• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.3
• /
• pp.274-279
• /
• 2015

The main goal of this research is to build a sentiment analysis system which automatically determines user opinions of the Stanford Sentiment Treebank in terms of three sentiments such as positive, negative, and neutral. Firstly, sentiment sentences are POS tagged and parsed to dependency structures. All nodes of the Treebank and their polarities are automatically extracted from the Treebank. We train two Support Vector Machines models. One is for a node level classification and the other is for a sentence level. We have tried various type of features such as word lexicons, POS tags, Sentiment lexicons, head-modifier relations, and sibling relations. Though we acquired 74.2% in accuracy on the test set for 3 class node level classification and 67.0% for 3 class sentence level classification, our experimental results for 2 class classification are comparable to those of the state of art system using the same corpus.

• Journal of Chest Surgery
• /
• v.11 no.4
• /
• pp.535-540
• /
• 1978

Between January 1974 and November 1978, 23 cases of double valve replacement were done in the Department of Thoracic Surgery, Seoul National university Hospital. All had symptoms of rheumatic valvular heart disease and belonged to functional class III or IV according to NYHA classification. Among 23 cases, mitral and aortic valves were replaced in 14, and mitral and tricuspid valves in 9 cases. Six operative deaths [26%] and 4 late deaths [23%] were found. In the former group 5 and in latter one operative death were noted. Main cause of operative death was low cardiac output syndrome due to myocardial failure. Among 4 late deaths, 2 were caused by thromboembolism, one by bacterial endocarditis, and one by arrhythmia.

• Journal of the Korean Home Economics Association
• /
• v.29 no.2
• /
• pp.135-154
• /
• 1991

The purposes of this study are: 1) To find out overall family life issues percieved by the middle-classhousewives in their forties. 2) To examine detailed aspects related to middle years crises, leisure activities, children issues, family economy issues, and housing issues. 3) To clarify solutions to, and provide basic data on family issues raised by the middle-class families. The middle-class housewives in their forties living in the Seoul area were the subject of the survey. The sample size analysed in this study was 422. Data were analysed by the frequency, mean, percentile, standard deviation, X2-test, analysis of variance, multiple classification analysis, analysis of multiple regression, and Scheffe-test as a post-hoc analysis. The conclusions are as follows: First, the middle-class housewives tend to give more importance on children issues, especially on academic achievement and career development. Second, family cohesion of middle-class families is comparatively high and intra-familial conflict is low, and middle years crisis of housewives is comparatively low, too. Third, the stability of middle-class families can be found in household economic management patterns. one fourth of the families own stocks and two fifths of the families own real estate except their own dwelling house. Be based on their property income add to their labor income, middle-class families are showed their economic stability, however, intra-class inequality is found, too. Fourth, the great part of middle-class families that possess their own house, tend to be unsatisfied with their housig scale, and a half of the families expect to enlarge their housing scale for more comfortable and convient living.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.60.2-61
• /
• 2017

A Convolutional Neural Network(CNN) is one of the well-known deep-learning methods in image processing and computer vision area. In this study, we apply CNN to two kinds of flare forecasting models: flare classification and occurrence. For this, we consider several pre-trained models (e.g., AlexNet, GoogLeNet, and ResNet) and customize them by changing several options such as the number of layers, activation function, and optimizer. Our inputs are the same number of SOHO)/MDI images for each flare class (None, C, M and X) at 00:00 UT from Jan 1996 to Dec 2010 (total 1600 images). Outputs are the results of daily flare forecasting for flare class and occurrence. We build, train, and test the models on TensorFlow, which is well-known machine learning software library developed by Google. Our major results from this study are as follows. First, most of the models have accuracies more than 0.7. Second, ResNet developed by Microsoft has the best accuracies : 0.77 for flare classification and 0.83 for flare occurrence. Third, the accuracies of these models vary greatly with changing parameters. We discuss several possibilities to improve the models.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2562-2570
• /
• 2014

One of the important hints for inferring the function of unknown proteins is the knowledge about protein subcellular localization. Recently, there are considerable researches on the prediction of subcellular localization of proteins which simultaneously exist at multiple subcellular localization. In this paper, label power-set classification is improved for the accurate prediction of multiple subcellular localization. The predicted multi-labels from the label power-set classifier are combined with their prediction probability to give the final result. To find the accurate probability estimates of multi-classes, this paper employs pair-wise comparison and error-correcting output codes frameworks. Prediction experiments on protein subcellular localization show significant performance improvement.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.563-568
• /
• 2016

The word sense disambiguation problem is to find the correct sense of an ambiguous word having multiple senses in a dictionary in a sentence. We regard this problem as a multi-class classification problem and classify the ambiguous word by using Support Vector Machines. Context words of the ambiguous word, which are extracted from Sejong sense tagged corpus, are represented to two kinds of vector space. One vector space is composed of context words vectors having binary weights. The other vector space has vectors where the context words are mapped by word embedding model. After experiments, we acquired accuracy of 87.0% with context word vectors and 86.0% with word embedding model.

• Journal of the Korean Society for Heat Treatment
• /
• v.36 no.2
• /
• pp.69-76
• /
• 2023

In this study, we present a system for identifying equivalent grades of standardized wire rod steel based on alloy composition using machine learning techniques. The system comprises two models, one based on a supervised multi-class classification algorithm and the other based on unsupervised autoencoder algorithm. Our evaluation showed that the supervised model exhibited superior performance in terms of prediction stability and reliability of prediction results. This system provides a useful tool for non-experts seeking similar grades of steel based on alloy composition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.3
• /
• pp.262-267
• /
• 2013

The recognition of human emotional state is one of the most important components for efficient human-human and human- computer interaction. In this paper, four emotions such as fear, disgust, joy, and neutral was a main problem of classifying emotion recognition and an approach of visual-stimuli for eliciting emotion based on physiological signals of skin conductance (SC), skin temperature (SKT), and blood volume pulse (BVP) was used to design the experiment. In order to reach the goal of solving this problem, half-against-half (HAH) multi-class support vector machine (SVM) with Gaussian radial basis function (RBF) kernel was proposed showing the effective techniques to improve the accuracy rate of emotion classification. The experimental results proved that the proposed was an efficient method for solving the emotion recognition problems with the accuracy rate of 90% of neutral, 86.67% of joy, 85% of disgust, and 80% of fear.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.375-386
• /
• 2022

The city of Khartoum, the capital of Sudan, was heavily damaged by the flood of the Nile in 2020. Classification using satellite images can define the damaged area and help emergency response. As Synthetic Aperture Radar (SAR) uses microwave that can penetrate cloud, it is suitable to use in the flood study. In this study, Random Forest classifier, one of the supervised classification algorithms, was applied to the flood event in Khartoum with various sizes of the training dataset and number of images using Sentinel-1 SAR. To create a training dataset, we used unsupervised classification and visual inspection. Firstly, Random Forest was performed by reducing the size of each class of the training dataset, but no notable difference was found. Next, we performed Random Forest with various number of images. Accuracy became better as the number of images in creased, but converged to a maximum value when the dataset covers the duration from flood to the completion of drainage.