• Database Research
• /
• v.34 no.3
• /
• pp.45-57
• /
• 2018

The drowsiness that occurs in the driving is a very dangerous driver condition that can be directly linked to a major accident. In order to prevent drowsiness, there are traditional drowsiness detection methods to grasp the driver's condition, but there is a limit to the generalized driver's condition recognition that reflects the individual characteristics of drivers. In recent years, deep learning based state recognition studies have been proposed to recognize drivers' condition. Deep learning has the advantage of extracting features from a non-human machine and deriving a more generalized recognition model. In this study, we propose a more accurate state recognition model than the existing deep learning method by learning image and PPG at the same time to grasp driver's condition. This paper confirms the effect of driver's image and PPG data on drowsiness detection and experiment to see if it improves the performance of learning model when used together. We confirmed the accuracy improvement of around 3% when using image and PPG together than using image alone. In addition, the multimodal deep learning based model that classifies the driver's condition into three categories showed a classification accuracy of 96%.

• Journal of Convergence for Information Technology
• /
• v.9 no.5
• /
• pp.27-33
• /
• 2019

Various technical and societal approaches are being made to realize the auto driving (AD) and cooperative driving (CD) including communication network and extended advanced driver support system is under development. In CD, it is important to share the roles of the driver and the system and to secure the stability of the driving, so a efficient interface scheme between the driver and the vehicle is required. This study proposes a research model including driver, system and driving environment considering the role and function of driver and system in CD. An efficient interface between the driver and the vehicle to cope with various driving situations on the CD using the analysis of the driving environment and the research model is also proposed. Through this study, it is expected that the proposed research model and interface scheme could contribute to CD system design, cockpit module development and interface device development.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.3
• /
• pp.361-370
• /
• 2017

In this paper, correlation analysis was performed between questionnaire and machine learning based aggressive tendency measurements. this study is part of a aggressive driver detection using machine learning and questionnaire. To collect two types tendency from questionnaire and measurements system, we constructed experiments environments and acquired the data from 30 drivers. In experiment, the machine learning based aggressive tendency measurements system was designed using a driver behavior detection model. And the model was constructed using accelerate and brake position data and hidden markov model method through supervised learning. We performed a correlation analysis between two types tendency using Pearson method. The result was represented to high correlation. The results will be utilize for fusing questionnaire and machine learning. Furthermore, It is verified that the machine learning based aggressive tendency is unique to each driver. The aggressive tendency of driver will be utilized as measurements for advanced driver assistance system such as attention assist, driver identification and anti-theft system.

• Journal of Korean Society of Transportation
• /
• v.25 no.3
• /
• pp.87-97
• /
• 2007

This paper proposes drivers' rational belief formation under a bounded traffic environment. This is to escape the criticism that excessive rationality (e.g., a driver's calculating ability and memory capacity) is required of drivers. Under bounded traffic environments. drivers do not have structural knowledge of traffic conditions and others' decisions. Simulations are carried out using a program coded in C. Consequently, the author found the learning process of drivers and the value of information can be differentiated by route conditions and the characteristics of driver groups. Also, it was found that rational drivers form different beliefs about traffic conditions even though they have the same traffic environment in a bounded traffic environment.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.11
• /
• pp.1201-1206
• /
• 2014

This paper presents the development of an event-based operator model of a wheel loader for virtual V-pattern working. The objective of this study is to analyze the performance and dynamic behavior of the wheel loader for a typical V-pattern. The proposed typical V-pattern working is divided into four stages. The developed operator model is based on eight events, and the operator's inputs are occurred sequentially by event. A 3D dynamic simulation model of the wheel loader is developed and used to analyze the dynamic behavior during working, and the simulation results are compared with the experimental data of V-pattern working. The proposed 3D dynamic simulation model and operator model are constructed using MATLAB/Simulink. The proposed operator model for V-pattern working is expected to enable evaluation of the working performance and dynamic behavior of the wheel loader.

• Journal of Korean Society of Transportation
• /
• v.26 no.6
• /
• pp.71-80
• /
• 2008

Typically uncontrolled intersections are characterized by the absence of signal, stop and yield sign, and by very light traffic volume. In this study, a gap acceptance model for such uncontrolled intersections has been modeled. The motivation is to identify the behavior of drivers so that the traffic flow phenomena can be easily understood. For this, actual traffic survey was accomplished at intersections in Suwon and the data have been fed into modeling process. The logit model was used and the results showed that total delay experienced by drivers, turning right movement, age, sex, and the existence of passenger affected gap acceptance. For example, male drivers, with experiencing longer delay and having passenger(s) with them, accepted shorter gaps. These identified characteristics regarding gap acceptance could be used for facility design and/or safety oriented traffic information dissemination near uncontrolled intersections.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.05a
• /
• pp.166-166
• /
• 2004

운전자 보조시스템에는 적응순항제어 (adaptive cruise control), 차선변경 (lane change), 충돌경고 (collision warning), 충돌회피 (collision avoidance), 및 자동주차 (automatic parking) 등이 있다. 이런 운전자 보조시스템은 어떤 목적을 가지고 있다. 운전자의 부담을 줄이고 안전을 위하여 차량의 주행방향에 있는 장애물이나 차량을 감지하여 차량간의 안전거리론 유지하고 자동차가 일정 속도를 유지하도록 한다. 운전자 보조시스템의 효율은 센서들로부터 얻어진 정보의 해석에 달려있다.(중략)

• Transactions of the Korean Society of Automotive Engineers
• /
• v.13 no.1
• /
• pp.76-82
• /
• 2005

In this paper, validation of Driver Steering Model has been conducted. The comparison between the simulation model and vehicle test results shows that the model is very feasible for describing combined human driver and actual vehicle dynamic behaviors. The 3D vehicle model is consisted of 6-DOF sprung mass and 4-quarter car model for vehicle body dynamics. Powertrain model including differential gear and Pacejka tire model are applied. The driver steering model is also validated with vehicle test result. The driver steering model is based on angle and displacement error from the desired path, recognized by driver.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.153-163
• /
• 2017

This research is based on the previous research that personally preferred safe distance, rotating angle and speed are differentiated. Thus, we use machine learning model for recognizing maneuvering modes trained per personal or per similar driving pattern groups, and we evaluate automatic driving according to maneuvering modes. By utilizing driving knowledge, we subdivided 8 kinds of longitudinal modes and 4 kinds of lateral modes, and by combining the longitudinal and lateral modes, we build 21 kinds of maneuvering modes. we train the labeled data set per time stamp through RNN, LSTM and Bi-LSTM models by the trips of drivers, which are supervised deep learning models, and evaluate the maneuvering modes of automatic driving for the test data set. The evaluation dataset is aggregated of living trips of 3,000 populations by VTTI in USA for 3 years and we use 1500 trips of 22 people and training, validation and test dataset ratio is 80%, 10% and 10%, respectively. For recognizing longitudinal 8 kinds of maneuvering modes, RNN achieves better accuracy compared to LSTM, Bi-LSTM. However, Bi-LSTM improves the accuracy in recognizing 21 kinds of longitudinal and lateral maneuvering modes in comparison with RNN and LSTM as 1.54% and 0.47%, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.173-182
• /
• 2021

In this paper, we analyzed driver's and passenger's motions that cause driver's distraction, and recognized 10 driver's behaviors related to mobile phones. First, distraction-inducing behaviors were classified into environments and factors, and related recent papers were analyzed. Based on the analyzed papers, 10 driver's behaviors related to cell phones, which are the main causes of distraction, were recognized. The experiment was conducted based on about 100,000 image data. Features were extracted through SURF and tested with three models (CNN, ResNet-101, and improved ResNet-101). The improved ResNet-101 model reduced training and validation errors by 8.2 times and 44.6 times compared to CNN, and the average precision and f1-score were maintained at a high level of 0.98. In addition, using CAM (class activation maps), it was reviewed whether the deep learning model used the cell phone object and location as the decisive cause when judging the driver's distraction behavior.