Driving Conditions Research Articles

Evaluation of driver status in autonomous vehicles: using thermal infrared imaging and other physiological measurements

Evaluation of driver status in autonomous vehicles: using thermal infrared imaging and other physiological measurements

Design and Implementation of a Drowsiness-Fatigue-Detection System Based on Wearable Smart Glasses to Increase Road Safety

This paper proposes a drowsiness-fatigue-detection system based on wearable smart glasses to increase road safety. The proposed system is composed of a pair of wearable smart glasses, an in-vehicle infotainment telematics platform, an on-board diagnostics-II-based automotive diagnostic bridge, an active vehicle rear light alert mechanism, and a cloud-based management platform. A dedicated miniature bandpass infrared (IR) light sensor is also proposed and implemented for the low-cost, lightweight, wearable smart glasses, which can provide a higher signal-to-noise ratio than a general commercial IR light sensor, minimize the ambient environmental light image, and efficiently increase the accuracy of detection. The proposed system can detect the status of the vehicle driver with respect to drowsiness or fatigue conditions in real time. When drowsiness or fatigue is detected, the active vehicle real light alert mechanism will automatically be flickered to alert following vehicles. The related information will also be concurrently transmitted to a cloud-based management platform. As a result, the proposed system can lead to increased road safety.

Drivers Drowsiness Detection with Speed Limiter Integrated Fatigue Anlyzer (SLIFA) on Fuel Tank Truck

Traffic accident is becoming the most serious problem in Indonesia as it happens every day and every time. It was proved by increasing fatalities from 321,301 to 85,596 accident cases. It means that there are 10 road fatalities per day. There are several factors that cause traffic accident, such as external 34%, attitude 24%, fatigue 20%, over speed 17% and technical vehicle 5%. Other factors might be caused by rapid growth of vehicles and industries which increase significantly. The average annual vehicle growth from 1996 to 2006 is 20% , which might take a higher possibility in increasing road fatalities. The method is to pair SLIFA on the fuel tank truck engine to control the driver's physical condition through the heartbeat of the driver with a sensor that has been placed directly in front of the driver and when the driver drowsiness speed will decrease up to 30 km /h. The result of this research is the decrease of accident ignored by sleepy driver from shift of incident data during January-Juny 2016 period there are 51 cases of Shift of incident that is in morning 20%, afternoon 33%, night 25%, daylight 22%, then after the SLIFA pair decreased the case shift of incident to 39 cases, consisting of 13% morning, 59% afternoon, night 23% and daylight 5%, a total decrease in incident shift by 76% in July 2016-January 2017 so SLIFA to be very effective at attach to the fuel tank truck in reducing the drivers drowsiness. What needs to be done in future research is how to get SLIFA integrated with image processing.

Fatigue Driving Detection Based on Machine Learning and Image Processing Technology

Fatigue driving is a major cause of traffic accidents. If fatigue driving can be detected and stopped in time, perhaps traffic accidents will be reduced. This paper proposes a fatigue driving detection algorithm using machine learning and image processing technology. The algorithm is designed to run on the vehicle’s smart terminal. In the algorithm, terminal has to analyze the status of driver’s eyes, nose and mouth using machine learning and image processing technology. When catch typical behaviors such as blink, yawn and nod, terminal will record the time and calculate the frequencies of these behaviors. If one of the frequencies is greater than the threshold, terminal will trigger the alert and take measures to make driver no longer fatigue driving. The algorithm works fine in the experiment. The experimental accuracy of the algorithm is 94%.

Drowsiness monitoring based on steering wheel status

Drowsy driving is one of the main causes of road traffic accidents. It is of great significance to study the use of steering wheel status to detect the drowsiness of the driver. In the studies of the steering wheel state, there is a general problem of the parameter selection being not comprehensive and individual differences in the way of the controlling of the steering wheel not being considered. A driving simulator was used to collect eleven parameters related to the steering wheel, where four parameters having significant correlations with driver status were selected using variance analysis. A multilevel ordered logit (MOL) model, support vector machine (SVM) model and BP neural network (BP) model were built based on the selection of the parameters. Under the same conditions of classification, the recognition accuracy of the MOL model was shown to be much higher than that of the two other models. It was concluded that the MOL model using the steering wheel parameters and considering differences among individuals outperforms the others in terms of driver's state recognition.

KEHIDUPAN SOSIAL EKONOMI MASYARAKAT SEKUPANG YANG BERPROFESI SEBAGAI SUPIR TAKSI TAHUN 2010 s/d 2016

This research is a descriptive qualitative research with social and economic science approach. The method used there are several stages including (1) data collection techniques consist of observation, interview and documentation (2) data analysis consisting of data reduction, data presentation and conclusion (3) data validity by using data triangulation technique. This research indicates that the factors driving people to choose the profession as a taxi driver because in the former this profession has a high income, according to the infoman in the 90's only job there is taxi driver taxi jobs, and his working time in this profession is flexible and has no contract work. Taxi drivers in Sekupang Sub-district average their education is graduated from junior high school to high school. Religion owned by taxi drivers in Sekupang Sub-district is more dominant in Islam, but it is not possible that there is no religion. The number of children owned by each taxi driver in Sekupang District consists of two people up to three children in one family. The marital status of each taxi driver in Sekupang Sub-district is already family. Old Tiban people who work as a taxi driver in the district Sekupang not have health insurance, they use personal money if they need medical treatment. Taxi drivers in Sekupang Sub-district come from a variety of regions, but more dominates many who come from the West Sumatra region. Revenue that can be obtained decreased slightly compared to income in the early 90's, which in a day only get Rp. 50,000 to Rp. 100,000.Keywords: Socio-Economic Life, Taxi Driver, Sekupang Sub-district

Surveillance of traffic incident management–related occupational fatalities in Kentucky, 2005–2016

ABSTRACTObjective: Traffic incidents occurring on roadways require the coordinated effort of multiple responder and recovery entities, including communications, law enforcement, fire and rescue, emergency medical services, hazardous materials, transportation agencies, and towing and recovery. The objectives of this study were to (1) identify and characterize transportation incident management (TIM)-related occupational fatalities; (2) assess concordance of surveillance data sources in identifying TIM occupations, driver vs. pedestrian status, and occupational fatality incident location; and (3) determine and compare U.S. occupational fatality rates for TIM industries.Methods: The Kentucky Fatality Assessment and Control Evaluation (FACE) program analyzed 2005–2016 TIM occupational fatality data using multiple data sources: death certificate data, Collision Report Analysis for Safer Highways (CRASH) data, and media reports, among others. Literal text analysis was performed on FACE data, and a multiple linear regression model and SAS proc sgpanel were used to estimate and visualize the U.S. TIM occupational mortality trend lines and confidence bounds.Results: There were 29 TIM fatalities from 2005 to 2015 in Kentucky; 41% of decedents were in the police protection occupation, and 21% each were in the fire protection and motor vehicle towing industries. Over one half of the TIM decedents were performing work activities as pedestrians when they died. Media reports identified the majority of the occupational fatalities as TIM related (28 of 29 TIM-related deaths); the use of death certificates as the sole surveillance data source only identified 17 of the 29 deaths as TIM related, and the use of CRASH data only identified 4 of the 29 deaths as TIM related. Injury scenario text analysis showed that law enforcement vehicle pursuit, towing and recovery vehicle loading, and disabled vehicle response were particular high-risk activities that led to TIM deaths. Using U.S. data, the motor vehicle towing industry had a significantly higher risk for occupational mortality compared to the fire protection and police protection industries.Conclusions: Multiple data sources are needed to comprehensively identify TIM fatalities and to examine the circumstances surrounding TIM fatalities, because no one data source in itself was adequate and undercounted the total number of TIM fatalities. The motor vehicle towing industry, in particular, is at elevated risk for occupational mortality, and targeted mandatory TIM training for the motor vehicle towing industry should be considered. In addition, enhanced law enforcement roadside safety training during vehicle pursuit and apprehension of suspects is recommended.

Driver ECG Measuring System With a Conductive Fabric-Based Dry Electrode

The dry electrodes that the automotive manufacturers use to measure electrocardiogram (ECG) signals for driver status monitoring have three technical problems: a lack of attachment flexibility, low ECG signal detection stability, and the potential to harm or irritate the driver. In addition, the complicated signal-conditioning circuits employed by automotive manufacturers to improve the SNR, increase the ECG signal detection stability, and to ensure a wider dynamic range of the electrodes increase the cost and complexity of driver ECG measuring systems. In this paper, we propose a driver ECG measuring system that resolves these three technical issues using a steering wheel covered with a conductive fabric-based dry electrode material, which is manufactured by an electroplating method. In addition, we employ a conductive fabric-shaping procedure in the development of the fabric-based dry electrode to improve the attachment flexibility and to reduce the cost and complexity of the required signal-conditioning circuit. We verify the ECG signal-measuring performance of the proposed system by comparing it with ECG signal measurement results from a clinical ECG monitoring system. In addition, despite applying a simpler signal conditional circuit than those used in conventional ECG measuring systems, we verify that the proposed system achieves higher SNR and ECG signal detection stability than conventional ECG measuring systems through various field tests in actual driving environments.

Globo H expression is associated with driver mutations and PD-L1 expressions in stage I non-small cell lung cancer.

Globo H is a tumor-associated carbohydrate antigen exclusively expressed in cancer cells rather than normal tissue. Globo H has been found on many cancers of epithelial origins, and become an attractive target for cancer vaccine. We aimed to study the expression of Globo H in non-small cell lung cancer (NSCLC) patients, and correlated its expression with common driver mutations, clinical outcomes, and status of immune checkpoint, programmed death-ligand 1 (PD-L1). The study enrolled 228 patients with surgically resected stage I NSCLC, including 139 patients with adenocarcinoma (ADC) and 89 patients with squamous cell carcinoma (SqCC). Using immunohistochemistry, tumors with moderate to strong membranous staining in ⩾ 1% tumor cells per section were scored as positive Globo H expression. Driver mutations including EGFR, KRAS, BRAF were detected by direct sequencing, while ALK, PI3KCA, FGFR1 and PD-L1 expression was detected by immunohistochemical (IHC) staining. Positive Globo H expression was detected in 88 of the 228 (38.6%) patients. These included 51 of 139 (36.7%) patients with ADC and 37 of 89 (41.6%) patients with SqCC. Positive Globo H expression was significantly associated with EGFR mutation and PD-L1 expression in the ADC group, and PI3KCA overexpression in the SqCC group. The survival analysis showed that Globo H expression was not an independent prognostic factor in stage I NSCLC. Globo H expression was correlated with specific driver mutations in ADC and SqCC NSCLC tumors, as well as PD-L1 status. Immunotherapy targeting Globo H may have potential application in lung cancer treatment.

Functional connectivity analysis of distracted drivers based on the wavelet phase coherence of functional near-infrared spectroscopy signals.

The present study aimed to evaluate the functional connectivity (FC) in relevant cortex areas during simulated driving with distraction based on functional near-infrared spectroscopy (fNIRS) method. Twelve subjects were recruited to perform three types of driving tasks, namely, straight driving, straight driving with secondary auditory task, and straight driving with secondary visual vigilance task, on a driving simulator. The wavelet amplitude (WA) and wavelet phase coherence (WPCO) of the fNIRS signals were calculated in six frequency intervals: I, 0.6–2 Hz; II, 0.145–0.6 Hz; III, 0.052–0.145 Hz; IV, 0.021–0.052 Hz; and V, 0.0095–0.021 Hz, VI, 0.005–0.0095Hz. Results showed that secondary tasks during driving led to worse driving performance, brain activity changes, and dynamic configuration of the connectivity. The significantly lower WA value in the right motor cortex in interval IV, and higher WPCO values in intervals II, V, and VI were found with additional auditory task. Significant standard deviation of speed and lower WA values in the left prefrontal cortex and right prefrontal cortex in interval VI, and lower WPCO values in intervals I, IV, V, and VI were found under the additional visual vigilance task. The results suggest that the changed FC levels in intervals IV, V, and VI were more likely to reflect the driver’s distraction condition. The present study provides new insights into the relationship between distracted driving behavior and brain activity. The method may be used for the evaluation of drivers’ attention level.

A Prospective Study

Category: Post-surgical Lifestyle Introduction/Purpose: Gastrocnemius recession is the most common surgical procedure in the foot and ankle orthopaedic community. After surgery, patients ask their surgeons when they can safely resume day-to-day activities such as driving. Most times, the surgeon responds with generalized instructions using pain and patient comfort level as benchmarks for when the patient can return to driving. Several studies have identified safe return times for driving after traumatic injuries. However, a safe return time for gastrocnemius recession patients has never been studied. Given the safety concerns and risk associated with driving after surgery, it is important to have evidence-based advice for patients. The purpose of this study is to determine when a patient can safely return to driving after gastrocnemius recession. Methods: IRB approval has already been obtained for this study. 20 patients undergoing right-sided gastrocnemius recession will be identified in the Foot and Ankle clinic. Inclusion criteria will include first time isolated gastrocnemius recession surgery, licensed driver, and age between 18 and 65. Exclusion criteria will include failure to meet inclusion criteria, inability to return for follow-up testing, non-active driver status, medical contraindication to driving, history of any prior foot and ankle surgeries, and performance of any concurrent foot and ankle surgical procedures alongside gastrocnemius recession. Study participants will attend a driving simulator session prior to undergoing their procedure and will follow-up with repeat simulations at 1, 2, and 4 weeks postoperatively. Collected data will include braking reaction time, total braking time, speed stability, and number of traffic violations. A matched healthy control dataset will be used for comparison. Results: There was no detailed data available at the time of writing this abstract. We anticipate data availability over the next couple of months. Conclusion: We anticipate conclusions on the safe time to resume driving in gastrocnemius recession patients after gathering and processing detailed data. This is the first prospective study to guide counseling for patients undergoing gastrocnemius recession regarding a safe time to resume driving.

1633PD - Co-amplification of KIT/KDR/PDGRA in over 100,000 advanced cancer cases

Background: The 4q12 amplicon (4q12amp) which harbors the tyrosine kinases KIT, KDR and PDGFRA has been thought to occur as frequently as 3-7% in lung adenocarcinoma (LA) (Ramos et al, 2009) and 5-15% in glioblastoma (GBM) (Holtkamp, 2006; Szerlip, 2012) as assessed by a variety of techniques. As 4q12amp is hypothesized to be an oncogenic driver, it remains unclear whether all three kinases participate equally in oncogenesis, or if one kinase can be preferentially targeted by a tyrosine kinase inhibitor (TKI) for patient benefit. We undertook a large-scale genomic analysis to describe the frequency of 4q12 across solid tumors. Methods: We prospectively analyzed 114,200 primarily advanced stage solid tumors in the course of clinical care using hybrid-capture based comprehensive genomic profiling (CGP) of 186 to 315 genes plus introns from 14 to 28 genes commonly rearranged in cancer. Results: 4q12amp was present in 0.65% of all cases (740/114,200), with a median copy number of 10, and was most abundant in the following cancers: 4.8% of GBM (155/3,222), 0.83% of lung cancers (191/22,857, 2/3 approximately being LA), 1.9% of sarcomas (106/5,391), and 0.77% of breast cancers (92/11,980). Of sarcomas, 7.1% of osteosarcomas (26/367) and 2.82% of soft tissue sarcomas NOS (22/780) harbored 4q12amp. Of 4q12amp lung cancer cases, the supramajority (86%) did not harbor known oncogenic drivers of NSCLC (alterations of EGFR/HER2/MET, ALK/ROS/RET fusions, or BRAF V600E). Index cases of durable responses to pazopanib and imatinib will be described in undifferentiated sarcoma, synovial sarcoma, and head and neck/salivary cancers. Conclusions: 4q12amp is significantly less frequent in GBM and lung cancer than previously reported by non-sequencing techniques, but is enriched in osteosarcoma and undifferentiated sarcomas. The driver status of 4q12amp is supported both by the predominant mutual exclusivity with other known drivers in lung cancer, and responses to various multi-TKIs. The specificities of the latter may help shed insight into whether singly or multiply targeting KIT/KDR/PDGFRA is a preferred approach for patient benefit. Legal entity responsible for the study: Foundation Medicine Funding: Foundation medicine, Inc funded a small part of the study Disclosure: U. Disel: Research agreement with Foundation Medicine, which provided funding to run a small number of genomic profiling assay (<15). R. Madison, J. Chung, A. Oztan, A. Benson, J. Webster, P.J. Stephens, A.B. Schrock, V.A. Miller: an employee of and has equity interest in Foundation Medicine Inc M. Gounder: No COI for this specific work. Advisory board or compensations: Tracon, Daiichi, Karyopharm, Epizyme, Amgen S.J. Klempner: Honoraria – Foundation Medicine, Inc. Consulting/Advisory Board – Lilly Oncology, Boston Biomedical S-H.I. Ou: Stock ownership Yes Membership of an advisory board or board of directors Genentech/Roche, Ariad, Pfizer, Novartis, Astra Zeneca Corporate sponsored research S. Ganesan: COI: Merck: Spouse is employee and owns equity Inspirata Inc.: am on SAB, own equity and have IP Novartis: consultant J.S. Ross: Employee of and has equity interest in Foundation Medicine Inc. paid speaker for several pharmaceutical companies. has equity interest in Sypher Inc. S. Ali: Employee of and have equity interest in Foundation Medicine. I own <5000 USD in stock in epizyme and exelexis. All other authors have declared no conflicts of interest.

Development of Real-Time Driver's Health Detection System by Using Smart Handle

The number of vehicle accidents due to driver's drowsiness continues to increase. Therefore, prompt and effective detection for driver's health during driving is crucial to improvement of traffic safety. A set of real-time healthdetection system built-in a smart handle for driver is proposed in the research. By monitoring driver’s biological signals, including respiration, hand gripping force, photoplethysmogram (PPG), and electrocardiogram (ECG), driver's health condition (drowsiness) is able to be detected via the developed algorithm. Meanwhile the driver's state of arrhythmia can be diagnosed too. The test results indicate that the developed real-time driver’s health detection system can effectively monitor not only the state of vigilance but also the state of arrhythmia of a driver.

Expression of epithelial-mesenchymal transition driver brachyury and status of tumor-infiltrating CD8+ and FOXP3+ lymphocytes in predicting treatment responses to neoadjuvant chemotherapy of breast cancer.

Brachyury has been characterized as a driver of epithelial-mesenchymal transition process which is regarded as an important mechanism of cancer cell invasion and metastatic progression. The status of tumor-infiltrating lymphocytes has been proposed to predict response to neoadjuvant chemotherapy in breast cancer. We investigated the clinical significance and value of tumor-infiltrating lymphocytes and brachyury as biomarkers to predict treatment responses to neoadjuvant chemotherapy in breast cancer. We also examined the correlation of the Neo-Bioscore with tumor-infiltrating lymphocytes and brachyury to indirectly predict long-term outcome. This retrospective study included a series of 44 consecutive patients treated between January 2011 and December 2015. All patient samples were obtained using core needle biopsy before neoadjuvant chemotherapy. The relationship of expression of Brachyury and tumor-infiltrating lymphocyte subsets (CD8+, forkhead box protein 3 tumor-infiltrating lymphocytes) with clinicopathological factors was assessed to identify its predictive role with respect to tumor response to neoadjuvant chemotherapy and the outcome. Of 44 patients, 6 showed no response, 31 had partial response, and 7 demonstrated pathological complete response. Forkhead box protein 3 was significantly higher in the response group than in the no response group (no response = 2.6, partial response = 7.0, complete response = 9.7, p = 0.020). Brachyury expression was inversely associated with response to neoadjuvant chemotherapy, but the difference was not statistically significant ( p = 0.62). We also observed a significant association between forkhead box protein 3 ( p = 0.001) and the Neo-Bioscore, while only a marginal difference was observed with CD8+ expression ( p = 0.074). This study demonstrated that forkhead box protein 3 expression has value as the only independent marker that predicts a good response to neoadjuvant chemotherapy and that it is related with a good prognosis according to the Neo-Bioscore. Brachyury was significantly associated with estrogen receptor positive and human epidermal growth factor receptor 2 negative status; further study would be needed to clarify how it affects treatment prognosis.

Age and the risk of All-Terrain Vehicle-related injuries in children and adolescents: a cross sectional study

BackgroundThe study was designed to determine if youth <16 years are at a greater risk of serious injuries related to all-terrain vehicle (ATV) use compared to older adolescents and adults.MethodsWe performed cross sectional study of children and adults presenting to pediatric and adult emergency departments between 1990 and 2009 in Canada. The primary exposure variable was age <16 years and the primary outcome measure was moderate to serious injury determined from physician report of type and severity of injury.ResultsAmong 5005 individuals with complete data, 58% were <16 years and 35% were admitted to hospital. The odds of a moderate to serious injury versus minor injury among ATV users <16 years of age was not different compared with those ≥16 years of age (OR: 0.94; 95% CI: 0.84, 1.06). After adjusting for era, helmet use, sex and driver status, youth <16 years were more likely to present with a head injury (aOR: 1.45; 95% CI: 1.19–1.77) or fractures (aOR: 1.60; 95% CI: 1.43–1.81), compared with those ≥16 years. Male participants (aOR: 1.21; 95% CI: 1.06–1.38) and drivers (aOR: 1.30, 95% CI: 1.12–1.51) were more likely to experience moderate or serious injuries than females and passengers. Helmet use was associated with significant protection from head injuries (aOR: 0.59; 95% CI: 0.44–0.78).ConclusionsYouth under 16 years are at an increased risk of head injuries and fractures. For youth and adults presenting to emergency departments with an ATV-related injury, moderate to serious injuries associated with ATV use are more common among drivers and males. Helmet use protected against head injuries, suggesting minimum age limits for ATV use and helmet use are warranted.

An interdisciplinary approach to bus information system: bus sensor networking and drivers cognition

Seoul Transport Operation and Information Service (TOPIS) collects traffic information from specific systems such as the bus card system, the unmanned traffic control system, traffic broadcasting, and the police. The bus information system (BIS) is a sensor network system that scientifically deals with information about the real-time location and control of buses. Using the BIS, bus companies can manage bus operations and driver status. Bus sensor network also reveals that drivers have differing cognition about the two component parts of the system, the support system and the surveillance system. Although sensor networks are convenient tools for assessing quality of life, they do not always guarantee positive results in the workplace. We suggest ways for the sensor network to move forward in order to satisfy employees and improve performance in companies. This study is valuable as convergence research for the individual cognitive dimensions of sensor networks.

Modernization of Diesel-electric Locomotive 2M62 and TEP-70 Locomotives with Respect to Electrical Subsystem

In article analysing typical electrical locomotives were manufactured with analogous control systems (2M62, TEP-70) of the entire power train and electric drive, which have a lot of deficiencies. The major deficiency was high fuel consumption. The locomotive traction force Fk= f(v) for the theoretical traction requirements must be inversely proportional to the movement speed v. This characteristics is called hyperbole, it allows optimum control of the locomotive in the entire speed range, i.e. to use the diesel engine power to its full extent. Once such locomotive traction characteristics are created, the diesel engine capacity in the hyperbole characteristics is constant. To solve this task the traction characteristics Fk= f(v) and traction generator load characteristics Ug= f(Ig) must be hyperbolic shape. In order to improve energy characteristics of diesel-electric locomotives 2M62, TEP-70, analysis of their automatic control systems was performed. Based on this, the systems which were proposed by the authors and implemented, have enabled significant reduction of fuel consumption, improved driver's working conditions, traffic safety, etc. Especially important technical tasks to be solved were to improve general reliability of locomotives, and to reduce operation costs. The authors have proposed not to use special electric machines for excitation of traction generators, but to replace them with contactless semiconductor static converters and to use microprocessor based locomotive parameters control systems.

Remote Monitoring of the Driver Status as a Means of Improving Transport Safety

The majority of accidents and accident occurrences on motor transport are connected with human factor. To reduce the risk of a negative effect of human factor it makes sense to use automatic remote monitoring of the driver status on a trip. The article describes the task presentation, description of the development and introduction of this system based on one of MOSTRANSAVTO (Moscow-based Transportation Enterprise) divisions.

基于驾驶员身份认证的车载酒精检测系统设计

近年来，我国机动车数量快速增长，交通事故成为危害公众安全的重要因素。事故成因包括超速、酒驾、疲劳驾驶等。本设计以单片机为控制核心，结合非接触式IC卡技术、GSM技术、传感器技术以及CAN总线技术，研究设计了一套基于驾驶员身份认证的酒精检测系统，通过IC卡绑定驾驶员与驾驶行为，通过酒精传感器对驾驶员入驾状态进行检测，根据检测结果进行预警，降低涉酒类交通事故的发生率。 In recent years, with the rapid growing of the quantity of motor vehicles in China, the traffic accident has become an important factor endangering the public security. The accident causes mainly include speeding, drunk driving and fatigue driving. The research shows that enhancing superintendency strength can effectively reduce the illegal operations of drivers. With the single chip processor as the core, combining with contactless IC card technology, GSM technology, sensor technology and controller area network bus technology, the study designs a set of the responsibility identification of driving system, which binds drivers and driving behavior through the IC card, automatically monitoring the driver status by using alcohol sensor before driving. According to the results of the detection, it gives the warning, and reduces the incidence of traffic accidents.

눈 개폐의 빈도수를 통한 운전자의 졸음판단 분석

본 논문은 개선된 얼굴검출 알고리즘과 눈의 개폐 빈도수로부터 운전자의 졸음을 판단하는 방법을 제안한다. 이를 위해 기존의 Viola-Jones 알고리즘과 얼굴의 공간적 상관관계를 이용하여 얼굴, 눈, 코, 입을 검출한다. 여기서, 얼굴의 공간적 상관관계는 7가지 특징에 기반한 DFP(Detect Face Part)에 의해 수행된다. Caltect 얼굴 데이터베이스에 실험을 한 결과, 특히 코 영역에 대한 검출률은 기존 Viola-Jones 알고리즘과 비교하여 13.78% 증가된 검출률을 보여주고 있다. 그리고, SVM(Support Vector Machine)과 PERCLOS(Percentage Closure of Eyes)을 사용해 시간에 따른 눈 개폐상태의 누적 값으로 운전자의 졸음 판단을 분석한다. 실험결과 93.28%의 운전자 졸음판단률을 얻어 제안된 방법의 유용성을 확인하였다. In this paper, we propose an improved face detection algorithm and determination method for drowsiness status of driver from the opening and closing frequency of the detected eye. For this purpose, face, eyes, nose, and mouth are detected based on conventional Viola-Jones face detection algorithm and spatial correlation of face. Here the spatial correlation of face is performed by DFP(Detect Face Part) based on seven characteristics. The experimental results on Caltect face image database revealed that the detection rates of noise particularly showed the improved performance of 13.78% in comparison to that of the previous Viola-Jones algorithm. Furthermore, we analyze the driver's drowsiness determination cumulative value of the eye closed state as a function of time based on SVM (Support Vector Machine) and PERCLOS(Percentage Closure of Eyes). The experimental results confirmed the usefulness of the proposed method by obtaining a driver's drowsiness determination rate of 93.28%.