• 지능정보연구
• /
• 제17권1호
• /
• pp.53-69
• /
• 2011

로봇 자체 또는 로봇에 탑재된 콘텐츠와의 상호작용을 위해 일반적으로 영상 또는 음성 인식 기술이 사용된다. 그러나 영상 음성인식 기술은 아직까지 기술 및 환경 측면에서 해결해야 할 어려움이 존재하며, 실적용을 위해서는 사용자의 협조가 필요한 경우가 많다. 이로 인해 로봇과의 상호작용은 터치스크린 인터페이스를 중심으로 개발되고 있다. 향후 로봇 서비스의 확대 및 다양화를 위해서는 이들 영상 음성 중심의 기존 기술 외에 상호보완적으로 활용이 가능한 인터페이스 기술의 개발이 필요하다. 본 논문에서는 로봇 인터페이스 활용을 위한 가속도 센서 기반의 제스처 인식 기술의 개발에 대해 소개한다. 본 논문에서는 비교적 어려운 문제인 26개의 영문 알파벳 인식을 기준으로 성능을 평가하고 개발된 기술이 로봇에 적용된 사례를 제시하였다. 향후 가속도 센서가 포함된 다양한 장치들이 개발되고 이들이 로봇의 인터페이스로 사용될 때 현재 터치스크린 중심으로 된 로봇의 인터페이스 및 콘텐츠가 다양한 형태로 확장이 가능할 것으로 기대한다.

• 한국멀티미디어학회논문지
• /
• 제14권10호
• /
• pp.1252-1261
• /
• 2011

본 논문은 내용기반 동영상 분할을 위한 장면의 유사도 패턴 비교 방법을 제안한다. 동영상 장면 전환의 종류는 크게 급진적 전환과 디졸브(dissolve), 페이드인(fade-in), 페이드아웃(fade-out), 와이프 전환(wipe transition)을 포함하는 점진적 전환 형태로 나눌 수 있다. 제안하는 방법은 모든 종류의 장면 전환 검출 문제를 단지 발생 유무의 문제로 간단 정의하고, 장면 전환 종류는 별도로 구분하지 않는다. 장면 전환을 검출하기 위해서는 프레임간의 유사도를 정의해야 한다. 본 논문에서는 장면 내 유사도(within similarity)와 장면 간 유사도(between similarity)를 정의하며 두 유사도의 통계적 패턴 비교를 통하여 최종적으로 장면 전환을 검출하게 된다. 장면 내 유사도와 장면 간 유사도의 비율을 구하는 방법을 통해 플래시라이트나영상 내 물체 움직임에 대한 거짓 양성 검출을 별도의 후처리 과정 없이도 방지할 수 있음을 확인하였다. 프레임의 특징 값으로는 컬러 히스토그램과 프레임 내 평균 화소값을 이용하였다. TREC-2001, TREC-2002 동영상 셋을 포함한 실험 셋에서 성능을 평가한 결과 제안하는 알고리즘의 경우 총 91.84%의 재현율(recall)과 86.43%의 정확도(precision)의 성능을 보임을 확인할 수 있었다.

• ETRI Journal
• /
• 제30권3호
• /
• pp.421-431
• /
• 2008

In this paper, we offer a new technique to discover frequent spatiotemporal patterns from a moving object database. Though the search space for spatiotemporal knowledge is extremely challenging, imposing spatial and timing constraints on moving sequences makes the computation feasible. The proposed technique includes two algorithms, AllMOP and MaxMOP, to find all frequent patterns and maximal patterns, respectively. In addition, to support the service provider in sending information to a user in a push-driven manner, we propose a rule-based location prediction technique to predict the future location of the user. The idea is to employ the algorithm AllMOP to discover the frequent movement patterns in the user's historical movements, from which frequent movement rules are generated. These rules are then used to estimate the future location of the user. The performance is assessed with respect to precision and recall. The proposed techniques could be quite efficiently applied in a location-based service (LBS) system in which diverse types of data are integrated to support a variety of LBSs.

• 한국콘텐츠학회논문지
• /
• 제7권2호
• /
• pp.73-83
• /
• 2007

완전 일치 방법을 주로 사용하는 정보 검색 시스템에서 외래어 이형태를 검색할 수 있도록 위해서는 외래어 이형태를 자동 생성하는 전처리나 질의어 확장이 필요하다. 본 연구에서는 하나의 외래어가 입력되면, 이를 근거로 실제 사용될 만한 외래어 이형태들을 효과적으로 생성하기 위한 방법을 제안한다. 혼동 자소를 단순하게 치환하는 방법은 불필요한 이형태를 과도하게 생성하므로, 본 연구에서는 실제 문서에 사용된 외래어 이형태들로부터 혼동 패턴을 학습하고, 이를 확률로 계산하여 생성 순서를 조절하였다. 특히, 혼동 패턴에서 좌우문맥을 고려하고 지역 치환 확률과 전역 치환 확률을 계산하여 조기에 많이 사용하는 이형태를 생성하도록 하였다. KT SET 2.0에서 추출한 이형태 데이터에 대해 실험한 결과, 상위 20개의 생성으로도 평균 80% 이상 찾아내어 이 방법이 매우 효과적임을 보였다.

• 디지털융복합연구
• /
• 제12권12호
• /
• pp.365-370
• /
• 2014

기존의 시스템에서는 서열 전체 혹은 정렬되지 않은 서열로부터 패턴들을 생성하기 때문에 패턴의 수가 기하급수적으로 증가하여 많은 시간과 비용이 소모된다. 본 논문에서는 단백질의 전체 서열로부터 패턴을 찾아내는 것이 아니라, 다중 서열 정렬 기법을 이용하여 단백질의 분할 서열 구간을 생성하고 분할 서열 구간의 순차 패턴을 생성하며 생성된 패턴들을 통합하여 전체 모티프 후보 집합을 만들어 SVM의 훈련 집합으로 선택 및 학습하며, 최종적으로 미지의 혹은 알려진 단백질 서열의 HPV 타입을 SVM을 통해 학습된 정보를 적용하여 예측하는 시스템을 제안한다. 제안된 시스템은 기존의 시스템에 비해 최소 지지도 30%에서 정확도와 재현율 측면에서 보다 향상된 성능을 보였다.

• 한국식품영양과학회지
• /
• 제28권6호
• /
• pp.1380-1390
• /
• 1999

To assess the food intake and diet quality of preschool children in Pusan, dietary survey was conducted with 176 subjects using 24hr recall method. Diet quality was assessed by food group pattern, dietary diversity score(DDS), dietary variety score(DVS), and dietary frequency score(DFS). The total number of food items consumed was 307. The foods consumed most frequently were rice, Korean cabbage kimchi, milk and green onion. When investigating the consumption pattern of major six food groups, 38.1% of subjects consumed all six groups. Food group was missed in order of fruit(41.5%), sweet(19.9%), dairy(16.5), vegetable(4.5%) and meat(1.7%). The mean values of DDS, DVS, and DFS were 5.16, 13.82, and 16.07 re spectively. Persons who had higher DDSs also had higher DVSs(p<0.001). DDS, DVS and DFS correlated positively with NAR(nutrient adequacy ratio) and MAR(mean adequacy ratio) significantly. Associations between the NAR of most nutrients and MAR with DVS and DFS were higher than those between the NAR of most nutrients and MAR with DDS. People with DDS of above 6 or DVS of above 16 or DFS of above 21 met two thirds of recommended dietary allowance for nutrients. Based on the result of the food group intake, the food intake of subjects was not adequate, especially the fruit and dairy groups. When assessing the dietary quality of subjects using DDS, DVS and DFS, many people appeared not to have a desirable food intake.

• 한국조리학회지
• /
• 제13권2호
• /
• pp.81-97
• /
• 2007

To assess the food intake and diet quality by the interrelationship of DDS and DVS of high school girls, this dietary survey was conducted with 253 subjects living in Iksan and Seoul areas using a 24-hour recall method. The average amount of total food intake was 1,133.2 g, with 79.9% of food intake being supplied by vegetable food and 20.1% by animal food and higher in Seoul area. The food consumed most frequently was rice, green onion, garlic, soy sauce, sesame oil, onion, and Kimchi. The food consumed in the largest amounts were rice(303.3 g), milk(62.2 g), and Kimchi(53.4 g). Diet quality was assessed by food group pattern, dietary diversity score(DDS), and dietary variety score(DVS). When investigating the consumption pattern of major five food groups(grain, meat, dairy, fruit, vegetable groups), nobody consumed all five food groups in each meal. The groups most frequently missing were fruits and dairy products. The average number of food consumed per day was 12.1(DVS) and Iksan area scored lower(11.7) on DVS than Seoul area(12.6). The higher DDS and DVS of subjects were, the more MAR and NAR of energy, calcium, vitamin A and C increased. The number of major food groups(DDS)(p<0.01, P<0.05) and that of food items (DVS)(p<0.01) correlated positively NAR(nutrient adequacy ratio) and MAR (mean adequacy ratio) significantly.

• 제어로봇시스템학회논문지
• /
• 제20권6호
• /
• pp.612-618
• /
• 2014

A pattern classifier-based approach for recognizing internal states of human participants in interactions is presented along with its experimental results. The approach includes a step for collecting video recordings of human-human interactions or humanrobot interactions and subsequently analyzing the videos based on human coded annotations. The annotation includes social signals directly observed in the video recordings and the internal states of human participants indirectly inferred from those observed social signals. Then, a pattern classifier is trained using the annotation data, and tested. In our experiments on human-robot interaction, 7 video recordings were collected and annotated with 20 social signals and 7 internal states. Several experiments were performed to obtain an 84.83% recall rate for interaction engagement, 93% for concentration intention, and 81% for task comprehension level using a C4.5 based decision tree classifier.

• Journal of Biosystems Engineering
• /
• 제27권2호
• /
• pp.151-160
• /
• 2002

Cow image processing technique would be useful not only for recognizing an individual but also for establishing the image database and analyzing the shape of cows. A cow (Holstein) has usually the unique speckle pattern. In this study, the individual recognition of cow was carried out using the speckle pattern and the content-based image retrieval technique. Sixty cow images of 16 heads were captured under outdoor illumination, which were complicated images due to shadow, obstacles and walking posture of cow. Sixteen images were selected as the reference image for each cow and 44 query images were used for evaluating the efficiency of individual recognition by matching to each reference image. Run-lengths and positions of runs across speckle area were calculated from 40 horizontal line profiles for ROI (region of interest) in a cow body image after 3 passes of 5$\times$5 median filtering. A similarity measure for recognizing cow individuals was calculated using Euclidean distance of normalized G-frame histogram (GH). normalized speckle run-length (BRL), normalized x and y positions (BRX, BRY) of speckle runs. This study evaluated the efficiency of individual recognition of cow using Recall(Success rate) and AVRR(Average rank of relevant images). Success rate of individual recognition was 100% when GH, BRL, BRX and BRY were used as image query indices. It was concluded that the histogram as global property and the information of speckle runs as local properties were good image features for individual recognition and the developed system of individual recognition was reliable.

• Nutrition Research and Practice
• /
• 제15권4호
• /
• pp.528-540
• /
• 2021

BACKGROUND/OBJECTIVES: In a healthy person, from 35 years of age, there is an annual loss of muscle mass at the rate of 1-2% and is associated with a decline in the quality of life. This study aimed to identify the particular dietary patterns associated with the risk of lower lean muscle mass in Korean postmenopausal women. SUBJECTS/METHODS: The Korea National Health and Nutrition Examination Survey (KNHANES) is a population-based, continuous cross-sectional annual survey. The participants of the KNHANES IV (2008-2009) and V (2010-2011) were considered for this study. The study sample consisted of 1548 postmenopausal women, aged 45-86 years. Lower lean muscle mass was defined as having appendicular skeletal muscle mass corrected for body weight less than 1 standard deviation of the young reference group aged 20 to 39 years in KNHANES IV and V. To identify the dietary pattern using factor analysis, 24-h recall data was used. RESULTS: The prevalence of lower lean muscle mass was 31.3% in this study population. Four dietary patterns were identified by factor analysis; 'Diverse', 'Western', 'Traditional', and 'Snacks and beverages'. The 'Western' pattern, highest factor loadings for flour and bread, potatoes, red meat, processed meat, eggs, and cheese, was significantly associated with a high (60%) risk of lower lean muscle mass (odds ratio [95% confidence interval] = 1.60 [1.07-2.39], P for trend = 0.01) after adjustments for potential covariates. The other 3 dietary patterns were not associated with lower lean muscle mass. CONCLUSIONS: The study findings suggest that the 'Western' dietary pattern that includes flour and bread, potatoes, red meat, processed meat, eggs, and cheese, may be associated with a higher risk of lower lean muscle mass in Korean postmenopausal women.