• Transactions of the Korean Society of Automotive Engineers
• /
• v.25 no.2
• /
• pp.219-226
• /
• 2017

This paper addresses the effective and quantitative image DB construction for the development of front looking camera systems. The automotive industry has expanded the capability of front camera solutions that will help ADAS(Advanced Driver Assistance System) applications targeting Euro NCAP function requirements. These safety functions include AEB(Autonomous Emergency Braking), TSR(Traffic Signal Recognition), LDW(Lane Departure Warning) and FCW(Forward Collision Warning). In order to guarantee real road safety performance, the driving image DB logged under various real road conditions should be used to train core object classifiers and verify the function performance of the camera system. However, the driving image DB would entail an invalid and time consuming task without proper guidelines. The standard working procedures and design factors required for each step to build an effective image DB for reliable automotive front looking camera systems are proposed.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.333-336
• /
• 1996

The sign language is a method of communication for deaf person. For sign communication, sign language and manual alphabet are used continuously. In this paper is proposed a system which recognize Korean sign language(KSL) and Korean manual alphabet(KMA) continuously. For recognizing KSL and KMA, basic elements for sign language, namely, the 14 hand directions, 23 hand postures, and 14 hand orientations are used. At first, this system recognize current motion state using speed and change of speed in motion by state automata. Using state, basic element classifiers using Fuzzy Min-Max Neural Network and Fuzzy Rule are executed. Meaning of signed gesture is selected by using basic elements which was recognized.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.10
• /
• pp.121-128
• /
• 2017

In this paper, we propose a multi-label classification method in which multi-label classification estimation techniques are applied to resolving location prediction problem. Most of previous studies related to location prediction have focused on the use of single-label classification by using contextual information such as user's movement paths, demographic information, etc. However, in this paper, we focused on the case where users are free to visit multiple locations, forcing decision-makers to use multi-labeled dataset. By using 2373 contextual dataset which was compiled from college students, we have obtained the best results with classifiers such as bagging, random subspace, and decision tree with the multi-label classification estimation methods like binary relevance(BR), binary pairwise classification (PW).

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.6
• /
• pp.1-7
• /
• 2018

A multi-label classification is to find multiple labels associated with the input pattern. Multi-label classification can be achieved by extending conventional single-label classification. Common extension techniques are known as Binary relevance, Label powerset, and Classifier chains. However, most of the extended multi-label naive bayes classifier has not been able to accurately estimate posterior probabilities because it does not reflect the label dependency. And the remaining extended multi-label naive bayes classifier has a problem that it is unstable to estimate posterior probability according to the label selection order. To estimate posterior probability well, we propose a new posterior probability estimation method that reflects the probability between all labels and labels efficiently. The proposed method reflects the correlation between labels. And we have confirmed through experiments that the extended multi-label naive bayes classifier using the proposed method has higher accuracy then the existing multi-label naive bayes classifiers.

• Proceedings of the SAREK Conference
• /
• 2008.06a
• /
• pp.36-41
• /
• 2008

Fault detection and diagnosis(FDD) system is beneficial in equipment management by providing the operator with tools which can help find out a failure of the system. An experimental study has been performed on fault detection and diagnosis method for a water chiller. Bayes classifier, which is one of classical pattern classifiers, is adopted in deciding whether fault occurred or not. FDD algorithm can detect refrigerant leak failure, when 20% amount of charged refrigerant for normal operation leaks from the water chiller. The refrigerant leak failure caused COP reduction by 6.7% compared with normal operation performance. When two kinds of faults, such as a decrease in the mass flow rate of cooling water and temperature sensor fault of cooling water inlet, are detected, COP is a little decreased by these faults.

• Annual Conference on Human and Language Technology
• /
• 2008.10a
• /
• pp.135-139
• /
• 2008

본 논문은 영한 기계번역에서 영어 수사가 포함된 영어 명사구를 한국어로 번역할 때, 영어 명사에 대응되는 한국어 명사의 적절한 분류사를 반자동으로 구축하는 방법에 대해 기술한다. 영한 번역의 측면에서, 분류사는 목표언어인 한국어에서만 나타나는 현상이다. 따라서 영어를 한국어로 번역할 때, 적절한 분류사를 생성하지 않으면 한국어 어법에 맞지 않는 부자연스러운 번역 결과를 생성한다. 본 논문에서는 한국어 태그드 코퍼스와 한국어 의미코드 체계에 따라 한국어 분류사를 반자동으로 구축하는 방법을 제안한다. 제안하는 방법에 따라 한국어 명사에 대해서 한국어 분류사가 구축되었으며, 이렇게 구축된 분류사는 영한 기계번역시스템의 번역 사전에 'KCOUNT'라는 자질을 할당하여 부가하였다. 제안하는 방법의 검증을 위해 수동평가와 자동평가를 수행하였으며, 그 결과, 영한 기계번역의 문장 생성에 있어서 자연스러움(fluency)의 측면에서 번역률 향상이 있었다.

• International Journal of Knowledge Content Development & Technology
• /
• v.7 no.1
• /
• pp.101-120
• /
• 2017

Healthcare professionals have edited many health questions (HQs) and their answers for healthcare consumers on the Internet. The HQs provide both readable and reliable health information, and hence retrieval of those HQs that are relevant to a given question is essential for health education and promotion through the Internet. However, retrieval of relevant HQs needs to be based on the recognition of the intention of each HQ, which is difficult to be done by predefining syntactic and semantic rules. We thus model the intention recognition problem as a text classification problem, and develop two techniques to improve a learning-based text classifier for the problem. The two techniques improve the classifier by location-based and area-based feature weightings, respectively. Experimental results show that, the two techniques can work together to significantly improve a Support Vector Machine classifier in both the recognition of HQ intentions and the retrieval of relevant HQs.

• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1489-1502
• /
• 2019

This work introduces a novel unweighted combination method (UCSS) for business failure perdition (BFP). With considering features of BFP in the age of big data, UCSS integrates the quantitative and qualitative analysis by utilizing soft set theory (SS). We adopt the conventional expert system (ES) as the basic qualitative classifier, the logistic regression model (LR) and the support vector machine (SVM) as basic quantitative classifiers. Unlike other traditional combination methods, we employ soft set theory to integrate the results of each basic classifier without weighting. In this way, UCSS inherits the advantages of ES, LR, SVM, and SS. To verify the performance of UCSS, it is applied to real datasets. We adopt ES, LR, SVM, combination models utilizing the equal weight approach (CMEW), neural network algorithm (CMNN), rough set and D-S evidence theory (CMRD), and the receiver operating characteristic curve (ROC) and SS (CFBSS) as benchmarks. The superior performance of UCSS has been verified by the empirical experiments.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.4
• /
• pp.240-248
• /
• 2014

We present a robust speaker identification algorithm that uses novel features based on soft bag-of-word representation and a simple Naive Bayes classifier. The bag-of-words (BoW) based histogram feature descriptor is typically constructed by summarizing and identifying representative prototypes from low-level spectral features extracted from training data. In this paper, we define a generalization of the standard BoW. In particular, we define three types of BoW that are based on crisp voting, fuzzy memberships, and possibilistic memberships. We analyze our mapping with three common classifiers: Naive Bayes classifier (NB); K-nearest neighbor classifier (KNN); and support vector machines (SVM). The proposed algorithms are evaluated using large datasets that simulate medical crises. We show that the proposed soft bag-of-words feature representation approach achieves a significant improvement when compared to the state-of-art methods.

• ETRI Journal
• /
• v.39 no.6
• /
• pp.851-858
• /
• 2017

Parkinson's disease is a growing and chronic movement disorder, and its diagnosis is difficult especially at the initial stages. In this paper, movement characteristics extracted by a computer using multilayer back propagation neural network mapping are converted to the symptoms of this disease. Then, modulation of three classifiers of C4.5, k-nearest neighbors, and support vector machine with majority voting are applied to support experts in diagnosing the disease. The purpose of this study is to choose appropriate characteristics and increase the accuracy of the diagnosis. Experiments were performed to demonstrate the improvement of Parkinson's disease diagnosis using this method.