• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1290-1295
• /
• 2017

Document classification, a task of classifying the category of each document based on text, is one of the fundamental areas for natural language processing. Document classification may be used in various fields such as topic classification and sentiment classification. Neural network models for document classification can be divided into two categories: word-level models and character-level models that treat words and characters as basic units respectively. In this study, we propose a neural network model that combines character-level and word-level models to improve performance of document classification. The proposed model extracts the feature vector of each word by combining information obtained from a word embedding matrix and information encoded by a character-level neural network. Based on feature vectors of words, the model classifies documents with a hierarchical structure wherein recurrent neural networks with attention mechanisms are used for both the word and the sentence levels. Experiments on real life datasets demonstrate effectiveness of our proposed model.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.3
• /
• pp.1-7
• /
• 2007

In order to recognize a vehicle license plate, the region of the license plate should be extracted from a vehicle image. Then, character region should be separated from the background image and characters are recognized using some neural networks with selected feature vectors. Of course, choice of feature vectors which serve as the basis of the character recognition has an important effect on recognition result as well as reduction of data amount. In this paper, we propose a novel feature extraction method in which number images are decomposed into linear combination of eigennumbers and show the validity of this method by applying to the recognition of numeric characters in license plates. The experimental results show the recognition rate of 95.3% for about 500 vehicle images with multi-layer perceptron neural network in the eigennumber space. Compared with the conventional mesh feature, it shows a better recognition rate by 5%.

• Journal of KIISE:Software and Applications
• /
• v.33 no.10
• /
• pp.836-850
• /
• 2006

Nowadays, due to the rapidly increasing number of package software products, quality test has been emphasized for package software products. When testing software products, one of the most important factors is to select metrics which form the bases for tests. In this paper, the types of package software are represented as characteristic vectors having probabilistic relationships with metrics. The characteristic vectors could be regarded as indicators of software type. To assign the metrics for each software type, the past test metrics are collected and analyzed. Using Bayesian belief network, the dependency relationship network of the characteristic vectors and metrics is constructed. The dependency relationship network is then used to find the proper metrics for the test of new package software products.

• The Journal of the Korea Contents Association
• /
• v.6 no.9
• /
• pp.50-59
• /
• 2006

This paper proposes an automatic video monitoring system and its application to emergency detection by analyzing human behavior using neural network. The object area is identified by subtracting the statistically constructed background image from the input image. The identified object area then is transformed to the feature vector. Neural network has been adapted for analyzing the human behavior using the feature vector, and is designed to classify the behavior in rather simple numerical calculation. The system proposed in this paper is able to classify the three human behavior: stand, faint, and squat. Experiment results shows that the proposed algorithm is very efficient and useful in detecting the emergency situation.

• The KIPS Transactions:PartB
• /
• v.11B no.6
• /
• pp.735-742
• /
• 2004

We present a new use of common graphics hardware to perform a faster artificial neural network. And we examine the use of GPU enhances the time performance of the image processing system using neural network, In the case of parallel computation of multiple input sets, the vector-matrix products become matrix-matrix multiplications. As a result, we can fully utilize the parallelism of GPU. Sigmoid operation and bias term addition are also implemented using pixel shader on GPU. Our preliminary result shows a performance enhancement of about thirty times faster using ATI RADEON 9800 XT board.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2006.11a
• /
• pp.289-292
• /
• 2006

In this paper, the hybrid algorithm of Support Vector Machine md Artificial Neural Network is used for the defect diagnostics algorithm for the aircraft turbo-shaft engine. The results of learning of ANN, especially, accuracy or speed of convergence are sensitive to the number of data, so a comparison between design point and off-design area, especially, Mach number and fuel flow variable area, is essential research. From application results for diagnostics of gas turbine engine, it was confirmed that the hybrid algorithm could detect well in the of-design area as well as design point.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.11
• /
• pp.2133-2146
• /
• 1994

In this paper, we present a method for dynamic Jaso segmentation and Hangeul recognition using neural network. It uses the feature vector which is extracted from the mesh depending on the segmentation result. At first, each character is converted to 256 dimension feature vector by four direction contributivity and $8\times8$ mesh. And then, the character is classified into 6 class by neural network and is segmented into Jaso using the classification result the statistic vowel location information and the structural information. After Jaso segmentation, Hanguel recognition using neural network is performed. We experiment on four font of which three fonts are used for training the neural net and the rest is used of testing. Each font has the 2350 characters which are comprised in KS C 5601. The overall recognition rates for the training data and the testing data are 97,4% and 94&% respectively. This result shows the effectivness of proposed method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.3
• /
• pp.513-520
• /
• 2020

Recently, the development of a vision inspection system using machine learning has become more active. This study seeks to develop a defect inspection model using machine learning. Defect detection problems for images correspond to classification problems, which are the method of supervised learning in machine learning. In this study, defect detection models are developed based on algorithms that automatically extract features and algorithms that do not extract features. One-dimensional CNN and two-dimensional CNN are used as algorithms for automatic extraction of features, and MLP and SVM are used as algorithms for non-extracting features. A defect detection model is developed based on four models and their accuracy and AUC compare based on AUC. Although image classification is common in the development of models using CNN, high accuracy and AUC is achieved when developing SVM models by converting pixels from images into RGB values in this study.

• Journal of the Korea Society for Simulation
• /
• v.20 no.4
• /
• pp.115-125
• /
• 2011

Manufacturing companies usually manage the process to achieve high quality using various types of control chart in statistical process control. When an assignable cause occurs in a process, the data in the control chart changes with different patterns by the specific causes. It is important in process control to classify the CCP (Control Chart Pattern) recognition for fast decision making. In former research, gathered data from process used to apply as raw data, leads to degrade the performance of recognizer and to decrease the learning speed. Therefore, feature based recognizer, employing feature extraction method, has been studied to enhance the classification accuracy and to reduce the dimension of data. We propose the method to extract features that take the distances between CCP data and reference vector generated from BDK (Bi-Directional Kohonen Network). We utilize those features as the input vectors in ANN (Artificial Neural Network) and compare with raw data applied ANN to evaluate the performance.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.9
• /
• pp.4455-4461
• /
• 2013

This paper investigates the diagnosis performance of Artificial Neural Network (ANN) depending on the structure and the input vector type of ANN, which has been used to detect the partial discharge to lead to the electric machinery deterioration. The diagnosis performance of one hidden layer and two hidden layer in ANN are compared. The performance using the 2048 time-series data and the performance using the feature input vector are compared. For measuring the partial discharge signal, the tip-to-plate, the sphere-to-sphere, the tip-to-tip, the tip-to-sphere and the sphere-to-plate electrodes are used respectively. For ANN's learning, Matlab and C-code program are used. For evaluating the diagnosis performance of ANNs, the simulation studies are performed.