• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.11
• /
• pp.537-542
• /
• 2017

Aggressive driving is a major cause of car accidents. Previous studies have mainly analyzed young driver's aggressive driving tendency, yet they were only done through pure clustering or classification technique of machine learning. However, since elderly people have different driving habits due to their fragile physical conditions, it is necessary to develop a new method such as enhancing the characteristics of driving data to properly analyze aggressive driving of elderly drivers. In this study, acceleration data collected from a smartphone of a driving vehicle is analyzed by a newly proposed ECA(Enhanced Clustering method for Acceleration data) technique, coupled with a conventional clustering technique (K-means Clustering, Expectation-maximization algorithm). ECA selects high-intensity data among the data of the cluster group detected through K-means and EM in all of the subjects' data and models the characteristic data through the scaled value. Using this method, the aggressive driving data of all youth and elderly experiment participants were collected, unlike the pure clustering method. We further found that the K-means clustering has higher detection efficiency than EM method. Also, the results of K-means clustering demonstrate that a young driver has a driving strength 1.29 times higher than that of an elderly driver. In conclusion, the proposed method of our research is able to detect aggressive driving maneuvers from data of the elderly having low operating intensity. The proposed method is able to construct a customized safe driving system for the elderly driver. In the future, it will be possible to detect abnormal driving conditions and to use the collected data for early warning to drivers.

• KIPS Transactions on Computer and Communication Systems
• /
• v.1 no.2
• /
• pp.71-78
• /
• 2012

The digital tachograph is a device that automatically records speed and distance of a vehicle, together with the driver's activity and vehicle status at an accident. It records vehicle speed, break status, acceleration, engine RPM, longitude and latitude of GPS, accumulated distance, and so on. European Commission regulation made digital tachographs mandatory for all trucks from 2005. Republic of Korea made digital tachographs mandatory for all new business vehicles from 2011 and is widening the range of vehicles that must install digital tachographs year by year. This device is used to analyze driver's daily driving information and car accidents. Under a car accident that makes the device reliability unpredictable, it is very important to store driving information with maximum reliability for its original mission. We designed and implemented a practical digital tachograph. This paper presents a storage scheme that consists of a first storage device with small capacity at a high reliability and a second storage device with large capacity at a low cost in order to reliably records data with a hardware at a low cost. The first storage device records data in a SLC NAND flash memory in a log-structured style. We present a reverse partial scan that overcomes the slow scan time of log-structured storages at the boot stage. The scheme reduced the scan time of the first storage device by 1/50. In addition, our design includes a scheme that fast stores data at a moment of accident by 1/20 of data transfer time of a normal method.

• Journal of Internet of Things and Convergence
• /
• v.8 no.6
• /
• pp.55-63
• /
• 2022

In recent years, with the rapid development of large and medium-sized urban rail transit in China, the total operating mileage of high-speed railway and the total number of EMUs(Electric Multiple Units) are rising. The system complexity of high-speed EMU is constantly increasing, which puts forward higher requirements for the safety of equipment and the efficiency of maintenance.At present, the maintenance mode of high-speed EMU in China still adopts the post maintenance method based on planned maintenance and fault maintenance, which leads to insufficient or excessive maintenance, reduces the efficiency of equipment fault handling, and increases the maintenance cost. Based on the intelligent operation and maintenance technology of PHM(prognostics and health management). This thesis builds an integrated PHM platform of "vehicle system-communication system-ground system" by integrating multi-source heterogeneous data of different scenarios of high-speed EMU, and combines the equipment fault mechanism with artificial intelligence algorithms to build a fault prediction model for traction motors of high-speed EMU.Reliable fault prediction and accurate maintenance shall be carried out in advance to ensure safe and efficient operation of high-speed EMU.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.51-58
• /
• 2022

Drivable area detection, one of the main functions of advanced driver assistance systems, means detecting an area where a vehicle can safely drive. The drivable area detection is closely related to the safety of the driver and it requires high accuracy with real-time operation. To satisfy these conditions, V-disparity-based method is widely used to detect a drivable area by calculating the road disparity value in each row of an image. However, the V-disparity-based method can falsely detect a non-road area as a road when the disparity value is not accurate or the disparity value of the object is equal to the disparity value of the road. In a road environment including vegetation, such as a highway and a country road, the vegetation area may be falsely detected as the drivable area because the disparity characteristics of the vegetation are similar to those of the road. Therefore, this paper proposes a drivable area detection method and hardware architecture with a high accuracy in road environments including vegetation areas by reducing the number of false detections caused by V-disparity characteristic. When 289 images provided by KITTI road dataset are used to evaluate the road detection performance of the proposed method, it shows an accuracy of 90.12% and a recall of 97.96%. In addition, when the proposed hardware architecture is implemented on the FPGA platform, it uses 8925 slice registers and 7066 slice LUTs.

• Journal of the Society of Disaster Information
• /
• v.18 no.3
• /
• pp.622-635
• /
• 2022

Purpose: Due to the change of demography, the ratio of senior drivers has increased and the transition to a super-aged society is expected to make more seniors drive in the future. Method: In this research, we analyzed medical characteristics of the driver's age-specific decline in body function and saw that both the function of the physical as well as mental capacities deteriorates as people age. Among them, various functions are precipitously weakened after reaching 70, implying that those over the age of 70 are classified as seniors in a medical sense. In this context, we also could identify that based on such age criteria, various safety policies for senior drivers should be developed and set up in Korea. Result: We could find a steep fall in the physical function of body after reaching 70 from the chronological change of cognitive function and judgment ability. In particular, it is revealed that the driving license institution and aptitude test for drivers over 70 should be thoroughly examined, as physical functions necessary for driving such as eyesight and hearing ability is not strong enough in many drivers over 70. Conclusion: Focusing on the physical capacity to drive, we tried to find the hazardous age bracket of senior drivers which might influence driving behaviors. Going forward, we expect this work would help to understand the policies for senior drivers and drivers' physical differences.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.224-226
• /
• 2016

With the technical development and rapid increase of private demand, the new market for unmanned vehicle combined with the characteristics of 'unmanned automation' and 'vehicle' is rapidly growing. Even though the pilot driving is currently allowed in some countries, there is no country that has institutionalized the formal driving of self-driving cars. In case of the existing vehicles, safety incidents are frequently happening due to the frequent malfunction of the rear sensor, blind spot of the rear camera, or drivers' carelessness. Once such minor flaws are complemented, the relevant regulations for the commercialization of self-driving car and small drone could be relieved. Contrary to the ultrasonic and laser sensors used for the existing vehicles, this paper aims to attempt the distance measurement by using the depth sensor. A depth camera calculates the distance data based on the TOF method calculating the time difference by lighting laser or infrared light onto an object or area and then receiving the beam coming back. As this camera can obtain the depth data in the pixel unit of CCD camera, it can be used for collecting depth data in real-time. This paper suggests to solve problems mentioned above by using depth data in real-time and also to design the obstacle avoidance system through distance measurement.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.5
• /
• pp.23-29
• /
• 2015

In this study, human is the subject of driving a car, the actual EEG is a biological information in a number of reactions that are displayed while driving the vehicle by using a measuring device, occurs during travel of the road EEG to be collected, number of experiments the collected material on the basis of changes associated with running time, extracts the factors such as changes due to road geometry, and analysis was performed. The required changes in the EEG occurring during traveling experiment analysis alpha (${\alpha}$) waves, beta (${\beta}$) wave, after the primary extraction in the form of gamma (${\gamma}$) faction, the brain wave frequency of the entire period of the experiment change rate extracts, to calculate the change in frequency in response to EEG characteristics by applying the regression model to observe a learning effect in response to an increase in the number of experiments, as a result, depending on the number of experiments, EEG changes due to individual differences. The show, by repeatedly driving a section like this, it was possible to verify that comfortably travels driver accustomed in accordance with the stored road geometry and signal, safety facilities.

• Science of Emotion and Sensibility
• /
• v.23 no.2
• /
• pp.103-120
• /
• 2020

Using driving simulation, this study investigated the effects of driver's trust in the adaptive cruise control (ACC) system and road density on driver's workload and situation awareness. The drivers were allocated into one of four experimental conditions manipulated by ACC system trust level (trust-increased vs. trust-decreased) and road congestion (high vs. low). The workload and situational awareness of the participants were measured as dependent variables. The results showed followings. First, trust-decreased group for the ACC system had significantly lower trust scores for the system in all of the measurement items, including reducing the driving load and securing safe driving due to the use of this system, than the trust-increased group. Second, the trust-decreased group showed a slower reaction time in the secondary tasks and higher subjective workload than trust-increased group. Third, in contrast, the situational awareness for the driving situation was significantly higher in the trust-decreased group than trust-increased group. The results of this study showed that the driver's trust in the ACC system can affect the various information processing performed while driving. Also, these results suggest that trust in the user's system should be considered as an important variable in the design of an automated driving assistance system.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.21 no.6
• /
• pp.185-195
• /
• 2017

In recent years, unexpected bridge fire accidents have increased because of augmenting the number of traffic volumes and hazardous materials by the increment in traffics and distribution business. Furthermore, in accordance with the effort of using the under space of bridges, the ratio of occupied by combustible materials like oil tanker or lorry has been increased. As a result, the occurrence of bridge fire has been growing drastically. In order to mitigate the accident of bridge fire, risk assessment of bridge fire has been studied, however, practical risk models considering safety from users' viewpoints were scarce. This study represented quantitative risk assessment model applicable to national road bridges in Korea. The primary factors with significant impacts on bridge fire accidents was chosen such as clearance height, materials of bridges, arrival time of fire truck and fire intensity. The selected factors were used for Fire Dynamics Simulation (FDS) and the peak temperature calculated by FDS in accordance with the fire duration and fire intensity. The risk assessment model in bridge fire reflected the FDS analysis results, the fire damage criteria, and the grade of fire truck arrival time was established. Response plans for bridge fire accidents according to the risk assessment output has been discussed. Lastly, distances between bridges and fire stations were calculated by GIS network analysis. Based on the suggested assessment model and methodology, sample bridges were selected and graded for the risk assessment.

• Journal of Digital Convergence
• /
• v.15 no.12
• /
• pp.313-321
• /
• 2017

Traffic accidents in the country have steadily increased. Although IOT technologies have been applied so as to prevent the primary accident, practical solutions to prevent the secondary accident have not been suggested. A general guideline is simply recommended. In this paper, utilizing existing communication technology, we implement a proposed model and its simulation to prevent the secondary accident. When it is possible for a driver to secure visibility, the secondary accident can be prevented; In areas like tunnel, mountain terrain, and curve road with heavy traffic, where the driver has difficulty in securing the visibility, the secondary accident rates after the primary accident have been increasing. Therefore, we implement an accident prevention system that determines the primary accident utilizing sensor technology and prevents the secondary accident communicating through V2V or V2I. After the simulation, we found that the proposed model and the existing model made no difference with regard to the secondary accident rates when the visibility of the driver is secured; With the application of the proposed model, however, the accident rates decreased for 3-7 percent even though the visibility and communication were not secured.