http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
머신 러닝을 이용한 영상 특징 기반 전기차 검출 및 분류 시스템
김상혁(Sanghyuk Kim),강석주(Suk-Ju Kang) 대한전기학회 2017 전기학회논문지 Vol.66 No.7
This paper proposes a novel way of vehicle detection and classification based on image features. There are two main processes in the proposed system, which are database construction and vehicle classification processes. In the database construction, there is a tight censorship for choosing appropriate images of the training set under the rigorous standard. These images are trained using Haar features for vehicle detection and histogram of oriented gradients extraction for vehicle classification based on the support vector machine. Additionally, in the vehicle detection and classification processes, the region of interest is reset using a number plate to reduce complexity. In the experimental results, the proposed system had the accuracy of 0.9776 and the F₁ score of 0.9327 for vehicle classification.
에너지 하베스터의 현장 적용 위한 방수방진 케이스 제작
강민수(Minsu Kang),김상혁(Sanghyuk Kim),김태균(Taekyun Kim),이태희(Tae Hee Lee) 대한기계학회 2021 대한기계학회 춘추학술대회 Vol.2021 No.11
Energy harvesting is an energy transducer that generates useful electrical energy from wasted energy. Though its generating power is low, it can be utilized for low-power or self-powering devices’ power supplier. For field application as a sustainable energy source, energy harvester should be operated steadily regardless of various operating environments of the application site. For that, the energy harvester should be protected from contaminants that can cause malfunction. Therefor, aim of this study is to fabricate a waterproof and dustproof case for field application of energy harvester. The case structure consists of rubber sealing and cable gland for power transmission to external space, and the case material is selected with low magnetic permeability considering operation characteristics of the harvester, and 3D printing is used for fabricating complex exterior shape. As a result, fabricated case is certificated as IP65 rating.
A Low Cost ZugBee-based Air Monitoring System for Subway Station Using Multi-Hop Mesh Networking
Jongwon Kwon(권종원),Sangjun Koo(구상준),Hiesik Kim(김희식),Sanghyuk Kang(김상혁) 제어로봇시스템학회 2008 제어로봇시스템학회 국내학술대회 논문집 Vol.2008 No.10
Subway air pollution is very harmful to passengers, employees and the shop owners who are staying in underground of subway stations. The air in subway has high density of dust particles and chemical components that may be critically harm to health. Subway management organizations expect a stable, real time and remote type of air monitoring system. Wireless sensor networks (WSNs) allow a stable data transfer from sensor nodes to the main server. WSNs have been widely applied to a wide range of fields such as environmental monitoring, infrastructure management, medical, home, military and so on. The WSN technology was applied to an air pollution monitoring system in a subway station. The system is installed with ZigBee devices for making up wireless network. The existing specified facilities that measure PM10, CO2, CO, NOX, NO, VOCs temperature, humidity respectively have very large structure. They are also too expensive. So it is difficult that such conventional equipments are applied to air pollution monitoring in such fields. In this paper the ZigBee device for air pollution monitoring was newly designed and tested. It is small-size and inexpensive. It employs sensors with enough precision and ZigBee chip. It is expected that this system protects passengers and workers health and the managers can use the reliable ubiquitous environment monitoring system. In addition, the capability of each sensor node and networks were tested to prove efficient telecommunication and this paper proposes future challenges.