• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1705-1708
• /
• 2002

Spreading codes with ZCD(zero-correlation duration) property have the MAI(multiple access interference) rejection ability in the CDMA systems. A class of multi-level spreading codes, i.e., Zero padded ternary ZCD codes are introduced in this paper. By the selected zero-padding method to the binary ZCD codes, ternary ZCD codes are generated and they have enhanced ZCD property and family size than the binary ZCD codes.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.985-988
• /
• 1993

An alternative approach to the design of application-driven fuzzy systems is proposed. A broad class of fuzzy systems applications requires a certain fuzzy partition of the input space while it demands for simple numerical quantities. For this class, a dedicated fuzzy system archictecture is presented and a design strategy is proposed. Both the single-input/single-output and multi-input/multi-output cases are considered. Numerical analysis are complete illustrating several aspects of the proposed framework.

• Korean Journal of Childcare and Education
• /
• v.10 no.6
• /
• pp.5-23
• /
• 2014

The purpose of this study was to investigate the teachers' multi-media application ability, their perception on the use of multi-media for story-telling, and actual use in class. The survey, using a questionnaire, was conducted targeting 225 teachers in Seoul, Gyeonggi and Incheon. The results of the study are as follows: Firstly, teachers who were younger, had a higher level of education, were experienced in taking multi-media courses, and took charge of larger classes showed better ability of multi-media application. And teachers who were trained on multi media as well as kindergarten teachers indicated a more positive perception about applying multi-media for story-telling. In addition, teachers who had higher levels of education, were experienced in taking multi-media courses, and teaching larger classes at national/public institutions applied multi-media more frequently. Secondly, the teachers' ability of applying multi-media, their perception on the use of multi-media for story-telling, and their multi-media use in class indicated strong positive correlations. Thirdly, a teacher's perception on the significance of the multi-media application for story-telling, their skills for multi-media use, the size of classes, and the training experiences on multi-media affected their actual application of multi-media for story-telling.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.45-59
• /
• 2023

Weakly supervised object localization (WSOL) is a task of localizing an object in an image using only image-level labels. Previous studies have followed the conventional class activation mapping (CAM) pipeline. However, we reveal the current CAM approach suffers from problems which cause original CAM could not capture the complete defects features. This work utilizes a convolutional neural network (CNN) pretrained on image-level labels to generate class activation maps in a multi-scale manner to highlight discriminative regions. Additionally, a vision transformer (ViT) pretrained was treated to produce multi-head attention maps as an auxiliary detector. By integrating the CNN-based CAMs and attention maps, our approach localizes defective regions without requiring bounding box or pixel-level supervision during training. We evaluate our approach on a dataset of apple images with only image-level labels of defect categories. Experiments demonstrate our proposed method aligns with several Object Detection models performance, hold a promise for improving localization.

• The Journal of the Korean dental association
• /
• v.13 no.10
• /
• pp.929-933
• /
• 1975

A girl aged 15 years 6 months, had a class Ⅲ malocclusion characterized by severe maxillary anterior crowding and a retarded maxilla. Molar relationship was class Ⅲ on both sides, incisor overjet was - 2.9mm. and incisor overbite was 5.5mm. The patient underwent extraction of four first premolars and was trested with a multi-banded light force system. After 13 months, the patient gained a normal verbite-overjet relationship of anterior teeth and a class 1 molar relationship. Superimposition of pretreatment and posttreatment cephalograms upon the line SN registered at S showed backward downward rotation of the mandible.

• Journal of Korean Society of Transportation
• /
• v.17 no.4
• /
• pp.85-97
• /
• 1999

The Purpose of this Paper is the development of the day-to-day dynamic combined model on the evaluation of traveller's traffic information for multi-mode and multi-class environments. Information is assumed to be provided for multi-mode such as bus and automobile. and multi-class such as a driver with and without route guidance equipment when they depart for their trips. The information provision strategies have been developed in the base of user equilibrium, system optimum and in between them. The Sioux Falls network is used for the evaluation of the model and information provision strategies. In the numerical analysis, a Braess' paradox for the information provision, which is the increase of travel time even though the number of information usage level and user are increased, has been occurred so that these kinds of information strategies should be implemented with special care.

• Kyungpook Mathematical Journal
• /
• v.9 no.1_2
• /
• pp.77-78
• /
• 1969

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.8
• /
• pp.958-964
• /
• 2016

In this paper, we propose an i-vector based language recognition system to identify the spoken language of the speaker, which uses multiple discriminative deep neural network (DNN) models analogous to the multi-class support vector machine (SVM) classification system. The proposed model was trained and tested using the i-vectors included in the NIST 2015 i-vector Machine Learning Challenge database, and shown to outperform the conventional language recognition methods such as cosine distance, SVM and softmax NN classifier in open-set experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.1
• /
• pp.16-22
• /
• 2010

Electrocardiogram(ECG) analysis and arrhythmia recognition are critical for diagnosis and treatment of ill patients. Cardiac arrhythmia is a condition in which heart beat may be irregular and presents a serious threat to the patient recovering from ventricular tachycardia (VT) and ventricular fibrillation (VF). Other arrhythmias like atrial premature contraction (APC), Premature ventricular contraction (PVC) and superventricular tachycardia (SVT) are important in diagnosing the heart diseases. This paper presented new method to classify various arrhythmias contrary to other techniques which are limited to only two or three arrhythmias. ECG is decomposed into Intrinsic Mode Functions (IMFs) by Empirical Mode Decomposition (EMD). Burg algorithm was performed on IMFs to obtain AR coefficients which can reduce the dimension of feature vector and utilized as Multi-class SVM inputs which is basically extended from binary SVM. We chose optimal parameters for SVM classifier, applied to arrhythmias classification and achieved the accuracies of detecting NSR, APC, PVC, SVT, VT and VP were 96.8% to 99.5%. The results showed that EMD was useful for the preprocessing and feature extraction and multi-class SVM for classification of cardiac arrhythmias, with high usefulness.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.4
• /
• pp.845-854
• /
• 2016

Sentiment analysis or opinion mining is a technique of text mining employed to identify subjective information or opinions of an individual from documents in blogs, reviews, articles, or social networks. In the literature, only a problem of binary classification of ratings based on review texts in an online review. However, because there can be positive or negative reviews as well as neutral reviews, a multi-class classification will be more appropriate than the binary classification. To this end, we consider the multi-class classification of ratings based on review texts. In the preprocessing stage, we extract words related with ratings using chi-square statistic. Then the extracted words are used as input variables to multi-class classifiers such as support vector machines and proportional odds model to compare their predictive performances.