• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3608-3626
• /
• 2021

The detection of bolts is an important task in high-speed train inspection systems, and it is frequently performed to ensure the safety of trains. The difficulty of the vision-based bolt inspection system lies in small sample defect detection, which makes the end-to-end network ineffective. In this paper, the problem is resolved in two stages, which includes the detection network and cascaded classification networks. For small bolt detection, all bolts including defective bolts and normal bolts are put together for conducting annotation training, a new loss function and a new boundingbox selection based on the smallest axis-aligned convex set are proposed. These allow YOLOv3 network to obtain the accurate position and bounding box of the various bolts. The average precision has been greatly improved on PASCAL VOC, MS COCO and actual data set. After that, the Siamese network is employed for estimating the status of the bolts. Using the convolutional Siamese network, we are able to get strong results on few-shot classification. Extensive experiments and comparisons on actual data set show that the system outperforms state-of-the-art algorithms in bolt inspection.

• 한국농촌간호학회지
• /
• 제15권2호
• /
• pp.66-73
• /
• 2020

Purpose: This study was done to report nursing case for ADL improvement of elders who have CVA(Cerebrovascular Accident) sequelae. Methods: The client had registered in the C visiting nursing center after being decided a long-term care Grade 2. Data were collected through consultation logs for recipients, Activities of Daily Living (ADL) records, fall risk assessment (Huhn) sheets, decubitus ulcer risk assessment (Braden Scale) sheets, cognition assessment (K-MMSE) sheets, long-term care benefit provision records, and interviews with visiting nurse. Data were collected and analyzed according to the Omaha System problem classification. The intervention scheme and the problem rating scale for performance were applied to present the case for home-visit nursing. Results: The client registered in August, 2018, was provided home-visit nursing care once a week as of September 2020. ADL, cognitive levels and decubitus ulcer risks were found to have improved. Conclusion: This case report presents the value of classifying nursing problems and checking nursing intervention provided to patients with problems of ADL. The presentation of home-visit nursing cases applying a standardized nursing problem classification scheme for clients with various problems showed that a high quality level of care is guaranteed and evidence-based nursing can be provided by visiting nurses.

• 한국의류학회지
• /
• 제45권1호
• /
• pp.1-16
• /
• 2021

This study classified short adult male body types and identified characteristics by body type according to Size Korea's 7th human system measurement data for men in their 20s to 60s. There were four body types for short adult males. Type 1 was a 'short bird legs-normal body shape' with an average body size, low body height, short torso length, thin legs, and no sagging shoulders. Type 2 was a 'short torso thin body' with a small body size, a slim body, a high body height, a short torso length and no sagging shoulders. Type 3 was a 'thick leg-overweight body shape' with a large body size, thick legs, low body height, small shoulder length and obesity. Type 4 was a 'long bird legs-normal body' with a normal body size, high body height, thin legs, long torso and sagging shoulders. The development of clothing design and pattern reflecting the body shape characteristics of short adult males should be improved to fit clothing and suitability. It is necessary to increase the satisfaction of ready-to-wear for consumers with various body types by adding the size for shorter men through a subdivision of the ready-made size system.

• 한국초전도ㆍ저온공학회논문지
• /
• 제25권3호
• /
• pp.13-17
• /
• 2023

Magnetic separation technology for small paramagnetic particles has been desired for the volume reduction of contaminated soil from the Fukushima nuclear power plant accident and for the separation of scale and crud from nuclear power plants. However, the magnetic separation for paramagnetic particles requires a superconducting high gradient magnetic separation system applied, hence expanding the bore diameter of the magnets is necessary for mass processing and the initial and running costs would be enormous. The use of high magnetic fields makes safe onsite operation difficult, and there is an industrial need to increase the magnetic separation efficiency for paramagnetic particles in as low a magnetic field as possible. Therefore, we have been developing a magnetic separation system combined with a selection tube, which can separate small paramagnetic particles in a low magnetic field. In the previous technique we developed, a certain range of particle size was classified, and the classified particles were captured by magnetic separation. In this new approach, the fluid control method has been improved in order to the selectively classify particles of various diameters by using a multi-stage selection tube. The soil classification using a multi-stage selection tube was studied by calculation and experiment, and good results were obtained. In this paper, we report the effectiveness of the multi-stage selection tube was examined.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2008년도 학술대회
• /
• pp.302-307
• /
• 2008

The development technology for the helicopter is improved by the increasing of computing power and advanced test facilities. The increasing efficiency of fuel consuming by the developing of improved lift-to-drag rotor system is the major issue, the noise reduction for ecology(civil area) and increase of survivability to reduce noise detection(battlefield) also are important. This investigation shows the classification of helicopter external noise and requirements, the noise flight test methods, the numerical modeling method for aero-acoustic of rotor blade and the result of CAA(Computational Aero-Acoustic) for main rotor blade.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2008년 추계학술대회논문집
• /
• pp.302-307
• /
• 2008

The development technology for the helicopter is improved by the increasing of computing power and advanced test facilities. The increasing efficiency of fuel consuming by the developing of improved lift-to-drag rotor system is the major issue, the noise reduction for ecology(civil area) and increase of survivability to reduce noise detection(battlefield) also are important. This investigation shows the classification of helicopter external noise and requirements, the noise flight test methods, the numerical modeling method for aero-acoustic of rotor blade and the result of CAA(Computational Aero-Acoustic) for main rotor blade.

• Journal of electromagnetic engineering and science
• /
• 제15권1호
• /
• pp.37-43
• /
• 2015

We implemented a real-time radar system for an unmanned ground vehicle designed to run on unpaved or bumpy roads. The system must be able to detect slow targets in a cluttered environment and cover wide angular sections with high resolution at the same time. The system consists of array antennas, preprocessors for digital beam forming, and digital signal processors for the detection process which uses sawtooth waveforms and high-resolution estimation, and is called forward/backward spatial smoothing beamspace multiple signal classification (FBSS BS-MUSIC). We show that the sawtooth waveforms enhance the angular estimation capability of FBSS BS-MUSIC in addition to their well-known advantages of removing the ambiguity of targets and detecting slow targets with improved velocity resolution.

• 한국ITS학회 논문지
• /
• 제11권5호
• /
• pp.125-135
• /
• 2012

본 연구는 도로 위의 객체를 분류하고 그 위치를 추정하기 위해 카메라와 레이저스캐너를 이용한 이종센서 검지 시스템의 연구를 다루고 있다. 이러한 도로인프라에서의 검지시스템은 ADAS(Advanced Driver Assist System) 및 (반)자동제어 서비스 등의 새로운 C-ITS 서비스에서 요구되는 객체의 위치 정보를 검지할 수 있다. 본 연구에서는 국외 관련 사례를 살펴보고, 카메라와 레이저스캐너를 이용한 검지시스템의 가능성을 살펴보았다. 그 후 이종센서 처리 알고리즘을 제안하고, 실 도로환경에서 몇 가지 도로상황 시나리오를 설정하여 시험검증을 실시하였다. 그 결과 이종센서 검지시스템으로 차량, 보행자 및 기타 장애물에 대한 검지 및 위치 추정에 대하여 비교적 용이하게 이용될 수 있음을 확인할 수 있었다. 본 연구의 경우 매우 이상적인 조건에서 실험이 실시되었으며, 조도, 날씨 등의 외부환경 조건의 변화에 따른 알고리즘의 평가가 필요하다. 이러한 연구는 향후 미래의 C-ITS 환경 하에서 객체 검지 기술로 활용될 수 있을 것으로 기대한다.

• 센서학회지
• /
• 제13권6호
• /
• pp.454-461
• /
• 2004

We have designed a portable electronic nose (e-nose) system using an array of commercial gas sensors and personal digital assistants (PDA) for the recognition and analysis of volatile organic compounds (VOC) in the field. Field screening of pollutants has been a target of instrumental development during the past years. A portable e-nose system was advantageous to localize the special extent of a pollution or to find pollutants source. The employment of PDA improved the user-interface and data transfer by Internet from on-site to remote computer. We adapted the Lavenberg-Marquardt algorithm based on the back-propagation and proposed the method that could predict the concentration levels of VOC gases after classification by separating neural network into two parts.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2018년도 하계학술대회
• /
• pp.45-46
• /
• 2018

This paper focuses on human activities monitoring problem using onboard smartphone sensors as data generator. Monitoring such activities can be very important to detect anomalies and prevent disease from patients. Machine learning (ML) algorithms appear to be ideal approaches to use for processing data from smartphone to get sense of how to classify human activities. ML algorithms depend on quality, the quantity and even more important, the properties or features, that can be learnt from data. This paper proposes a mobile virtual reality visualization system that helps to view data representation in a very immersive way so that its quality and discriminative characteristics may be evaluated and improved. The proposed system comes as well with a handy data collecting application that can be accessed directly by the VR visualization part.