Journal of Intelligence and Information Systems,
Vol. 11, No. 2, November 2005
Comparison Shopping Systems using Image Retrieval based on Semantic Web
Kee-Sung Lee, Heung-Nam Kim, Young-Hoon Yu, and Gun-Sik Jo
Vol. 11, No. 2, Page: 1 ~ 15
Keywords : Semantic Web, Image Annotation, Comparison Shopping
The explosive growth of the Internet leads to various on-line shopping malls and active E-Commerce. however, as the internet has experienced continuous growth, users have to face a variety and a huge amount of items, and often waste a lot of time on purchasing items that are relevant to their interests. To overcome this problem the comparison shopping systems, which can help to compare items' information with those other shopping malls, have been issued as a solution. However, when users do not have much knowledge what they want to find, a keyword-based searching in the existing comparison shopping systems lead users to waste time for searching information. Thereby, the performance is fell down. To solve this problem in this research, we suggest the Comparison Shopping System using Image Retrieval based on Semantic Web. The proposed system can assist users who don't know items' information that they want to find and serve users for quickly comparing information among the items. In the proposed system we use semantic web technology. We insert the Semantic Annotation based on Ontology into items' image of each shopping mall. Consequently, we employ those images for searching the items instead of using a complex keyword. In order to evaluate performance of the proposed system we compare our experimental results with those of Keyword-based Comparison Shopping System and simple Semantic Web-based Comparison Shopping System. Our result shows that the proposed system has improved performance in comparison with the other systems.
A Study on the e-Learning Communities Interaction Under the CSCL by Using Network Mining
Namho Chung
Vol. 11, No. 2, Page: 17 ~ 29
Keywords : Computer Supported Corporative Work(CSCL), Network Mining, Social Network Analysis (SNA)
The purpose of the study was to explore the potential of the Social Network Analysis as an analytical tool for scientific investigation of learner-learner, or learner-tutor interaction within a Computer Supported Corporative Learning (CSCL) environment. Theoretical and methodological implication of the Social Network Analysis had been discussed. Following theoretical analysis, an exploratory empirical study was conducted to test statistical correlation between traditional performance measures such as achievement and team contribution index, and the centrality measure, one of the many quantitative measures the Social Network Analysis provides. Results indicate the centrality measure was correlated with the higher order teaming performance and the peer-evaluated contribution indices. An interpretation of the results and their implication to instructional design theory and practices were provided along with some suggestions for future research.
A Study of Dynamic Web Ontology for Comparison-shopping Agent based on Semantic Web
Su Kyoung Kim, and Ki Hing Ahn
Vol. 11, No. 2, Page: 31 ~ 45
In this paper, convert in RDF triple and a RDF document through RDF document converters and design metadata schema about a digital camcorder after use Wrapper technology, and acquiring commodity information of a HTML page about the digital camcorder which these papers are defined so as to be different by electronic commerce stores, and is expressed. Save in digital camcorder domain ontology storage that implemented to relational database to DCC knowledge base ontology as convert to OWL Web ontology based on designed metadata schema. Through compare with rdf and DCCKBO, mapping, and inference process, provide to buyers by DCC information of the store that had the commodity purchasing information which is the best, and proposed a dynamic Web ontology guessed to contents of the best commodity purchasing information, and to define domain ontology saved in DCCKBO.
Fuzzy Algorithm Development for the Integration of Vehicle Simulator with All Terrain Unmanned Vehicle
Duk Sun Yun, Hwan Sin Yu, and Ha Young Lim
Vol. 11, No. 2, Page: 47 ~ 57
In this research, the main theme is the system integration of driving simulator and unmanned vehicle. The total system is composed of the mater system and the slave system. The master system has a cockpit system and the driving simulator. The slave system means an unmanned vehicle, which is composed of the actuator system the sensory system and the vision system. The communication system is composed of RS-232C serial communication system which combines the master system with the slave system. To integrate both systems, the signal classification and system characteristics considered DSP(Digital Signal Processing) filter is designed with signal sampling and measurement theory. In addition, to simulate the motion of tele-operated unmanned vehicle on the driving simulator, the classical washout algorithm is applied to this filter, because the unmanned vehicle does not have a limited working space, while the driving simulator has a narrow working space and it is difficult to cover all the motion of the unmanned vehicle. Because the classical washout algorithm has a defect of fixed high pass later, fuzzy logic is applied to reimburse it through an adaptive filter and scale factor for realistic motion generation on the driving simulator.
Learning a Classifier for Weight Grouping of Export Containers
Jaeho Kang, Byoungho Kang, Kwang Ryel Ryu, and Kap Hwan Kim
Vol. 11, No. 2, Page: 59 ~ 79
Keywords : Container Weight Grouping, Rehandling, Cost-sensitive Learning
Export containers in a container terminal are usually classified into a few weight groups and those belonging to the same group are placed together on a same stack. The reason for this stacking by weight groups is that it becomes easy to have the heavier containers be loaded onto a ship before the lighter ones, which is important for the balancing of the ship. However, since the weight information available at the time of container arrival is only an estimate, those belonging to different weight groups are often stored together on a same stack. This becomes the cause of extra moves, or rehandlings, of containers at the time of loading to fetch out the heavier containers placed under the lighter ones. In this paper, we use machine learning techniques to derive a classifier that can classify the containers into the weight groups with improved accuracy. We also show that a more useful classifier can be derived by applying a cost-sensitive learning technique, for which we introduce a scheme of searching for a good cost matrix. Simulation experiments have shown that our proposed method can reduce about 57% of rehandlings when compared to the traditional weight grouping method.
Physiological Fuzzy Neural Networks for Image Recognition
Kwang-Baek Kim, Yong-Eun Moon, and Choong-Shik Park
Vol. 11, No. 2, Page: 81 ~ 103
Keywords : Nervous System, Agonistic Neuron, Antagonist Neurons, Bronchial Squamous Cell Carcinoma Images, Car Plate Images
The Neuron structure in a nervous system consists of inhibitory neurons and excitory neurons. Both neurons are activated by agonistic neurons and inactivated by antagonist neurons. In this paper, we proposed a physiological fuzzy neural network by analyzing the physiological neuron structure in the nervous system. The proposed structure selectively activates the neurons which go through a state of excitement caused by agonistic neurons and also transmit the signal of these neurons to the output layers. The proposed physiological fuzzy neural networks based on the nervous system consists of a input player, and the hidden layer which classifies features of learning data, and output layer. The proposed fuzzy neural network is applied to recognize bronchial squamous cell carcinoma images and car plate images. The result of the experiments shows that the learning time, the convergence, and the recognition rate of the proposed physiological fuzzy neural networks outperform the conventional neural networks.
Distributed REID Information Service Architecture for Ubiquitous Logistics
Jae Won Lee, and Young-Koo Lee
Vol. 11, No. 2, Page: 105 ~ 121
Keywords : Information Service Architecture, Physical Markup Language, RFID, Electronic Product Code
To realize a ubiquitous logistics management system using the smart object of Electronic Product Code(EPC) enabled RFID tag, the design and management of RFID Information Service is very important. RFID Information Service searches, transfers and responds to the other's PML request, but Physical Markup Language (PML) data management between trading system elements has issues of standardization of PML data description and processing, and problems of data traffic and communication time overload because of the innate distributed characteristics. As a complementary study, this research analyzes the usage patterns and data types of PML. On that analysis we provide a design of the distributed RFID Information Service architecture of PML data management that is using DB middleware. Standalone and Integrated type of RFID IS were proposed.
The Structure of Knowledge Management Capability and Its Impact on Organizational Performance
Jae-Nam Lee, and Jang-Hwan Lee
Vol. 11, No. 2, Page: 123 ~ 149
Keywords : Knowledge management capability, Organizational performance, Resource-based view
What the structure of knowledge management capability (KMC) to improve the organizational performance is an important issue for researchers and practitioners with growing interest in recent years. In this paper, we begin with a deep thinking about the resource-based view and knowledge-based view of the firm applying to knowledge management issues. By exploring the two underlying theories of knowledge management, together with an intensive review and interpretation of existing literatures, we obtain six major dimensions of KMC. We then propose an integrated conceptual model of KMC and its relationship with organizational performance. A PLS analysis of the gathered data from organizations in Korea which already have enterprise-wide knowledge management systems is conducted to validate the proposed model. We discuss several meaningful implications and draw several insightful conclusions surrounding the KMC.
The Effect of Knowledge Acquisition through OntoRule: XRML Approach
Sangun Park, Jae Kyu Lee, and Juyoung Kang
Vol. 11, No. 2, Page: 151 ~ 173
Keywords : Knowledge Acquisition, Rule Acquisition, Rule Identification, Ontology, OntoRule, Ontology Engineering, RuleML, XML
We developed a methodology of rule acquisition from texts such as Web pages which utilizes ontology in identification of rule components. We expect that the proposed methodology can reduce the bottleneck of rule acquisition and contribute to the utilization of rule based systems. As parts of our research, we designed an ontology for rule acquisition named OntoRule and proposed a rule acquisition methodology through OntoXRML which is an acquisition tool using OntoRule. Also, we evaluated our approach by calculating missed recommendations and wrong recommendations of rule components in rule acquisition experiments over three online bookstores.
Simultaneous Optimization Model of Case-Based Reasoning for Effective Customer Relationship Management
Hyunchul Ahn, Kyoung-jae Kim, and Ingoo Han
Vol. 11, No. 2, Page: 175 ~ 195
Keywords : Case-based reasoning, Genetic algorithms, Customer relationship management
Case-based reasoning(CBR) has been widely used in various areas due to its convenience and strength in complex problem solving. Generally, in order to obtain successful results from CBR, effective retrieval of useful prior cases for the given problem is essential. However, designing a good matching and retrieval mechanism for CBR systems is still a controversial research issue. In this study, we suggest a novel model for enhancing the performance of CBR systems - simultaneous optimization model of feature weights and instance selection using a genetic algorithm(GA). We apply it to a customer classification model which utilizes demographic characteristics of customers as inputs to predict their buying behavior for a specific product. Experimental results show that simultaneously optimized CBR may improve the classification accuracy and outperform various optimized models of CBR as well as other classification models including logistic regression, multiple discriminant analysis, artificial neural networks and support vector machines.

Advanced Search
Date Range