• 인터넷정보학회논문지
• /
• 제20권4호
• /
• pp.21-27
• /
• 2019

RNA 시퀀싱 데이터 (RNA-seq)에서 수집된 많은 양의 데이터에 변별력이 확실한 특징 패턴 선택이 유용하며, 차별성 있는 특징을 정의하는 것이 쉽지 않다. 이러한 이유는 빅데이터 자체의 특징으로써, 많은 양의 데이터에 중복이 포함되어 있기 때문이다. 해당이슈 때문에, 컴퓨터를 사용하여 처리하는 분야에서 특징 선택은 랜덤 포레스트, K-Nearest, 및 서포트-벡터-머신 (SVM)과 같은 다양한 머신러닝 기법을 도입하여 해결하려고 노력한다. 해당 분야에서도 SVM-기반 제약을 사용하는 서포트-벡터-머신-재귀-특징-제거(SVM-RFE) 알고리즘은 많은 연구자들에 의해 꾸준히 연구 되어 왔다. 본 논문의 제안 방법은 RNA 시퀀싱 데이터에서 빅-데이터처리를 위해 SVM-RFE에 강화학습의 Q-learning을 접목하여, 중요도가 추가되는 벡터를 세밀하게 추출함으로써, 변별력이 확실한 특징선택 방법을 제안한다. NCBI-GEO와 같은 빅-데이터에서 공개된 일부의 리보솜 단백질 클러스터 데이터에 본 논문에서 제안된 알고리즘을 적용하고, 해당 알고리즘에 의해 나온 결과와 이전 공개된 SVM의 Welch' T를 적용한 알고리즘의 결과를 비교 평가하였다. 해당결과의 비교가 본 논문에서 제안하는 알고리즘이 좀 더 나은 성능을 보여줌을 알 수 있다.

• 동의생리병리학회지
• /
• 제30권6호
• /
• pp.376-384
• /
• 2016

Systems biology is an emerging field aiming at a systems level understanding of living organisms and focusing on the characteristics of the whole network of them. The emergence of systems biology is partly because of the availability of huge amounts of data on organisms and the extensive support of computational technologies as the tools for understanding complex biological systems. The scientific understanding of Korean medicine has been obstructed because of the lack of proper methods examining the complex nature and the unique property of it. However, systems biology could give a chance understanding Korean medicine objectively and scientifically. Pattern classification is a unique tool of Korean medicine to diagnose and treat patients and systems biology would give a useful tool to interpret pattern classification. Various omics technologies has been used to explain the relations between pattern classification and biological factors and then many characteristics of pattern classification in various diseases have been discovered. Therefore, pattern classification could be a bridge to understand the features and differences of western medicine and Korean medicine and it could be a basis to develop pattern-based personalized medicine.

• 한국환경과학회지
• /
• 제29권4호
• /
• pp.361-369
• /
• 2020

With the increasing role of environmental design in promoting urban safety, new design attempts have been made to improve pedestrian safety in crosswalks. This study proposes an evidence-based design solution for improving crosswalk function by conducting simulations and field experiments. Drivers with more than one-year driving experience participated in this study. Four different crosswalk design patterns were prepared: (1) a zebra pattern, (2) zebra pattern with colored triangles, (3) 3D pattern, and (4) art pattern with unique colors and design. The results supported that the zebra pattern with colored triangles could be the most effective solution for crosswalk design by increasing visibility, attention, deceleration, and landscape aesthetics. This study provided objective data to support the performance of various crosswalk patterns and suggested the need to reevaluate the present crosswalk design guidelines.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권10호
• /
• pp.1335-1343
• /
• 1999

This paper presents concrete pattern recognition method to identify the strength of concrete by evidence accumulation with multiple parameters based on artificial intelligence techniques. At first, zero-crossing(ZCR), mean frequency(MEANF), median frequency(MEDF) and autoregressive model coefficient(ARC) are extracted as feature parameters from ultrasonic signal of concrete. Pattern recognition is carried out through the evidence accumulation procedure using distance measured with reference parameters. A fuzzy mapping function is designed to transform the distances for the application of the evidence accumulation method. Results are presented to support the feasibility of the suggested approach for concrete pattern recognition.

• Journal of Mechanical Science and Technology
• /
• 제18권10호
• /
• pp.1849-1858
• /
• 2004

For examining friction-factor characteristics of round-hole pattern surfaces which are usually applied on damper seals, flat plate test apparatus is designed and fabricated. The measurement method of leakage and pressure distribution along round-hole pattern specimen with different hole area is described and a method for determining the Fanning friction factor is discussed. Results show that the round-hole pattern surfaces provide a much larger friction factor than smooth surface, and the friction factor vs. clearance behavior yields that the friction factor generally decreases as the clearance increases unlike the results of Nava's flat plate test. As the hole depth is decreased, the friction factor is increased, and maximum friction factor is obtained for 50% of hole area. Since the present experimental friction factor results show coincident characteristics with Moody's friction factor model, empirical friction factors for round-hole pattern surfaces are obtained by using the Moody's formula based on curve-fit of the experimental data. Results of Villasmil's 2D CFD simulation support the present experimental test result.

• 센서학회지
• /
• 제20권6호
• /
• pp.388-392
• /
• 2011

In this paper, a face detection method for interactive TV control system using a new feature, edge histogram feature, with a support vector machine(SVM) in the near-infrared(NIR) images is proposed. The edge histogram feature is extracted using 16-directional edge intensity and a histogram. Compared to the previous method using local binary pattern(LBP) feature, the proposed method using edge histogram feature has better performance in both smaller feature size and lower equal error rate(EER) for face detection experiments in NIR databases.

• 컴퓨터교육학회논문지
• /
• 제6권1호
• /
• pp.1-8
• /
• 2003

본 논문에서는 frequent itemset을 빠르게 발견해내기 위한 효율적인 vertical 마이닝 알고리즘을 제안한다. 본 알고리즘은 frequent itemset을 구하기 위해 아이템들을 Least Support Itemset(LSI) 과의 유사도에 의해 올림차순으로 정렬하여 탐색 트리를 구축하여 보다 빠르고 효율적으로 frequent itemset을 찾아낸다. 또한, 트리를 탐색 시, 2가지의 휴리스틱 방법을 사용하여 탐색의 초기에 많은 후보 아이템들을 탐색 트리로부터 제거함으로써 탐색 공간을 크게 줄인다. 본 논문에서 제안하는 알고리즘은 이전의 알고리즘들과 비교해, long pattern을 가지는 데이터 베이스에서 보다 빠르게 frequent itemset을 발견해 냄을 실험을 통해 발견하였다.

• 한국산업정보학회논문지
• /
• 제18권1호
• /
• pp.1-9
• /
• 2013

Most calls of a called user are invoked by the group of calling users. This call pattern is defined as call locality. Similarly Internet sessions including IP telephony calls have this pattern. We define it session locality. In this paper, we propose a caching scheme to support session locality in hierarchical SIP networks. The proposed scheme can be applied easily by adding only one filed to cache to a data structure of the SIP mobility agent. And this scheme can reduce signaling cost, database access cost and session setup delay to locate a called user. Moreover, it distributes the load on the home registrar to the SIP mobility agents. Our performance evaluation shows the proposed caching scheme outperforms the hierarchical SIP scheme when session to mobility ratio is high.

• 한국전자통신학회논문지
• /
• 제2권2호
• /
• pp.99-105
• /
• 2007

MANET(Mobile Ad-hoc network) have recently attracted a lot of attention in the research community as well as in industry. Although the previous research mainly focused on various of MANET in routing, we consider, in this paper, how to efficiently support applications such as variable geocasting basd on MANET. The goal of a geocasting protocol is deliver data packet to a group of nodes that are located within a specified geocasting region. Previous research that support geocast service in mobilie computing based on MANET have the non-optimization problem of data delivery path, overhead by frequent reconstruction of the geocast tree, and service disruption problem. In this paper, we propose the mobility pattern based geocast technique using variable service range according to the mobility of destination node and resource reservation to solve this problem. The experimental results show that our proposed mechanism has improved performance of Accessibility & Network Overhead than previous research.

• 터널과지하공간
• /
• 제4권2호
• /
• pp.119-131
• /
• 1994

This is a Double-Track Railway tunnel in typical Tae-Gu black and gray shale forming part of the No.1 Line of the Tae-Gu Subway. The main fault zone at tunnel is a moderately to highly weathered and closely jointed zone, 0.5 m wide with associated paralled jointing which is slickensided and fractured. After excavation by blasting, the soft rocks should need to be reinforced with optimal supporting pattern which might be better redesigned through the consideration of the results of in-situ rock measurements at the field. Performances fo the field tests included Point Load Test, Schmidt Hammer Test, and field joint measurement gave the detail data for the optimum support design and safe excavation of the No.1 Line of Tae-Gu Subway at the No.1-7 consturction site adn the safety of this redesigned supports system was analysed by the FDM program FLAC.