• The KIPS Transactions:PartB
• /
• v.10B no.3
• /
• pp.287-296
• /
• 2003

There has been much research focused on collaborative filtering technique in Recommender System. However, these studies have shown the First-Rater Problem and the Sparsity Problem. The main purpose of this Paper is to solve these Problems. In this Paper, we suggest the user's predicting preference method using Bayesian estimated value and the associative user clustering for the recalculation of preference. In addition to this method, to complement a shortcoming, which doesn't regard the attribution of item, we use Representative Attribute-Neighborhood method that is used for the prediction when we find the similar neighborhood through extracting the representative attribution, which most affect the preference. We improved the efficiency by using the associative user's clustering analysis in order to calculate the preference of specific item within the cluster item vector to the collaborative filtering algorithm. Besides, for the problem of the Sparsity and First-Rater, through using Association Rule Hypergraph Partitioning algorithm associative users are clustered according to the genre. New users are classified into one of these genres by Naive Bayes classifier. In addition, in order to get the similarity value between users belonged to the classified genre and new users, and this paper allows the different estimated value to item which user evaluated through Naive Bayes learning. As applying the preference granted the estimated value to Pearson correlation coefficient, it can make the higher accuracy because the errors that cause the missing value come less. We evaluate our method on a large collaborative filtering database of user rating and it significantly outperforms previous proposed method.

• Journal of the Korean Statistical Society
• /
• v.30 no.2
• /
• pp.247-263
• /
• 2001

This paper concerns a problem of classification based on training dta. A framework of information geometry is given to elucidate the characteristics of discriminant functions including logistic discrimination and AdaBoost. We discuss a class of loss functions from a unified viewpoint.

• Journal for History of Mathematics
• /
• v.13 no.1
• /
• pp.99-112
• /
• 2000

In this paper we discuss the teaching methods about statistical inferences. Bayesian methods have the attractive feature that statistical conclusions can be stated using the language of subjective probability. Simple methods of teaching Bayes' rule described, and these methods are illustrated for inference and prediction problems for one proportions. Also, we discuss the advantages and disadvantages of traditional and Bayesian approachs in teaching inference.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.316-325
• /
• 2003

A user preference prediction method using an exiting collaborative filtering technique has used the nearest-neighborhood method based on the user preference about items and has sought the user's similarity from the Pearson correlation coefficient. Therefore, it does not reflect any contents about items and also solve the problem of the sparsity. This study suggests the preference prediction system using the similarity weight granted Bayesian estimated value and the associative user clustering to complement problems of an exiting collaborative preference prediction method. This method suggested in this paper groups the user according to the Genre by using Association Rule Hypergraph Partitioning Algorithm and the new user is classified into one of these Genres by Naive Bayes classifier to slove the problem of sparsity in the collaborative filtering system. Besides, for get the similarity between users belonged to the classified genre and new users, this study allows the different estimated value to item which user vote through Naive Bayes learning. If the preference with estimated value is applied to the exiting Pearson correlation coefficient, it is able to promote the precision of the prediction by reducing the error of the prediction because of missing value. To estimate the performance of suggested method, the suggested method is compared with existing collaborative filtering techniques. As a result, the proposed method is efficient for improving the accuracy of prediction through solving problems of existing collaborative filtering techniques.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.1
• /
• pp.39-49
• /
• 2003

Watermark detection has a crucial role in copyright protection of and authentication for multimedia and has classically been tackled by means of correlation-based algorithms. Nevertheless, when watermark embedding does not obey an additive rule, correlation-based detection is not the optimum choice. So a new detection algorithm is proposed which is optimum for non-additive watermark embedding. By relying on statistical decision theory, the proposed method is derived according to the Bayes decision theory, Neyman-Pearson criterion, and distribution of wavelet coefficients, thus permitting to minimize the missed detection probability subject to a given false detection probability. The superiority of the proposed method has been tested from a robustness perspective. The results confirm the superiority of the proposed technique over classical correlation- based method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.3A
• /
• pp.221-230
• /
• 2002

This paper presents a new moving object segmentation algorithm using markov random field. The algorithm is based on signal detection theory. That is to say, motion of moving object is decided by binary decision rule, and false decision is corrected by markov random field model. The procedure toward complete segmentation consists of two steps: motion detection and object segmentation. First, motion detection decides the presence of motion on velocity vector by binary decision rule. And velocity vector is generated by optical flow. Second, object segmentation cancels noise by Bayes rule. Experimental results demonstrate the efficiency of the presented method.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.7
• /
• pp.170-178
• /
• 1994

The nearest neighbor classification rule is widely used because it is not only simple but the error rate is asymptotically less than twice Bayes theoretical minimum error. But the method basically use the whole training patterns as the reference vectors. so that both storage and classification time increase as the number of training patterns increases. LVQ(Learning Vector Quantization) resolved this problem by training the reference vectors instead of just storing the whole training patterns. But it is a heuristic algorithm which has no theoretic background there is no terminating condition and it requires a lot of iterations to get to meaningful result. This paper is to propose a new training method of the reference vectors. which minimize the given error function. The nearest neighbor network,the network version of the nearest neighbor classification rule is proposed. The network is funtionally identical to the nearest neighbor classification rule is proposed. The network is funtionally identical to the nearest neighbor classification rule and the reference vectors are represented by the weights between the nodes. The network is trained to minimize the error function with respect to the weights by the steepest descent method. The learning algorithm is derived and it is shown that the proposed method can adjust more reference vectors than LVQ in each iteration. Experiment showed that the proposed method requires less iterations and the error rate is smaller than that of LVQ2.

• Journal of the Korean Statistical Society
• /
• v.10
• /
• pp.128-139
• /
• 1981

The Bayesian sequential estimation problem for k parameters exponential families is considered using loss related to the Fisher information. Tractable expressions for the Bayes estimator and the posterior expected loss are found, and the myopic or one-step-ahead stopping rule is defined. Sufficient conditions are given for optimality of the myopic procedure, and the myopic procedure is shown to be asymptotically optimal in all cases considered.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.104-107
• /
• 2003

본 논문에서는 웨이브릿 영역에서 HVS 및 NVF 함수를 사용하여 영상특성에 기반한 통계적 판정법을 이용한 적응 워터마크 검출 알고리즘을 판정법을 제안한다. 워터마크는 4레벨로 분해된 웨이브릿 영역에서 JND(just noticeable difference) 특성과 NVF(noise visibility function)를 이용한 통계적 특성을 기반으로 정상상태 가우시안 모델에 따라 지각적 동조 특성을 이용하여 적응적으로 삽입하고, Bayes 이론 및 Neyman-Pearson 정리를 이용한 통계적 판정법을 이용하여 워터마크를 추출함으로써 기존의 통계적 판정법 보다 정확하게 워터마크 존재 유무를 판정 할 수 있음을 확인하였다.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1821-1822
• /
• 2007

무선 센서 네트워크에서 위치인식 기술은 데이터 수집, 라우팅, 위치기반 서비스와 같은 기술에 필수적인 기술이다. 본 논문에서는 베이즈 이론을 이용한 그리드방식의 분산형 위치 인식기술을 제안한다. 이 기법은 센서 노드들이 받은 신호세기를 바탕으로 하여 그리드를 구성해서 베이즈 이론을 이용하여 가장 큰 확률을 갖는 그리드를 자신의 위치로 인식하는 방식이다. 우리는 시뮬레이션을 통하여 기존의 방식보다 제안된 알고리즘이 정확한 위치를 갖으며, 더욱 효율적인 연산을 수행함을 알 수 있다.