Driving Conditions Research Articles

Highly sensitive driver health condition monitoring system using nonintrusive active electrodes

Abstract The proposed electrocardiogram (ECG) measurement system uses a nonintrusive ECG sensor with electrically active electrodes to measure an ECG signal without any noise effects. In this manner, the optimal position and size of the active electrodes attached to a car seat can be selected from several practical scenarios considering the physical position of the subject's heart to minimize the noise effects for the nonintrusive ECG measurement system in the car. The ECG signals from a clothed and seated occupant of the automobile are measured at a sampling rate of 100 Hz. A signal conditioning circuit was also designed to reduce the noise effects generated by the internal circuitry. The ECG signals are measured and transmitted wirelessly to a base station connected to a server PC in a personal area network for signal processing. The driver's condition is monitored wirelessly and analyzed by performing a heart rate variability analysis in the time and frequency domains.

Young drivers’ perceptions of culpability of sleep-deprived versus drinking drivers

Introduction: Sleep-deprived driving can be as dangerous as alcohol-impaired driving, however, little is known about attitudes toward sleep-deprived drivers. This study examined the extent to which young drivers regard sleep-deprived compared to drinking drivers as culpable for a crash, and how their perceptions of driving while in these conditions differ. Method: University student participants (N=295; M=20.4years, SD=1.3; 81% women) were randomly assigned to read one of five fatal motor-vehicle crash scenarios, which differed by aspects of the driver's condition. Culpability ratings for the drinking driver were higher than those for the sleep-deprived driver. Results: Qualitative findings revealed that driving while sleep-deprived was viewed as understandable, and driving after drinking was viewed as definitely wrong. The dangers of sleep-deprived driving remain under-recognized.

Realization and Optimization of Embedded Driver Status Detection System

摘要: 提出了一种可以在嵌入式平台上实时运行的驾驶员状态检测算法. 状态检测采用了基于统计学习的Adaboost算法与动态建模算法. 与传统的采用主动红外光的方法相比, 本系统采用对人眼更为安全的被动式方法, 且对光线的变化有更好的鲁棒性. 算法的主要创新点是: 1) 提出了检测区域自适应调整的单双眼检测相结合的Adaboost人眼检测算法, 提高了人眼检测的准确性与速度; 2)提出基于高斯混合模型的人眼动态建模跟踪算法, 自动提取驾驶员眼睛区域灰度分布的信息, 实现了对不同驾驶员人眼的建模与跟踪定位. 在多个公共数据集以及实车采集的视频上进行的实验表明, 该算法能够准确判断驾驶员的状态, 满足实时处理的要求. 关键词: 嵌入式系统 / 驾驶员状态检测 / 人眼动态模型 / 人眼跟踪

The Need for Transition from Macroscopic to Microscopic Traffic Management Schemes to Improve Safety and Mobility

Traditionally, macroscopic (aggregated) traffic management schemes have been applying the principle of ‘one-sizefits-all’ without segmenting drivers based on their competence and level of performance. Road type, traffic environment, driver's physical conditions, mental load and others are some factors which influence the performance of vehicular control by drivers and contribute into tragic driver errors. This paper explores the impact of illperformances by drivers and technological devices to detect and correct the errors they make. A transition towards a microscopic (disaggregated) and driver-performance-responsive traffic management strategy is presented. VISSIM microscopic traffic simulation and Surrogate Safety Assessment Model (SSAM) are used to evaluate the potential benefits of the proposed traffic management strategy in terms of improved safety and traffic operations.

Extraction and Recognition Methods of Vehicle Driving Tendency Feature Based on Driver-vehicle-environment Dynamic Data under Car Following

Driving tendency is the comprehensive embodiment of driver's physiological and psychological characteristics. It reflects driver's psychological condition during the process of driving. Identification of the driving tendency has great significance to researching of the driver assistant system, especially the active security warning system. In this paper, data from simulative driving and real driving experiment of different drivers (risk-taking, cautious and conservative type, etc) under the state of car-following flow are obtained through questionnaires on psychological test. The feature eigenvectors with good ability to classify the type of driving tendency is extracted based on rough set theory. Dynamic recognition method of driving tendency is put forward with model calibration and verification making use of real data. The results of verification are compared with the results of the questionnaires. It is shown that the pattern recognition model is feasible, and can realize real-time recognition of the driver tendency under the state of car-following.

The Human Vehicle Interface System for Integrating and Managing the In-Vehicle Interactions with IT Devices

Objective: The aim of this study is to investigate the system to integrate and manage the in-vehicle interactions between the drivers and the in-vehicle mobile IT devices. Background: As the mobile IT technology is being used anywhere, the drivers are interacting with the mobile IT device on driving situations. The distraction of the driver's attention causes the car accidents. It is necessary to develop the HVI(Human Vehicle Interface System) to integrate and manage the in-vehicle interactions with IT devices. Method: The HVI System is designed not as the interfacing subject but as the supervising system to monitor the driver's status and support the driver to concentrate on the primary tasks. The HVI system collects the status information of the car and driver and estimate the driving workload. Results: The HVI system controls how to provide the output information based on the driving workload. We implemented the HVI system prototype and applied in the real vehicle with the HVI cell phone and the HVI car navigation system. Conclusion: Depending on the driving situations, the HVI system prevented the information output in dangerous situation and diversified the modality and the intensity of the output information. Application: We will extend the HVI system to be connected the other various IT devices and verity the effectiveness of the system through various experiments.

Long-term social outcome in children with moyamoya disease who have reached adulthood

Although the reported surgical outcome is favorable, there is little information regarding the long-term quality of life in pediatric patients with moyamoya disease (MMD) when they grow to adulthood. The authors conducted a survey to provide details of social adaptation and satisfaction in adults who underwent revascularization surgery for MMD during childhood. One hundred twenty-three patients with MMD who had undergone surgery during childhood and were older than 18 years of age were recruited for this study. The authors mailed self-administered questionnaires regarding each patient's education, employment, marriage, driver's license, physical condition, and satisfaction. Sixty-five patients (53%) responded. Compared with the general population, the patients showed a similar rate of attaining a higher education. Forty-nine (80%) of 61 patients who were not currently high school students had entered college or university. However, the presence of neurological deficits on preoperative examination was a negative predictor of entrance into a college or university, as well as employment. Some patients had difficulty in planning marriage because of physical handicaps, and the rate of acquiring a driver's license and actual driving were relatively low. Approximately 80% of the responders were satisfied with their treatment outcomes, but more than one-half reported subjectively assessed neurological problems. In this study, pediatric patients with MMD showed favorable social adaptation in adulthood. The findings also indicated that early diagnosis and intervention before the establishment of neurological deficits are essential to children with MMD in becoming better socially adapted. Further, more thorough clinical examinations are required during follow-up in patients with MMD.

Influences on Sponsorship Deals in NASCAR: Indirect Evidence from Time on Camera

When corporate sponsors want to maximize their exposure, they often focus sponsorship dollars on events, teams, and athletes that will prove to be reliable, respectable, and, most important, repetitive advertising outlets. Analyzing the factors that increase a broadcaster’s propensity to display a sponsor during television broadcasts is often hard to measure. Using a unique data set describing NASCAR broadcasts, we indirectly analyze what influences the value of a sponsorship contract through a proxy for driver sponsorship value: the value of time on camera. We find that the value of time on camera is influenced by driver performance and their celebrity status, as measured by driver experience and inherited brand-name capital. Although the values of individual sponsorship contracts are generally not reported, the evidence herein suggests that driver performance and status likely influence the value of NASCAR sponsorship contracts.

Karakteristik Kecelakaan Transportasi Di Jalan Tol Ruas Jakarta-Cikampek

T1re advantages of toll road as the highwm; tend 111£lke tire driver tend to ignor the safehJ endangeredhimself and others. T1rerefore, it needs many efforts to minimize the possibility of an aaident. T1re tollroad accident frequently happened on tire Jaka.rta-Okampek toll road. The number and level of accidentson this toll road quite high. 'Dre approach used in this research is descriptive analysis of thepercentage bi; using priman; survei; and secondan; data collected from accident reports PT.JasaMarga which is tire depiction of the location of aaident research at Jaka.rta-Cikampek toll road.From tire research, tire causes of accidents at aaident prone areas in tire Jakarta-Cikampek toll road isdue to the driver's condition factor (79.7%), damage to vehicles (19.4%) and road conditions (0.14%).Descriptively driver who had an aaident on tire toll roads is largely caused bi; lack of anticipation(60.8%). The most frequent accident occun'ence time between of 12:00 to 18:00 P.M. T1re truck is avehicle h;pe that is often involved in aaiden.ts. Front of the rear end collision is tire most common h;peof aaident. Accidents more frequently in sunny ·weather conditions.At the Jakarta-Cikampek toll road there are some segments which include the accident spot km 12 -km 14 for Jakarta route toward Cikampek and km 10 - km 14, km 25 - km 27 and km 29 - km 30 fortire reverse direction. Dominating factor in the location of tire critical points including the driver's lackof anticipation, tire driver's drowsiness and the tires burst.

Development of a drowsiness warning system based on the fuzzy logic

Nowadays, driving support systems, such as car navigation systems, are getting common, and they support drivers in several aspects. It is important for driving support systems to detect status of driver's consciousness. Particularly, detecting driver's drowsiness could prevent drivers from collisions caused by drowsy driving. In this paper, we discuss a system and a method for detecting driver's drowsiness, which uses the Image processing and Fuzzy logic to detect Driver‟s drowsiness.

Identifying Driver Characteristics Influencing Overtaking Crashes

Objective: To identify the most important driver characteristics influencing crash-causing overtaking maneuvers on 2-lane, 2-way rural roads of Iran. Methods: Based on the crash data for rural roads of Iran over 3 years from 2006 to 2008, the classification and regression tree (CART) method combined with the quasi-induced exposure concept was applied for 4 independent variables and one target variable of “driver status” with 2 classes of at fault and not at fault. The independent variables were vehicle type, driver's age, driving license, and driving experience of the driver—the latter 2 driver characteristics are relatively new in traffic safety studies. Results: According to the data set, 16,809 drivers were involved in 2-lane, 2-way rural roads overtaking crashes. The analysis revealed that drivers who are younger than 28 years old, whose driving license is type 2—a common driving license that is for driving with passenger car and light vehicles—and whose driving experience is less than 2 years are most probably responsible for overtaking crashes. Conclusion: It was indicated that vehicle type is the most important factor associated with drivers being responsible for the crashes. The results also revealed that younger drivers (18–28 years) are most likely to be at fault in overtaking crashes. Therefore, enforcement and education should be more concentrated on this age group. Due to the incompliant nature of this group, changing the type and amount of traffic fines is essential for more preventing objectives. The research also found 2 relatively new factors of driving license and driving experience to have considerable effects on drivers being at fault, such that type 2 licensed drivers are more responsible compared to type 1 (a driving license for driving with all motor vehicles, which has some age and experience requirements) licensed drivers or drivers with a special license (a driving license with special vehicle types). Moreover, drivers with less than 2 years’ driving experience are more responsible for these kind of crashes; thus prohibiting new drivers from driving on rural roads for new drivers seems substantial.

Female involvement in U.S. nonfatal crashes under a three-level hierarchical crash model

Men have long held the lead in motor-vehicle crashes; however, research indicates that women are closing the gap. To further investigate this problem, we applied a hierarchical model to investigate female involvement in fatal crashes in the United States. The hierarchical model recognizes that decisions at higher levels affect the decisions at lower levels. At the top level, the model assumes that the driver's condition (e.g., inattention, fatigue, impairment) affects the next level (e.g., speeding or other failures to obey traffic laws), which subsequently affects the basic maneuvering skills (i.e., the lowest level) were either nonexistent, or largely explained by gender differences in alcohol consumption. We found that although female involvement in skill-related crashes was not different from that of males, females were more likely than males to apply wrong maneuvers when speeding was involved. We also found that the most important contributing factor to gender differences in nonfatal crashes can be traced back to gender-based differences in alcohol consumption.

Information fusion for robust ‘context and driver aware’ active vehicle safety systems

Although there is currently significant development in active vehicle safety (AVS) systems, the number of accidents, injury severity levels and fatalities has not reduced. In fact, human error, low performance, drowsiness and distraction may account for a majority in all the accident causation. Active safety systems are unaware of the context and driver status, so these systems cannot improve these figures. Therefore, this study proposes a ‘context and driver aware’ (CDA) AVS system structure as a first step in realizing robust, human-centric and intelligent active safety systems. This work develops, evaluates and combines three sub-modules all employing a Gaussian Mixture Model (GMM)/Universal Background Model (UBM) and likelihood maximization learning scheme: biometric driver identification, maneuver recognition, and distraction detection. The resultant combined system contributes in three areas: (1) robust identification: a speaker recognition system is developed in an audio modality to identify the driver in-vehicle conditions requiring robust operation; (2) narrow the available information space for fusion: maneuver recognition system uses estimated driver identification to prune the selection of models and further restrict search space in a novel distraction detection system; (3) response time and performance: the system quickly produces a prediction of driver’s distracted behaviour for possible use in accident prevention/avoidance. Overall system performance of the combined system is evaluated on the UTDrive Corpus, confirming the suitability of the proposed system for critical imminent accident cases with narrow time windows.

The effect of the driving activity on target detection as a function of the visibility level: Implications for road lighting

The small target visibility model used in road lighting design is based on a strong simplification of the driving task. To specify the driver's visibility needs in a way consistent with state-of-the-art lighting engineering practice, a field experiment was designed in order to investigate target detection performances, comparing driver and passenger status conditions. Sixteen target visibility levels (VL) were used. In the driver status, 34 participants had to press a button as soon as they detected the target stimulus placed on the experimental lighted section. In the passenger status, the same participants had to detect the target stimulus while the experimenter drove. The results show that the passengers' performances (detection distance) were higher than the drivers' performances (p = .0014). Furthermore, the higher the VL, the higher the detection distance (p < .0001). These results lead up to modify the reference scenario in order to take into account human factor components for road lighting design.

1E3-1 シートに取り付けた脈波計測用エアパックセンサーの設置位置と精度の検討(GS4:生体計測・医学機器,一般セッション)

We have been working on a project on "Development of the drive dozing prevention technique using the sensor installed in the seat for detecting the driver's condition" for about five years. As a non-invasive sensor equipped with a drivers' seat for passenger cars, we developed so called "air pack sensor" which is expected to an alternative of finger plethysmogram. In the previous paper, mathematical modeling for air pack sensor was conducted and the method for extracting the heart rate signal from the signal obtained by the air pack sensor was proposed. In this paper, we mainly investigated the relation between the effect of the sensor position and the accuracy.

Does the built environment affect when American teens become drivers? Evidence from the 2001 National Household Travel Survey

Problem Motor vehicle crashes are the most common cause of death for American adolescents. However, the impact of where teens live on when they begin driving has not been studied. Method Data from the 2001 National Household Travel Survey were used to estimate the effect of residential density on the driver status of teens aged 16 to 19 years after matching on demographic characteristics. Results Controlling for demographic characteristics, 16 and 17 year old teens in high density neighborhoods had driver rates 15 percentage points below teens living in less dense areas (p < 0.001). The effect for 18 and 19 year olds was a 9 percentage point decrease (p < 0.001). Summary These results suggest teens living in less dense and more sprawling communities initiate driving at a younger age than comparable teens in compact areas, placing them at increased risk for crash related injuries. Impact on Industry: The role of environmental factors, such as neighborhood walkability and provision of transit, should be considered in young driver programs.

Recklessness in Context

Traffic-related injury and fatality are major health risks in the United States and worldwide. One contributor to road accidents is unsafe and aggressive driving practices. We examined individual and situational aspects of aggressive driving by having 152 undergraduate students complete self-report measures. Aggressive driving was related to personality variables, such as hostility, sensation seeking, and competitiveness, as well as to social variables such as driving without passengers and characteristics of the target vehicle (e.g., passengers, age, and status of driver), environmental variables (e.g., type of road, traffic, and weather), and temporal variables (e.g., time pressure and time of day).

Implementation of Safety Driving System Using e-Health and Telematics Technology

This research aimed to develop a safety driving system using e-health and telematics technology. Biosignal sensors were installed in an automobile to check the driver's health status with an automatic diagnosis system providing health information to the driver. Measured data were sent to the e-health center through a telematics device, and a medical doctor analyzed these data, sending diagnosis and prescription information to the driver. This system recognizes the driver's sleeping, drinking impairment, excitability, and fatigue using biosensors. The system initially provides alerts in the automobile. It also controls the driving environment in the car, searches for a highway service area using Global Positioning System (GPS), and provides additional information for safety driving. If a car accident has occurred, it makes an emergency call to the nearest hospital, emergency center, and insurance company. A conceptual and prototype model for an imbedded system is presented with initial data for driver condition. Such a system could prevent car accidents caused by drivers driving while intoxicated and falling asleep at the wheel using the driver's biosignals measured by biosensors. The system can provide various e-health services using a telematics system to enhance the technical compatibility of the automobile.

2C1-2 シートに取り付けた脈波計測用エアパックセンサーのモデリング(身体運動の計測とモデリング,一般講演)

We have been working on a project on "Development of the drive dozing prevention technique using the sensor installed in the seat for detecting the driver's condition" for about five years. As a non-invasive sensor equipped with a drivers' seat for passenger cars, we developed so called "air pack sensor" which is expected to an alternative of finger plethysmogram. In this paper, mathematical modeling for air pack sensor is explained in detail. In addition, the method for extracting the heart rate signal from the signal obtained by the air pack sensor is shown and the results are compared with the waveform obtained by finger plethysmogram.

349 生体信号を用いた飲酒・非飲酒状態検知に関する研究

Recently, a system which can monitor a car driver's biological condition and warn the driver of drowsiness is being proposed. Many researchers have presented evidence that biological signals like brain waves, pulsation waves, and cardiac beat, are different between a normal state and a drinking state of a person beforehand. However, current systems to measure those signals are assumed to be used in a laboratory or with invasive monitoring. A basic theory of the system that prevents drunken driving beforehand is constructed by establishing a new algorithm that distinguishes the person's state and ordinary drinking.