• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06c
• /
• pp.131-134
• /
• 1998

본 논문에서는 전자 개인 비서 시스템(PEAS)의 일부인 일정관리 시스템을 화자인식 기술을 적용하여 구현하였다. 본 시스템은 음성을 패스워드로 개인을 확인하여 각 개인의 일정을 관리해 주는 것으로 보안성과 함께 사용자에게 편의성을 제공한다. 사용자 등록을 자유롭게 하였으며 인식에서는 계산 시간 등을 고려하여 DTW 알고리즘에서 얻을 수 있는 경로정보를 이용해 하나의 참조패턴을 구성하도록 하였다. 또한 시간 흐름에 따라 인식율 저하를 방지하기 위해 실험결과에 따라 일정기간 뒤에 자동으로 참조패턴이 갱신되도록 하였다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.1
• /
• pp.56-73
• /
• 2019

Probe-based systems have been gaining popularity in advanced traveler information systems. However, the high possibility of providing inaccurate travel-time information due to the inherent time-lag phenomenon is still an important issue to be resolved. To mitigate the time-lag problem, different prediction techniques have been applied, but the techniques are generally regarded as less effective for travel times with high variability. For this reason, current 5-min aggregated data have been commonly used for real-time travel-time provision on highways with high travel-time fluctuation. However, the 5-min aggregation interval itself can further increase the time-lags in the real-time travel-time information equivalent to 5 minutes. In this study, a new scheme that uses both individual probe and 5-min aggregated travel times is suggested to provide reliable real-time travel-time information. The scheme utilizes individual probe data under congested conditions and 5-min aggregated data under uncongested conditions, respectively. As a result of an evaluation with field data, the proposed scheme showed the best performance, with a maximum reduction in travel-time error of 18%.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06c
• /
• pp.107-110
• /
• 1998

본 논문은 DTW(Dynamic Time Warping)을 이용한 음성인식에서 표준패턴(reference patterns)으로 사용되는 벡터열을 GA(Genetic Algorithm)을 이용하여 보다 적응된 패턴의 벡터열로 생성하는 방법을 제시한다. 본 논문의 필요성은 다음과 같다. 음성인식의 주요한 엔진들 중에 하나로 DTW가 사용된다[1]. DTW는 표준패턴과 시험패턴(test patterns)간의 최적 경로(optimal path)를 찾아내어 가장 유사한 패턴을 찾아내는 방법을 말한다. 그러나 음성은 같은 발음에 대해서도 사람의 발성 길이와 목의 상태 등에 따라 다양한 패턴으로 나타나며 동일 화자의 같은 어휘도 시간과 환경에 따라 변한다. 따라서 이러한 음성의 동적 특성에 적응하는 방법이 필요하다. 본 논문은 이러한 문제에 대한 해결 방법으로 GA를 이용하여 보다 적합하고 적응적인 표준 패턴을 생성시켜 적응하는 방법을 개발하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.287-292
• /
• 2007

본 연구에서는 동적 수신호 패턴에 대한 효과적인 인식을 위하여, 특징추출 단계와 패턴 분류 단계의 두 모듈로 이루어지는 복합형 신경망 모델을 제안한다. 특징추출 모듈을 위하여 고유의 특징표현 기법과 3차원 수용영역 구조의 CNN 모델을 제안한다. 이는 3차원 형식의 데이터로 표현되는 수신호 패턴으로부터 특징점의 공간적 변이뿐만 아니라 시간적 변이에 강인한 특징추출 기능을 제공한다. 패턴 분류 모듈에서는 효율적인 학습과 인식 기능을 위하여 수정된 구조의 GFMM 모델을 제안한다. 또한 학습패턴의 빈도를 고려한 활성화 특성과 학습 방법을 정의함으로써 기존의 GFMM 모델이 갖는 단점인 학습결과가 학습순서에 종속되는 특성과 비정상적 패턴 및 노이즈 패턴에 민감한 현상을 개선한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04a
• /
• pp.639-641
• /
• 2000

캐쉬를 사용하는 분산 공유 메모리 시스템에서는 캐쉬들 사이의 일관성 유지를 위한 지연 시간이 성능에 큰 영향을 미친다. 최근에는 각 공유 메모리의 일반적인 접근 패턴을 학습하여 일관성 유지의 예측적 수행을 가능하게 하는 메모리 공유 패턴 예측기가 연구되고 있다. 기존의 메모리 공유 패턴 예측기는 패턴 정보를 저장하기 위해서 모든 메모리 블락마다 예측 테이블들을 할당하지만 실제로 성능 향상에 도움을 주는 테이블들은 소수에 불과하다. 본 논문에서는 적은 양의 패턴 저장 공간을 사용하면서 기존의 예측기와 유사한 성능을 낼 수 있는 캐쉬 구조의 메모리 공유 패턴 예측기를 제안한다, 제안된 예측기에서는 좋은 성능을 내는 예측 테이블들을 선택적으로 저장하게 하는 효율적인 테이블 교체 기법이 요구된다. 본 논문에서는 LRU 교체 기법을 캐쉬 구조의 예측기에 적용시켰을 때의 문제점을 분석하고 제안된 예측기의 특성에 적합한 테이블 교체 기법을 제안한다.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.42 no.11
• /
• pp.1753-1758
• /
• 2013

A debate over the association between dietary patterns and obesity is not settled in the literature. Some studies suggest that there are significant differences in the mean body mass index (BMI) across dietary patterns, while others refute the result. Therefore, we extended this line of study to examine whether the influence of dietary pattern is strong enough to affect the incidence of obesity based on the criterion, BMI=25. We identified 3 dietary patterns using a cluster analysis of food intake data obtained from the food frequency survey conducted as a part of Korean genome epidemiologic study: 'variety', 'unrefined grain', and 'rice' dietary patterns. A Cox Hazard regression result showed that the all the dietary pattern variable parameters were not significant. Hence, it was concluded that the dietary patterns do not affect the incidence of obesity under the control of variables, such as age, energy intake, and etc.

• Journal of Digital Convergence
• /
• v.15 no.6
• /
• pp.229-236
• /
• 2017

An efficient frequent pattern algorithm is essential for mining association rules as well as many other mining tasks for convergence with its application spread over a very broad spectrum. Models for mining pattern have been proposed using a FP-tree for storing compressed information about frequent patterns. In this paper, we propose a centroid frequent pattern growth algorithm which we called "CAWFP-Growth" that enhances he FP-Growth algorithm by making the center of weights and frequencies for the itemsets. Because the conventional constraint of maximum weighted support is not necessary to maintain the downward closure property, it is more likely to reduce the search time and the information loss of the frequent patterns. The experimental results show that the proposed algorithm achieves better performance than other algorithms without scarifying the accuracy and increasing the processing time via the centroid of the items. The MapReduce framework model is provided to handle large amounts of data via a pseudo-distributed computing environment. In addition, the modeling of the proposed algorithm is required in the fully distributed mode.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.8
• /
• pp.565-570
• /
• 2013

Previous researches on mining sequential patterns mainly focused on discovering patterns from the point-based event. Interval events with a time interval occur in the real world that have the start and end point. Existing interval pattern mining methods that discover relationships among interval events based on the Allen operators have some problems. These are that interval patterns having three or more interval events can be interpreted as several meanings. In this paper, we propose the I_TPrefixSpan algorithm, which is an efficient sequence pattern mining technique for removing ambiguity in the Interval Patterns Mining. The proposed algorithm generates event sequences that have no ambiguity. Therefore, the size of generated candidate set can be minimized by searching sequential pattern mining entries that exist only in the event sequence. The performance evaluation shows that the proposed method is more efficient than existing methods.

• Journal of Internet Computing and Services
• /
• v.10 no.5
• /
• pp.79-93
• /
• 2009

For developing the location based service which is individualized and specialized according to the characteristic of the users, the spatio-temporal pattern mining for extracting the meaningful and useful patterns among the various patterns of the mobile object on the spatio-temporal area is needed. Thus, in this paper, as the practical application toward the development of the location based service in which it is able to apply to the real life through the pattern mining from the huge historical data of mobile object, we are proposed STOMP(using Frequency of sequence and Weight) that is the new mining method for extracting the patterns with spatial and temporal constraint based on the problems of mining the optimal moving pattern which are defined in STOMP(F)[25]. Proposed method is the pattern mining method compositively using weighted value(weights) (a distance, the time, a cost, and etc) for our previous research(STOMP(F)[25]) that it uses only the pattern frequent occurrence. As to, it is the method determining the moving pattern in which the pattern frequent occurrence is above special threshold and the weight is most a little bit required among moving patterns of the object as the optimal path. And also, it can search the optimal path more accurate and faster than existing methods($A^*$, Dijkstra algorithm) or with only using pattern frequent occurrence due to less accesses to nodes by using the heuristic moving history.

• Journal of Nutrition and Health
• /
• v.48 no.3
• /
• pp.228-235
• /
• 2015

Purpose: Along with the adaptation of a Western dietary pattern and low physical activity, pediatric obesity is increasing in Korea, especially for boys. The aim of this study was to identify dietary behavior patterns and examine the snack consumption, dietary habit, and pediatric obesity by pattern groups. Methods: Boys aged 15~19 years were recruited from one high school in Seoul. A questionnaire including dietary behaviors and lifestyle factors was administered and height and weight were measured. A total of 932 boys participated except boys who had missing or incomplete response (n = 30). Three dietary behavior patterns were identified by cluster analysis; 'Healthy pattern', 'Mixed pattern' and 'Unhealthy pattern'. Results: Snack consumption differed according to dietary behavior patterns group. The healthy and mixed patterns showed higher frequencies of white milk and fruit consumption while the unhealthy pattern as well as the mixed patterns showed higher frequencies of sweetened snack and ice cream consumption. Food availability at home of each food differed according to pattern groups but showed a similar trend with food consumption. Regarding dietary habits, the mixed pattern showed higher proportion of taking dietary supplement and eating dessert while the unhealthy pattern showed lower proportion of eating regular meals and appropriate amount of meals. When the healthy pattern was set as a reference group, the odds ratio of pediatric obesity was 1.11 (CI 0.65-1.87) in the mixed pattern group and 1.88 (CI 1.14-3.10) in the unhealthy pattern group. Conclusion: In conclusion, dietary behaviors including snack consumption and lifestyle factors were connected. Unbalanced diet and undesirable dietary practice are important determinants in pediatric obesity.