• 대한의용생체공학회:의공학회지
• /
• 제10권2호
• /
• pp.83-88
• /
• 1989

This paper is a study on the design of adptive filter for QRS complex detection. We propose a simple adaptive algorithm to increase capability of noise cancelation in QRS complex detection with two stage adaptive filter. At the first stage, background noise is removed and at the next stage, only spectrum of QRS complex components is passed. Two adaptive filters can afford to keep track of the changes of both noise and QRS complex. Each adaptive filter consists of prediction error filter and FIR filter The impulse response of FIR filter uses coefficients of prediction error filter. The detection rates for 105 and 108 of MIT/BIH data base were 99.3% and 97.4% respectively.

• The Journal of the Acoustical Society of Korea
• /
• 제18권1E호
• /
• pp.13-19
• /
• 1999

This paper introduces an adaptive wavelet transform based on the lifting scheme, which is applied to signal denoising. The wavelet representation using orthogonal wavelet bases has received widespread attention. Recently the lifting scheme has been developed for the construction of biorthogonal wavelets in the spatial domain. Wavelet transforms are performed through three stages: the first stage or Lazy wavelet splits the data into two subsets, even and odd, the second stage calculates the wavelet coefficients (highpass) as the failure to interpolate or predict the odd set using the even, and the third stage updates the even set using neighboring odd points (wavelet coefficients) to compute the scaling function coefficients (lowpass). In this paper, we adaptively find some of the prediction coefficients for better representation of signals and this customizes wavelet transforms to provide an efficient framework for denoising. Special care has been given to the boundaries, where we design a set of different prediction coefficients to reduce the prediction error.

• 교육녹색환경연구
• /
• 제11권3호
• /
• pp.46-54
• /
• 2012

The accuracy of cost estimation at an early stage in school building project is one of the critical factors for successful completion. So various of techniques are developed to predict the construction cost accurately and expeditely. Among the techniques, Support Vector Machine(SVM) has an excellent ability for generalization performance. Therefore, the purpose of this study is to construct the prediction model for construction cost of educational building project using support vector machine technique. And to verify the accuracy of prediction model for construction cost. The performance data used in this study are 217 school building project cost which have been completed from 2004 to 2007 in Gyeonggi-Do, Korea. The result shows that average error rate was 7.48% for SVM prediction model. So using SVM model on predicting construction cost of educational building project will be a considerably effective way at the early project stage.

• 한국초등과학교육학회지:초등과학교육
• /
• 제33권1호
• /
• pp.115-128
• /
• 2014

Students' argumentation during science inquiry should be regarded important as it could help students to make meaningful connections between theories and experiments and to make scientific claims based on evidences. In this study, elementary science-gifted students' argumentation during small group inquiry was analyzed according to inquiry process. There were three stages of argumentation during students' inquiry. The first argumentation was to predict what would happen(Prediction stage). In this stage, the scientific problem was presented by concept cartoon as a way to start and to facilitate students' argumentation. The second argumentation was to design an experiment to solve the problem(Planning stage) and the third was to interpret the result of experiment(Interpretation stage). The discourse move, level of grounds and their relationship were analyzed to find the characteristics of argumentation during science inquiry. In terms of discourse move, 'Asking for opinion' was the most frequent whereas 'Claim' or 'Rebuttal' were rare. Students tended to listen to or ask others' opinion rather than provide their own claims or critics on others' opinion. 'Rebuttal' was shown a few times only during prediction and planning stage. There was no single 'Rebuttal' during interpretation stage. Students tended to easily accept or agree other student's interpretation of data instead of arguing their own ideas. In terms of level of grounds, students mostly provided their ideas without any attempt to justify their position. Especially during planning stage, students tended to suggest or decide ways of measuring or controlling variables without any grounds. They used evidences only a few times during prediction stage. In terms of relation between discourse move and level of grounds, students provided grounds most frequently when they dispute others' claims. The level of grounds were higher when they advocate or clarify their own or others' ideas than when they claim their ideas. The result of this study showed that the quality of elementary science-gifted students' argumentation during science inquiry was undesirable in many ways. Implications for scaffolding and facilitating argumentation during science inquiry were discussed.

• 스마트미디어저널
• /
• 제9권4호
• /
• pp.126-133
• /
• 2020

병원에서는 폐암 환자의 최종병기를 기준으로 치료방침 및 예후를 결정하고 있다. 폐암 환자의 최종병기는 미국 암 연합회(AJCC)에서 제공하는 TNM 분류방법을 바탕으로 7단계로 나누어 진단된다. 이런 접근 방법은 환자의 치료, 예후 및 생존일 예측 등 다양한 분야에서 사용하기에 한계가 있다. 이 논문에서는 데이터 과학적 접근을 통해 T, N, M병기를 사용하여 생존일수별 환자집단을 나눌 수 있는지 알아보기 위해 비지도 학습 중 하나인 군집분석(Clustering)을 진행한 후 군집분석의 결과를 Cox비례위험모형을 사용하여 비교 하였다. 환자들의 최종병기를 사용하지 않고, T, N, M병기 정보만 사용하였을 때 생존시간 예측정확도가 더 높은 것을 확인하였다. 특히, AJCC의 최종병기 7단계와 같이 군집의 개수를 7로 설정했을 때보다 군집의 수를 축소하거나 확장했을 때 T, N, M 병기 군집분석을 통한 생존시간 예측정확도가 향상하는 것을 확인하였다.

• 대기
• /
• 제17권4호
• /
• pp.327-337
• /
• 2007

In this study, we examined the new ensemble training approach to reduce the systematic error and improve prediction skill of wind by using the Short-range Ensemble prediction system (SENSE), which is the mesoscale multi-model ensemble prediction system. The SENSE has 16 ensemble members based on the MM5, WRF ARW, and WRF NMM. We evaluated the skill of surface wind prediction compared with AWS (Automatic Weather Station) observation during the summer season (June - August, 2006). At first stage, the correction of initial state for each member was performed with respect to the observed values, and the corrected members get the training stage to find out an adaptive weight function, which is formulated by Root Mean Square Vector Error (RMSVE). It was found that the optimal training period was 1-day through the experiments of sensitivity to the training interval. We obtained the weighted ensemble average which reveals smaller errors of the spatial and temporal pattern of wind speed than those of the simple ensemble average.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2003년도 제2차 연례학술대회 발표논문집
• /
• pp.7-16
• /
• 2003

In this paper, we propose a probabilistic framework to predict the interaction probability of proteins. The notion of domain combination and domain combination pair is newly introduced and the prediction model in the framework takes domain combination pair as a basic unit of protein interactions to overcome the limitations of the conventional domain pair based prediction systems. The framework largely consists of prediction preparation and service stages. In the prediction preparation stage, two appearance pro-bability matrices, which hold information on appearance frequencies of domain combination pairs in the interacting and non-interacting sets of protein pairs, are constructed. Based on the appearance probability matrix, a probability equation is devised. The equation maps a protein pair to a real number in the range of 0 to 1. Two distributions of interacting and non-interacting set of protein pairs are obtained using the equation. In the prediction service stage, the interaction probability of a protein pair is predicted using the distributions and the equation. The validity of the prediction model is evaluated fur the interacting set of protein pairs in Yeast organism and artificially generated non-interacting set of protein pairs. When 80% of the set of interacting protein pairs in DIP database are used as foaming set of interacting protein pairs, very high sensitivity(86%) and specificity(56%) are achieved within our framework.

• 한국화재소방학회논문지
• /
• 제32권2호
• /
• pp.7-16
• /
• 2018

본 연구에서는 화재 시뮬레이션에 사용하기 위해 제안된 기존의 디자인 화재곡선을 일부 수정한 디자인 화재곡선을 제안하였다. ISO 9705 구획실 내 형성된 헵탄과 옥탄 풀화재를 대상으로 기존에 제안된 1-stage 디자인 화재곡선과 수정된 2-stage 디자인 화재곡선을 입력조건으로 적용하여 FDS와 CFAST를 이용한 시뮬레이션을 수행하고 실험결과와 비교하였다. FDS와 CFAST 시뮬레이션 결과에서 온도와 $O_2$, $CO_2$ 농도에 대해서 전체적으로 2-stage 디자인 화재곡선이 1-stage 디자인 화재곡선보다 잘 예측하였으며, 특히 화재 초기 성장단계에서 온도에 대한 예측은 2-stage 디자인 화재곡선의 결과가 더 합리적임을 확인하였다. 구획실 내 온도변화에 대한 FDS와 CFAST 시뮬레이션 결과는 상층부에 대해서는 비교적 합리적으로 예측하였고 두 계산결과에 차이가 크지 않았지만 하층부에 대해서는 두 계산 모두 너무 낮게 예측하였으며 두 계산결과에도 차이가 크게 나타나는 것을 알 수 있었다.

• 한국융합학회논문지
• /
• 제12권7호
• /
• pp.169-179
• /
• 2021

본 연구는 기존의 k-평균 군집화를 활용한 2단계 k-평균 군집화 방법을 사용하여 한류콘텐츠 기업들의 주식가격을 예측함으로써 본 기법이 예측성능을 개선할 수 있음을 보이고자 하였다. 이를 위하여 본 연구는 2단계 k-평균 군집화의 알고리즘을 소개하고, 다양한 머신러닝 기법들과의 예측값 비교를 통하여 본 기법의 예측성능을 검증하였다. 본 기법은 기존의 k-평균 군집화로부터 얻어진 군집들 중에서 예측 대상에 근접한 군집을 추출하고 이 군집에 k-평군 군집화 방법을 다시 적용하여 실제 값에 보다 근접한 군집을 탐색하는 방식이다. 본 기법을 한류콘텐츠 기업들의 주가 시계열 자료에 적용한 결과, 다른 머신러닝 기법의 예측값들보다 실제 주식가격에 근접한 예측값을 나타내어, 기존의 k-평균 군집화 방법보다 개선된 예측성능을 보였다. 또한, 본 기법은 상대적으로 적은 크기의 군집을 사용함에도 불구하고 비교적 안정적인 예측값을 나타내었다. 이에 따라, 2단계 k-평균 군집화 기법은 예측의 정확성과 안정성을 동시에 개선할 수 있으며, 소규모 자료에도 유용할 수 있는 새로운 군집화 방식을 제시했다고 볼 수 있다. 향후에는 본 기법을 발전시켜 대규모 자료에도 적용하는 방안을 검토하는 연구가 요구된다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.207-209
• /
• 2022

IoT환경에서 스마트 디바이스로부터 사람의 신체 활동을 인식하여 생활 패턴 데이터를 수집할 수 있게 되었다. 본 논문에서는 제안된 모델은 예측단계와 추천단계로 구성한다. 예측 단계는 생활 패턴 데이터로부터 수집된 데이터셋을 기계학습을 통해 로지스틱 회귀와 k-최근접 이웃 알고리즘을 활용하여 불안과 우울의 척도를 예측한다. 추천 단계는 불안과 우울 증상으로 분류된 경우 이를 호전시킬 수 있는 음식과 가벼운 운동을 추천하기 위해 주성분 분석 알고리즘을 적용한다. 제안한 불안·우울 예측과 음식·운동 추천은 개인의 삶의 품질 개선에 파급효과가 있을 것으로 기대한다.