Anomaly Driving Speed Detection and Correction Algorithm based on Quantiles and KNN

Guo Yanling,Liu Lichen,Gao Meng,Gao Lewen 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.3

Driving speed is a key parameter for building the traffic state identification model, its precision directly affects the model reliability and the traffic state identification accuracy. Aiming at the standard normal deviation method’s defects in dealing with the extreme noise data, an anomaly driving speed detection algorithm based on quantiles is proposed, use historical data to establish the exception borders which are used to detect whether an unknown data is abnormal; on the basis of the abnormal data detection, a driving speed prediction algorithm based on improved KNN is proposed, use K-means algorithm to clustering the historical data, and predict the next moment’s speed according to the distance between the data to be predicted and the clusters, the predicted speed can be used to correct the abnormal speed. Experimental results show that the detection rate of the proposed anomaly detection algorithm has improved about 4.25% compared with the standard normal deviation method, and the false detection rate has reduced about 25.51%; the mean relative error of the proposed speed prediction algorithm is 13.69%, it can predict the driving speed well, namely, the anomaly driving speed detection and correction algorithm based on quantiles and KNN is feasible and effective.

고속주행상황의 운전자 인지·반응시간에 관한 연구

최재성,정승원,김정민,김태호,신준수 한국도로학회 2017 한국도로학회논문집 Vol.19 No.1

PURPOSES : The desire of drivers to increase their driving speeds is increasing in response to the technological advancements in vehicles and roads. Therefore, studies are being conducted to increase the maximum design speed in Korea to 140 km/h. The stopping sight distance (SSD) is an important criterion for acquiring sustained road safety in road design. Moreover, although the perception-reaction time (PRT) is a critical variable in the calculation of the SSD, there are not many current studies on PRT. Prior to increasing the design speed, it is necessary to confirm whether the domestic PRT standard (2.5 s) is applicable to high-speed driving. Thus, in this study, we have investigated the influence of high-speed driving on PRT. METHODS : A driving simulator was used to record the PRT of drivers. A virtual driving map was composed using UC-Win/Road software. Experiments were carried out at speeds of 100, 120, and 140 km/h while assuming the following three driving scenarios according to driver expectation: Expected, Unexpected, and Surprised. Lastly, we analyzed the gaze position of the driver as they drove in the simulated environment using Smarteye. RESULTS: Driving simulator experimental results showed that the PRT of drivers decreased as driving speed increased from 100 km/h to 140 km/h. Furthermore, the gaze position analysis results demonstrated that the decrease in PRT of drivers as the driving speed increased was directly related to their level of concentration. CONCLUSIONS : In the experimental results, 85% of drivers responded within 2.0 s at a driving speed of 140 km/h. Thus, the results obtained here verify that the current domestic standard of 2.5 s can be applied in the highways designated to have 140 km/h maximum speed

운전자의 속도 욕구좌절이 운전 스트레스에 미치는 영향

이순열,이순철 한국문화및사회문제심리학회 2009 한국심리학회지: 문화 및 사회문제 Vol.15 No.2

This study was intended to recognize whether speed desire frustration influences in driving stress. Stress desire frustration is the difference between prefer speed and normal speed. As a result, driver's the prefer speed is higher than the normal speed on 4 road condition(high-way, urban-way, residential-way, rural-way). Also, driver's speed desire frustration caused statistical effect in driving stress on 4 road condition. speed desire frustration effect Driving Stress Scale(DSS) 5 sub-scale factors(progress obstacle, traffic circumstance, accident & regulation, regulation obedience, time pressure). This is that driver who experience much speed desire frustration creates high driving stress. Speed desire frustration analyzed high driver and low driver's Driving Stress Scale(DSS) score and overspeed regulation and traffic accident experience difference. As analysis result, speed desire frustration high driver driving stress high appear. However, difference of overspeed regulation experience or traffic accident experience by speed desire frustration did not appear. 본 연구는 차량 운전 중 운전자가 원하는 속도만큼 속도를 내지 못하는 상황이 운전 스트레스에 어떠한 영향을 미치는지를 알아보고자 실시되었다. 운전자의 속도에 대한 욕구좌절은 희망 주행속도와 실제 주행속도의 차이로 구성개념화 되었다. 연구결과 4가지 도로조건(고속도로, 국도도로, 시내도로, 시골도로) 모두에서 운전자들의 희망 주행속도는 실제 주행속도보다 높게 나타났다. 4가지 도로조건(고속도로, 국도도로, 시내도로, 시골도로)을 종합한 평균 속도 욕구좌절은 운전 스트레스 척도 모든 점수(전체 DSQ점수, 전체 DSI점수, 전체 DSF점수, 진행장애 요인, 운전환경 요인, 사고단속 요인, 교통법규 요인, 시간압력 요인)들에 정적으로 유의한 영향을 미치는 것으로 나타났다. 특히, 속도 욕구좌절이 높아짐에 따라 운전 스트레스 척도의 강도 점수와 진행장애 요인, 시간압력 요인 등이 다른 운전 스트레스 척도 점수들보다 더 큰 영향을 받는 것으로 나타났다. 평균 속도 욕구좌절을 백분위 점수에 따라 4가지 수준으로 구분하여 운전 스트레스 척도 점수들과 과속단속 그리고 가해·피해 교통사고 경험 차이를 분석하였다. 분석결과 속도 욕구좌절이 높은 운전자들은 속도 욕구좌절이 낮은 운전자들보다 운전 스트레스 척도의 점수들도 유의하게 높은 것으로 나타났다. 하지만, 속도 욕구좌절 정도에 따른 과속단속 경험이나 가해·피해사고 경험은 차이가 나타나지 않았다.

가상주행과 실차주행의 운전자 주행행태 차이에 관한 연구

박진호,임준범,주성갑,이수범 한국도로학회 2015 한국도로학회논문집 Vol.17 No.2

PURPOSES : The use of virtual driving tests to determine actual road driving behavior is increasing. However, the results indicate a gap between real and virtual driving under same road conditions road based on ergonomic factors, such as anxiety and speed. In the future, the use of virtual driving tests is expected to increase. For this reason, the purpose of this study is to analyze the gap between real and virtual driving on same road conditions and to use a calibration formula to allow for higher reliability of virtual driving tests. METHODS : An intelligent driving recorder was used to capture real driving. A driving simulator was used to record virtual driving. Additionally, a virtual driving map was made with the UC-Win/Road software. We gathered data including geometric structure information, driving information, driver information, and road operation information for real driving and virtual driving on the same road conditions. In this study we investigated a range of gaps, driving speeds, and lateral positions, and introduced a calibration formula to the virtual record to achieve the same record as the real driving situation by applying the effects of the main causes of discrepancy between the two (driving speed and lateral position) using a linear regression model. RESULTS: In the virtual driving test, driving speed and lateral position were determined to be higher and bigger than in the real Driving test, respectively. Additionally, the virtual driving test reduces the concentration, anxiety, and reality when compared to the real driving test. The formula includes four variables to produce the calibration: tangent driving speed, curve driving speed, tangent lateral position, and curve lateral position. However, the tangent lateral position was excluded because it was not statistically significant . CONCLUSIONS: The results of analyzing the formula from MPB (mean prediction bias), MAD (mean absolute deviation) is after applying the formula to the virtual driving test, similar to the real driving test so that the formula works. Because this study was conducted on a national, two-way road, the road speed limit was 80 km/h, and the lane width was 3.0-3.5 m. It works in the same condition road restrictively.

주행 중 네비게이션 조작 상황에서 주행 속도와 네비게이션 위치에 따른 운전행동 및 안구운동 특성

홍승희(Seung-Hee Hong),강진규(Jin-Kyu Kang),김보성(Boseong Kim),민철기(Cheol-Kee Min),정순철(Soon-Cheol Chung),Shun'ich Doi, 민병찬(Byung-Chan Min) 한국산업경영시스템학회 2011 한국산업경영시스템학회지 Vol.34 No.4

The purpose of this study was to examine drivers' driving behaviors and eye-movements according to driving speed and navigation-position while operation of the navigation in driving. For this purpose, two driving conditions (low-speed and high-speed) and two navigation-positions (top and bottom location of the center console) were set. Drivers' driving behaviors (speed, speed variation, coefficient of variation, and the number of collisions) and eye-movements (overall eye pattern, the average scanning time of navigation, and the number of gaze-out on the road for more 2 seconds) were measured. As a result, when the navigation was located at the bottom of the console, difficulties of lateral control was appeared in low-speed driving condition, and the that of longitudinal control was appeared in high-speed driving condition. In addition, above situation made the drivers' scanning times of navigation long, increased the number of gaze-out on the road for more 2 seconds, and made overall eye pattern monotonous. These results could be interpreted that the manipulation of the navigation at the bottom of console cause reduced attention capacity due to the cognitive load.

가상주행과 실차주행의 운전자 주행행태 차이에 관한 연구

박진호,임준범,주성갑,이수범 한국도로학회 2015 한국도로학회논문집 Vol.17 No.2

PURPOSES : The use of virtual driving tests to determine actual road driving behavior is increasing. However, the results indicate a gap between real and virtual driving under same road conditions road based on ergonomic factors, such as anxiety and speed. In the future, the use of virtual driving tests is expected to increase. For this reason, the purpose of this study is to analyze the gap between real and virtual driving on same road conditions and to use a calibration formula to allow for higher reliability of virtual driving tests. METHODS : An intelligent driving recorder was used to capture real driving. A driving simulator was used to record virtual driving. Additionally, a virtual driving map was made with the UC-Win/Road software. We gathered data including geometric structure information, driving information, driver information, and road operation information for real driving and virtual driving on the same road conditions. In this study we investigated a range of gaps, driving speeds, and lateral positions, and introduced a calibration formula to the virtual record to achieve the same record as the real driving situation by applying the effects of the main causes of discrepancy between the two (driving speed and lateral position) using a linear regression model. RESULTS: In the virtual driving test, driving speed and lateral position were determined to be higher and bigger than in the real Driving test, respectively. Additionally, the virtual driving test reduces the concentration, anxiety, and reality when compared to the real driving test. The formula includes four variables to produce the calibration: tangent driving speed, curve driving speed, tangent lateral position, and curve lateral position. However, the tangent lateral position was excluded because it was not statistically significant . CONCLUSIONS: The results of analyzing the formula from MPB (mean prediction bias), MAD (mean absolute deviation) is after applying the formula to the virtual driving test, similar to the real driving test so that the formula works. Because this study was conducted on a national, two-way road, the road speed limit was 80 km/h, and the lane width was 3.0-3.5 m. It works in the same condition road restrictively.

속도에 대한 욕구좌절감이 운전자의 스트레스에 미치는 영향

이순열 ( Lee Sun-yeol ) 한국도로교통공단 2017 교통안전연구 Vol.36 No.-

This study was intended to recognize whether speed desire frustration influences in driving stress. Stress desire frustration is the difference between prefer speed and normal speed. As a result, driver's the prefer speed is higher than the normal speed on 4 road condition. Also, driver's speed desire frustration caused statistical effect in driving stress on 4 road condition. speed desire frustration effect Driving Stress Scale 5 sub-scale factors. This is that driver who experience much speed desire frustration creates high driving stress. Speed desire frustration analyzed high driver and low driver's Driving Stress Scale(DSS) score and overspeed regulation and traffic accident experience difference. As analysis result, speed desire frustration high driver driving stress high appear. However, difference of overspeed regulation experience or traffic accident experience by speed desire frustration did not appear.

속도저감형 시설이 차량 주행 속도에 미치는 영향 분석

강수철 ( Soochul Kang ),유순덕 ( Soonduck Yoo ),조규철 ( Gyucheol Cho ) 한국안전학회(구 한국산업안전학회) 2016 한국안전학회지 Vol.31 No.5

It has been applied several ways in order to prevent traffic accidents and speed management on the road which is one of very important factors to prevent accidents. In this study, it is analyzed whether the facility such as the flashing and crosswalk, speed cameras and intermittent warning signs affect on a driving deceleration or not. It has been shown that the flashing and crosswalk and speed cameras except intermittent warning signs play a role of reducing the driving speed. The result showed that these traffic safety facilities help to improve the average speed as well as velocity distribution which was derived by the speed deviation even if there were the difference between facilities. Speed limit display does not affect the deceleration of the driver. Therefore, it was founded in this research that there were the driving speed reduction effect due to the facilities on the road. In order to control the driving speed on the road, it is necessary to install facilities with appropriate location and spacing on the road. In addition, place that turns out suppressed speeding through speed management also are required adequate facilities such as speed cameras.

초보운전자의 운전확신수준 특성이 위험운전에 미치는 영향: 경로분석을 이용한 연구

이순열,이순철,박선진 한국문화및사회문제심리학회 2007 한국심리학회지: 문화 및 사회문제 Vol.13 No.3

초보운전자들은 교통사고 다발 집단 중 하나이며, 운전경험이 상대적으로 적기 때문에 이들의 운전확신수준이 운전행동에 미치는 영향은 다른 운전자들과 다르다. 본 연구는 초보운전자의 운전확신수준에 초점을 맞추어 초보운전자들의 운전확신수준과 과속운전, 음주운전, 가해교통사고의 관계를 밝혀내고 운전확신수준이 가해교통사고에 이르는 경로를 알아보고자 하였다. 192명의 초보운전자를 대상으로 운전확신수준질문지와 운전경험질문지를 실시하였다. 운전확신수준의 상황둔감성, 불안전운전, 주의집중소홀, 운전자신감 모두 초보운전자의 과속운전과 유의한 관계를 가지고 있었다. 특히, 상황둔감성은 과속운전뿐만 아니라 음주운전과 가해교통사고와도 관계가 있는 것으로 나타났다. 경로모형 분석결과, 운전확신수준은 초보운전자들의 과속운전을 22% 설명하고 있었으며, 음주운전과 가해교통사고를 각각 12%, 21% 설명하는 것으로 나타났다. 상황둔감성이 초보운전자들의 위험한 운전행동에 가장 큰 영향력을 가지는 것으로 나타났으며, 운전자신감이 과속운전을 통해 가해교통사고에 이르는 경로를 확인하였다. This study focused on novice drivers. Novice drivers get involved in more traffic accidents than the other drivers because of less driving experience. The aim of this study is to investigate the relationship between driving confidence levels and speeding, drunken driving, and traffic accidents. 192 drivers responded driving confidence levels questionnaire and driving experience items. ‘Circumstance Insensibility’, ‘Unsafe Driving’, ‘Incautious Driving’, and ‘Self-efficacy of Driving’ had significant relations with speeding in novice divers group. Especially, ‘Circumstance Insensibility’ showed a significant relation with speeding, drunken driving and traffic accidents. In the result of path analysis, driving confidence levels explained 22% of the speeding, 12% of the drunken driving and 21% of the traffic accidents in novice drivers group. ‘Circumstance Insensibility’ was most effective for traffic accidents of novice drivers. We verified that 'Self-efficacy of Driving' affects on traffic accidents via speeding.

주행속도선택 기반 주행위험도 평가방법론 개발 (차내 교통안전정보 제공 효과 평가를 중심으로)

김원철 대한교통학회 2011 대한교통학회지 Vol.29 No.1

This paper presents a Driving Risk Model (DRM) based on driving speed choices using an Ordered Response Probit (ORP) model. The DRM is conceptualized based on the relation between speed deviation and the occurrence of crashes found by Solomon. The impacts of various driving risk factors are revealed by applying the DRM to evaluate the effectiveness of In-Vehicle Traffic Warning Information (IVTWI) in expressway driving. Regarding driving risk, the results show that: (1) the risk is lower among male drivers, those with more driving experience and those with less accident history, (2) the risk is higher when driving takes place on wet road surface, in the afternoon, and under conditions of low traffic volume, and (3) the risk is also higher on both downgraded and long curve sections. Additionally, the results provide evidence that provision of IVTWI can decrease the driving risk. The proposed DRM provides a solution for assessing the traffic safety impacts of countermeasures on roadways when there is a shortage of traffic accidents data. 본 연구에서는 Solomon이 제안한 속도편차 (주행속도와 평균속도와의 차) 개념을 이용하여 주행위험도를 정립하고, 순서프로빗모형을 이용하여 주행속도선택 기반 주행위험도평가모델을 개발한다. 제안모델을 고속도로의 차내 교통안전정보 제공효과 평가실험에 적용하여, 주행위험에 미치는 다양한 요인의 효과를 분석한 결과, 다음과 같은 연구결과가 도출되었다. 첫째, 남성이 여성보다, 경력 운전자가 초보 운전자보다, 교통사고의 경험이 적은 운전자가 고속도로를 안전하게 주행할 확률이 높다. 둘째, 고속도로를 오후에 주행하는 경우, 도로표면이 젖어있는 경우, 교통량이 한산하여 서비스수준이 너무 좋은 경우 주행위험도는 증가한다. 셋째, 경사진 회전구간을 주행하는 경우와 도로연장이 긴 곡선부 구간을 주행하는 경우 주행위험도는 증가한다. 한편, 주행위험도 증가는 차내 교통안전정보를 제공함으로써 어느 정도 감소될 수 있는 것으로 나타나 차내 교통안전정보의 제공의 중요성이 확인되었다. 본 제안모델은 새로 도입된 교통안전시설물의 교통안전도 효과를 평가 시 교통사고 자료가 부족하거나 없는 경우 교통안전도를 평가하는데 활용할 수 있다.