Journal of Intelligence and Information Systems,
Vol. 13, No. 2, June 2007
Formation of Nearest Neighbors Set Based on Similarity Threshold
Jae Sik Lee, and Jin Chun Lee
Vol. 13, No. 2, Page: 1 ~ 14
Keywords : Nearest Neighbors, Case-based Reasoning, Classification
Case-based reasoning (CBR) is one of the most widely applied data mining techniques and has proven its effectiveness in various domains. Since CBR is basically based on k-Nearest Neighbors (NN) method, the value of k affects the performance of CBR model directly. Once the value of k is set, it is fixed for the lifetime of the CBR model. However, if the value is set greater or smaller than the optimal value, the performance of CBR model will be deteriorated. In this research, we propose a new method of composing the NN set using similarity scores as themselves, which we shall call s-NN method, rather than using the fixed value of k. In the s-NN method, the different number of nearest neighbors can be selected for each new case. Performance evaluation using the data from UCI Machine Learning Repository shows that the CBR model adopting the s-NN method outperforms the CBR model adopting the traditional k-NN method.
SOHO Bankruptcy Prediction Using Modified Bagging Predictors
Seung Hyuk Kim, and Jong Woo Kim
Vol. 13, No. 2, Page: 15 ~ 26
Keywords : Bankruptcy Prediction, Data Mining, Bagging Predictors, Decision Tree Induction
In this study, a SOHO (Small Office Home Office) bankruptcy prediction model is proposed using Modified Bagging Predictors which is modification of traditional Bagging Predictors. There have been several studies on bankruptcy prediction for large and middle size companies. However, little studies have been done for SOHOs. In commercial banks, loan approval processes for SOHOs are usually less structured than those for large and middle size companies, and largely depend on partial information such as credit scores. In this study, we use a real SOHO loan approval data set of a Korean bank. First, decision tree induction techniques and artificial neural networks are applied to the data set, and the results are not satisfactory. Bagging Predictors which has been not previously applied for bankruptcy prediction and Modified Bagging Predictors which is proposed in this paper are applied to the data set. The experimental results show that Modified Bagging Predictors provides better performance than decision tree inductions techniques, artificial neural networks, and Bagging Predictors.
A Structured Methodology with Device Collaboration Diagram for Evaluating Context-Aware Systems
Oh Byung Kwon , and Nam Yeon Lee
Vol. 13, No. 2, Page: 27 ~ 41
Keywords : Context-aware system, Device collaboration modeling, Device collaboration, System evaluation
Nowadays the context-aware systems have been regarded as a promising opportunity to create differentiated e-marketplaces. Context-aware system aims to provide personalized services by understanding the user's current situation which is automatically acquired from the context data. This aim naturally leads us to a motivation to evaluate to what extent a system is context-aware. Even though lots of endeavors have stated about the level of context-aware system, a structured evaluation has been so far very rare. Hence, the purpose of this paper is to propose a two-phased methodology for assessing context-aware systems. In the first phase, we perform a requisite analysis to discriminate a context-aware system from general or context-based systems. Once an information system is recognized as context-aware system, then level of collaboration, mobility and embeddedness is derived to determine the level of context-aware system in the second phase. To do so, device collaboration diagram (DCD) is proposed to visualize the system architecture. Moreover, readiness and level of system are Jointly considered in the phase to provide a development strategy for each context-aware system development project. To show the feasibility of the idea proposed in this paper, legacy context-aware systems are actually analyzed and evaluated.
Intelligence e-Learning System Supporting Participation of Students based on Face Recognition
Kyoung Yul Bea, Jin Oo Joung , and Seung Wook Min
Vol. 13, No. 2, Page: 43 ~ 53
Keywords : Biometries, Face Recognition, e-Learning, Middle ware
e-Learning education system as the next educational trend supporting remote and multimedia education. However, the students stay mainly at remote place and it is hard to certificate whether he is really studying now or not. To solve this problem, some solutions were proposed such as instructor's supervision by real time motion picture or message exchanging. Unhappily, as you can see, it needs much cost to establish the motion exchanging system and trampling upon human rights could occasion to reduce the student's will. Accordingly, we propose the new intelligent system based on face recognition to reduce the system cost. The e-Learning system running on the web page can check the student's status by motion image, and the images transfer to the instructor. For this study, 20 students and one instructor takes part in capturing and recognizing the face images. And the result produces the prevention the leave of students from lecture and improvement of attention.
A DNA Sequence Alignment Algorithm Using Quality Information and a Fuzzy Inference Method
Kwang-Baek Kim
Vol. 13, No. 2, Page: 55 ~ 68
Keywords : DNA sequence alignment algorithms, Quality information, Fuzzy inference method, Needleman-Wunsch, NCBI (National Center for Biotechnology Information)
DNA sequence alignment algorithms in computational molecular biology have been improved by diverse methods. In this paper, we proposed a DNA sequence alignment algorithm utilizing quality information and a fuzzy inference method utilizing characteristics of DNA sequence fragments and a fuzzy logic system in order to improve conventional DNA sequence alignment methods using DNA sequence quality information. In conventional algorithms, DNA sequence alignment scores were calculated by the global sequence alignment algorithm proposed by Needleman-Wunsch applying quality information of each DNA fragment. However, there may be errors in the process for calculating DNA sequence alignment scores in case of low quality of DNA fragment tips, because overall DNA sequence quality information are used. In the proposed method, exact DNA sequence alignment can be achieved in spite of low quality of DNA fragment tips by improvement of conventional algorithms using quality information. And also, mapping score parameters used to calculate DNA sequence alignment scores, are dynamically adjusted by the fuzzy logic system utilizing lengths of DNA fragments and frequencies of low quality DNA bases in the fragments. From the experiments by applying real genome data of NCBI (National Center for Biotechnology Information), we could see that the proposed method was more efficient than conventional algorithms using quality information in DNA sequence alignment.
Considering Customer Buying Sequences to Enhance the Quality of Collaborative Filtering
Yeong-Bin Cho, and Yoon-Ho Cho
Vol. 13, No. 2, Page: 69 ~ 80
Keywords : Recommender systems, Purchase sequence, Collaborative Filtering, Association Rules
The preferences of customers change over time. However, existing collaborative filtering (CF) systems are static, since they only incorporate information regarding whether a customer buys a product during a certain period and do not make use of the purchase sequences of customers. Therefore, the quality of the recommendations of the typical CF could be improved through the use of information on such sequences. In this study, we propose a new methodology for enhancing the quality of CF recommendation that uses customer purchase sequences. The proposed methodology is applied to a large department store in Korea and compared to existing CF techniques. Various experiments using real-world data demonstrate that the proposed methodology provides higher quality recommendations than do typical CF techniques with better performance.

Advanced Search
Date Range