• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2004년도 가을 학술발표논문집 Vol.31 No.2 (2)
• /
• pp.703-705
• /
• 2004

Conventional support vector machines (SVMs) find optimal hyperplanes that have maximal margins by treating all data equivalently. In the real world, however, the data within a data set may differ in degree of uncertainty or importance due to noise, inaccuracies or missing values in the data. Hence, if all data are treated as equivalent, without considering such differences, the optimal hyperplanes identified are likely to be less optimal. In this paper, to more accurately identify the optimal hyperplane in a given uncertain data set, we propose a membership-induced distance from a hyperplane using membership values, and formulate three kinds of membership-induced SVMs.

• 한국정보통신학회논문지
• /
• 제15권2호
• /
• pp.292-298
• /
• 2011

생체신호 데이터의 의미와 그들 간의 연관관계를 정의하여 새로운 정보를 획득할 수 있는 형태의 모델링방법으로 온톨로지가 제시되고 있다. 온톨로지를 이용하여 생체신호 데이터를 지속적으로 관리함으로써 생체 신호 데이터의 체계적이고 논리적으로 표현이 가능하고, 이는 나아가 의료정보, 건강서비스 등 다양한 분야에서 질적으로 향상된 서비스를 제공하게 해주는 지식 자원으로 활용된다. 하지만 현재로는 생체 신호간의 연관 관계 중요성에 비해서 관련 연구가 활발하게 이루어지지 않고 있다. 따라서 생체 신호간의 연관관계를 찾아서 정의하고, 생체정보간의 의미표현이 필요하다. 그러기 위해서는 다양한 생체정보간의 연관 관계를 통해 체계적이고 구조화 된 정보를 만드는 것이 필요하다. 본 논문에서는 생체정보를 체계적이고 구조화 된 도메인 지식으로 활용하기 위한 모델로써 온톨로지를 이용하여 생체정보 온톨로지를 구축하고, 시나리오를 통해서 생체정보 온톨로지의 유용성을 검증하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 춘계학술대회
• /
• pp.768-770
• /
• 2015

유전체 염기서열 분석비용이 크게 감소하면서 유전체 정보 생산이 본격화됨에 따라 시스템 생물학 기반의 통합 및 표준화된 오믹스 데이터베이스 구축이 필요하다. 이에 따라 현재 진행중인 연구 수행의 결과로 얻어진 차세대유전체서열(NGS) 및 전사체(transcriptome) 등의 대용량 정보를 수집하였고 이를 표준화 형식에 맞춰 농업생명공학정보센터(NABIC)에 등록하였다. 또한 농업생명자원 생물정보를 품목별, 개체별로 통합 저장소를 구축하였으며 농업생명자원 생물정보를 품목별, 개체별로 통합 저장소를 구축하였다. 농업생명공학정보센터 오믹스 정보등록시스템 서비스와의 연계 및 확충작업을 하기위해 시스템 기능 개선 및 유지보수 작업을 수행하였다.

• Smart Structures and Systems
• /
• 제7권3호
• /
• pp.229-240
• /
• 2011

Recent developments in Smart Structures with very large scale embedded sensors and actuators have introduced new challenges in terms of data processing and sensor fusion. These smart structures are dynamically classified as a large-scale system with thousands of sensors and actuators that form the musculoskeletal of the structure, analogous to human body. In order to develop structural health monitoring and diagnostics with data provided by thousands of sensors, new sensor informatics has to be developed. The focus of our on-going research is to develop techniques and algorithms that would utilize this musculoskeletal system effectively; thus creating the intelligence for such a large-scale autonomous structure. To achieve this level of intelligence, three major research tasks are being conducted: development of a Bio-Inspired data analysis and information extraction from thousands of sensors; development of an analytical technique for Optimal Sensory System using Structural Observability; and creation of a bio-inspired decision-making and control system. This paper is focused on the results of our effort on the first task, namely development of a Neuro-Morphic Engineering approach, using a neuro-symbolic data manipulation, inspired by the understanding of human information processing architecture, for sensor fusion and structural diagnostics.

• 한국정밀공학회지
• /
• 제28권7호
• /
• pp.834-850
• /
• 2011

In this paper, a novel tissue engineering scaffold design method based on triply periodic minimal surface (TPMS) is proposed. After generating the hexahedral elements for a 3D anatomical shape using the distance field algorithm, the unit cell libraries composed of triply periodic minimal surfaces are mapped into the subdivided hexahedral elements using the shape function widely used in the finite element method. In addition, a heterogeneous implicit solid representation method is introduced to design a 3D (Three-dimensional) bio-mimetic scaffold for tissue engineering from a sequence of computed tomography (CT) medical image data. CT image of a human spine bone is used as the case study for designing a 3D bio-mimetic scaffold model from CT image data.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 춘계학술대회 학술발표 논문집 제14권 제1호
• /
• pp.273-276
• /
• 2004

Genome-scale expression data provides us with valuable insights about organisms, but the biological validation of in-silico analysis is difficult and often controversial. Here we present a new approach for integrating previously established knowledge with computational analysis. Based on the known biological evidences, IGAM (Integrated Gene Association Matrix) automatically estimates the relatedness between a pair of genes. We combined this association knowledge to the regulatory network modeling and fuzzy clustering in yeast 5. Cerevisiae. The result was found to be more effective for extracting biological meanings from in-silico inferences for gene expression data.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.211-212
• /
• 2021

최근 건강에 대한 관심이 증가하며 다양한 생체정보를 수집할 수 있는 웨어러블 시장이 확대되고 있다. 또한 이러한 생체신호를 통한 원격의료와 헬스케어 서비스가 보편화될 것으로 예상된다. 본 논문에서는 IoT 장비를 통해 수집한 생체신호를 데이터베이스에 저장 및 웹을 통해 실시간 모니터링이 가능한 서비스를 소개한다. 생체 데이터의 수집 및 저장과 실시간 모니터링을 시스템을 구현함으로 다양한 건강관리 진단에 활용될 수 있다.

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2008년도 하계학술발표대회 논문집
• /
• pp.737-741
• /
• 2008

The indoor environment has an effect on heath of human in indoor room that they live largely. We will know Bio-Aerosol that causes illness, such as a flu, an asthma and an atopy etc. and see a relationship between Bio-Aerosol and temperature as an experiment in Air-Conditioned room. In the future, this data can use a basic data for an effect of Bio-Aerosol on indoor environment.

• Journal of Microbiology and Biotechnology
• /
• 제14권5호
• /
• pp.1081-1085
• /
• 2004

Genome research has become very popular in most nations. In order to enhance the efficiency of collaboration among genome research groups, ways to store and share data, communicate with each other, be guided through right research strategies, and to easily use well-established databases. In addition, since techniques and softwares for genome research groups are well established, a similar research road map could commonly be applied. In this study, we developed a web-based work place for effective genome research, named 'BioPlace.' From the beginning of writing a proposal, research members can work on the same environment with convenient aid to share files or data. BioPlace provides various ways of collaboration methods among genome researchers. The BioPlace system supports two types of workplaces, namely 'Personal Workspace' and 'Team Workspace.' For each BioPlace user, a Persona] Workspace is provided, while a Team Workspace is provided for each group with the same purpose. In addition, BioPlace provides a 'General Research Road Map' for genome research, and several Korean user interfaces for BLAST, PDB, and Primer3. We expect that BioPlace may facilitate collaboration of genome research among the experienced scientists and help beginners in many different ways as well.

• Journal of Pharmaceutical Investigation
• /
• 제40권1호
• /
• pp.1-7
• /
• 2010

K-$BEtest^{(R)}$ is a well known program for bioequivalence test using a $2{\times}2$ design. Lee et al.(1998) and Park et al.(1999) suggested a $3{\times}3$ and $3{\times}2$ design, and also discussed their benefits. We developed a computer program, called BioEquiv, which can analyze some complex experimental designs such as, $3{\times}3$ design and $3{\times}2$ design including a standard $2{\times}2$ design. This program is a user-friendly one and overcomes the disadvantages of K-$BEtest^{(R)}$. The detailed statistical formula and structure of BioEquiv are presented with some examples. The comparison between K-$BEtest^{(R)}$ and BioEquiv are given with actual data analysis. BioEquiv is able to present a table of ANOVA test over some complex experimental designs. Moreover K-$BEtest^{(R)}$ and BioEquiv draw the same result when data consists of $2{\times}2$ design.