• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.36T no.4
• /
• pp.24-29
• /
• 1999

In this paper, a simple contour-preserving filtering algorithm is proposed. The goal of the contour-preserving filtering method is to remove noise ad granularity as the preprocessing for the image segmentation procedure. Our method finds edge map and separates the image into the edge region and the non-edge region using this edge map. For the non-edge region, typical smoothing filters could be used to remove the noise and the small areas during the segmentation procedure. The result of simulation shows that our method is slightly better than the typical methods such as the median filtering and gradient inverse weighted filtering in the point of view of analysis of variance (ANOVA).

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.05a
• /
• pp.232-239
• /
• 2005

Collaborative-filtering-enabled Web sites that recommend books, CDs, movies, and so on, have become very popular on the Internet. Such sites recommend items to a user on the basis of the opinions of other users with similar tastes. This paper discuss an approach to collaborative filtering based on the Simple Bayesian and apply this model to two variants of the collaborative filtering. One is user-based collaborative filtering, which makes predictions based on the users' similarities. The other is item-based collaborative filtering which makes predictions based on the items' similarities. To evaluate the proposed algorithms, this paper used a database of movie recommendations. Empirical results show that the proposed Bayesian approaches outperform typical correlation-based collaborative filtering algorithms.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.2
• /
• pp.105-109
• /
• 2006

In this paper, we constructed a two-phase spam-mail filtering system based on the lexical and conceptual information. There are two kinds of information that can distinguish the spam mail from the ham (non-spam) mail. The definite information is the mail sender's information, URL, a certain spam keyword list, and the less definite information is the word list and concept codes extracted from the mail body. We first classified the spam mail by using the definite information, and then used the less definite information. We used the lexical information and concept codes contained in the email body for SVM learning in the 2nd phase. According to our results the ham misclassification rate was reduced if more lexical information was used as features, and the spam misclassification rate was reduced when the concept codes were included in features as well.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.10
• /
• pp.1418-1425
• /
• 2015

In this paper, an filtering method of FI(Fault Indication) information generated by FRTU(Feeder Remote Terminal Unit)s is proposed for the present DAS(Distribution Automation System). In order to find fault area, correct FI information should be generated. But when a single line-to-ground fault occurs, FI information is generated in downside of the fault in some circumstance because existing FI algorithm considers only magnitude. These wrong FI information can be removed by changing existing algorithm. An improved algorithm considers both the direction of zero-sequence current and the phase of three-phase current&voltage. But many FRTUs are distributed in DAS and Changing the algorithm all of FRTU will spend a lot of time and cost. On the other hand, an filtering algorithm proposed in this paper can substitute for it. The filtering algorithm also considers both the direction of zero-sequence current and the phase of three-phase current&voltage. In case study, the proposed method has been shown the reasonability in filtering the fault indication information.

• Journal of Korean Institute of Industrial Engineers
• /
• v.43 no.3
• /
• pp.192-202
• /
• 2017

This study develops a text spam filtering system for Facebook based on two variable categories: keywords learned from Instagram and meta-information of Facebook posts. Since there is no explicit labels for spam/ham posts, we utilize hash tags in Instagram to train classification models. In addition, the filtering accuracy is enhanced by considering meta-information of Facebook posts. To verify the proposed filtering system, we conduct an empirical experiment based on a total of 1,795,067 and 761,861 Facebook and Instagram documents, respectively. Employing random forest as a base classification algorithm, experimental result shows that the proposed filtering system yield 99% and 98% in terms of filtering accuracy and F1-measure, respectively. We expect that the proposed filtering scheme can be applied other web services suffering from massive spam posts but no explicit spam labels are available.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.432-434
• /
• 2008

This paper deals with the DTW algorithm for the filtering contents, in order to improve the filtering performance rate. Contents filtering is the technology that confirm the identification of contents by using the feature of voice. Such technique is classified into general contents and adults contents. This proposed method extracts the information of voice contribute to improvement of filtering contents. In other words, We proposed filtering identification rate can be improved by using DTW algorithm. As a result, the proposed method is utilized improvement of filtering contents. Finally, we provide contents examples to test the accuracy of the proposed feature. Consequently, We know that the difference of characteristic between general contents and adults contents. In the future, We utilize this to improve filtering performance rate.

• Spatial Information Research
• /
• v.8 no.1
• /
• pp.155-170
• /
• 2000

When we use R-Tree,a spatial index, to find objects matches some predicate, it often leads to an incorrect result of perform filtering step only with MBR. And , each candidates need to be inspected to conform if it really satisfies with given query, so called, 'refinement step'. In refinement step. we should perform disk I/O and expansive spatial operations which is the cause of increasing retrieval costs. Therefore, to minimize the number of candidate after filtering step, two-phase filtering methods were studied, but there was many problems such as inefficiency of filtering,maintenance of additional informations and reconstruction of data resulted from the loss of original information. So , in this paper, I propose an Extended R-Tree which provides ability to retrieve spatial objects only with some simple logical operations using Grid Table, truth table strong the information about the existence of spatial objects, in second filtering step. Consequently , this Extended R-Tree using Grid Filter has low cost of operation for filtering because of efficient second filtering step, and better filtering efficiency caused by high quality of approximation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.643-648
• /
• 2005

In order to supply services necessary for users intelligently in the ubiquitous computing, effective filtering of context information is necessary. But studies of context information filtering have not been made much yet. In order for filtering of context information, we can use collaborative filtering being used much at electric commerce, etc. In order to use such collaborative filtering method in the filtering of ubiquitous computing environment, we must solve such problems as first rater problem, sparsity problem, stored data problem and etc. In this study, in order to solve such problems, the researcher proposes the collaborative filtering method using types of context information. And as the result of applying this filtering method to MAUCA, the P2P mobile agent system, the researcher could confirm the average result of 7.7% in the aspect of service supporting function.

• Journal of the Korean Society for information Management
• /
• v.20 no.3
• /
• pp.111-127
• /
• 2003

The purpose of this study is to ascertain whether event tracking is more effective in event retrieval than information filtering. This study examined the two techniques for event retrieval to suggest the more effective one. The event-retrieval performances of the event tracking technique based on a kNN classifier and the query-based information filtering technique were compared. Two event tracking experiments, one with the static training set and the other with the dynamic training set , were carried out. Two information filtering experiments, one with initial queries and the other with refined queries, were also carried out to evaluate the event-retrieval effectiveness. We found that the event tracking technique with the static training set performed better than on with the dynamic training set. It was also found that the information fitering technique using intial queries performed better than one using the refined queries. In conclusion, the comparison of the best cases of event tracking and information filtering revealed that the information filtering technique outperformed the event tracking technique in event retrieval.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.5C
• /
• pp.461-467
• /
• 2003

We propose an efficient method for separable symmetric linear filtering in the DCT domain. First, separable 2-D linear filtering is decomposed into the cascade of 1-D filtering in the DCT domain. We investigate special characteristics of DCT domain filtering matrices when the filter coefficients are symmetric. Then we present the DCT domain 2-D filtering method using these characteristics. The proposed method requires smaller number of multiplications including typical sparseness of DCT coefficients compared to previous DCT domain linear filtering methods. Also, the proposed method is composed of simple and regular operations, which would be appropriate for efficient VLSI implementation.