• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.4
• /
• pp.109-118
• /
• 2011

In this research estimated accuracies that were results in all the area of filtering of the plane equation that was used by whole data set, and regional of filtering that was driven by the plane equation for each vertual Grid. All of this estimates were based by all the area of filtering that deduced the plane equation by multiple linear regression analysis that was used by ground data set. Therefore, accuracy of all the area of filtering that used whole data set has been dropped about 2~3% when average of accuracy of all the area of filtering was based on ground data set while accuracy of Regional of filtering dropped 2~4% when based on virtual Grid. Moreover, as virtual Grid which was set 3~4 cm was difference about 2% of accuracy from standard data. Thus, it leads conclusion of set 3~4 times bigger size in virtual Grid filtering over LiDAR scan gap will be more appropriated. Hence, the result of this research allow us to conclude that there was difference in average accuracy has been noticed when we applied each different approaches, I strongly suggest that it need to research more about real topography for further filtering accuracy.

• Journal of Korea Multimedia Society
• /
• v.15 no.12
• /
• pp.1417-1429
• /
• 2012

In neuroscientific research, image segmentation is one of the most important processes. The morphology of axons plays an important role for researchers seeking to understand axonal functions and connectivity. In this study, we evaluated the level set segmentation method for neuronal axons in a Brainbow confocal microscopy image. We first obtained a reconstructed image on an x-z plane. Then, for preprocessing, we also applied two methods: anisotropic diffusion filtering and bilateral filtering. Finally, we performed image segmentation using the level set method with three different approaches. The accuracy of segmentation for each case was evaluated in diverse ways. In our experiment, the combination of bilateral filtering with the level set method provided the best result. Consequently, we confirmed reasonable results with our approach; we believe that our method has great potential if successfully combined with other research findings.

• 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 the Acoustical Society of Korea
• /
• v.28 no.3E
• /
• pp.118-135
• /
• 2009

The level set based approach is one of active methods for contour extraction in image segmentation. Since Osher and Sethian introduced the level set framework in 1988, the method has made the great impact on image segmentation. However, there are some problems to be solved; such as multi-objects segmentation, noise filtering and much calculation amount. In this paper we address the drawbacks of the previous level set methods and propose an extension of the traditional fast level set to cope with the limitations. We introduce a relationship matrix, a new split-and-merge criterion, a modified Chan-Vese criterion and a novel filtering criterion into the traditional fast level set approach. With the segmentation experiments we evaluate the proposed method and show the promising results of the proposed method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.4
• /
• pp.662-674
• /
• 1997

In order to post process the vector-quantized images employing the theory of projections onto convex sets or the constrained minimization technique, the the projector onto QCS(quantization constraint set) as well as the filter that smoothes the lock boundaries should be investigated theoretically. The basic idea behind the projection onto QCS is to prevent the processed data from diverging from the original quantization region in order to reduce the blurring artifacts caused by a filtering operation. However, since the Voronoi regions in order to reduce the blurring artifacts caused by a filtering operation. However, since the Voronoi regions in the vector quantization are arbitrarilly shaped unless the vector quantization has a structural code book, the implementation of the projection onto QCS is very complicate. This paper mathematically analyzes the projection onto QCS from the viewpoit of minimizing the mean square error. Through the analysis, it has been revealed that the projection onto a subset of the QCS yields lower distortion than the projection onto QCS does. Searching for an optimal constraint set is not easy and the operation of the projector is complicate, since the shape of optimal constraint set is dependent on the statistical characteristics between the filtered and original images. Therefore, we proposed a hyper-cube as a constraint set that enables a simple projection. It sill be also shown that a proper filtering technique followed by the projection onto the hyper-cube can reduce the quantization distortion by theory and experiment.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1302-1306
• /
• 2004

This paper proposes a model for information filtering (IF) on the Web. The user information need is described into two levels in this model: profiles on category level, and Boolean queries on document level. To efficiently estimate the relevance between the user information need and documents by fuzzy, the user information need is treated as a rough set on the space of documents. The rough set decision theory is used to classify the new documents according to the user information need. In return for this, the new documents are divided into three parts: positive region, boundary region, and negative region. We modified user profile by the user's relevance feedback and discerning words in the documents. In experimental we compared the results of three methods, firstly is to search documents that are not passed the filtering system. Second, search documents that passed the filtering system. Lastly, search documents after modified user profile. The result from using these techniques can obtain higher precision.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.489-498
• /
• 2006

Clustering results differ according to the datasets and the performance worsens even while using web documents which are manually processed by an indexer, because although representative clusters for a feature can be obtained by statistical feature selection methods, irrelevant features(i.e., non-obvious features and those appearing in general documents) are not eliminated. Those irrelevant features should be eliminated for improving clustering performance. Therefore, this paper proposes three feature-filtering algorithms which consider feature values per document set, together with distribution, frequency, and weights of features per document set: (l) features filtering algorithm in a document (FFID), (2) features filtering algorithm in a document matrix (FFIM), and (3) a hybrid method combining both FFID and FFIM (HFF). We have tested the clustering performance by feature selection using term frequency and expand co link information, and by feature filtering using the above methods FFID, FFIM, HFF methods. According to the results of our experiments, HFF had the best performance, whereas FFIM performed better than FFID.

• Journal of Korea Multimedia Society
• /
• v.11 no.9
• /
• pp.1213-1226
• /
• 2008

A recommender system supports people in making recommendations finding a set of people who are likely to provide good recommendations for a given person, or deriving recommendations from implicit behavior such as browsing activity, buying patterns, and time on task. We proposed new recommender system which combined SOM(Self-Organizing Map) neural networks with the Collaborative filtering which most recommender systems hat applied First, we segmented user groups according to demographic characteristics and then we trained the SOM with people's preferences as ito inputs. Finally we applied the classic collaborative filtering to the clustering with similarity in which an recommendation seeker belonged to, and therefore we didn't have to apply the collaborative filtering to the whose data set. Experiments were run for EachMovies data set. The results indicated that the predictive accuracy was increased in terms of MAE(Mean-Absolute-Error).

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.45 no.2
• /
• pp.256-264
• /
• 1996

In this paper, the decentralized suboptimal H$_{2}$ filtering problem is considered. An additional term is added to the centralized optimal H$_{2}$ filter so that the whole filter is decentralized. We derive a necessary and sufficient condition for existence of proposed decentralized filters By employing the solution procedure for the exact model matching problem, we obtain a set of decentralized H$_{2}$ filters, and choose a suboptimal filter from this set of decentralized H$_{2}$ filters.

• Bulletin of the Korean Mathematical Society
• /
• v.43 no.4
• /
• pp.861-868
• /
• 2006

We present a Choquet-Deny-type theorem for downward filtering convex sets of continuous functions and show that the Identity Korovkin cone of a downward filtering convex cone S is exactly the uniform closure of S.