• 전기전자학회논문지
• /
• 제26권3호
• /
• pp.488-493
• /
• 2022

제조 현장에 사용되는 전기적 구동 모터는 베어링의 결함 발생 시 시스템 전체의 작동 정지를 초래하게 된다. 제조 환경 작동의 정지는 시간과 금전적으로 막대한 손해를 일으키며 이러한 베어링의 결함 원인으로는 회전 요소들의 지속적인 접촉으로 인한 마모, 과도한 하중 적용, 구동 환경 등 다양한 요소가 될 수 있다. 따라서 본 논문에서는 국내 제조 환경과 유사한 모터 구동 환경을 제작하여, 다양한 원인의 베어링 환경을 모의한다. 또한 구축된 환경을 바탕으로 정상 및 결함 상태에 따라 달라지는 진동 특성의 변화를 센서를 통해 수집하여 베어링 결함 예지 정비를 위한 데이터셋을 제안한다. 진동 특성 수집에 사용된 센서는 Microphone G.R.A.S. 40PH-10을 사용하여 수집하였으며, 다양한 기계학습 모델을 사용하여 제안하는 데이터셋에 훈련된 견본 베어링 예지 정비 시스템을 제작해본 결과, 심층 신경망 모델 기준 시간 영역 92.3%, 주파수 영역 98.3%의 높은 정확도 성능을 보여준다.

• 한국공간구조학회논문집
• /
• 제23권3호
• /
• pp.95-103
• /
• 2023

With the increasing number of aging buildings across Korea, emerging maintenance technologies have surged. One such technology is the non-contact detection of concrete cracks via thermal images. This study aims to develop a technique that can accurately predict the depth of a crack by analyzing the temperature difference between the crack part and the normal part in the thermal image of the concrete. The research obtained temperature data through thermal imaging experiments and constructed a big data set including outdoor variables such as air temperature, illumination, and humidity that can influence temperature differences. Based on the collected data, the team designed an algorithm for learning and predicting the crack depth using machine learning. Initially, standardized crack specimens were used in experiments, and the big data was updated by specimens similar to actual cracks. Finally, a crack depth prediction technology was implemented using five regression analysis algorithms for approximately 24,000 data points. To confirm the practicality of the development technique, crack simulators with various shapes were added to the study.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 춘계학술대회 논문집
• /
• pp.608-611
• /
• 2002

In GMAW(Gas Metal Arc Welding) process, bead geometry (penetration, bead width and height) is a criterion to estimate welding quality. Bead geometry is affected by welding current, arc voltage and travel speed, shielding gas, CTWB (contact- tip to workpiece distance) and so on. In this paper, welding process variables were selected as welding current, arc voltage and travel speed. And bead geometry was reasoned from the chosen welding process variables using negro-fuzzy algorithm. Neural networks was applied to design FL(fuzzy logic). The parameters of input membership functions and those of consequence functions in FL were tuned through the method of learning by backpropagation algorithm. Bead geometry could be reasoned from welding current, arc voltage, travel speed on FL using the results learned by neural networks.

• 음성과학
• /
• 제8권2호
• /
• pp.93-106
• /
• 2001

The pronunciation of English l and r was a consistent problem in learning English in Korea as well as Japan. This problem occurs from the fact that in Korea and Japan there is only one liquid sound. Substituting the Korean liquid for English l and r was a common error. The pronunciation of the dark l causes a further problem in pronouncing the English l sound. To see the relationship between the English l, r, and the Korean liquid sound, an electropalatographic (EPG) experiment was done. The findings were (1) there were no tongue contacts either on the alveolar ridge or on the palate during the articulation of the dark l. (2) The Korean liquid sound was different in the tongue contact points either from English l or r. The English clear l consistently touched the alveolar ridge in the forty tokens, but the Korean liquid sound in the intervocalic and word-final position touched mainly the alveopalatal area. The English r touched exclusively the velum area. The Korean intervocalic /l/ was similar to English flap in EPG and spectrographic data. There was evidence that the word-final Korean /l/ is a lateral.

• International journal of advanced smart convergence
• /
• 제11권3호
• /
• pp.49-55
• /
• 2022

Hair styling has a significant influence on human social perception. An increasing number of people are learning hair styling and obtaining hair designer licenses. However, it takes a considerable amount of money and time to learn professional hairstyle and beauty techniques for hair styling. Since COVID-19, there has been a growing need for offline and video lectures due to the decline in onsite training opportunities. This study provides a field practice environment in which real hair beauty is performed in a virtual space. Further, the hairstyle that is most similar to the user's hair taken with a webcam or mobile phone is determined through an image matching system using the speeded up robust features (SURF) method. The matching hairstyle was created into a three-dimensional (3D) hair model. The created 3D hair model uses a head-mounted display (HMD) and a controller that enables finger tracking through mapping to reproduce the haircutting scissors' motion while providing a feeling of real hair beauty.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.506-508
• /
• 2023

비접촉 음파 센서와 기계학습을 결합하여 도로 표면의 투명한 블랙아이스 감지 및 노면 분류 97%의 정확도를 달성한 새로운 접근 방법을 제안한다. 개발된 시스템은 블랙아이스를 포함한 다양한 물질의 반사 특성을 분석하여 미끄러운 도로 상황을 실시간 감지 및 예측이 가능하여 도로 안정성을 향상한다. 본 연구에서는 테스트 벤치와 투명하고 미끄러운 물질을 이용하여 블랙아이스를 감지할 수 있는 기술의 정확도를 비교하며, 실험 결과를 통해 제안된 블랙아이스 감지 방법의 타당성을 입증하고자 한다.

• Clinical and Experimental Vaccine Research
• /
• 제12권1호
• /
• pp.77-79
• /
• 2023

The Philippines is still in a tight battle with the coronavirus disease 2019 pandemic since many cases are detected daily. With the continuous spread of another disease worldwide-monkeypox, many Filipinos are alarmed if the country's healthcare system is prepared enough, especially with the detection of its first case. Learning from the unfortunate experiences of the country during the current pandemic is essential in facing another health crisis. With this, recommendations for a robust healthcare system are proposed centered on: a massive digital information campaign about the disease; training healthcare workers to raise awareness about the virus and its transmission, management, and treatment; an intensified surveillance and detection procedure to monitor cases and execute contact tracing properly; and a persistent procurement of vaccines and drugs for treatment, with a well-designed vaccination program.

• International Journal of Advanced Culture Technology
• /
• 제12권1호
• /
• pp.249-253
• /
• 2024

The ultimate purpose of this study is as follows: The current primary concern in the defense sector revolves around how to strategically utilize Fourth Industrial Revolution technologies in combat. The Fourth Industrial Revolution denotes a shift towards an environment where automation and connectivity are maximized, driven by technologies such as artificial intelligence. Coined by Klaus Schwab in the 2015 Davos Forum, this term highlights the significant role of machine learning and artificial intelligence. Particularly, the military application of Fourth Industrial Revolution technologies is expected to be actively researched and implemented. Combat involves military actions between units, typically conducted as part of a larger war, with units striving to achieve one or more objectives. The concept of combat refers to the fundamental ideas of how units should engage with the enemy, both presently and in future scenarios, to achieve assigned objectives.

• 한국문헌정보학회지
• /
• 제29권
• /
• pp.257-279
• /
• 1995

Cooperative program planning and teaching is a strategy for developing and implementing resource based learning. This approach combines the classroom teacher's subject expertise and knowledge of the students with the teacher­librarian's specialized knowledge of the availability and use of learning materials. And the purpose of cooperative program planning is to develop learning experiences or units of study that effectively integrate the student's resource center activities with other learning experiences. There are also some conditions that are conducive to effective planning sessions. First, the teacher-librarian must be prepared to initiate planning with teachers, rather than waiting for teachers to come to them. Second, the teacher-librarian must be prepared to present suggestions in such a way that the teacher can respond. The purpose of this study is (1) to investigate the planning process of cooperative program planning and teaching in the previous studies and (2) to find general problems when the cooperative program planning and teaching apply in actual situation. For these purposes, I chose a school library and a teacher-librarian in Seoul to observe how this cooperative program planning and teaching carry out in the school library. Main findings are summarized as follows: (1) A teacher who teaches alone for one grade is more proper to carry out the cooperative program planning and teaching. Young teachers are usually more active to change their teaching methods. (2) The cooperative program planning and teaching is a program what needs a lot of materials. When there is no right reference book in a school library, it would be good to access DB through PC telecommunication. It is also possile to contact lirarians who work in large public libraries or university libraries. (3) The cooerative program planning and teaching needs cooperative working between a teacher-librarian and a teacher. Thus a teacher-librarian should be in his school in the day time like the other teachers for the program's planning process. ( 4) There has to be a guide to change into resource based learning in teaching method. Thus the Korean Library Association or Korean Library and Information Science Society should offer a seminar or a workshop about cooperative program planning and teaching for the teacher-librarians. (5) It needs a system that a teacher-librarian can know about student's assignments so that he can prepare reference books for them. (6) The school library can be able to offer excellent service like cooperative program planning and teaching to the teachers and students according to a teacher-librarian's enthusiasm.

• 한국터널지하공간학회 논문집
• /
• 제26권1호
• /
• pp.39-58
• /
• 2024

TBM (Tunnel boring machine)은 터널 굴착 과정에서 여러 디스크 커터를 이용하여 암석을 절삭한다. 디스크 커터는 암석과의 지속적인 접촉과 마찰로 인해 마모된다. 디스크 커터의 표면이 마모되면 절삭 능력이 감소하고 굴착 효율이 떨어진다. 암석의 마모성은 디스크 커터 마모에 큰 영향을 미친다. 높은 마모도를 가진 암석은 커터에 더 큰 마모를 일으키며, 이는 디스크 커터의 수명을 단축시킨다. 세르샤 마모지수(Cerchar abrasivity index, CAI)는 암석의 마모성을 평가하는데 널리 사용되는 지표로 CAI는 암석의 마모특성을 나타내며, 디스크 커터의 수명과 성능 예측에 필수적인 요소로 인식되고 있다. 본 연구의 목적은 암석의 강도, 암석학적 특성과 선형회귀, 머신러닝 기법을 이용하여 CAI를 효과적으로 추정하는 새로운 방법을 개발하는 것이다. 문헌 조사를 통해 CAI, 일축압축강도, 압열인장강도, 등가석영함량이 포함된 데이터베이스를 구축하고 파생변수를 추가하였다. 통계적 유의성과 다중공선성을 고려하여 다중선형회귀분석을 위한 입력변수를 선정하였고, 머신러닝 모델의 입력변수는 변수중요도 분석을 통해 선정하였다. 머신러닝 예측모델 중 Gradient Boosting 모델의 예측 성능이 가장 높게 나타나 최적의 CAI 예측 모델로 선정되었다. 마지막으로 본 연구에서 도출한 다중선형회귀분석과 Gradient Boosting 모델의 예측 성능을 선행연구들의 CAI 예측모델과 비교하여 연구 결과의 타당성을 확인하였다.