• 대한임베디드공학회논문지
• /
• 제15권3호
• /
• pp.119-127
• /
• 2020

The detection and recognition of abnormal driving becomes crucial for achieving safety in Intelligent Transportation Systems (ITS). This paper presents a feature extraction method based on spectral data to train a neural network model for driving behavior recognition. The proposed method uses a two stage signal processing approach to derive time-saving and efficient feature vectors. For the first stage, the feature vector set is obtained by calculating variances from each frequency bin containing the power spectrum data. The feature set is further reduced in the second stage where an intersection method is used to select more significant features that are finally applied for training a neural network model. A stream of live signals are fed to the trained model which recognizes the abnormal driving behaviors. The driving behaviors considered in this study are weaving, sudden braking and normal driving. The effectiveness of the proposed method is demonstrated by comparing with existing methods, which are Particle Swarm Optimization (PSO) and Convolution Neural Network (CNN). The experiments show that the proposed approach achieves satisfactory results with less computational complexity.

• 인터넷정보학회논문지
• /
• 제11권4호
• /
• pp.59-72
• /
• 2010

WIM(Weigh-In-Motion) 시스템은 고속으로 이동 중인 차량의 무게를 측정하는 시스템이다. 기존의 WIM 시스템에서는 등속을 기준으로 차량의 무게를 측정하며 오차율이 10% 범위에 있다. 하지만 운전자의 가 감속 조작과 같은 비정상 주행패턴을 고려하고 있지 않으므로 실제 오차율은 더욱 크다. 이러한 오차를 최소화하기 위해서 비정상적인 주행패턴을 찾고 이를 적용한 개선된 WIM 시스템이 필요하다. 본 논문에서는 기존의 WIM 시스템의 오차율에 영향을 미치는 비정상 주행패턴을 분석하고 오차율을 최소화하는 개선된 WIM 시스템을 설계한다. 개선된 WIM 시스템은 기존의 시스템에 루프센서를 추가한 다단 루프 구조를 가진다. 또한 내부적으로 정의된 측정 함수를 개선하여 비정상 주행패턴별로 측정된 무게를 보정한다. 실험 분석 결과 개선된 WIM 시스템은 기존의 최대 평균 오차율 22.98% 에서 8% 미만으로 오차율이 감소한 사실을 알 수 있다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2014년도 추계학술대회 논문집
• /
• pp.472-475
• /
• 2014

Abnormal cab vibrations in the Y direction in commercial vehicles during driving(70~90kph) are not common vibrations that happen to vehicles during driving and can be an obstacle to normal driving. This study conducted Operation Deflection Shape(ODS) testing to identify the causes of those abnormal cab vibrations and find solutions for them and also a sine sweep test to find resonance and frequency in the cab suspension system and set directions for improvement. The study also altered the shape of the bush inner part for changes to the rigidity features of the cab bush in the Y direction and revised the design with optimal rigidity in the Y direction, thus improving abnormal cab vibrations in the Y direction during driving.

• 한국철도학회논문집
• /
• 제9권1호
• /
• pp.29-35
• /
• 2006

Trains in LRT(Light Railway Transit) system usually have shorter car length than metro's because of their smaller passensers demand. Therefore it is very likely that the load condition of LRT system in abnormal operation, in case of which trains are in close proximity by system broke or train rescue works, could be worse rather than in normal operation, in spite of rare probability of abnormal operation. In this study, the target reliability indexes of several abnormal operations are estimated in accordance with the occurrence probabilities of each abnormal operation case and the reliability index of normal operation presented by the specification. From the indexes, load factors for the abnormal operation cases are estimated and the safety evaluation is performed for Yong-in LRT project.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권2호
• /
• pp.119-128
• /
• 2022

Recently, due to the development of related technologies for autonomous vehicles, driving work is changing more safely. However, the development of support technologies for level 5 full autonomous driving is still insufficient. That is, even in the case of an autonomous vehicle, the driver needs to drive through forward attention while driving. In this paper, we propose a method to monitor driving tasks by recognizing driver behavior. The proposed method uses pre-trained deep convolutional neural network models to recognize whether the driver's face or body has unnecessary movement. The use of pre-trained Deep Convolitional Neural Network (DCNN) models enables high accuracy in relatively short time, and has the advantage of overcoming limitations in collecting a small number of driver behavior learning data. The proposed method can be applied to an intelligent vehicle safety driving support system, such as driver drowsy driving detection and abnormal driving detection.

• 자동차안전학회지
• /
• 제10권3호
• /
• pp.32-37
• /
• 2018

Recently, the driver can be assisted by the advanced active safety devices such as ADAS from road traffic risks. With this system, driver and passenger may freed from can driving tasks or kept eyes on forward direction while on the road. Help from adoptive cruise control, auto parking and newly develped automated driving vehicles technologies, the driver positions will vary significantly from the current standard driver position during the travel time. On this hypothesis, the objective of this study is analyze the behavior and injuries of drivers in the event of frontal impact under these abnormal driver position. Based on the KNCAP frontal impact testing method, this simulation matrix was set-up with dummies of 5 th tile female Hybrid III dummy and 50 th tile male Hybrid III dummy. The small sedan type passenger car was modeled in this simulation. The series of simulation was performed to compare the injuries and behaviour of each dummy, varying the seating status and seat position of each dummy.

• 유기물자원화
• /
• 제26권3호
• /
• pp.15-22
• /
• 2018

본 연구는 전국적으로 운영되고 있는 음식물류 폐기물 공공자원화 시설 중에서 초기에 제시된 운전조건과 맞지 않게 비정상적으로 운전되고 있는 DDM환경자원센터의 퇴비화 시설을 대상으로 하여 실시하였다. DDM환경자원센터의 비정상적인 퇴비화 시설에 대한 쟁점사항을 점검하고 그 쟁점의 원인을 분석하기 위하여 유사 공정사례를 조사하였다. 또한 비정상적인 운전시설을 정상적 운전시설로 전환하기 위한 몇 가지 개선방안 및 대안을 제시하였으며 이를 현장 적용시에 쟁점으로 부각된 주요 비정상적 운전사항의 문제점은 해결될 수 있을 것으로 사료된다.

• 대한안전경영과학회지
• /
• 제20권3호
• /
• pp.21-26
• /
• 2018

This paper describes result of a study on safety against a fire of charging cable for mobile phone for vehicle. Combustion on the USB cable in the car was happened while driving. Gas coming from the burning USB cable could be a reason which can make a secondary car accident since the driver also can be embarrassed while driving. In order to prevent a secondary car accident connected on the road, to research a reason why USB cable can emit gas and be burned in charging. We did simulation test with abnormal fault condition for the electronic component on the board in the USB cable. So we get the result from abnormal fault condition simulation test, for instance, shorted test for output terminal of 8 pin switch, shorted test for chip resistor after thermal aging in the condition $25^{\circ}C$, 93 % RH during 48 hours. To analysis the result of all test, Combustion on the USB cable was not the 8 pin but other electrical component such as a chip resistor. Therefore we guess that the reason for USB cable combustion in charging in a car was not 8 pin and a LED but another defective component.

• 자동차안전학회지
• /
• 제11권3호
• /
• pp.13-18
• /
• 2019

According to the development of autonomous vehicles worldwide, the driver's posture may not be a normal posture but the various seating positions. Recently, a numbers of research activities has been focused to protect of driver and passengers in various seating positions as well as seating postures. In this paper, the occupant injury severity was evaluated with different seat positions, seatback angles and TTF times.

• Journal of Radiation Protection and Research
• /
• 제11권1호
• /
• pp.65-69
• /
• 1986

Picker C-9 $^{60}Co$원격치료장치에 의한 선량분포의 비대칭을 물팬톰에 의한 측정으로부터 발견하고 비대칭적인 선량분포의 원인이 선원의 비정상적인 'ON' 위치였음을 확인하였다. 선원이 비정상적인 위치에서 정지하게 된 원인이 선원을 'OFF'위치로 되돌리는 태엽의 일부 인접면이 접촉하게되어 마찰의 발생과 증대였음을 확인하였다. 태엽에 윤활유를 쳤을 때 선량분포의 대칭성이 다소 호전되었지만 근본적인 해결책은 태엽을 교체하는 것이다. 예방대책으로는 주기적인 선량분포의 측정에 의한 확인과 보수유지계획에 의한 관리가 수행되어야 할 것이다.