• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.13-21
• /
• 1995

In this paper, we improve an image classifier algorithm based on neural network learning. It consists of two steps. The first is input pattern generation and the second, the global neural network implementation using an improved back-propagation algorithm. The feature vector for pattern recognition consists of the codebook data obtained from self-organization feature map learning. It decreases the input neuron number as well as the computational cost. The global neural network algorithm which is used in classifier inserts a control part and an address memory part to the back-propagation algorithm to control weights and unit-offsets. The simulation results show that it does not fall into the local minima and can implement easily the large-scale neural network. And it decreases largely the learning time.

• Korean Journal of Cognitive Science
• /
• v.10 no.1
• /
• pp.13-24
• /
• 1999

In this paper, we propose a classifier based on modular networks using an unsupervised learning method. The structure of each module is designed through stochastic analysis of input data and each module classifier data independently. The result of independent classification of each module and a measure of the nearest distance are integrated during the final data classification phase to allow more precise c classification. Computation time is decreased by deleting modules that have been classified to be incorrect during the final classification phase. Using this method. a neural network sharing the best performance was implemented without considering. lots of of variables which can affect the performance of the neural network.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.295-297
• /
• 2001

최근 생물 유전자 정보를 효과적으로 분석하기 위한 적절한 도구의 필요성이 대두되고 있다. 본 논문에서는 백혈병 환자의 골수로부터 얻어낸 DNA Microarray 유전 정보를 분류하여 환자가 가지고 있는 암의 종류를 예측하기 위한 최적의 특징추출방법과 분류 방법을 찾고자 한다. 이를 위해 피어슨 상관관계, 유클리디안 거리, 코사인 계수, 스피어맨 상관관계, 정보 이득, 상호 정보, 신호 대잡음비의 7가지 특징 추출 방법을 사용하였으며, 역전과 신경망, 의사결정 트리, 구조 적응형 자기구성 지도, $textsc{k}$-최근접 이웃 등 가지의 기계학습 분류기를 이용하여 분류 실험을 하였다. 실험결과, 피어슨 상관관계와 역전파 신경망을 이용한 분류 방법이 97.1%의 인식률을 보임을 알 수 있었다.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.192-201
• /
• 2002

Automated text classification is considered as an important method to manage and process a huge amount of documents in digital forms that are widespread and continuously increasing. Recently, text classification has been addressed with machine learning technologies such as k-nearest neighbor, decision tree, support vector machine and neural networks. However, only few investigations in text classification are studied on real problems but on well-organized text corpus, and do not show their usefulness. This paper proposes and analyzes text classification methods for a real application, email document classification task. First, we propose a combining method of multiple neural networks that improves the performance through the combinations with maximum and neural networks. Second, we present another strategy of combining multiple machine learning classifiers. Voting, Borda count and neural networks improve the overall classification performance. Experimental results show the usefulness of the proposed methods for a real application domain, yielding more than 90% precision rates.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.53-56
• /
• 1998

본 논문에서의 공학적인 체계성을 갖고 초기 연결 가중치 및 임계치를 결정해 주면서, 학습까지 가능한 신경망을 제안한다. 기존의 오류 역전파 신경망을 적용할 때 경험에 의하여 은닉층 노드수를 결정하거나 임의의 실수 값으로 초기 연결 가중치 및 임계값을 주었을 때 자주 발생하는 학습 마비 현상을 피할 수 있고, Bose가 제안된 Voronoi 공간 분류에 의한 신경망 구성에서 학습이 불가능하다는 제안적인 단점을 보안하였다. 초기 가중치는 Voronoi 공간 분류가 이루어져 있다고 할 때 Bose가 제안한 초기 가중치 결정법을 개선하여 사용하고, Bose의 경우 신경망 노드가 Step function을 이용하여 정보를 전달하였으나 본 연구에서는 학습이 가능한 함수인 Sigmoid function을 이용하였다. 제안된 새로운 신경망의 성능 및 효율성을 비교하기 위하여 선형분리가 불가능한 XOR문제를 실험한 결과, 기존의 학습 가능한 EBP에서 허용오차 0.05 수준일 때 80%정도 학습마비 현상이 발생하였던 심각한 문제점을 보완할 수 있었고, 또한 학습 속도면에서 8~9배 정도 빠른 성능을 나타내었다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.5
• /
• pp.97-102
• /
• 2017

Recently deep learning techniques such as convolutional neural networks (CNN) have been introduced to classify high-resolution remote sensing data. In this paper, we investigated the possibility of applying CNN to crop classification of farmland images captured by drones. The farming area was divided into seven classes: rice field, sweet potato, red pepper, corn, sesame leaf, fruit tree, and vinyl greenhouse. We performed image pre-processing and normalization to apply CNN, and the accuracy of image classification was more than 98%. With the output of this study, it is expected that the transition from the existing image classification methods to the deep learning based image classification methods will be facilitated in a fast manner, and the possibility of success can be confirmed.

• Journal of Korea Multimedia Society
• /
• v.5 no.5
• /
• pp.505-514
• /
• 2002

In this Paper, we propose a method of content-based image classification using neural network. The images for classification ate object images that can be divided into foreground and background. To deal with the object images efficiently, object region is extracted with a region segmentation technique in the preprocessing step. Features for the classification are texture and shape features extracted from wavelet transformed image. The neural network classifier is constructed with the extracted features and the back-propagation learning algorithm. Among the various texture features, the diagonal moment was more effective. A test with 300 training data and 300 test data composed of 10 images from each of 30 classes shows correct classification rates of 72.3% and 67%, respectively.

• Journal of the Korean Data and Information Science Society
• /
• v.12 no.2
• /
• pp.11-25
• /
• 2001

There are several algorithms for classification in modeling relations, patterns, and rules which exist in data. We learn to classify objects on the basis of instances presented to us, not by being given a set of classification rules. The Bayesian learning uses the probability distribution to express our knowledge about unknown parameters and update our knowledge by the law of probability as the evidence gathered from data. Also, the neural network models are designed for predicting an unknown category or quantity on the basis of known attributes by training. In this paper, we compare the misclassification error rates of Bayesian Neural Network method with those of other classification algorithms, CHAID, CART, and QUBST using several data sets.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.592-599
• /
• 2020

This paper proposes a Convolutional Recurrent Neural Net (CRNN) structure that can simultaneously reflect both static and dynamic characteristics of seismic waveforms for various earthquake events classification. Addressing various earthquake events, including not only micro-earthquakes and artificial-earthquakes but also macro-earthquakes, requires both effective feature extraction and a classifier that can discriminate seismic waveform under noisy environment. First, we extract the static characteristics of seismic waveform through an attention-based convolution layer. Then, the extracted feature-map is sequentially injected as input to a multi-input single-output Long Short-Term Memory (LSTM) network structure to extract the dynamic characteristic for various seismic event classifications. Subsequently, we perform earthquake events classification through two fully connected layers and softmax function. Representative experimental results using domestic and foreign earthquake database show that the proposed model provides an effective structure for various earthquake events classification.

• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1275-1281
• /
• 2017

The supervised learning approach is suitable for classification of insulting sentences, but pre-decided training sentences are necessary. Since a Character-level Convolution Neural Network is robust for each character, so is appropriate for classifying abusive sentences, however, has a drawback that demanding a lot of training sentences. In this paper, we propose transfer learning method that reusing the trained filters in the real classification process after the filters get the characteristics of offensive words by generated abusive/normal pair of sentences. We got higher performances of the classifier by decreasing the effects of data shortage and class imbalance. We executed experiments and evaluations for three datasets and got higher F1-score of character-level CNN classifier when applying transfer learning in all datasets.