• 전기학회논문지
• /
• 제63권12호
• /
• pp.1667-1670
• /
• 2014

This paper describes a method for detecting the pupil region and identification of the eye status for driver drowsiness detection system. This program detects a driver's face and eyes using viola-jones face detection algorithm and extracts the pupil area by utilizing mean values of each row and column on the eye area. The proposed method uses binary images and the number of black pixels to identify the eye status. Experimental results showed that the accuracy of classification eye status(open/close) was above 90%.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.871-876
• /
• 2022

In the construction industry, fatal accidents related to scaffolds frequently occur. To prevent such accidents, scaffolds should be carefully monitored for their safety status. However, manual observation of scaffolds is time-consuming and labor-intensive. This paper proposes a method that automatically analyzes the installation status of scaffold joints based on images acquired from a Unmanned Aerial Vehicle (UAV). Using a deep learning-based object detection algorithm (YOLOv5), scaffold joints and joint components are detected. Based on the detection result, a two-stage rule-based classifier is used to analyze the joint installation status. Experimental results show that joints can be classified as safe or unsafe with 98.2 % and 85.7 % F1-scores, respectively. These results indicate that the proposed method can effectively analyze the joint installation status in UAV-acquired scaffold images.

• 산업경영시스템학회지
• /
• 제43권2호
• /
• pp.33-38
• /
• 2020

Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.

• 한국전자통신학회논문지
• /
• 제8권10호
• /
• pp.1443-1449
• /
• 2013

전방 차량의 자동검출은 충돌회피, 자동운행제어 그리고 자동 헤드램프 조정 등의 고급 운전지원시스템의 통합 요소이다. 주야간 상관없이 전방 차량 자동 검출과 운행 상태를 인지하는데 있어 후미등은 중요한 역할한다. 그런데, 많은 운전자들이 차량의 후미등 상태를 알지 못하고 운행하는 경우가 많다. 따라서, 후미등에 이상이 있는 차량에 대하여 자동으로 후미등 이상 상태를 알려주는 시스템이 필요하다. 본 논문에서는 영상처리 및 인식기술을 기반으로 차량의 후미등 상태를 인식하는 방법을 제안한다. 톨게이트 등으로 진입하는 차량을 검출하기 위하여 배경추정기법, 옵티컬 플로우(optical flow) 그리고 Euclidean 척도를 이용한다. Lab 색좌표에서 집중 맵(saliency map)을 적용하여 차량에서 후미등 영역을 검출하고 상태를 판정한다. 고속도로 톨게이트 영상을 이용하여 후미등 상태인식 실험을 하고, 제안하는 방법이 운전자에게 후미등 상태 전달하는데 활용할 수 있음을 보인다.

• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.282-292
• /
• 2020

In order to minimize casualties from marine vessel accidents that occur frequently at home and abroad, it is important to ensure the safety of the passengers aboard the vessel in the event of an accident. There is an EPIRB system as a system for disaster preparedness in the marine situation currently on the market, but there is a problem that the price is very expensive. In order to overcome the cost problem, which is a disadvantage of previous system, LoRaWAN-based communication is used. LoRaWAN communication-based vessel positioning and risk detection system based on LoRaWAN communication transmits measurement data of each module using two Beacon and GPS modules to stably perform position measurement for both indoor and outdoor situations. The rider danger situation detection system can detect the safety status of the rider using the 3-axis acceleration sensor, collect data from the rider positioning system and the rider safety status detection system, and send to server using LoRa communication. When conducting communication experiments in the long-distance maritime situation and actual communication experiments using the implemented system, it was found that the two experiments showed over 90% communication success rate on average.

• 품질경영학회지
• /
• 제45권1호
• /
• pp.25-38
• /
• 2017

Purpose: Hot strip rolling mill consists of a lot of mechanical and electrical units. In condition monitoring and diagnosis phase, various units could be failed with unknown reasons. In this study, we propose an effective method to detect early the units with abnormal status to minimize system downtime. Methods: The early warning problem with various units is defined. K-means and PAM algorithm with Euclidean and Manhattan distances were performed to detect the abnormal status. In addition, an performance of the proposed algorithm is investigated by field data analysis. Results: PAM with Manhattan distance(PAM_ManD) showed better results than K-means algorithm with Euclidean distance(K-means_ED). In addition, we could know from multivariate field data analysis that the system reliability of hot strip rolling mill can be increased by detecting early abnormal status. Conclusion: In this paper, clustering-based monitoring and fault detection algorithm using Manhattan distance is proposed. Experiments are performed to study the benefit of the PAM with Manhattan distance against the K-means with Euclidean distance.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제14권3호
• /
• pp.191-196
• /
• 2014

The importance of railway safety has become increasingly significant domestically as well as internationally, as a series of high speed railway accidents and other major accidents have occurred recently. Especially for the domestic railway, the Korean Railway Safety Law has been revised recently, mandates all the domestic railway operation authorities to render the performance of RAMS and RCM. This study inspects and analyzes the current status of the sensing technology of the electric detection system to tell the status of railway facilities in the highway railway in a real time through a sensor. It also performs the reliability analysis of the electric detection system that is being progressed as a study assignment and suggests the system construction for the higher reliability.

• 한국전자통신학회논문지
• /
• 제9권2호
• /
• pp.261-266
• /
• 2014

국내 보안관제센터들의 현황을 검토하였으며, 보안관제 체계의 특징인 패턴기반 보안관제체계와 중앙집중형 보안관제 체계에 대한 분석과 장단점을 분석하였다. 또한 국내 보안관제 체계 발전방안에서는 기존 패턴 기반의 중앙집중형 관제 체계가 가지고 있는 문제점을 개선하기 위해 이상행위 탐지기반의 허니넷과 다크넷을 분석하여 이를 적용한 발전 방안을 기술하였다.

• 수산해양기술연구
• /
• 제56권4호
• /
• pp.384-394
• /
• 2020

This paper proposes an outlier detection model based on machine learning that can diagnose the presence or absence of major engine parts through unsupervised learning analysis of main engine big data of a ship. Engine big data of the ship was collected for more than seven months, and expert knowledge and correlation analysis were performed to select features that are closely related to the operation of the main engine. For unsupervised learning analysis, ensemble model wherein many predictive models are strategically combined to increase the model performance, is used for anomaly detection. As a result, the proposed model successfully detected the anomalous engine status from the normal status. To validate our approach, clustering analysis was conducted to find out the different patterns of anomalies the anomalous point. By examining distribution of each cluster, we could successfully find the patterns of anomalies.

• 전기전자학회논문지
• /
• 제25권4호
• /
• pp.750-755
• /
• 2021

본 논문에서는 YOLOv4를 이용하여 차량의 부위별 파손현황을 검출하는 기법을 제안한다. 제안 알고리즘은 YOLOv4를 통해 차량의 부위와 파손을 각각 학습시킨 후 검출되는 바운딩 박스의 좌표 정보들을 추출하여 파손과 차량부위의 포함관계를 판단하는 알고리즘을 적용시켜 부위별 파손현황을 도출한다. 또한 성능비교의 객관성을 위하여 동일분야의 VGGNet을 이용한 기법, 이미지 분할과 U-Net 모델을 이용한 기법, Weproove.AI 딥러닝 모델 등을 대조 모델로 포함한다. 이를 통하여 제안 알고리즘의 성능을 비교, 평가하고 검출 모델의 개선 방안을 제안한다.