• Journal of Broadcast Engineering
• /
• v.19 no.3
• /
• pp.316-328
• /
• 2014

In this paper, we parallelize the popular feature detection algorithms, i.e. SIFT and SURF, and its application to fast panoramic image generation on the latest embedded GPU. Parallelized algorithms are implemented using recently developed OpenCL as the embedded GPGPU software platform. We compare the implementation efficiency and speed performance of conventional OpenGL Shading Language and OpenCL. Experimental result shows that implementation on OpenCL has comparable performance with GLSL. Compared with the performance on the embedded CPU in the same application processor, the embedded GPU runs 3~4 times faster. As an example of using feature extraction, panorama image synthesis is performed on embedded GPU by applying image matching using detected features.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.3
• /
• pp.45-54
• /
• 2014

In this paper, an improved two-step P2P traffic classification scheme is proposed to overcome the limitations of the existing methods. The first step is a signature-based classifier at the packet-level. The second step consists of pattern heuristic rules and a statistics-based classifier at the flow-level. With pattern heuristic rules, the accuracy can be improved and the amount of traffic to be classified by statistics-based classifier can be reduced. Based on the analysis of different decision tree algorithms, the statistics-based classifier is implemented with REPTree. In addition, the ensemble algorithm is used to improve the performance of statistics-based classifier Through the verification with the real datasets, it is shown that our hybrid scheme provides higher accuracy and lower overhead compared to other existing schemes.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.22 no.2
• /
• pp.145-150
• /
• 2004

A protocol for the web-based GPS data processing system has been developed. The system is developed following the typical ASP system, in which the GPS data acquired by various users can be uploaded through the web and the data is processed with data processing components selected by the users. After the processing, the results are also transported to the users through the web. The developed system is designed for easy software upgrade and it is an synchronous process mode so that the multiple accesses can be handled with high user flexibility. The database components for the efficient GPS data maintenance are developed so that the data from CORS can be used for the data processing. Currently, the absolute and relative positioning algorithms using code measurements are integrated and much more algorithms such as the data quality control, absolute and relative positioning using phases will be integrated in near future.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.04a
• /
• pp.81-92
• /
• 2003

A protocol for the web-based GPS data processing system has been developed. The system is developed following the typical ASP system, in which the GPS data acquired by various users can be uploaded through the web and the data is processed with data processing components selected by the users. After the processing, the results are also transported to the users through the web. The developed system is designed for easy software upgrade and it is an asynchronous process mode so that the multiple accesses can be handled with high user flexibility. The database components for the efficient GPS data maintenance are developed so that the data from CORS can be used for the data processing. Currently, the absolute and relative positioning algorithms using code measurements are integrated and much more algorithms such as the data quality control, absolute and relative positioning using phases will be integrated in near future.

• Journal of Information Technology Services
• /
• v.16 no.4
• /
• pp.137-148
• /
• 2017

Researches on the Artificial Intelligence has been explosively activated in various fields since the advent of AlphaGo. Particularly, researchers on the application of multi-layer neural network such as deep learning, and various machine learning algorithms are being focused actively. In this paper, we described a development of an artificial intelligence Janggi game based on reinforcement learning algorithm and MCTS (Monte Carlo Tree Search) algorithm with accumulated game data. The previous artificial intelligence games are mostly developed based on mini-max algorithm, which depends only on the results of the tree search algorithms. They cannot use of the real data from the games experts, nor cannot enhance the performance by learning. In this paper, we suggest our approach to overcome those limitations as follows. First, we collects Janggi expert's game data, which can reflect abundant real game results. Second, we create a graph structure by using the game data, which can remove redundant movement. And third, we apply the reinforcement learning algorithm and MCTS algorithm to select the best next move. In addition, the learned graph is stored by object serialization method to provide continuity of the game. The experiment of this study is done with two different types as follows. First, our system is confronted with other AI based system that is currently being served on the internet. Second, our system confronted with some Janggi experts who have winning records of more than 50%. Experimental results show that the rate of our system is significantly higher.

• Journal of KIISE:Software and Applications
• /
• v.34 no.1
• /
• pp.30-39
• /
• 2007

The existing content-based spam mail filtering algorithms have difficulties in filtering spam mails when e-mails contain images but little text. In this thesis we propose an efficient spam mail classification algorithm that utilizes the link structure of e-mails. We compute the number of hyperlinks in an e-mail and the in-link frequencies of the web pages hyperlinked in the e-mail. Using these two features we classify spam mails and legitimate mails based on the decision tree trained for spam mail classification. We also suggest a hybrid system combining three different algorithms by majority voting: the link structure analysis algorithm, a modified link structure analysis algorithm, in which only the host part of the hyperlinked pages of an e-mail is used for link structure analysis, and the content-based method using SVM (support vector machines). The experimental results show that the link structure analysis algorithm slightly outperforms the existing content-based method with the accuracy of 94.8%. Moreover, the hybrid system achieves the accuracy of 97.0%, which is a significant performance improvement over the existing method.

• KSBB Journal
• /
• v.20 no.2 s.91
• /
• pp.71-75
• /
• 2005

Alignment of 2D-gel images of biological samples can visualize the difference of expression profiles and also inform us candidates of protein spots to be further analyzed. However, comparison of two proteome images between the case and control does not always successfully identify differentially expressed proteins because of sample-to-sample variation, poor reproducibility of 2D-gel electrophoresis and inconsistent electrophoresis conditions. Multiple alignment of 2D-gel image must be preceded before visualizing the difference of expression profiles or clustering proteome images. Thus, a software for the alignment of multiple 2D-Gel images and their clustering was developed by applying various algorithms and statistical methods. Microsoft Visual C++ was used to implement the algorithms in this work. Multiresoultion-multilevel algorithm was found out to be suitable for fast alignment and for largely distorted images. Clustering of 10 different proteome images of Fetal Alcohol Syndrome, was carried out by implementing a k-means algorithm and it gave a phylogenetic tree of proteomic distance map of the samples. However, the phylogenetic tree does not discriminate the case and control. The whole image clustering shows that the proteomic distance is more dependent to age and sex.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.2
• /
• pp.51-62
• /
• 2018

High utility sequential pattern (HUSP) mining has been considered as an important research topic in data mining. Although some algorithms have been proposed for this topic, they incur the problem of producing a large search space for HUSPs. The tighter utility upper bound of a sequence can prune more unpromising patterns early in the search space. In this paper, we propose a sequence expected utility (SEU) as a new utility upper bound of each sequence, which is the maximum expected utility of a sequence and all its descendant sequences. A sequence utility list for each pattern is used as a new data structure to maintain essential information for mining HUSPs. We devise an algorithm, high sequence utility list-span (HSUL-Span), to identify HUSPs by employing SEU. Experimental results on both synthetic and real datasets from different domains show that HSUL-Span generates considerably less candidate patterns and outperforms other algorithms in terms of execution time.

• Journal of The Korean Association of Information Education
• /
• v.23 no.6
• /
• pp.561-571
• /
• 2019

Programming education generally includes problem analysis process, automation through algorithms and programming, and generalization process. It is a good software education method for students in improving computing thinking. However, it was found that beginners had difficulties in understanding instruction usage, writing algorithms, and implementing programming. In this study, we developed a game programming education model and curriculum for programming education of pre-service teachers. The 4E model consisted of empathy, exploration, engagement and evaluation. In addition, it is configured to learn game core elements and core command blocks by each stage. To help the pre-service teachers understand the use of various programming blocks, a three-step teaching and learning method was presented, consisting of example learning, self-game creation, and team-based projects. As a result of applying and verifying the curriculum for 15 weeks, it showed significant results in the 4E model and pre-service teachers' perception of block programming competence and the level of computational thinking on the submitted game project results was also high.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.38 no.8
• /
• pp.19-29
• /
• 2001

The recent explosion in the Internet applications, Internet. host number and the traffic in the IP backbone network is posing new challenges for transport network. This requires a high-speed IP backbone network that has a substantially higher bandwidth than the one offered by current networks, which prompts the development of all-optical network. To obtain optical network utilization gains, we need a software which establishs logical topology to make possible the efficient use or physical topology, and control the optical network in combination with the IP layer routing protocols. Finally, the logical topology is required higher efficient than physical topology. For this an efficient algorithm for the routing and wavelength assignment(RWA) in the WDM all-optical network is necessary. In this paper, two kinds of heuristic algorithms to establish logical topology for WDM networks and arc applied to the design of logical topology of domestic backbone network. These algorithms are found to work quite well and they arc compared with each other in terms of blocking rate, etc.