• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.354-360
• /
• 1998

In general, it is very difficult to find optimal fuzzy rules by experience when a system is dynamical and/or complex. Futhermore proper fuzzy partitioning is not deterministic and there is no unique solution. Therefore we propose a new design method of an optimal fuzzy logic controller, that is a co-evolutionary genetic algorithm finding optimal fuzzy rule and proper membership functions at the same time. We formalize the relation between fuzzy rules and membership functions in terms of fitness. We review the typical approaching methods to co-evolutionary genetic algorithms , and then classify them by fitness relation matrix. Applications of the proposed method to a path planning problem of autonomous mobile robots when moving objects exist are presented to demonstrate the performance and effectiveness of the method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.7
• /
• pp.589-595
• /
• 2013

The agents for security surveillance are not enough for monitoring CCTV system, so the intelligent automatic surveillance system is needed. In this paper, object detection, tracking and abnormal event detection system is implemented for intelligent CCTV system. Each modules are tested on the real CCTV environment and promoted for commercialization. Abnormal event detection module and loitering detection and sudden running detection function and it's detection time is under 1 second which is satisfied level.

• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.609-611
• /
• 2019

본 논문에서는 교육 훈련생의 교육 상태에 맞는 콘텐츠를 추천해주는 교육 콘텐츠 추천시스템을 제안한다. 제안하는 시스템은 데이터베이스에 저장되어 있는 콘텐츠의 텍스트를 활용하여 콘텐츠를 등급별로 분류하는 콘텐츠 분류 기능부분과 교육 훈련생의 등급 및 교관 등에 의해 설정되는 필터링 정보를 활용하여 교육 훈련생에 맞는 콘텐츠 추천리스트를 생성하는 콘텐츠 추천 기능으로 구성되어있다. 실험에서는 콘텐츠 분류기능에 대한 정확도 평가를 수행하였고, ANN 평가모델로 평균 65%의 정확도를 보였다.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2007.11a
• /
• pp.602-609
• /
• 2007

Combining collaborative filtering with some other technique is most common in hybrid recommender systems. As many recommended items from collaborative filtering seem to be similar with respect to content, the collaborative-content hybrid system suffers in terms of quality recommendation and recommending new items as well. To alleviate such problem, we have developed a novel method that uses a diversity metric to select the dissimilar items among the recommended items from collaborative filtering, which together with the input when fed into content space let us improve and include new items in the recommendation. We present experimental results on movielens dataset that shows how our approach performs better than simple content-based system and naive hybrid system

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.8
• /
• pp.1-6
• /
• 2015

The MapReduce Program of Hadoop Distributed File System operates on any unspecified nodes due to distributed-parallel process and block replicate for data stability. Since it is difficult to guarantee the cache locality when a Solid State Drive is used as a cache in hadoop, cache hit-rate is decreased. In this paper, we suggest a method to improve cache hit rate by pre-loading the input data of the MapReduce onto the SSD cache. To perform this method, we estimated the blocks that are used on each node by using capacity scheduler and block metadata. Eventually we could increase the performance of SSD cache by loading the blocks onto SSD cache before the Map Task run.

• Journal of Sensor Science and Technology
• /
• v.28 no.1
• /
• pp.7-12
• /
• 2019

Significant progress has been made recently in detection of highly sensitive volatile organic compounds (VOCs) using chemical sensors. Combined with the progress in design of micro sensors array and electronic nose systems, these advances enable new applications for detection of extremely low concentrations of breath-related VOCs. State of the art detection technology in turn enables commercial sensor systems for health care applications, with high detection sensitivity and small size, weight and power consumption characteristics. We have been developing an intelligent electronic nose system for detection of VOCs for healthcare breath analysis applications. This paper reviews our contribution to monitoring of respiratory diseases and to diabetic monitoring using an intelligent electronic nose system for detection of low concentration VOCs using breath analysis techniques.

• Annual Conference of KIPS
• /
• 2013.11a
• /
• pp.327-328
• /
• 2013

최근 클라우드 컴퓨팅 환경 내에서 많은 IT 기업들이 그동안에 쌓아두었던 소프트웨어, 하드웨어 기술력을 바탕으로 클라우드 컴퓨팅을 제공하는 데 필요한 IT 인프라 구축에 힘쓰고 있는 시점에서 경쟁력이 심화되고 있다. 그렇기 때문에 대용량의 데이터를 사용자에게 고속으로 제공할 수 있는 방안을 연구하는 것이 클라우드 컴퓨팅 환경에서 대두되고 있는 이슈 중에 하나이다. 본 논문에서는 HSS(Hybrid Storage System) 내부 소프트웨어 시스템 설계 기법에 고속 캐싱을 접목시켜 사용자에게 고속으로 데이터를 제공하는 방안을 제시하였다.

• Annual Conference of KIPS
• /
• 2009.11a
• /
• pp.319-320
• /
• 2009

본 논문은 Open Quotient 정보와 Fundamental Frequency 정보를 이용한 성별 분류에 관한 것이다. 기존의 대표적인 성별 분류 특징정보로 Fundamental Frequency가 있으나, Fundamental Frequency 정보로는 이용하여 분류하는 데에 중점을 두어왔으나 이 정보는 노인 혹은 어린이에 대해서는 성별 분류 특징이 어렵다는 단점이 있었다. 한편 본 논문에서 제안하는 방법은 Open Quotient와 Fundamental Frequency의 연령대에 따른 차별 정보를 이용하여 학습시켜 성별분류를 보다 나은 성능으로 분류할 수 있다.

• Annual Conference of KIPS
• /
• 2009.04a
• /
• pp.50-52
• /
• 2009

Ontology maintenance is a time consuming and costly process which requires special skill and knowledge. It requires joint effort of both ontology engineer and domain specialist to properly maintain ontology and update knowledge in it. This is specially true for medical domain which is highly specialized domain. This paper proposes a novel approach for maintenance and update of existing ontologies in a medical domain. The proposed approach is based on modified Ontology Maturing Process which was originally developed for web domain. The proposed approach provides way to populate medical ontology with new knowledge obtained from medical documents. This is achieved through use of natural language processing techniques and highly specialized medical knowledge bases such as Unified Medical Language System.

• Electronics and Telecommunications Trends
• /
• v.38 no.3
• /
• pp.47-56
• /
• 2023

Physical rehabilitation consists of exercises that help individuals who have suffered injury, disease, or nervous system disorders to recover lost or impaired functions. The exercises need to be tailored to the degree and type of the patient's condition. To this end, a comprehensive rehabilitation data delivery system that connects medical institutions and local communities should be established, and an intelligent rehabilitation service technology should be developed. An intelligent rehabilitation service integrates and manages the patient's health information provided by medical institutions and the overall function evaluation information measured in the community. Based on the collected data, personalized rehabilitation services can be provided. We examine supportive policies and technological trends for rehabilitation exercise and sports. Additionally, we investigate development trends and key technologies of intelligent rehabilitation services being developed at ETRI.