• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.6
• /
• pp.261-268
• /
• 2015

In spoken chatting systems, users'spoken queries are converted to text queries using automatic speech recognition (ASR) engines. If the top-1 results of the ASR engines are incorrect, these errors are propagated to the spoken chatting systems. To improve the top-1 accuracies of ASR engines, we propose a post-processing model to rearrange the top-n outputs of ASR engines using a ranking support vector machine (RankSVM). On the other hand, a number of chatting sentences are needed to train chatting systems. If new chatting sentences are not frequently added to training data, responses of the chatting systems will be old-fashioned soon. To resolve this problem, we propose a data collection model to automatically select chatting sentences from TV and movie scenarios using a support vector machine (SVM). In the experiments, the post-processing model showed a higher precision of 4.4% and a higher recall rate of 6.4% compared to the baseline model (without post-processing). Then, the data collection model showed the high precision of 98.95% and the recall rate of 57.14%.

• Journal of Korea Multimedia Society
• /
• v.19 no.10
• /
• pp.1782-1791
• /
• 2016

Various color spaces such as RGB, HSV, log-chromaticity have been used in the field of person re-identification. However, not enough studies have been done to find suitable color space for the re-identification. This paper reviews color invariance of color spaces by diagonal model and explores the suitability of each color space in the application of person re-identification. It also proposes a method for person re-identification based on a histogram refinement technique and some fusion strategies of color spaces. Two public datasets (ALOI and ImageLab) were used for the suitability test on color space and the ImageLab dataset was used for evaluating the feasibility of the proposed method for person re-identification. Experimental results show that RGB and HSV are more suitable for the re-identification problem than other color spaces such as normalized RGB and log-chromaticity. The cumulative recognition rates up to the third rank under RGB and HSV were 79.3% and 83.6% respectively. Furthermore, the fusion strategy using max score showed performance improvement of 16% or more. These results show that the proposed method is more effective than some other methods that use single color space in person re-identification.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.987-999
• /
• 2017

Extraction of influential people from their respective domains has attained the attention of scholastic community during current epoch. This study introduces an innovative interaction strength metric for retrieval of the most influential users in the online social network. The interactive strength is measured by three factors, namely re-tweet strength, commencing intensity and mentioning density. In this article, we design a novel algorithm called IPRank that considers the communications from perspectives of followers and followees in order to mine and rank the most influential people based on proposed interaction strength metric. We conducted extensive experiments to evaluate the strength and rank of each user in the micro-blog network. The comparative analysis validates that IPRank discovered high ranked people in terms of interaction strength. While the prior algorithm placed some low influenced people at high rank. The proposed model uncovers influential people due to inclusion of a novel interaction strength metric that improves results significantly in contrast with prior algorithm.

• Communications for Statistical Applications and Methods
• /
• v.22 no.4
• /
• pp.313-320
• /
• 2015

In this research, we compare the efficiency of two test procedures proposed by Prentice and Gloeckler (1978) and Park and Hong (2009) for grouped data with possible right censored observations. Both test statistics were derived using the likelihood ratio principle, but under different semi-parametric models. We review the two statistics with asymptotic normality and consider obtaining empirical powers through a simulation study. The simulation study considers two types of models the location translation model and the scale model. We discuss some interesting features related to the grouped data and obtain null distribution functions with a re-sampling method. Finally we indicate topics for future research.

• Journal of Preventive Medicine and Public Health
• /
• v.38 no.2
• /
• pp.208-214
• /
• 2005

Objectives: This study was performed to examine the factors affecting re-smoking in male workers. Methods: A self-administrated questionnaire survey was conducted during April 2003 to examine the smoking state of 1,154 employees of a company that launched a smoking cessation campaign in1998. Five hundred and eighty seven persons, who had stopped smoking for at least one week, were selected as the final study subjects. This study collected data on smoking cessation success or failure for 6 months, and looked at the factors having an effect on re-smoking within this period. This study employed the Health Belief Model as its theoretical basis. Results: The re-smoking rate of the 587 study subjects who had stopped smoking for at least one week was 44.8% within the 6 month period. In a simple analysis, the re-smoking rates were higher in workers with a low age, on day and night shifts, blue collar, of a low rank, where this was their second attempt at smoking cessation and for those with a shorter job duration (p<0.05). Of the cues to action variables in the Heath Belief Model, re-smoking was significantly related with the perceived susceptibility factor, economic advantages of smoking cessation among the perceived benefits factor, the degree of cessation trial's barrier of the perceived barriers factor, smoking symptom experience, recognition of the degree of harmfulness of environmental tobacco smoke and the existence of chronic disease due to smoking (p<0.05). In the multiple logistic regression analysis for re-smoking, the significant variables were age, perceived susceptibility for disease, economic advantages due to smoking cessation, the perceived barrier for smoking cessation, recognition on the degree of harmfulness of environmental tobacco smoke, the existence of chronic disease due to smoking and the number of attempts at smoking cessation (p<0.05). Conclusion: From the result of this study, for an effective smoking ban policy within the work place, health education that improves the knowledge of the adverse health effects of smoking and the harmfulness of environmental tobacco smoke will be required, as well as counter plans to reduce the barriers for smoking cessation.

• Journal of Ocean Engineering and Technology
• /
• v.19 no.5 s.66
• /
• pp.50-57
• /
• 2005

This study has been conducted to investigate corrosivity of carbon steel, Cu, Zn and Al for one year from Sept. 2003 to Aug. 2004. A model of ISO 9223-ISO 9226 that represents the relation between metal corrosions and environmental parameters was used for atmospheric corrosion evaluations. Environmental parameters for these evaluations are time of wetness(TOW), $SO_2$ and Chloride. Corrosion rates for four metals which are exposed indoors and outdoors were measured on five locations in Jeju Island; Gosan, Seogwipo, Seongsan, Chuna hill and Jeju city. The environmental factor of atmospheric corrosion of Jeju Island for $SO_2$ class is P0, a clean area. TOW as T3 and T4 indicates that Jeju has the characteristics of a tropical area. Chlorides class within 3 km from the coast show the features of costal area as S2 and S3 classes. Chuna hill show the features of woodland as a S1 class. In Corrosion classes of each site which was measured outdoors is higher than indoors. Gosan is the highest class as the rank of C5, and indicated that they're ranked as C3 or C4.

• The Journal of Fisheries Business Administration
• /
• v.43 no.2
• /
• pp.79-94
• /
• 2012

The purpose of this study is to investigate the production efficiencies of the Korean aquaculture fishery with respect to species and methods using a Data Envelopment Analysis. The study extracted the 8 fishes in each of the sea cage culture, aquarium basin, and enclosed aquaculture for the analytical purposes. First, the study estimated the technical, pure technical, and scale efficiencies of the total of 24 aquaculture fishes based on the traditional DEA under the assumptions of both CRS and VRS. 2 fishes were identified as the efficient DMUs under the CCR-model, and 6 fishes under the BCC-model. Second, we tested to see if there was any difference in production efficiencies regarding those three different methods of aquaculture. we could not find any evidence of the differences in efficiency using a rank sum test based on the traditional DEA. However, we could do find that the pure technical efficiency in the sea cage culture was lower than others at 1% level of significance and the pure technical efficiency in enclosed aquaculture was also lower than others at 5% level of significance using Bilateral-DEA, which could explicitly consider the heterogeneity in the 3 production methods of aquaculture. Finally, the study obtained the 95% confidence intervals of the efficiency scores for the 24 fishes under our study using the smoothed bootstraping method in the process of the re-sampling in cooperation with both a kernel density estimation and a reflection method. At the same time, we could estimate the bias-corrected efficiency scores while the traditionally estimated efficiency scores suffered from the biases in the process of solving a linear programming with the deterministic nature of a production frontier. And hence, we could distinguish the differences in production efficiencies of the 8 fishes with respect to those 3 methods of aquaculture.

• Asian-Australasian Journal of Animal Sciences
• /
• v.32 no.3
• /
• pp.334-340
• /
• 2019

Objective: The objective of this study was to investigate the genetic components of daily milk yield and to re-rank bulls in South Korea by estimated breeding value (EBV) under heat stress using the temperature-humidity index (THI). Methods: This study was conducted using 125,312 monthly test-day records, collected from January 2000 to February 2017 for 19,889 Holstein cows from 647 farms in South Korea. Milk production data were collected from two agencies, the Dairy Cattle Genetic Improvement Center and the Korea Animal Improvement Association, and meteorological data were obtained from 41 regional weather stations using the Automated Surface Observing System (ASOS) installed throughout South Korea. A random regression model using the THI was applied to estimate genetic parameters of heat tolerance based on the test-day records. The model included herd-year-season, calving age, and days-in-milk as fixed effects, as well as heat tolerance as an additive genetic effect, permanent environmental effect, and direct additive and permanent environmental effect. Results: Below the THI threshold (${\leq}72$; no heat stress), the variance in heat tolerance was zero. However, the heat tolerance variance began to increase as THI exceeded the threshold. The covariance between the genetic additive effect and the heat tolerance effect was -0.33. Heritability estimates of milk yield ranged from 0.111 to 0.176 (average: 0.128). Heritability decreased slightly as THI increased, and began to increase at a THI of 79. The predicted bull EBV ranking varied with THI. Conclusion: We conclude that genetic evaluation using the THI function could be useful for selecting bulls for heat tolerance in South Korea.

• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.233-240
• /
• 2004

This paper presents a method to implicitly resolve ambiguities using dynamic incremental clustering in Korean-to-English and Japanese-to-English cross-language information retrieval (CLIR). The main objective of this paper shows that document clusters can effectively resolve the ambiguities tremendously increased in translated queries as well as take into account the context of all the terms in a document. In the framework we propose, a query in Korean/Japanese is first translated into English by looking up bilingual dictionaries, then documents are retrieved for the translated query terms based on the vector space retrieval model or the probabilistic retrieval model. For the top-ranked retrieved documents, query-oriented document clusters are incrementally created and the weight of each retrieved document is re-calculated by using the clusters. In the experiment based on TREC test collection, our method achieved 39.41% and 36.79% improvement for translated queries without ambiguity resolution in Korean-to-English CLIR, and 17.89% and 30.46% improvements in Japanese-to-English CLIR, on the vector space retrieval and on the probabilistic retrieval, respectively. Our method achieved 12.30% improvements for all translation queries, compared with blind feedback in Korean-to-English CLIR. These results indicate that cluster analysis help to resolve ambiguity.

• The KIPS Transactions:PartD
• /
• v.8D no.5
• /
• pp.483-494
• /
• 2001

Most of hypertext retrieval models consider documents as independent entities. They ignore relationships between documents of link semantics. in an information retrieval system for hypertext documents, retrieval effectiveness can be improved when ling information is used. Previous link-based hypertext retrieval models ignore link information while indexing. They utilize link information to re-rank the retrieval results. Therefore they are limited that only the documents is result-set utilize link information. This paper utilizes link information when indexing. We present how to use term weighting and inLinks weighting for ranking the relevant documents. Experimental results show that recall and precision evaluation according to the link semantics and the comparison with previously link_based hypertext retrieval model.