• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.129-131
• /
• 2009

Hearing loss is one of the most common birth defects among infants. Most hearing-impaired children are not diagnosed until one to three years of age, which is too late to treat for normal speech and language development. If a hearing impairment is identified and treated in its early stage, child's speech and language skills could be comparable to his or her normal-hearing peers. In this study, we applied the 'Fsp' method to distinguish between normal and impaired hearing. We have developed a battery-operated portable A - ABR(automated auditory brain stem response) system that automatically detects hearing impairment for neonates or infants in a nursery room, as well as in a sound-proof room. We partially validated the accuracy of the system in five normal-hearing adults.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.1377-1382
• /
• 1990

In Multi-Layer Perceptron (MLP) which realizes continuous mappings, the output errors is directly affected by the weight errors which may be caused by the limited precision of digital or analog hardware in implementations. So, it is important to study the sensitivity due to the perturbation of connection weights between neurons. In this paper, we derive a sensitivity function to the statistical weight perturbations in MLP with differentiable activation functions. This sensitivity function can be regarded as an ensemble average of deterministic sensitivity measures due to the perturbations of weights. Hence, this sensitivity function can be used as the criteria for selecting weights with the minimum sensitivity among possible sets of connection weights in MLP. For the verification of the validity of the proposed sensitivity function, computer simulations have been performed and through the simulations we find good agreement between the theoretical and simulation results.

• Genomics & Informatics
• /
• 제5권1호
• /
• pp.24-29
• /
• 2007

Computational virtual screening has become an essential platform of drug discovery for the efficient identification of active candidates. Moleculardocking, a key technology of receptor-centric virtual screening, is commonly used to predict the binding affinities of chemical compounds on target receptors. Despite the advancement and extensive application of these methods, substantial improvement is still required to increase their accuracy and time-efficiency. Here, we evaluate several advanced structure-based virtual screening approaches for elucidating the rank-order activity of chemical libraries, and the quantitative structureactivity relationship (QSAR). Our results show that the ensemble-average free energy estimation, including implicit solvation energy terms, significantly improves the hit enrichment of the virtual screening. We also demonstrate that the assignment of quantum mechanical-polarized (QM-polarized) partial charges to docked ligands contributes to the reproduction of the crystal pose of ligands in the docking and scoring procedure.

• 대한전기학회논문지
• /
• 제43권6호
• /
• pp.1027-1035
• /
• 1994

This paper aims to make an artificial arm control strategy. For this, we propose a new feature extraction method and design artificial neural network for the functional classification of myoelectric signal(MES). We first transform the two channel myoelectric signals (MES) for biceps and triceps into frequency domain using fast Fourier transform (FFT). And features were obtained by comparing the magnitudes of ensemble spectrum data and used as inputs to the three-layer neural network for the learning. By changing the number of units in hidden layer of neural network we observed the improvement of classification performance. To observe the effeciency of the proposed scheme we performed experiments for classification of six arm functions to the three subjects. And we obtained on average 94[%] the ratio of classification.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1993년도 추계학술대회
• /
• pp.151-155
• /
• 1993

Evoked potentials(EP) measured with scalp electrodes are often described as a deterministic process corrupted by uncorrelated electrical activities occuring in the brain and These electrical activities(ongoing EEG) refer to noise in EP recording. The Conventional method to determine the EP waveform requires long recording time. Unfortunately most of algorithm developed are too complicated for implementation in real time. Thus, conner EP recording devices use Ensemble average for real time processing. In this paper introduce EP recording hardware for processing advanced algorithm in real tlne. This hardware is composed of DSP chip(TMS320c25) and microcomputer.

• 시스템엔지니어링학술지
• /
• 제17권2호
• /
• pp.98-105
• /
• 2021

As the average life expectancy is rising, the population is aging and the number of chronic diseases is increasing. This has increased the importance of healthy life and health management, and interest in mobile health services is on the rise thanks to the development of ICT(Information and communication technologies) and the smartphone use expansion. In order to meet these interests, many mobile services related to daily health are being launched in the market. Therefore, in this study, the characteristics of users who actually use mobile health services were analyzed and a predictive model applied with machine learning modeling was developed. As a result of the study, we developed a prediction model to which the decision tree and ensemble methods were applied. And it was found that the mobile health service users' continued use can be induced by providing features that require frequent visit, suggesting achievable activity missions, and guiding the sensor connection for user's activity measurement.

• 한국통신학회논문지
• /
• 제39B권11호
• /
• pp.723-729
• /
• 2014

본 논문에서는 임의의 선형 재생 부호 앙상블에 대하여 복구 대역폭(Repair bandwidth)과 접속 비용(Repair read cost)의 평균을 유도한다. 한 데이터가 여러 노드에 부호화 되어 분산 저장된 상황에서 하나의 노드가 소실될 경우, 이를 복구하기 위해 필요한 데이터 량을 복구 대역폭, 접속해야 하는 노드 수를 복구 접속 비용이라 한다. 이 때, 선형 재생 부호 앙상블은 데이터 심볼의 수 k와 패리티 심볼의 수 m, 그리고 그들의 차수 분포로 주어진다. 우리는 이러한 부호들이 시스터메틱(Systematic)이며 정확한 복구(Exact repair)를 수행하고 n=k+m개의 모든 저장소(Storages)들이 전부 연결되어 있는 상황을 가정한다. 본 논문의 결과는 파운틴 부호 등과 같이 위와 같은 파라미터들로 랜덤하게 만들어진 부호들에 바로 적용 가능하다. 최종 결과식은 평균 복구 접속 비용이 차수 분포와 n, k에 따라 결정됨을 보여준다.

• 비파괴검사학회지
• /
• 제30권4호
• /
• pp.302-310
• /
• 2010

본 논문에서는 원자력 발전소 증기발생기 세관에 발생할 수 있는 결함의 크기측정에 사용되는 Bagging 신경회로망에 대한 연구를 수행하였다. Bagging은 부트스트랩(bootstrap) 샘플링에 기반을 둔 추정기 앙상블을 생성하는 방법이다. 증기발생기 세관의 결함 크기측정을 위하여 다양한 폭과 깊이를 갖는 4가지 결함패턴의 eddy current testing 신호를 생성하였다. 그 다음, 단일 신경회로망(single neural network; SNN)과 Bagging 신경회로망(Bagging neural network; BNN)을 구성하여 각 결함의 폭과 깊이를 추정하였다. SNN과 BNN 추정성능은 최대오차를 이용해서 측정하였다. 실험결과, 결함 깊이 추정시의 SNN과 BNN 최대오차는 0.117mm와 0.089mm 이었다. 또한, 결함 폭 추정 시에는 SNN과 BNN 최대오차는 0.494mm와 0.306mm 이었다. 이러한 실험결과는 BNN 추정성능이 SNN 추정성능보다 우수하다는 것을 보여준다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 1998년도 학술발표회 논문집
• /
• pp.3-3
• /
• 1998

In this pressentation it is argued that the heterogeneity of a hydrologic attribute which may seem to be nonstationary at one scale, may become stationary at a larger scale. The fundamental reason for transformation from nonstationarity to stationarity whith the increase in scale is the phenomenon of coarse-graining of the hydrologic processes with increasing scale. Due to the phenomenon of aliasing, a particular scale hydrologic process heterogeneity which is observed as a nonstationary process at that scale, may be observed as a stationary process at a higher(larger) scale whose size is bigger than the stationary extent of the lower scale heterogeneity. As one goes through a hierarchical sequence of larger and larger scales for observations, one would eliminate nonstationarities which emerge at some lower scales at the expense of losing information on the high frequency fluctuations of the lower scale heterogeneities which will no longer be observed at the larger sampling scales. We call this phenimenon as the "coarse-graining in hydrologic observations". In this presentation, it is also argued that by the coarse-graining of hydrologic processes due to the averaging and aliasing operations at increasing scales, the conservation laws corresponging to these scales may still be quite parsimonious, and need not be more complicated as the scales get larger. It is shown that shen a higher(larger) scale process is formed by averaging a lower(smaller) scale process in time or space, the high frequency components of the lower scale process will be eliminated by the averaging operation. Thereby, the resuliiting average hydrologic dynamics, free from the effects of the high frequency components of the lower scale process, can still be quite simple in form. This is demonstrated by means of some recent upscaling work on the solute teansport conservation equation for hetergeneous aquifers. By means of this solute transport example, it is also shown that for the ensemble average form of a hydrologic conservation equation to be equivalent to its volume-average form at any scale, the parameter functions of that conservation equation at the immediately lower scale must be ergodic.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제7권9호
• /
• pp.351-360
• /
• 2018

전통적으로 나태한 학습에 해당하는 국소가중회귀(LWR: Locally Weighted Regression)모델은 입력변수인 질의지점에 따라 예측의 해를 얻기 위해 일정구간 범위내의 학습 데이터를 대상으로 질의지점의 거리에 따라 가중값을 달리 부여하여 학습 한 결과로 얻은 짧은 구간내의 회귀식이다. 본 연구는 메모리 기반학습의 형태에 해당하는 LWR을 위한 점진적 앙상블 학습과정을 제안한다. LWR를 위한 본 연구의 점진적 앙상블 학습법은 유전알고리즘을 이용하여 시간에 따라 LWR모델들을 순차적으로 생성하고 통합하는 것이다. 기존의 LWR 한계는 인디케이터 함수와 학습 데이터의 선택에 따라 다중의 LWR모델이 생성될 수 있으며 이 모델에 따라 예측 해의 질도 달라질 수 있다. 하지만 다중의 LWR 모델의 선택이나 결합의 문제 해결을 위한 연구가 수행되지 않았다. 본 연구에서는 인디케이터 함수와 학습 데이터에 따라 초기 LWR 모델을 생성한 후 진화 학습 과정을 반복하여 적절한 인디케이터 함수를 선택하며 또한 다른 학습 데이터에 적용한 LWR 모델의 평가와 개선을 통하여 학습 데이터로 인한 편향을 극복하고자 한다. 모든 구간에 대해 데이터가 발생 되면 점진적으로 LWR모델을 생성하여 보관하는 열심학습(Eager learning)방식을 취하고 있다. 특정 시점에 예측의 해를 얻기 위해 일정구간 내에 신규로 발생된 데이터들을 기반으로 LWR모델을 생성한 후 유전자 알고리즘을 이용하여 구간 내의 기존 LWR모델들과 결합하는 방식이다. 제안하는 학습방법은 기존 단순평균법을 이용한 다중 LWR모델들의 선택방법 보다 적합도 평가에서 우수한 결과를 보여주고 있다. 특정지역의 시간 별 교통량, 고속도로 휴게소의 시간별 매출액 등의 실제 데이터를 적용하여 본 연구의 LWR에 의한 결과들의 연결된 패턴과 다중회귀분석을 이용한 예측결과를 비교하고 있다.