• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.34-37
• /
• 2002

This paper presents a new stochastic binary neural network based on the Hopfield model. We apply the proposed network to TSP and compare it with other methods by computer simulations. Furthermore, we apply 2-opt to the proposed network to improve the performance.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 하계학술대회 논문집 D
• /
• pp.2432-2434
• /
• 2004

In this paper, we present a novel approach for the structure of Fuzzy Neural Network(FNN) based on wavelet function and apply this network structure to the solution of the tracking problem for mobile robots. Generally, the wavelet fuzzy model(WFM) has the advantage of the wavelet transform by constituting fuzzy basis function(FBF) and the conclusion part to equalize the linear combination of FBF with the linear combination of wavelet functions. However, it is very difficult to identify the fuzzy rules and to tune the membership functions of the fuzzy reasoning mechanism. Neural networks, on the other hand, utilize their learning capability for automatic identification and tuning. Therefore, we design a wavelet based FNN structure(WFNN) that merges these advantages of neural network, fuzzy model and wavelet. To verify the efficiency of our network structure, we evaluate the tracking performance for mobile robot and compare it with those of the FNN and the WFM.

• 재활복지공학회논문지
• /
• 제6권1호
• /
• pp.67-73
• /
• 2012

본 논문에서는 표면 근전도 신호를 사용하여 손목 움직임의 동작을 분류하기 위해 인공 신경 회로망(ANN : Artificial Neural Network)기반의 동작 분류 알고리즘을 제안한다. 손목 움직임에 무리가 없는 20~30대 성인 26명을 대상으로 척측 수근 굴근과 척측 수근 신근에 부착한 2채널의 전극으로부터 표면 근전도 신호를 취득하고, 취득한 근전도로부터 손목의 굴곡, 신전, 내전, 외전, 휴식 다섯 동작을 인식한다. 빠른 처리 속도를 위해 획득한 신호로부터 시간 영역에서의 특징점을 추출하고 ANN을 이용한 동작 분류에 사용된다. 특징점으로 DAMV, DASDV, MAV, RMS를 사용하였으며, ANN 기반의 동작 분류의 인식율은 DAMV는 98.03%, DASDV는 97.97%, MAV는 96.95%, 그리고 RMS는 96.82%의 정확도를 나타낸다.

• Earthquakes and Structures
• /
• 제11권5호
• /
• pp.841-859
• /
• 2016

Bridge bearings are important connection elements between bridge superstructures and substructures, whose health states directly affect the performance of the bridges. This paper systematacially presents a new method to identify the bridge bearing damage based on the neural network theory. Firstly, based on the analysis of different damage types, a description of the bearing damage is introduced, and a uniform description for all the damage types is given. Then, the feasibility and sensitivity of identifying the bearing damage with bridge vibration modes are investigated. After that, a Radial Basis Function Neural Network (RBFNN) is built, whose input and output are the beam modal information and the damage information, respectively. Finally, trained by plenty of data samples formed by the numerical method, the network is employed to identify the bearing damage. Results show that the bridge bearing damage can be clearly reflected by the modal information of the bridge beam, which validates the effectiveness of the proposed method.

• Journal of the Korean Data and Information Science Society
• /
• 제28권6호
• /
• pp.1327-1336
• /
• 2017

본 연구에서는 단기 예측을 위한 자기회귀누적이동평균모형, 역전파 신경망 및 유전자 알고리즘의 결합 적용에 대하여 논의하고 이를 통한 유전자-신경망 알고리즘의 효용성을 살펴본다. 일반적으로 역전파 알고리즘은 지역 최소값에 수렴될 수 있는 단점이 있기 때문에, 여기서는 예측 정확도를 높이기 위해 역전파 신경망 구조를 최적화하고 유전자 알고리즘을 결합한 유전자-신경망 알고리즘 기반 예측모형을 구축한다. 실험을 통한 오차 비교는 KOSPI 지수를 이용한다. 결과는 이 연구에서 제안된 유전자-신경망 모형이 역전파 신경망 모형과 비교할 때 예측 정확도에서 어느 정도 유의한 효율성을 보여주고자 한다.

• 대한의용생체공학회:의공학회지
• /
• 제40권2호
• /
• pp.62-67
• /
• 2019

The purpose of this study was to evaluate the performance of deep neural network model in order to determine whether there is a risk factor for coronary artery disease based on the cardiac variation parameter. The study used unidentifiable 297 data to evaluate the performance of the model. Input data consists of heart rate parameters, which are SDNN (standard deviation of the N-N intervals), PSI (physical stress index), TP (total power), VLF (very low frequency), LF (low frequency), HF (high frequency), RMSSD (root mean square of successive difference) APEN (approximate entropy) and SRD (successive R-R interval difference), the age group and sex. Output data are divided into normal and patient groups, and the patient group consists of those diagnosed with diabetes, high blood pressure, and hyperlipidemia among the various risk factors that can cause coronary artery disease. Based on this, a binary classification model was applied using Deep Neural Network of deep learning techniques to classify normal and patient groups efficiently. To evaluate the effectiveness of the model used in this study, Kernel SVM (support vector machine), one of the classification models in machine learning, was compared and evaluated using same data. The results showed that the accuracy of the proposed deep neural network was train set 91.79% and test set 85.56% and the specificity was 87.04% and the sensitivity was 83.33% from the point of diagnosis. These results suggest that deep learning is more efficient when classifying these medical data because the train set accuracy in the deep neural network was 7.73% higher than the comparative model Kernel SVM.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권3호
• /
• pp.123-128
• /
• 2019

본 논문에서는 RCNN (recurrent convolution neural network) 계층 모델을 채택한 인공 지능에 기반을 둔 주가 예측을 제안한다. LSTM (long-term memory model) 기반 신경망은 시계열 데이터의 예측에 사용된다. 다른 한편, 컨볼루션 신경망은 데이터 필터링, 평균화 및 데이터 확장을 제공한다. 제안된 주가 예측에서는 위에서 언급 한 장점들을 RCNN 모델에서 결합하여 적용함으로써 다음날의 주가 종가를 예측한다. 그리고 최근의 시계열의 데이터를 강조하기 위해 커스텀 가중치 손실 함수가 채택되었다. 또한 시장의 상황을 반영하기 위해 주가 인덱스에 관련된 데이터를 입력으로 포함하였다. 제안된 주가 예측 방식은 실제 주가를 대상으로 한 실험에서 3.19%로 테스트 오차를 줄였으며, 다른 방법보다 약 19%의 성능 향상을 거둘 수 있었다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.328-330
• /
• 2004

In this paper, ECG based cardiac disease diagnosis models are developed. Conventionally, ECG monitoring equipments can only measure and store ECG signals and they always require medical doctor's diagnosis actions which are not desirable for continuous ambulatory monitoring and diagnosis healthcare systems. In this paper, two kinds of neural based self cardiac disease diagnosis engines are developed and tested for four kinds of diseases, sinus bradycardia, sinus tachycardia, left bundle branch block and right bundle branch block. For diagnosis engines, error backpropagation neural network (BP) and probabilistic neural network (PNN) were applied. Five signal features including heart rate, QRS interval, PR interval, QT interval, and T wave types were selected for diagnosis characteristics. To show the validity of proposed diagnosis engine, MIT-BIH database were used to test. Test results showed that BP based diagnosis engine has 71% of diagnosis accuracy which is superior to accuracy of PNN based diagnosis engine. However, PNN based diagnosis engine showed superior diagnosis accuracy for complex-disease diagnoses than BP based diagnosis engine.

• 한국정보처리학회논문지
• /
• 제5권1호
• /
• pp.119-127
• /
• 1998

본 논문에서는 한글 인쇄체 인식 시스템의 실시간 처리를 위하여 인식 프로세스중 시간이 많이 걸리는 한글 문자 유형 분류 및 자소 인식 단계를 고속 처리할 수 있는 다층구조 신경망을 VLSI 설계 하였으며, 신경망과 호스트 컴퓨터간의 인터페이스와 신경망 제어를 담당하는 코프로세서 구조를 제안하였다. 이를 VHDL 모델링 및 논리합성을 통하여 설계하여 시뮬레이션을 통하여 구조와 동작 및 성능을 검증하였다. 실험결과 제안한 신경망 coprocessor는 기존의 소프트웨어 구현 인식 시스템의 유형 분류 및 자소 인식률과 대등한 성능을 보인 반면 고속의 인식속도를 보였다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2013년도 추계학술대회 논문집
• /
• pp.320-324
• /
• 2013

A crack identification method using an equivalent bending stiffness for cracked beam and committee of neural networks is presented. The equivalent bending stiffness is constructed based on an energy method for a straight thin-walled pipe, which has a through-the-thickness crack, subjected to bending. Several numerical analysis for a steel cantilever pipe using the equivalent bending stiffness are carried out to extract the natural frequencies and mode shapes of the cracked beam. The extracted modal properties are used in constructing a training patterns of a neural network. The input to the neural network consists of the modal properties and the output is composed of the crack location and size. Multiple neural networks are constructed and each individual network is trained independently with different initial synaptic weights. Then, the estimated crack locations and sizes from different neural networks are averaged. Experimental crack detection is carried out for 3 damage cases using the proposed method, and the identified crack locations and sizes agree reasonably well with the exact values.