• 품질경영학회지
• /
• 제45권4호
• /
• pp.709-716
• /
• 2017

Purpose: NCS(National Competency Standards) is a systematic organization of knowledge, skills, and literacy required for performing tasks in industrial settings. This research aims to search for keywords that are important to us and to present key directions of education for the fourth industrial age in the future. Methods: The systematic classification system of NCS was investigated and the classification code structure was analyzed. Among them, the frame and structure analysis of the classification code of quality was analyzed using R-program. Results: This study grasped the quality classification situation of NCS and suggested improvement plan from the operational aspect of the fourth industrial revolution era. Conclusion: In conclusion, this study suggested the idea of education direction of SMEs(Small and Medium-sized Enterprises) in the era of the 4th industrial revolution by understanding NCS which reflects Korean characteristics.

• 한국통신학회논문지
• /
• 제24권12B호
• /
• pp.2447-2454
• /
• 1999

본 논문은 기존 분류형 신경망의 인식성능을 향상시키기 위하여 프레임 정규화와 비선형 사후확률 추정법(N-APPEM)을 제안하고 한국어 숫자음에 대하여 예측형과 분류형 신경망으로 인식성능을 평가하였다. 실험결과 예측형 신경망에서 최고 98.0%의 인식률을 얻었다. 예측형 신경망은 네트워크가 입력패턴의 카테고리 수만큼 마련되는 복잡한 네트워크를 가지는 반면에 분류형 신경망은 단일 네트워크로 구성되며 프레임 정규화와 비선형 사후확률 추정법으로 85.5%까지 인식률을 향상시킬 수 있었으며 이는 기존의 방법보다 인식률이 12.0% 향상된 것이다.

• 대한인간공학회지
• /
• 제28권2호
• /
• pp.35-55
• /
• 2009

The purpose of this study was to analyze the somatotypes of women in the early 20's, which were likely to deform due to bad posture in growth period. Accordingly, bodies of women aged 20 to 24, whose growth stopped, were measured directly and indirectly, and factors related to body shapes were extracted, body shapes were categorized based on the data, and the characteristics of each body shape were analyzed. As a result, 10 factors related to body shapes were extracted in the factor analysis, and body shapes were categorized into 6 types. Type 1 was the volume of body that was big and the longest; and the general frame was large. The straight body shape with small back protrusion; the shoulder is relatively thick and the width of the shoulder was normal. Type 2 was the volume of body that was the biggest and the upper body was the longest; the general frame was of average height. The forward body shape with the back flat; the shoulder was very thick, wide, and serious leaning forward. Type 3 was a body that was thin and the shortest. The sway-back body shape with big curvature at the back; the shoulder was thin, narrow, and straight. Type 4 was a body that was short stature, and the general frame was of average build. The forward body shape with the most serious back protrusion; the shoulder was normally thick, narrow, and straight. Type 5 was a group with small body, and the lower body and general frame are long. The sway-back body shape with protrusion at the upper shoulder and the sides leaning backward; the shoulder was thin, wide, and leaning forward. Type 6 was a thin and short body; and the general frame was small. The lean-back body shape with the smallest back protrusion and leaning backward; the shoulder was thin, narrow, and leaning backward. Characteristics of the classified body shapes can be used in producing ready-made clothes, and it is hoped that there will be follow-up studies on clothing pattern design and production based on this result.

• 방송공학회논문지
• /
• 제22권6호
• /
• pp.734-743
• /
• 2017

본 논문에서는 동영상의 압축 정보를 이용하여 동영상 조작 시 발생하는 특징 패턴을 분석하여 동영상의 삭제 여부를 검출하는 기법에 대해 소개한다. 제안 방식에서는 최근 표준 코덱으로 개발되어 향후 널리 사용될 것으로 예상되는 HEVC 코덱을 이용한다. 우선 조작된 동영상과 그렇지 않은 동영상의 HEVC 부호화 패턴 중 분류하기가 용이한 여러 패턴들을 분석하여 특징벡터로 선정하고, 선정된 특징벡터를 기계학습을 통해 학습하여 두 그룹 간의 분류 기준을 모델링하여 동영상에 대한 삭제 여부를 판단한다. 실험 결과, 제안한 방식이 이전의 연구 결과에 비해 HEVC 코덱 환경에서 더욱 효과적으로 삭제 여부를 판단함을 확인하였다.

• 한국의류산업학회지
• /
• 제4권2호
• /
• pp.156-162
• /
• 2002

The purposes of this study were to classify somatotype was obtained from the factor scores of the upper half of body and analyze the somatometric characteristics. The sample group was drawn from boys at the ages 9 to 10 living in Pusan and Kyungsangnam-do. Data from each boy comprised 36 anthropometric measurements and 7 photographic measurements. The study reached following conclusions. 1. According to the analysis to draw somatometric factors, seven indicative factors were obtained from measurements of the upper half of body. The most significant factor "sectional size" and the second most significant factor "longitudinal size" characterized most aspects of body shape. 2. According to the analysis of somatometric characteristics by the upper half of body, they were categorized into four types; Boys in type 1 had high stature, broadest shoulders, average frame, flattest chest and quite protruded shoulder blades and belly; boys in type 2 had shortest stature, smallest frame, most sloping shoulders and flattest shoulder blades and belly; boys in type 3 had quite corpulent with average stature, rising shoulders, most protruded chest and shoulder blades and belly of protrusion close to the average; boys in type 4 had highest stature, biggest frame, broad shoulders and back, and most protruded shoulder blades and belly.

• 정보관리학회지
• /
• 제25권4호
• /
• pp.131-148
• /
• 2008

본 연구에서는 비디오의 의미를 잘 표현하고 있는 키프레임들을 추출하는 알고리즘을 설계하고 평가하였다. 구체적으로 영상 초록의 키프레임 선정을 위한 이론 체계를 수립하기 위해서 선행 연구와 이용자들의 키프레임 인식 패턴을 조사하여 분석해 보았다. 그런 다음 이러한 이론 체계를 기초로 하여 하이브리드 방식으로 비디오에서 키프레임을 추출하는 알고리즘을 설계한 후 실험을 통해서 그 효율성을 평가해 보았다. 끝으로 이러한 실험 결과를 디지털 도서관과 인터넷 환경의 비디오 검색과 브라우징에 활용할 수 있는 방안을 제안하였다.

• 한국통신학회논문지
• /
• 제27권3A호
• /
• pp.211-220
• /
• 2002

본 논문에서는 비교적 간단한 컴퓨터 셀 애니메이션 동영상을 대상으로 낮은 비트율에서 효율적인 압축 알고리듬을 제안한다. 제안하는 알고리듬은 인트라 프레임 부호화와 인터 프레임 부호화를 기본 구조로 한다. 인트라 프레임 부호화에서는 팔레트를 이용한 칼라 양자화, 색인 재배치, JPEG-LS의 ADPCM 및 매핑, 분류화 및 블록단위의 색인에 대한 엔트로피 부호화로 구성되고, 인터 프레임 부호화에서는 움직임의 특성을 분류하여 블록 단위의 움직임 리플레니쉬먼트 기법을 이용해서 부호화한다. 제안하는 알고리듬은 기존의 방식인 Flash, FLC, Motion-JPEG, MPEG-1 및 MPEG-4 등과 낮은 비트율에서 부호화 성능을 비교해 볼 때 우수한 성능을 나타내었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권3호
• /
• pp.1689-1701
• /
• 2019

In recent years, personal videos have been shared online due to the popular uses of portable devices, such as smartphones and action cameras. A recent report predicted that 80% of the Internet traffic will be video content by the year 2021. Several studies have been conducted on the detection of main video events to manage a large scale of videos. These studies show fairly good performance in certain genres. However, the methods used in previous studies have difficulty in detecting events of personal video. This is because the characteristics and genres of personal videos vary widely. In a research, we found that adding a dataset with the right perspective in the study improved performance. It has also been shown that performance improves depending on how you extract keyframes from the video. we selected frame segments that can represent video considering the characteristics of this personal video. In each frame segment, object, location, food and audio features were extracted, and representative vectors were generated through a CNN-based recurrent model and a fusion module. The proposed method showed mAP 78.4% performance through experiments using LSVC data.

• 한국건축시공학회지
• /
• 제8권2호
• /
• pp.131-136
• /
• 2008

Safety management is the most important factor in the construction industry. If the construction company don't control the risk, it causes the accident which give the company fatal loss. According to the Korea industrial safety analysis reports, the 25.72% of the disasters are from the construction industry, and the 13.6% construction disasters are caused by not properly using the safety gears. Therefore, this study is to investigate the Wearing Safety Gear by Occupational Classification and the Satisfaction in the Construction Field. The results are ; Carpenters are dissatisfied with the safety shoes and belt, re-bar workers are dissatisfied with the safety helmet and shoes, Concrete workers are dissatisfied with the safety helmet and goggles.

• 전자공학회논문지B
• /
• 제30B권12호
• /
• pp.21-30
• /
• 1993

In this paper, we propose a connected Korean digit recohnition system employing neural networks and lexical constraints of the Korean digits. In the proposed recognition system, firstly, each frame of digit string is labelled by phoneme classification neural networks.which are trained with the reference phoneme segments extracted form an isolated digit based on the position information. And, the frame labels are combined with each other for constructing the phoneme segments. Then, these segments are combined to form a digit candidate using the digit combination rules. The digit candidate is decided based on the condition for digit decision. If the condition is not satisfied, the digit candidate is further recognized using the digit decision neural network in the next step. In our approach, the neural networks are trained with 10 isolated digits uttered by 5 male speakers. To investigate the performance of the proposed recognition system, an intensive computer simulation on the 30 connected digit strings uttered by 5 male speakers is performed. The simulation result indicates that 95.6% digit recognition rate and 82% digit string recognition rate are provided by the proposed Korean digit recognition system.