Journal of Intelligence and Information Systems,
Vol. 15, No. 3, September 2009
Ensemble Learning for Solving Data Imbalance in Bankruptcy Prediction
Myong-Jong Kim
Vol. 15, No. 3, Page: 1 ~ 15
Keywords : Support Vector Machine, Under-Sampling, Over-Sampling, Bankruptcy Prediction, Geometric Mean-based Boosting
In a classification problem, data imbalance occurs when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. This paper proposes a Geometric Mean-based Boosting (GM-Boost) to resolve the problem of data imbalance. Since GM-Boost introduces the notion of geometric mean, it can perform learning process considering both majority and minority sides, and reinforce the learning on misclassified data. An empirical study with bankruptcy prediction on Korea companies shows that GM-Boost has the higher classification accuracy than previous methods including Under-sampling, Over-Sampling, and AdaBoost, used in imbalanced data and robust learning performance regardless of the degree of data imbalance.
Java based Platform for Educational Robots on AVR
Lee Sub Lee, and Seong Hoon Kim
Vol. 15, No. 3, Page: 17 ~ 29
C programming is a main programming for the Educational Robot Arm which is based on AVR ATmega128. The development environment is not integrated, so it is complex and difficult to study for middle or high school students who want to learn programming and control the educational robot arm. Furthermore, there is no debug and testing environment support. This paper presents a Java-based development platform for the educational robot arm. This platform includes: an up-to-date tiny Java Virtual Machine (NanoVM) for the educational robot arm; An Eclipse based Java integrated development environment as an Eclipse plug-in; a 3D simulator on the PCs to support testing and debugging programs without real robots. The Java programming environment makes development for educational robot arm easier for students.
Effectiveness of Model-Driven Development Process : Case Study
Sungwook Moon , and Saneung Hong
Vol. 15, No. 3, Page: 31 ~ 51
Keywords : MDE, MDA, MDD, Case Study
Research on how to develop information systems efficiently and effectively since early 1960s has resulted in many techniques, methods and methodologies. Only a few of them, however, have been successfully practiced in the field. Model-Driven Development(MDD) is an innovative approach emphasizing the central role of model for development activities, attracting many practitioners' attention as well as researchers'. As MDD matures, many researchers have been trying to establish the evidence of its effectiveness. But many of them only suggest lessons learned or report limited evidence of effectiveness based on isolated case studies. This paper reports the state of the art of Model-Driven Engineering(MDE) and its major issues. We reviewed a number of papers and collected the conceptual definitions of MDE effectiveness from the technological and organizational perspectives. A case study in which MDD technology was adopted has been performed in order to measure the effectiveness of MDD quantitatively and qualitatively. This paper also analyzes and summarizes key considerations and lessons learned for IT organizations to adopt MDE successfully from the case study.
A Model of English Part-Of-Speech Determination for English-Korean Machine Translation
Sung Dong Kim, and Sung Hoon Park
Vol. 15, No. 3, Page: 53 ~ 65
Keywords : Machine Translation, Part-Of-Speech Determination, Part-Of-Speech Tagging, Statistical Methods
The part-of-speech determination is necessary for resolving the part-of-speech ambiguity in English-Korean machine translation. The part-of-speech ambiguity causes high parsing complexity and makes the accurate translation difficult. In order to solve the problem, the resolution of the part-of-speech ambiguity must be performed after the lexical analysis and before the parsing. This paper proposes the CatAmRes model, which resolves the part-of-speech ambiguity, and compares the performance with that of other part-of-speech tagging methods. CatAmRes model determines the part-of-speech using the probability distribution from Bayesian network training and the statistical information, which are based on the Penn Treebank corpus. The proposed CatAmRes model consists of Calculator and POSDeterminer. Calculator calculates the degree of appropriateness of the partof-speech, and POSDeterminer determines the part-of-speech of the word based on the calculated values. In the experiment, we measure the performance using sentences from WSJ, Brown, IBM corpus.
Ontology based Preprocessing Scheme for Mining Data Streams from Sensor Networks )
Jason J. Jung
Vol. 15, No. 3, Page: 67 ~ 80
Keywords : Ontology, Sensor networks, Knowledge discovery
By a number of sensors and sensor networks, we can collect environmental information from a certain sensor space. To discover more useful information and knowledge, we want to employ data mining methodologies to sensor data stream from such sensor spaces. In this paper, we present a novel data preprocessing scheme to improve the performances of the data mining algorithms. Especially, ontologies are applied to represent meanings of the sensor data. For evaluating the proposed method, we have collected sensor streams for about 30 days, and simulated them to compare with other approaches.
Customer buying process based Managerial factors for ISM Differentiation
Weon Sang Yoo, Hyun Soo Han , and Ja Heon Koo
Vol. 15, No. 3, Page: 81 ~ 102
Keywords : ISM(Internet Shopping Mall), Differentiation Strategy, Customer Buying Decision Process
In this study, we investigated how to achieve differentiation for the ISM (Internet Shopping Mall) to improve profitability, which is required for survival in the fiercely competitive ISM industry. We analyzed implementation level key managerial factors that could contribute to the differentiation of the ISM. The research model is constructed through integration of two distinctive research streams of e-commerce. The one is B2C differentiation strategy research, most of which are conceptual and conducted at a strategy level, and the other is empirical research analyzing the antecedents of customer satisfaction at the ISM. This study is organized as follows. First, we draw upon transaction cost theory to organize constructs representing customer value associated with the customer buying decision process. Next, after reviewing comprehensive managerial factors that could impact on customer value, we selected 15 managerial factors that could contribute to the differentiation of the ISM to deliver value to customers. Finally, the resulting structural model is validated through empirical analyses. The results provide insights for future studies on ISM differentiation.
Design and Implementation of A Real Time Process Management System for Telecom Operations and Management
Byeong Yun Chang , Byungjoo Park , and Seung June Hwang
Vol. 15, No. 3, Page: 103 ~ 118
To face with the fast and ever changing telecommunication environments, we need a real time process management system that can detect abnormal events in real time and warn the suspicious events to operations personnel. Additionally, a real time process management system can be adapted fast to various services that are developed by telecom companies. In this paper we develop a real time process management system to monitor and analyze telecom operations and management processes in real time. Toward this, we design application and database architectures of telecom operations and management processes based on Enhanced Telecom Operations Map (eTOM) that is business process framework in telecommunication operations and management field and recognized as an international standard in ITU-T M.3050. With these application and databasearchitectures we implement eight main functions for the real time process management system based on service oriented architecture. Therefore, new services can be applied to these functions fast. Also, the functions can detect abnormal event fast. Finally, since the functions are developed along with the international standard, the system has the flexibility for the development in various situations. Overall, this research can be a good guideline of developing a process management system regarding the telecom operations and management field or other fields that need to manage the processes in real time.
Design and Implementation of the Simulator for Evaluating the Performance of Container Cranes
Seung Hwan Won, and Sang Hei Choi
Vol. 15, No. 3, Page: 119 ~ 136
Keywords : Container Crane, Simulation, Mechanical Productivity, Performance Evaluation
According to the increase of container flows and the appearance of large-sized container vessels, the container handling equipment in ports is evolving continuously. This research introduces the simulation model for evaluating in detail the mechanical productivity of container cranes. The model considers a single trolley and dual trolleys as the mechanism of a container crane and a single lift, a twin lift, and a tandem lift as the spreader type of it. Additionally, the detail specifications such as the dimension and the speed of a container crane are inputted and the kinematic characteristics of it are simulated. The model also considers the size of a vessel, the storage position of containers in the vessel, and the weight of containers as external physical constraints. Experimental conditions can be configured conveniently because various parameters in the model are separated. Moreover, the model can accommodate flexibly new equipment types and the changes of the existing equipment because it is designed and developed in object-oriented concept
Hybrid Heuristic Applied by the Opportunity Time to Solve the Vehicle Routing and Scheduling Problem with Time Window
Young Hoon Yu, Sang Jin Cha, and Geun Sik Jo
Vol. 15, No. 3, Page: 137 ~ 150
Keywords : VRSPTW(Vehicle Routing and Scheduling Problem with Time Window), Insertion Heuristic, Tabu Search, Opportunity Time, Opportunity Time, 2-Opt Algorithm
This paper proposes the hybrid heuristic method to apply the opportunity time to solve the vehicle routing and scheduling problem with time constraints(VRSPTW). The opportunity time indicates the idle time which remains after the vehicle performs the unloading service required by each customer's node. In this proposed heuristic, we add the constraints to VRSPTW model for the opportunity time. We also obtain the initial solution by applying the cost evaluation function to the insertion strategy considering the opportunity time. In addition, we improve the former result by applying the opportunity time to the tabu search strategy by swapping the customer's node. Finally, we suggest the construction strategies of initial routing which can efficiently acquire the nearest optimal solution from various types of data in terms of geographical condition, scheduling horizon and vehicle capacity. Our experiment show that our heuristic can get the nearest optimal solution more efficiently than the Solomon's I1 heuristic.
Design and Evaluation of ANFIS-based Classification Model
Hee Seok Song, and Jea Kyeong Kim
Vol. 15, No. 3, Page: 151 ~ 165
Keywords : Fuzzy System, Fuzzy Neural Network, ANFIS
Fuzzy neural network is an integrated model of artificial neural network and fuzzy system and it has been successfully applied in control and forecasting area. Recently ANFIS(Adaptive Network-based Fuzzy Inference System) has been noticed widely among various fuzzy neural network models because of its outstanding accuracy of control and forecasting area. We design a new classification model based on ANFIS and evaluate it in terms of classification accuracy. We identified ANFIS-based classification model has higher classification accuracy compared to existing classification model, C5.0 decision tree model by comparing their experimental results.

Advanced Search
Date Range