http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
딥러닝 기반 달 표면 모사 환경 실시간 객체 인식 및 매칭 시스템 개발
나종호,공준호,이수득,신휴성,Jong-Ho Na,Jun-Ho Gong,Su-Deuk Lee,Hyu-Soung Shin 한국암반공학회 2023 터널과지하공간 Vol.33 No.4
Continuous research efforts are being devoted to unmanned mobile platforms for lunar exploration. There is an ongoing demand for real-time information processing to accurately determine the positioning and mapping of areas of interest on the lunar surface. To apply deep learning processing and analysis techniques to practical rovers, research on software integration and optimization is imperative. In this study, a foundational investigation has been conducted on real-time analysis of virtual lunar base construction site images, aimed at automatically quantifying spatial information of key objects. This study involved transitioning from an existing region-based object recognition algorithm to a boundary box-based algorithm, thus enhancing object recognition accuracy and inference speed. To facilitate extensive data-based object matching training, the Batch Hard Triplet Mining technique was introduced, and research was conducted to optimize both training and inference processes. Furthermore, an improved software system for object recognition and identical object matching was integrated, accompanied by the development of visualization software for the automatic matching of identical objects within input images. Leveraging satellite simulative captured video data for training objects and moving object-captured video data for inference, training and inference for identical object matching were successfully executed. The outcomes of this research suggest the feasibility of implementing 3D spatial information based on continuous-capture video data of mobile platforms and utilizing it for positioning objects within regions of interest. As a result, these findings are expected to contribute to the integration of an automated on-site system for video-based construction monitoring and control of significant target objects within future lunar base construction sites.
SMT 장비의 동작 상태 분류를 위한 음향 스펙트럼 비교에 관한 연구
나종호(Jongho Na),신휴성(Hyusoung Shin),박영현(Younghyun Park),윤일동(Ildong Yun) 한국산학기술학회 2021 한국산학기술학회논문지 Vol.22 No.11
SMT(Surface Mount Technology) 장비는 PCB(Printed Circuit Board) 기판에 각종 소형 전자 부품을 장착하고 납땜하는 자동화 장비를 의미한다. SMT 장비를 주기적으로 유지보수하지 않으면 장비의 고장이 발생하여 막대한 경제적 손실을 가져올 수 있으므로 SMT 장비의 동작상태 진단은 매우 중요하다. 본 논문에서는 데이터 전처리 단계에서 신호처리 기법인 시간-평균 스펙트럼의 특징 추출을 위한 새로운 기법을 제안한다. 데이터는 학습데이터와 실험데이터로 구분되며, 학습데이터를 이용하여 각 동작(소자 마운트, 실린더 에어 분출, 내부 부품 흔들림, 정지)의 정상신호를 정의한다. 그리고 시간-평균 스펙트럼 특징을 유사도 비교 기법(Histogram Intersection, KL-Divergence, Earth Mover Distance)으로 정상 임계치 범주에 속하는지 판단한다. 마지막으로, 모든 동작의 임계치 범주에 속하지 않는다면 새로운 동작이 발생하였고 비정상신호라 판단하는 시스템을 제안한다. 실험을 통해 검증 결과, 제안한 유사도 비교방법이 상대적으로 적은 학습시간으로 인공신경망과 유사한 분류 성능을 얻을 수 있다. Surface Mount Technology (SMT) devices, referred to as automated equipment, are used to mount and solder various small electronic parts of PCB boards. If the SMT equipment is not regularly maintained, the equipment may malfunction, leading to enormous economic damage. Thus, diagnosing the operating state of SMT devices is very important. In this paper, we propose a new technique for feature extraction of time-averaged spectra, which is a signal processing technique in the data preprocessing stage. The data is split into training data and testing data, and the normal signal of each operation (Element Mount, Cylinder Air Blowout, Oscillation, Stop) is defined using the learning data. Then, the signal is examined to see whether the time-averaged spectral feature belongs to the normal threshold range by using a similarity comparison technique (Histogram Intersection, KL-Divergence, Earth Mover Distance). Lastly, if the signal does not belong to the threshold range of all motions, a new motion is said to have occurred and a proposed system decides that the signal is abnormal. As a result of the verification through experiments, the proposed similarity comparison method was able to obtain classification performance similar to that of an artificial neural network with relatively less learning time.
JD-R 모형을 이용한 호텔종사원들의 직무자원들의 차별적 효과 -대응가설을 중심으로-
나종호 ( Jong Ho Na ) 대한관광경영학회 2014 觀光硏究 Vol.29 No.2
본 연구는 호텔종사원들의 감정적 직무요구가 감정적 탈진에 영향을 미치고 감정적 탈진은 감정적 몰입도에 영향을 미치는 매개과정을 분석하였다. 또한 감정적 직무요구가 감정적 탈진에 미치는 영향이 감정적(인지적) 직무자원의 크기(조절변수)에 의하여 달라지는지에 관한 조절효과를 살펴보았다. 그리고 매개분석과 조절분석을 결합하여 매개과정이 조절변수에 의하여 조절되는지에 관한 조절된 매개분석을 실시하였다. 국내호텔에 근무하는 175명의 호텔종사원들의 설문지를 이용하여 자료분석을 실시한 결과 주요결론들은 다음과 같다. 먼저 감정적 직무요구가 감정적 탈진에 미치는 영향이 감정적 직무자원에 의하여 조절되는 조절효과가 나타났고 인지적 직무자원에 의해서는 조절되지 않았다. 즉, 감정적 직무자원의 크기가 증가할수록 감정적 직무요구가 감정적 탈진에 미치는 부정적인 효과는 점점 감소하는 것으로 나타났다. 이는 삼중대응기준(triple match principle)의 효과를 지지하는 것이다. 둘째로 감정적 직무요구는 감정적 탈진에 영향을 미치고 감정적 탈진은 감정적 몰입도에 영향을 주는 매개효과가 확인되었다. 셋째, 이러한 매개효과는 감정적 직무요구의 크기가 증가함에 따라 감소하는 조절된 매개효과가 나타났다. 기존 연구들은 직무요구가 탈진에 미치는 영향이 직무자원에 의하여 조절되는 단순조절분석만을 실시한 반면에 본 연구는 매개효과분석과 조절효과분석을 결합하여 조절된 매개분석을 실시하였다는 특징이 있다. 또한 직무요구와 직무자원이 동질적인 차원인 경우에 조절효과가 나타났으므로 이에 입각하여 호텔경영자들은 호텔종사원들의 감정적 탈진을 감소시키고 조직몰입도를 증가시키기 위해서는 호텔종사원들에게 부과되는 직무요구에 대응되는 직무자원을 제공 또는 개발시켜야 할 것이다. The aim of this study was to investigate whether job resources should be matched to show moderating effects of job resources(matching hypothesis). Based on the Demand-Induced Strain Compensation(DISC) Model that stipulates that specific job resources should match specific job demands to attenuate the negative effect of job demands, mediation, moderation and moderated mediation analyses were performed to test various hypotheses. Self-report questionnaires were distributed to 212 hotel service employees, of which 175 returned the questionnaire. Findings showed that emotional job demands significantly affected emotional exhaustion and emotional exhaustion significantly influenced affective commitment, meaning that emotional exhaustion mediated the effects of emotional job demands on affective commitment. And emotional job resources moderated the relation between emotional job demands and emotional exhaustion which supports the triple match hypothesis. Particularly, results of moderated mediation analysis demonstrate that, for emotional job resources, the conditional indirect effect of emotional job demands was stronger and significant in the low emotional job resources condition but were not significant in the high emotional job resources condition, indicating that emotional exhaustion would mediate the relation between emotional job demands and affective commitment, but only at lower levels of emotional job resources. Providing hotel service employees with more matching job resources would be necessary to make emotional job demands less stressful.
나종호(Jongho Na),이재우(Jaewoo Lee),강오성(Ohsung Kang) 한국자동차공학회 2011 한국자동차공학회 학술대회 및 전시회 Vol.2011 No.11
BEV (Battery Electric Vehicle) is not currently launching and applied at domestic market .In spite of that, it is getting important to make a vehicle which has a performance such as high fuel efficiency or of environmental protection. For those reasons, it is expected for vehicles to be developed. UCCB (Underhood Cross-Car Beam) ,one of main components for Electric Vehicle, is sustaining and fixing a some of parts(HVAC (Heating Ventilating and Air Conditioning)) and Electric Modules Nowadays It is widely going on a research to evaluate a strength and durability in all over the world. Strength and performance of structure are pre-expected by using a Fatigue simulation through FEA (Finite Element Analysis) to reduce a developing time and cost. Also, it can be compared with real and virtual test result. As a result of this paper, it is systematized how to set up an analysis of UCCB and proved it with reliability.