• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권2호
• /
• pp.102-106
• /
• 2003

This paper describes a new pattern classifier neural network to extract the feature from a letter. The proposed pattern classifier is based on relative distance, which is measure between an input datum and the center of cluster group. So, the proposed classifier neural network is called relative neural network(RNN). According to definitions of the distance and the learning rule, the structure of RNN is designed and the pseudo code of the algorithm is described. In feature extraction of letter, RNN, in spite of deletion of learning rate, resulted in the identical performance with those of winner-take-all(WTA), and self-organizing-map(SOM) neural network. Thus, it is shown that RNN is suitable to extract the feature of a letter.

• Journal of Electrical Engineering and Technology
• /
• 제3권2호
• /
• pp.167-176
• /
• 2008

Vulnerability assessment of power systems is important so as to determine their ability to continue to provide service in case of any unforeseen catastrophic contingency such as power system component failures, communication system failures, human operator error, and natural calamity. An approach towards the development of on-line power system vulnerability assessment is by means of using an artificial neural network(ANN), which is being used successfully in many areas of power systems because of its ability to handle the fusion of multiple sources of data and information. An important consideration when applying ANN in power system vulnerability assessment is the proper selection and dimension reduction of training features. This paper aims to investigate the effect of using various feature extraction methods on the performance of ANN as well as to evaluate and compare the efficiency of the proposed feature extraction method named as neural network weight extraction. For assessing vulnerability of power systems, a vulnerability index based on power system loss is used and considered as the ANN output. To illustrate the effectiveness of ANN considering various feature extraction methods for vulnerability assessment on a large sized power system, it is verified on the IEEE 300-bus test system.

• 한국산업정보학회:학술대회논문집
• /
• 한국산업정보학회 2003년도 추계공동학술대회
• /
• pp.721-727
• /
• 2003

This study designed and implemented a system to extract of vowel from a word. The system is comprised of a voice feature extraction module and a neutral network module. The voice feature extraction module use a LPC(Linear Prediction Coefficient) model to extract a voice feature from a word. The neutral network module is comprised of a learning module and voice recognition module. The learning module sets up a learning pattern and builds up a neutral network to learn. Using the information of a learned neutral network, a voice recognition module extracts a vowel from a word. A neutral network was made to learn selected vowels(a, eo, o, e, i) to test the performance of a implemented vowel extraction recognition machine. Through this experiment, could confirm that speech recognition module extract of vowel from 4 words.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.672-675
• /
• 1999

In this paper, we propose a MLP neural network architecture and feature extraction for Korean syllable recognition. In the proposed syllable recognition system, firstly onset is classified by onset classification neural network. And the results information of onset classification neural network are used for feature selection of imput patterns vector. The feature extraction of Korean syllables is based on sonority. Using the threshold rate separate the syllable. The results of separation are used for feature of onset. nucleus and coda. ETRI's SAMDORI has been used by speech DB. The recognition rate is 96% in the speaker dependent and 93.3% in the speaker independent.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.547-550
• /
• 2009

The object recognition mechanism of human being is not well understood yet. On research of animal experiment using an ape, however, neurons that respond to simple shape (e.g. circle, triangle, square and so on) were found. And Hypothesis has been set up as human being may recognize object as combination of such simple shapes. That mechanism is called Figure Alphabet Hypothesis, and those simple shapes are called Figure Alphabet. As one way to research object recognition algorithm, we focused attention to this Figure Alphabet Hypothesis. Getting idea from it, we proposed the feature extraction algorithm for object recognition. In this paper, we described recognition of binarized images of multifont alphabet characters by the recognition model which combined three-layered neural network in the feature extraction algorithm. First of all, we calculated the difference between the learning image data set and the template by the feature extraction algorithm. The computed finite difference is a feature quantity of the feature extraction algorithm. We had it input the feature quantity to the neural network model and learn by backpropagation (BP method). We had the recognition model recognize the unknown image data set and found the correct answer rate. To estimate the performance of the contriving recognition model, we had the unknown image data set recognized by a conventional neural network. As a result, the contriving recognition model showed a higher correct answer rate than a conventional neural network model. Therefore the validity of the contriving recognition model could be proved. We'll plan the research a recognition of natural image by the contriving recognition model in the future.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1281-1285
• /
• 2004

There are numerous emotions in the human world. Human expresses and recognizes their emotion using various channels. The example is an eye, nose and mouse. Particularly, in the emotion recognition from facial expression they can perform the very flexible and robust emotion recognition because of utilization of various channels. Hybrid-feature extraction algorithm is based on this human process. It uses the geometrical feature extraction and the color distributed histogram. And then, through the independently parallel learning of the neural-network, input emotion is classified. Also, for the natural classification of the emotion, advancing two-dimensional emotion space is introduced and used in this paper. Advancing twodimensional emotion space performs a flexible and smooth classification of emotion.

• Journal of Electrical Engineering and Technology
• /
• 제13권6호
• /
• pp.2468-2478
• /
• 2018

We propose the Sparse Feature Convolutional Neural Network (SFCNN) to reduce the volume of convolutional neural networks (CNNs). Despite the superior classification performance of CNNs, their enormous network volume requires high computational cost and long processing time, making real-time applications such as online-training difficult. We propose an advanced network that reduces the volume of conventional CNNs by producing a region-based sparse feature map. To produce the sparse feature map, two complementary region-based value extraction methods, cluster max extraction and local value extraction, are proposed. Cluster max is selected as the main function based on experimental results. To evaluate SFCNN, we conduct an experiment with two conventional CNNs. The network trains 59 times faster and tests 81 times faster than the VGG network, with a 1.2% loss of accuracy in multi-class classification using the Caltech101 dataset. In vehicle classification using the GTI Vehicle Image Database, the network trains 88 times faster and tests 94 times faster than the conventional CNNs, with a 0.1% loss of accuracy.

• 전자공학회논문지CI
• /
• 제39권3호
• /
• pp.32-43
• /
• 2002

본 논문에서는 신경망에 기반한 디지털 신호를 위한 패턴분류 시스템을 제안한다. 제안하는 시스템은 두 가지 신경망 모델로 구성된다. 첫 번째 부분은 특징 추출의 역할을 하는 웨이블릿 신경망이다. 이 부분을 위해 기존의 웨이블릿 신경망 모델들을 비교한 후, 특징 추출을 위한 새로운 웨이블릿 신경망 모델을 제안한다. 다른 부분은 패턴 분류를 위한 웨이블릿 신경망이다. 패턴 분류에 적용하기 위해 기존의 웨이블릿 신경망 구조를 수정하고 학습 방법을 제안한다. 패턴 분류 웨이블릿 신경망의 입력은 특징 추출 신경망의 은닉노드의 연결강도, 확장 및 이동 파라미터로 구성되었다. 또 출력은 특징 추출 신경망의 입력 신호가 속한 부류를 나타낸다. 제안한 시스템을 EEG 신호를 주파수에 따라서 분류하는 문제에 적용하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.37.4-37
• /
• 2002

$\textbullet$ Feature extraction method for robot application $\textbullet$ Using ultrasonic sensor arrays $\textbullet$ Differentiate the target as plane, corner and edge $\textbullet$ Neural network approach

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2209-2212
• /
• 2003

In this paper, we propose the method to extract the important frequency bands from the EMG signal, and for generation of feature vector using the important frequency bands. The EMG signal is measured with 4 sensor and is recorded as 4 channel’s time series data. The same frequency bands from 4 channel’s frequency components are selected as the important frequency bands. The feature vector is calculated by the function formed using the combination of selected same important frequency bands. The EMG signals acquired from seven wrist motion type are recognized by changing into the feature vector formed. Then, the extraction and generation is performed by using the double combination of the genetic algorithm (GA) and the neural network (NN). Finally, in order to illustrate the effectiveness of the proposed method, computer simulations are done.