• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1993년도 학술논문발표회 논문집 제12권 1호
• /
• pp.117-120
• /
• 1993

In this paper, we explore the possibility of URAN(Universally Reconstructable Artificial Neural-network) VLSI chip for speech recognition. URAN, a newly developed analog-digital hybrid neural chip, is discussed in respects to its input, output, and weight accuracy and their relations to its performance on speaker independent digit recognition. Multi-layer perceptron(MLP) nets including a large frame input layer are used to recognize a digit syllable at a forward retrieval. The simulation results using the full and limited floating precision computations for the input, output, and weight variables of the network give the comparable classification performance. An MLP with piecewise linear hidden and output units is also trained successfully using low accuracy computation.

• 전자공학회논문지B
• /
• 제33B권3호
• /
• pp.186-192
• /
• 1996

A modified learning rule is introduced for the implementation of feedforward artificial neural networks with on-chip learning circuitry using standard analog CMOS technology. Learning rule, is modified form the EBP (error back propagation) rule which is one of the well-known learning rules for the feedforward rtificial neural nets(FANNs). The employed MEBP ( modified EBP) rule is well - suited for the hardware implementation of FANNs with on-chip learning rule. As a ynapse circuit, a four-quadrant vector-product linear multiplier is employed, whose input/output signals are given with voltage units. Two $2{\times}2{\times}1$ FANNs are implemented with the learning circuitry. The implemented FANN circuits have been simulatied with learning test patterns using the PSPICE circuit simulator and their results show correct learning functions.

• 한국정밀공학회지
• /
• 제20권11호
• /
• pp.71-78
• /
• 2003

The exit burrs in the micro-drilling of precision miniature holes are of interest, especially for ductile materials. As burrs from this process can be difficult to remove, it is important to acquire the way of predicting burr types as well as optimal cutting conditions which minimize the burrs. In this paper, an artificial neural network was used for the prediction of burr formation in micro-drilling. First, the influence of cutting conditions including cutting speed, feed and drill diameter on the exit burr characteristics, such as burr size and type, were observed and analyzed. Then. the burr types were classified by using the influential experimental data as input parameters to the neural nets.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.232-235
• /
• 1998

This paper evaluates the performance of a rough set based pattern classifier using the benchmarks in artificial neural nets depository found in internet. The definition of rough set in soft computing paradigm is briefly introduced. next the design of rough set classifier is suggested. Finally benchmark test results are shown the performance of rough set compare to that of ANNs and decision tree.

• 한국IT서비스학회지
• /
• 제7권2호
• /
• pp.149-164
• /
• 2008

As the computing landscape is shifting to ubiquitous computing environments, there is increasingly growing the demand for a variety of device controls that react to user's implicit activities without excessively drawing user attentions. We developed an EMG-based car interface that enables the physically handicapped to drive a car using their functioning peripheral nerves. Our method extracts electromyogram signals caused by wrist movements from four places in the user's forearm and then infers the user's intent from the signals using multi-layered neural nets. By doing so, it makes it possible for the user to control the operation of car equipments and thus to drive the car. It also allows the user to enter inputs into the embedded computer through a user interface like an instrument LCD panel. We validated the effectiveness of our method through experimental use in a car built with the EMG-based interface.

• 정보처리학회논문지B
• /
• 제15B권4호
• /
• pp.323-330
• /
• 2008

복합질환은 다수의 유전자들이 상호작용하여 유발되는 질병으로서, 여러 유전자들이 관여한다는 복잡성 때문에 전통적인 분석 방법을 적용하는데 한계가 있다. 최근에는 기계학습 기법을 이용한 새로운 분석 방법들이 제안되고 있다. 신경망은 이처럼 복잡한 데이터에서 일정한 패턴을 찾아 이를 분류하는데 적합한 모델이다. 그러나 다량의 데이터가 입력으로 들어오는 경우에 학습에 오랜 시간이 걸리고 패턴을 찾기가 어려워지는 단점이 있다. 본 연구에서는 다량의 SNP 데이터로부터 질병에 연관된 소수의 중요 SNP을 찾기 위한 통계학적인 방법인 집합결합(set association)과 신경망을 결합한 모델을 제시한다. 이 모델을 천식 관련 SNP 데이터에 적용하여 천식 발병 여부를 예측한 결과, 신경망만 사용했을 때보다 실행 시간도 빠르고 예측 정확도도 높았다. 이 모델은 다른 복합질환의 예측에도 효과적으로 사용할 수 있을 것으로 기대한다.

• Nuclear Engineering and Technology
• /
• 제53권2호
• /
• pp.522-531
• /
• 2021

We describe a new deep learning model - Convolutional eXtreme Gradient Boosting (ConvXGB) for classification problems based on convolutional neural nets and Chen et al.'s XGBoost. As well as image data, ConvXGB also supports the general classification problems, with a data preprocessing module. ConvXGB consists of several stacked convolutional layers to learn the features of the input and is able to learn features automatically, followed by XGBoost in the last layer for predicting the class labels. The ConvXGB model is simplified by reducing the number of parameters under appropriate conditions, since it is not necessary re-adjust the weight values in a back propagation cycle. Experiments on several data sets from UCL Repository, including images and general data sets, showed that our model handled the classification problems, for all the tested data sets, slightly better than CNN and XGBoost alone and was sometimes significantly better.

• Nuclear Engineering and Technology
• /
• 제54권12호
• /
• pp.4751-4758
• /
• 2022

Two-phase flow may almost exist in every branch of the energy industry. For the corresponding engineering design, it is very essential and crucial to monitor flow patterns and their transitions accurately. With the high-speed development and success of deep learning based on convolutional neural network (CNN), the study of flow pattern identification recently almost focused on this methodology. Additionally, the photographing technique has attractive implementation features as well, since it is normally considerably less expensive than other techniques. The development of such a two-phase flow pattern online monitoring system is the objective of this work, which seldom studied before. The ongoing preliminary engineering design (including hardware and software) of the system are introduced. The flow pattern identification method based on CNNs and transfer learning was discussed in detail. Several potential CNN candidates such as ALexNet, VggNet16 and ResNets were introduced and compared with each other based on a flow pattern dataset. According to the results, ResNet50 is the most promising CNN network for the system owing to its high precision, fast classification and strong robustness. This work can be a reference for the online monitoring system design in the energy system.

• 한국신재생에너지학회:학술대회논문집
• /
• 한국신재생에너지학회 2009년도 추계학술대회 논문집
• /
• pp.427-430
• /
• 2009

풍력 터빈 블레이드용 익형의 경우 운용 조건에서 높은 양항비를 가지도록 설계되나 풍속, 풍향의 변동에 의해 운용조건에 변화가 발생할 경우 성능의 저하가 발생할 수 있다. 따라서 운용조건의 변동이 발생하더라도 공력 성능이 크게 변하지 않는 익형이 요구된다. 본 연구에서는 이러한 운용조건의 불확실성을 고려하여 풍력 터빈 블레이드용 익형의 신뢰성 기반 강건 최적 설계를 수행하였다. 익형 설계를 위해서 여러 익형 형상 변수들을 고려할 수 있는 익형 모델링 함수를 정의하였고 기저형상으로는 NREL에서 개발한 S809 익형을 사용하였다.

• 센서학회지
• /
• 제7권6호
• /
• pp.418-425
• /
• 1998

로봇을 비롯한 자동화 기계의 3차원 작업에서 스테레오 카메라는 가장 널리 사용되는 센서 장치이다. 스테레오 카메라를 사용함으로써 3차원 실세계 공간내 임의 목표점의 위치를 측정할 수 있으며, 카메라의 보정은 이를 위한 중요한 선행작업이다. 기존의 카메라 보정법은 크게 선형과 비선형의 기법으로 나눌 수 있는데, 선형의 기법은 간단하나 정확도의 면에서 문제점을 지니고, 비선형 기법은 렌즈의 왜곡을 보상하기 위한 모델링 과정과 이의 비선형 해를 구하는 비교적 복잡한 과정을 필요로 한다는 문제가 있다. 본 논문에서는 이러한 문제의 한 해결방안으로 인공신경망을 적용하는 방법을 연구하고 그 결과를 제시한다. 특히 역전파 알고리즘에 의해 학습된 다층 신경망의 함수 근사화 능력을 활용하여 선형기법의 오차 패턴을 학습함으로써 간단하고 효과적으로 계측의 정확도를 향상시킬 수 있음을 실험을 통하여 보인다.