• The Journal of the Acoustical Society of Korea
• /
• v.25 no.1E
• /
• pp.20-24
• /
• 2006

In this paper, we focused on the real time implementation of a speech recognition system with medium size of vocabulary considering its application to a mobile phone. First, we developed the PC based variable vocabulary word recognizer having the size of program memory and total acoustic models as small as possible. To reduce the memory size of acoustic models, linear discriminant analysis and phonetic tied mixture were applied in the feature selection process and training HMMs, respectively. In addition, state based Gaussian selection method with the real time cepstral normalization was used for reduction of computational load and robust recognition. Then, we verified the real-time operation of the implemented recognition system on the TMS320C6201 EVM board. The implemented recognition system uses memory size of about 610 kbytes including both program memory and data memory. The recognition rate was 95.86% for ETRI 445DB, and 96.4%, 97.92%, 87.04% for three kinds of name databases collected through the mobile phones.

• Proceedings of the IEEK Conference
• /
• 2001.06b
• /
• pp.365-368
• /
• 2001

This paper described a design and implementation of the division/square-root for a redundant floating point binary number using high-speed quotient selector. This division/square-root used the method of a redundant binary addition with 25MHz clock speed. The addition of two numbers can be performed in a constant time independent of the word length since carry propagation can be eliminated. We have developed a 16-bit VLSI circuit for division and square-root operations used extensively in each iterative step. It peformed the division and square-root by a redundant binary addition to the shifted binary number every 16 cycles. Also the circuit uses the nonrestoring method to obtain a quotient. The quotient selection logic used a leading three digits of partial remainders in order to be implemented in a simple circuit. As a result, the performance of the proposed scheme is further enhanced in the speed of operation process by applying new quotient selection addition logic which can be parallelly process the quotient decision field. It showed the speed-up of 13% faster than previously presented schemes used the same algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.10
• /
• pp.4204-4222
• /
• 2015

Cloud is the latest buzz word in the internet community among developers, consumers and security researchers. There have been many attacks on the cloud in the recent past where the services got interrupted and consumer privacy has been compromised. Denial of Service (DoS) attacks effect the service availability to the genuine user. Customers are paying to use the cloud, so enhancing the availability of services is a paramount task for the service provider. In the presence of DoS attacks, the availability is reduced drastically. Such attacks must be detected and prevented as early as possible and the power of computational approaches can be used to do so. In the literature, machine learning techniques have been used to detect the presence of attacks. In this paper, a novel approach is proposed, where intelligent rule based feature selection and classification are performed for DoS attack detection in the cloud. The performance of the proposed system has been evaluated on an experimental cloud set up with real time DoS tools. It was observed that the proposed system achieved an accuracy of 98.46% on the experimental data for 10,000 instances with 10 fold cross-validation. By using this methodology, the service providers will be able to provide a more secure cloud environment to the customers.

• Journal of Sport and Applied Science
• /
• v.6 no.2
• /
• pp.19-25
• /
• 2022

Purpose: This study attempts to investigate causal and intervening conditions for sport participation of Korean immigrants in the United States. Research design, data, and methodology: Grounded theory approach was used to develop a conceptual framework that presents the psychosocial processes that occur in immigrants' experience of sport participation. Participants were selected purposefully for information-rich cases. Korean immigrants with current experience of having periodically participated in sports were the criterion for sample selection. Based on selection criteria, 9 Korean immigrants took part in interview. The interview discussions were taped and transcribed verbatim into a Word file. The process for data analysis included four grounded theory approaches of purposive and theoretical sampling, an open and axial coding, memo writing, and finally the development of the conceptual framework. Results: Six concepts were revealed in the causal conditions that facilitate the process of immigrants' sport participation in the states: Personal experience, significant others, personality, physical environment, psychological well-being, and social connection. Three concepts were revealed as the intervening conditions that block the process of immigrants' sport participation in the states: Conflict with cultural change of organization, Pressure at workplace, and Economic constraints. Conclusions: Conceptual model presents causal and intervening factors. Further implications were discussed.

• Journal of Distribution Science
• /
• v.14 no.11
• /
• pp.117-128
• /
• 2016

Purpose - In order to collect information needed for the establishment of more effective marketing strategies of on-line purchasing agent services targeting Chinese consumers, the study investigated the relationship among Chinese selection criteria. They included fashion products, use of information source, and satisfaction with on-line purchasing agent services. The study also identified the differences in the Chinese selection criteria of fashion products, use of information source, and the satisfaction level with on-line purchasing agent services according to their age and gender. Research design, data, and methodology - The study was implemented through a normative-descriptive survey method using a self-administered questionnaire. Data were collected from February 9 to 28, 2016, and analyzed by factor analysis, ANOVA and Duncan test, t-test, and multiple regression analysis. Results - Differences were found in selection criteria of fashion products and use of information sources among groups. Thirty's age group was concerned about price/brand more than the twenty's were. Twenty's were concerned about practicality/quality of the products more than the thirty's. Hallyu/broadcasting was used by men more than by women as an information source of Korean fashion. SNS/WOM(word of mouth) was used more by women than by man. Twenty's showed lower level of satisfaction with customer services/credibility than other factors. The thirty's showed lower level of satisfaction with informational role of the service than other factors. Those who utilize each type of fashion information source more showed higher satisfaction level with on-line purchasing agent service of Korean fashion products.. In general, according to the selection criteria and use of information, there were differences in satisfaction with on-line purchasing agent service of Korean fashion products. Conclusions - Considering the findings of the study, as well as age, gender, selection criteria and use of information source, Chinese consumers could be used as a criteria of market segmentation for on-line purchasing agent services of Korean fashion products. The results manifested that there is a need to differentiate marketing strategies according to the satisfaction levels with each satisfaction factors of on-line purchasing agent service of Korean fashion products.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.6
• /
• pp.677-682
• /
• 2018

The relationship-type research and development (R&D) portfolio is a method for selecting core technologies based on their unique purposes and characteristics when the criteria for selecting them are independent. This study presents a relationship-type R&D portfolio method as a way to derive core technologies, and describes the methodology by dividing it into three steps: 1) analyze the relationships between selection criteria and analytical indicators, 2) form a portfolio matrix that best matches each selection criteria, and 3) derive the core technologies. In this study, the relationships between four selection criteria for selecting core technologies and the analytical indicators for identifying the technology level, economics, and the technology itself, are written in a table with HoQ. Based on the relationship table, analytical indicators to be considered were derived to satisfy each selection criterion, and the derived analytical indicators and the selected technologies were constructed with two axes in the portfolio matrix. The satisfied portfolio, P0, that satisfies all four criteria, and the portfolio, P1~P4, that satisfies selection criteria based on the unique characteristics of the four criteria, were constructed, and core technologies derived. The selected core technologies can be utilized in selecting a core area against the future security environment through a process like key word analysis based on the specifications.

• Journal of Distribution Science
• /
• v.9 no.3
• /
• pp.15-23
• /
• 2011

This study examined the effects educational service elements have on the satisfaction of educational service; it also analyzed how such satisfaction influenced educational institutions' registration renewal and word-of-mouth communications about the schools. The key factors of educational services included the following four components: physical environment, education programs, instructors, and tuition fee. An investigation into how the factors of educational services in private educational institutions may affect consumer satisfaction was an additional goal of this study. Based on the cause-and-effect analysis of the above constructs, the degree of influence that each of the attributes and the component factors have on consumers' educational service selection, as well as the consumers' satisfaction, were explored. An empirical analysis was conducted on students who were taking classes in cram schools; the analysis was also conducted on the students' parents. The results indicated that the hypotheses regarding the elements of educational service, educational program, and the instructor factor were supported. Furthermore, a hypothesis concerning the effects educational service satisfaction has on re-registration and word of mouth was supported, as well. Upon aggregating the above study results, it was concluded that when determining the effects of satisfaction on educational service, the educational program, and the instructor factor played a crucial role, while physical surroundings and tuition did not. When addressing the influence of the educational services factors on educational services satisfaction, education programs and instructors had a positive effect, whereas physical environment and tuition fee had no statistically significant impact. According to the influence of educational services satisfaction on registration renewal and word-of-mouth effects, educational services satisfaction was found to be a positive influential factor for both. In addition, it was found that satisfaction of educational service had a positive effect on renewing enrollment and forming word-of-mouth recommendations. Although the research seems simple, some theoretical implications can be drawn, as follows: First, one interpretation of the findings that the programs' and instructors' factors had a positive effect on educational services satisfaction but the physical environment and tuition fee factors did not have a significant effect suggests that the greatest influence factors in educational services are educational programs and instructors. Second, increased educational services satisfaction may result in consumer behavior changing, resulting in more registration renewals and more favorable word-of-mouth comments. Third, increased educational services satisfaction may result in enhancing consumer responses, resulting in more registration renewals and more favorable word-of-mouth opinions. Further research directions should include developing an integrated model that will allow for variation over time, before and after purchases, in relation to consumers' choices of educational services.

• Journal of The Korean Association of Information Education
• /
• v.20 no.4
• /
• pp.333-340
• /
• 2016

When elementary students write their own sentences, it is often educationally beneficial to compare them with other people's similar sentences. However, it is impractical for use in most classrooms, because it is burdensome for teachers to look up all of the sentences written by students. To cope with this problem, we propose a novel approach for automatic selection of similar sentences based on a three-step process: 1) extracting the subword units from the word-level sentences, 2) training the model with the encoder-decoder architecture, and 3) using the approximate k-nearest neighbor search algorithm to find the similar sentences. Experimental results show that the proposed approach achieves the accuracy of 75% for our test data.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.1
• /
• pp.48-53
• /
• 2003

Eigenvoice method is known to be adequate for fast speaker adaptation, but it hardly shows additional improvement with increased amount of adaptation data. In this paper, to deal with this problem, we propose a modified method estimating the weights of eigenvoices in each feature vector dimension. We also propose an adaptation mode selection scheme that one method with higher performance among several adaptation methods is selected according to the amount of adaptation data. We used POW DB to construct the speaker independent model and eigenvoices, and utterances(ranging from 1 to 50) from PBW 452 DB and the remaining 400 utterances were used for adaptation and evaluation, respectively. With the increased amount of adaptation data, proposed dimensional eigenvoice method showed higher performance than both conventional eigenvoice method and MLLR. Up to 26% of word error rate was reduced by the adaptation mode selection between eigenvoice and dimensional eigenvoice methods in comparison with conventional eigenvoice method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.141-148
• /
• 2013

Automated classification systems which utilize machine learning develops classification models through learning process, and then classify unknown data into predefined set of categories according to the model. The performance of machine learning-based classification systems relies greatly upon the quality of features composing classification models. For textual data, we can use their word terms and structure information in order to generate the set of features. Particularly, in order to extract feature from Web documents, we need to analyze tag and hyperlink information. Recent studies on Web document classification focus on feature engineering technology other than machine learning algorithms themselves. Thus this paper proposes a novel method of incorporating feature selection and weighting which can improves classification models effectively. Through extensive experiments using Web-KB document collections, the proposed method outperforms conventional ones.