• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.31-34
• /
• 2009

유비쿼터스 환경에서 상황인지 능력을 가진 지능적 컴퓨팅 개체들 중 사람에게 의존적이지 않고 독립적으로 행동할 수 있는 개체는 유비쿼터스 로봇으로 볼 수 있다. 이러한 로봇은 최근 상호협력 함으로서 보다 최적화된 서비스를 제공하는 연구가 진행되고 있으며, 또한 다수의 로봇이 포함된 환경일 때는 특정한 작업을 수행하기 위하여 특정 로봇의 선별에 관한 연구가 진행 중이다. 본 논문에서는 유비쿼터스 환경에서 서로 다른 기능과 구조를 가지고 있는 지능형 로봇들이 협력하여 특수한 상황이나 임무를 그룹으로 대처할 수 있는 로봇 그룹핑을 설계하고 이를 구현한 결과에 대하여 기술한다. 다수의 로봇 중에서 특정 임무수행을 위한 로봇의 선별 알고리즘은 Entropy를 이용하여 결정 트리를 생성하였다. 또한 Grouping을 위한 Group Layer를 설계하여 구현하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.184-187
• /
• 2020

본 논문에서는 실시간 얼굴인식 기술을 활용한 인물 선별 송출 시스템을 제안한다. 실시간 동영상 안에 등장하는 다수의 인물 객체 얼굴을 검출하고 인식하기 위해 Haar 특징 정보 기반의 다단계(Cascade) 학습 알고리즘을 사용한다. 이 시스템은 다수의 인물을 인식하고 학습할 수 있으며 인식된 각 인물의 송출 여부를 사용자가 직접 선택할 수 있는데 이 모든 선택 송출 과정을 실시간으로 처리할 수 있다. 여기에서 제시한 기술은 다자간 화상 채팅이나 다자간 화상 회의에서 특정인의 프라이버시 보호를 위한 기술로 활용될 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.499-502
• /
• 2004

본 논문은 정보검색의 대상이 되는 XML 문서를 효율적으로 선별하기 위해 온톨로지를 기반으로 XML 문서를 여과하였으며, 여과된 XML 문서를 대상으로 문서에 내재한 정보를 효과적으로 검색하도록 XML 질의를 확장하였다. 이를 위해, 온톨로지로부터 포괄적 DTD를 생성하는 알고리즘을 개발하였고, XML 문서의 효과적인 정보 검색을 위해 온톨로지의 개념 구조와 연관 관계를 분석하여 XML 질의를 확장하는 알고리즘을 개발하였다. 제안한 문서 여과와 질의 확장 알고리즘의 효과를 샘플 XML 문서에 적용하였다.

• Journal of Internet Computing and Services
• /
• v.15 no.3
• /
• pp.53-62
• /
• 2014

DTN is the next generation network that is used in not guaranteed end-to-end connection such as communication between planet and satellite, frequent connection severance, and not enough for qualified network infrastructure. In this paper, we propose the hybrid Spray-and-Wait algorithm to predict the node contact time by monitoring the periodic contacts information between the nodes. Based on this method, we select one node on the basis of prediction time and copy a message for spray and wait algorithm. In order to verify the the hybrid Spray and Wait algorithm, we use the ONE(Opportunistic Network Environment) Simulator of Helsinki University. The delivery probability of the proposed algorithm is compared to the Binary Spray and Wait algorithm, it is showed that it has 10% less overhead than Binary Spray and Wait routing. It has also shown that it reduces unnecessary copying of this message.

• Smart Media Journal
• /
• v.6 no.1
• /
• pp.22-29
• /
• 2017

Due to the rapid advancement and distribution of smart devices of late, document data on the Internet is on the sharp increase. The increment of information on the Web including a massive amount of documents makes it increasingly difficult for users to understand corresponding data. In order to efficiently summarize documents in the field of automated summary programs, various researches are under way. This study uses TextRank algorithm to efficiently summarize documents. TextRank algorithm expresses sentences or keywords in the form of a graph and understands the importance of sentences by using its vertices and edges to understand semantic relations between vocabulary and sentence. It extracts high-ranking keywords and based on keywords, it extracts important sentences. To extract important sentences, the algorithm first groups vocabulary. Grouping vocabulary is done using a scale of specific weight. The program sorts out sentences with higher scores on the weight scale, and based on selected sentences, it extracts important sentences to summarize the document. This study proved that this process confirmed an improved performance than summary methods shown in previous researches and that the algorithm can more efficiently summarize documents.

• Journal of The Korean Society of Inherited Metabolic disease
• /
• v.16 no.1
• /
• pp.1-9
• /
• 2016

Newborn screening (NBS) is important if early intervention is effective in a disorder and if there are sensitive and specific biochemical markers to detect disorder. Methionine is a useful marker to detect abnormal methionine-homocysteine metabolism, especially homocystinuria which needs urgent medical intervention. However, hypermethioninemia could occur in other metabolic disorder including liver disease, tyrosinemia type I, methionine adenosyltransferase (MAT) I/III deficiency, glycine N-methyltransferase (GNMT) deficiency, or adenosylhomocysteine hydrolase deficiency. However, experience with NBS for homocystinurias and methylation disorders is limited. Especially, MAT I/III deficiency which is the most common cause of persistent hypermethioninemia have two inheritance, autosomal recessive (AR) and autosomal dominant (AD), and their clinical manifestation is different between AR and AD. Here, author reviewed recent articles of guideline and proposed guideline for homocystinuria and methylation disorder.

• Journal of Internet Computing and Services
• /
• v.21 no.2
• /
• pp.1-8
• /
• 2020

Recently, the number of APT(Advanced Persistent Threats) attack using malware has been increasing, and research is underway to prevent and detect them. While it is important to detect and block attacks before they occur, it is also important to make an effective response through an accurate analysis for attack case and attack type, these respond which can be determined by analyzing the attack group of such attacks. Therefore, this paper propose a framework based on genetic algorithm for analyzing malware and understanding attacker group's features. The framework uses decompiler and disassembler to extract related code in collected malware, and analyzes information related to author through code analysis. Malware has unique characteristics that only it has, which can be said to be features that can identify the author or attacker groups of that malware. So, we select specific features only having attack group among the various features extracted from binary and source code through the authorship clustering method, and apply genetic algorithm to accurate clustering to infer specific features. Also, we find features which based on characteristics each group of malware authors has that can express each group, and create profiles to verify that the group of authors is correctly clustered. In this paper, we do experiment about author classification using genetic algorithm and finding specific features to express author characteristic. In experiment result, we identified an author classification accuracy of 86% and selected features to be used for authorship analysis among the information extracted through genetic algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.581-587
• /
• 2021

Real-time video streaming scheme for multimedia content delivery and remote conference services is one of technologies that are significantly sensitive to data transmission delay. Recently, because of COVID-19, real-time video streaming contents for the services are significantly increased such as personal broadcasting and remote school class. In order to support the services, there is a growing emphasis on low transmission delay and secure content delivery, respectively. Therefore, our research proposed a packet aggregation algorithm to reduce the transmission delay of selectively encrypted video transmission for real-time video streaming services. Through the application of the proposed algorithm, the selectively encrypted video framework can control the amount of MPEG-2 TS packets for low latency transmission with a consideration of packet priorities. Evaluation results on testbed show that the application of the proposed algorithm to the video framework can reduce approximately 11% of the transmission delay for high and low resolution video.

• Journal of KIISE:Software and Applications
• /
• v.35 no.8
• /
• pp.463-478
• /
• 2008

Due to the high dimensional problem, typically machine learning algorithms have relied on feature selection techniques in order to perform effective classification in microarray gene expression datasets. However, the large number of features compared to the number of samples makes the task of feature selection computationally inprohibitive and prone to errors. One of traditional feature selection approach was feature filtering; measuring one gene per one step. Then feature filtering was an univariate approach that cannot validate multivariate correlations. In this paper, we proposed a function for measuring both class separability and correlations. With this approach, we solved the problem related to feature filtering approach.

• The Journal of the Korea Contents Association
• /
• v.21 no.2
• /
• pp.121-129
• /
• 2021

In this study, we try to minimize the tariff risk by constructing a hazardous cargo screening model by applying Association Rule Mining, one of the data mining techniques. For this, the risk level between supply chains is calculated using the Apriori Algorithm, which is an association analysis algorithm, using the big data of the import declaration form of the Korea Customs Service(KCS). We perform data preprocessing and association rule mining to generate a model to be used in screening the supply chain. In the preprocessing process, we extract the attributes required for rule generation from the import declaration data after the error removing process. Then, we generate the rules by using the extracted attributes as inputs to the Apriori algorithm. The generated association rule model is loaded in the KCS screening system. When the import declaration which should be checked is received, the screening system refers to the model and returns the confidence value based on the supply chain information on the import declaration data. The result will be used to determine whether to check the import case. The 5-fold cross-validation of 16.6% precision and 33.8% recall showed that import declaration data for 2 years and 6 months were divided into learning data and test data. This is a result that is about 3.4 times higher in precision and 1.5 times higher in recall than frequency-based methods. This confirms that the proposed method is an effective way to reduce tariff risks.