework which encompaces dimensions that would drive both economic and social lives of the population of the country generally and smart neighbourhood, specifically.The knowledge society framework involved defining and verifying the definition of the Knowledge Society (KS) in the Digital Malaysian context based on a five-round Delphi (R1-R5) technique conducted on ten experts; Part II, involved a semi-structured interview with two prominent experts; Part III involved public survey conducted to verify the significant dimensions of Malaysia’s KS, the important indicators of KS and to validate the generalisable measurement model for Malaysia’s KS based on the innovative Digital Malaysia context. Based on the 5-Round Delphi, KS in the Digital Malaysia context was defined; Part V involved development of tools and devices as proof of concept for sustainability and wellbeing of a specific section of the population (that is, the elderly) in a smart neighbourhood) in the big data era. A smart neighbourhood in the context of this study takes into consideration the Knowledge Society (KS) model in an innovative Digital Malaysia of which its members in the neighbourhood appreciate knowledge and data, shows concern in the holistic development of human capital which encompassesthe ability to generate, access, use, share, and disseminate knowledge and data through new technologies, in tandem with the innovative DM Dimensions: Technology, Education, Governance, Social and Environment. The framework was verified for its ‘goodness of fit’ model using the Structural Equation Modeling (SEM), based on the AMOS output.The elements that were significant were related to three main elements: environment: cleanliness; security and health. Thus, these elements were used to design the Smart Neighbourhood (SCSV) framework, which integrated the design of tools and devices such as the waste management system (health and cleanliness), the surveillance robot and human behaviour detection and analysis (security), the ambient interface, using the analog/digital watch (for elderly populace of the smart home in the smart neighbourhood through wearable computing).The waste management system involve the use RFID reader and camera are mounted in the truck to capture the serial number of the bin as well as the image of the bin and forwarded to the control server via GSM/GPRS network.The surveillance robot, JagaBot TM is an intelligent application based on a physical robotic system that can execute dynamic on site inspection and mitigation action upon detection of an anomalous event. It also enables the physical instantiation of remote operator on the event scene through JagaBot TM as an electromechanical avatar. The wearable computing device used by the elderly of a smart home, in the smart neighbourhood in a smart city/smart village can assist the elderly to monitor not just the cleanliness, security of the environment but also allows him/her to contact. All the data collected can be stored in the main server of the smart neighbourhood and can be presented by the dashboard technology using Big Data Analytics. These data could then be linked to the national intelligent data and knowledge lake to be shared by all citizens for societal well being.
CONVERSATIONAL RECOMMENDER SYSTEM BASED ON FUNCTIONAL REQUIREMENTS
Conversation Recommender System (CRS) is a system that applies the conversational mechanism between users and systems to refine needs and recommend products. CRS is one of the knowledge based recommender system, where interaction is generated based on the knowledge base of the system. In many studies, CRS interacts with users through product technical specification. For complex products that have many specification, however, not everyone is familiar with the technical features of this product. Thus, the interaction based on functional requirements will make it easier for users. Functional requirements are desired functions of the product that the user wants to buy. This paper will present an overview of our previous works, in developing CRS with interaction based on functional requirements. We use ontology as a knowledge base. CRS is able to mimic the ability of a professional sales support in interacting with users. The user study shows that usefulness of interaction in our CRS is better than that CRS based on product technical feature. Meanwhile, the query refinement mechanism is able to narrow down the average results’ size significantly within 4 interactions (< 6.9%).