• 말소리와 음성과학
• /
• 제2권1호
• /
• pp.77-85
• /
• 2010

This paper proposes an efficient feature vector processing technique to guard the Speech Emotion Recognition (SER) system against a variety of noises. In the proposed approach, emotional feature vectors are extracted from speech processed by comb filtering. Then, these extracts are used in a robust model construction based on feature vector classification. We modify conventional comb filtering by using speech presence probability to minimize drawbacks due to incorrect pitch estimation under background noise conditions. The modified comb filtering can correctly enhance the harmonics, which is an important factor used in SER. Feature vector classification technique categorizes feature vectors into either discriminative vectors or non-discriminative vectors based on a log-likelihood criterion. This method can successfully select the discriminative vectors while preserving correct emotional characteristics. Thus, robust emotion models can be constructed by only using such discriminative vectors. On SER experiment using an emotional speech corpus contaminated by various noises, our approach exhibited superior performance to the baseline system.

• 한국컴퓨터정보학회논문지
• /
• 제22권12호
• /
• pp.55-61
• /
• 2017

In this paper, we propose a novel tracking method using target separation and detection that are based on discriminative correlation filter (DCF), which is studied a lot recently. 'Retainability' is one of the most important factor of tracking. There are some factors making retainability of tracking worse. Especially, fast movement and occlusion of a target frequently occur in image data, and when it happens, it would make target lost. As a result, the tracking cannot be retained. For maintaining a robust tracking, in this paper, separation of a target is used so that normal tracking is maintained even though some part of a target is occluded. The detection algorithm is executed and find new location of the target when the target gets out of tracking range due to occlusion of whole part of a target or fast movement speed of a target. A variety of experiments with various image data sets are conducted. The algorithm proposed in this paper showed better performance than other conventional algorithms when fast movement and occlusion of a target occur.

• 한국작물학회지
• /
• 제45권5호
• /
• pp.316-321
• /
• 2000

Blast severity data of 39 rice varieties at 11 sites in Korea from 1997 to 1999 were analyzed using AMMI model and pattern analysis. Genotype x Environment (G$\times$E) interaction sum of squares (SS) accounted for 12 % of the total SS. Eight genotype groups and seven location groups were identified based on blast reaction pattern. The data obtained from over 21 sites with 44 test varieties from 1981 to 1996 were also considered. These were compared with the 1997-1999 data using the G$\times$E analysis results. Majority of the variability in the Korean Rice Blast Nursery (KRBN) were attributable to variations due to genotypes. Variations of G$\times$E interaction were maintained though test sites were reduced from 21 to 11 sites. Broadly compatible biological discriminative varieties identified were Nagdongbyeo and Akibare while broadly incompatible biological discriminative varieties identified were Hangangchalbyeo and Seogwangbyeo. Key sites for future evaluation work could be selected from location groups. Each location group should be represented by the site with the strongest interaction pattern. Blast responses in Cheolwon, Gyehwa, Suwon, Iksan, and Icheon showed different patterns from other locations.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권3호
• /
• pp.209-215
• /
• 2014

Sequence tagging is the task of predicting frame-wise labels for a given input sequence and has important applications to diverse domains. Conventional methods such as maximum likelihood (ML) learning matches global features in empirical and model distributions, rather than local features, which directly translates into frame-wise prediction errors. Recent probabilistic sequence models such as conditional random fields (CRFs) have achieved great success in a variety of situations. In this paper, we introduce a novel discriminative CRF learning algorithm to minimize local feature mismatches. Unlike overall data fitting originating from global feature matching in ML learning, our approach reduces the total error over all frames in a sequence. We also provide an efficient gradient-based learning method via gradient forward-backward recursion, which requires the same computational complexity as ML learning. For several real-world sequence tagging problems, we empirically demonstrate that the proposed learning algorithm achieves significantly more accurate prediction performance than standard estimators.

• 한국컴퓨터정보학회논문지
• /
• 제21권9호
• /
• pp.11-18
• /
• 2016

In this paper, we propose a gas classification method using combined features for an electronic nose system that performs well even when some loss occurs in measuring data samples. We first divide the entire measurement for a data sample into three local sections, which are the stabilization, exposure, and purge; local features are then extracted from each section. Based on the discrimination analysis, measurements of the discriminative information amounts are taken. Subsequently, the local features that have a large amount of discriminative information are chosen to compose the combined features together with the global features that extracted from the entire measurement section of the data sample. The experimental results show that the combined features by the proposed method gives better classification performance for a variety of volatile organic compound data than the other feature types, especially when there is data loss.

• 한국실내디자인학회:학술대회논문집
• /
• 한국실내디자인학회 2003년도 춘계학술발표대회 논문집
• /
• pp.74-77
• /
• 2003

After the Enforcement of Price Deregulation of Apartment, Apartment house get down to originality goods, The Housing Market have reorganized the nucleus by a user, have demanding the development for discriminative unit plan. The purpose of this study is that before and after the Price Decontrol of Apartment take part a variety of unit plan, search for transformation factor and analyze into the tendency of the distinction plan of Housing Goods. Before and after the Price Decontrol of Apartment, Apartment unit have analyzed from 85 $m^2$ till 152 $m^2$ private area; ten corporations of civil construction' unit in Seoul and The national capital region supply apartment, will supply apartment. For selected examples, first, unit plan is normalized from the ratio of front to side wall, bay, a Room' organization and a kind of Room, number, and for examples of unit plan of apartment, the examples were analyzed with respect to change of a Room' organization and the number of a room and the ratio of front wall to side wall for item investigated. Finally, I search out course of transformation tendency of an apartment unit plan after Enforcement of Price Deregulation and analyzed a factor. The results of the study are follows, after Enforcement of Price Deregulation, unit plan of apartment lead to change lay out, to secure each family's privacy, to secure feeling for open hearted, tendency of flexibility.

• 유통과학연구
• /
• 제15권1호
• /
• pp.31-42
• /
• 2017

Purpose - The multicultural society is a society where a variety of ethnic groups and cultures co-exist. Regarding Korean multicultural society, the public interest in the multicultural society and its problems are on a growing trend due to the increasing number of the multicultural families by international marriage and the foreign immigrant workers. Research design, data, and methodology - Models of the multicultural society policies have been divided into those of assimilation and multiculturalism, while they have been materialized into the models of discriminative exclusivism, assimilation and multiculturalism. Most countries are aiming at the model of either the multiculturalism or the assimilation focused on national managerial situations. Results - In the case of Europe where the multicultural society had been formed earlier than Korea, Islamic immigrants have been politically accepted in order for Europe to overcome the problem of population decrease caused by its low birth-rate. Also, in the case of the United States. Conclusions - Korean multicultural society policies are characterized mostly by supporting the multicultural families of international marriage. In this study, it is intended to present the characteristics of diversified immigrants and the possible directions of the polices on immigrant youth in accordance with each country's managerial policy.

• 대한안전경영과학회지
• /
• 제19권3호
• /
• pp.137-150
• /
• 2017

Logistic enterprises want to be competitive enterprises in fierce logistic market and worry about the securement of discriminative competitiveness for it. The standards for the judgement of logistic industry's maintenance of competitiveness are not only economic feasibility of logistic costs but also the satisfaction of users because well-established service system for variety and enhancement of logistic needs. Some of the quality attributes sufficiently satisfy expectation of customers, but not guarantee high-quality satisfaction. Therefore, it's difficult to grasp quality attributes with the existing approach of perceived service quality. Quality attribute model suggested by Kano is widely used as the concept is accurate, there is high possibility to be used at the stage of product/service planning, and it can be easily applied. Kano model has a limitation that quality attributes are classified with mode and the differences between strong property of the quality attribute and week property in quality attributes were ignored. Therefore, Timko calculated customer satisfaction coefficient with the result of Kano's survey and effects of customer satisfaction and unsatisfaction through relations between satisfaction coefficient and unsatisfaction coefficient. The purposes of this study are to use ASC, the average of satisfaction coefficient and unsatisfaction, as the satisfaction of quality characteristics, decide the importance of quality characteristics with TOPSIS, a representative multi-standard decision-making method, and calculate strategy improvement propriety of logistic service quality.

• 전자통신동향분석
• /
• 제33권5호
• /
• pp.103-110
• /
• 2018

Studies on artificial intelligence have been developed for the past couple of decades. After a few periods of prosperity and recession, a new machine learning method, so-called Deep Learning, has been introduced. This is the result of high-quality big- data, an increase in computing power, and the development of new algorithms. The main targets for deep learning are 1D audio and 2D images. The application domain is being extended from a discriminative model, such as classification/segmentation, to a generative model. Currently, deep learning is used for processing 3D data. However, unlike 2D, it is not easy to acquire 3D learning data. Although low-cost 3D data acquisition sensors have become more popular owing to advances in 3D vision technology, the generation/acquisition of 3D data remains a very difficult problem. Moreover, it is not easy to directly apply an existing network model, such as a convolution network, owing to the variety of 3D data representations. In this paper, we summarize the 3D deep learning technology that have started to be developed within the last 2 years.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2129-2147
• /
• 2019

This paper introduces an adaptive face recognition method based on a Novel Incremental Kernel Nonparametric Discriminant Analysis (IKNDA) that is able to learn through time. More precisely, the IKNDA has the advantage of incrementally reducing data dimension, in a discriminative manner, as new samples are added asynchronously. Thus, it handles dynamic and large data in a better way. In order to perform face recognition effectively, we combine the Gabor features and the ordinal measures to extract the facial features that are coded across local parts, as visual primitives. The variegated ordinal measures are extraught from Gabor filtering responses. Then, the histogram of these primitives, across a variety of facial zones, is intermingled to procure a feature vector. This latter's dimension is slimmed down using PCA. Finally, the latter is treated as a facial vector input for the advanced IKNDA. A comparative evaluation of the IKNDA is performed for face recognition, besides, for other classification endeavors, in a decontextualized evaluation schemes. In such a scheme, we compare the IKNDA model to some relevant state-of-the-art incremental and batch discriminant models. Experimental results show that the IKNDA outperforms these discriminant models and is better tool to improve face recognition performance.