Non-Intrusive Detection of Drowsy Driving Based on Eye Tracking Data

2019 ◽  
Vol 2673 (6) ◽  
pp. 247-257 ◽  
Author(s):  
Ali Shahidi Zandi ◽  
Azhar Quddus ◽  
Laura Prest ◽  
Felix J. E. Comeau
Keyword(s):  
Eye Tracking ◽  
Motor Vehicle ◽  
Binary Classification ◽  
The State ◽  
Support Vector ◽  
Tracking Data ◽  
Drowsy Driving ◽  
Vehicle Accidents ◽  
State Of Vigilance

Drowsy driving is one of the leading causes of motor vehicle accidents in North America. This paper presents the use of eye tracking data as a non-intrusive measure of driver behavior for detection of drowsiness. Eye tracking data were acquired from 53 subjects in a simulated driving experiment, whereas the simultaneously recorded multichannel electroencephalogram (EEG) signals were used as the baseline. A random forest (RF) and a non-linear support vector machine (SVM) were employed for binary classification of the state of vigilance. Different lengths of eye tracking epoch were selected for feature extraction, and the performance of each classifier was investigated for every epoch length. Results revealed a high accuracy for the RF classifier in the range of 88.37% to 91.18% across all epoch lengths, outperforming the SVM with 77.12% to 82.62% accuracy. A feature analysis approach was presented and top eye tracking features for drowsiness detection were identified. Altogether, this study showed a high correspondence between the extracted eye tracking features and EEG as a physiological measure of vigilance and verified the potential of these features along with a proper classification technique, such as the RF, for non-intrusive long-term assessment of drowsiness in drivers. This research would ultimately lead to development of technologies for real-time assessment of the state of vigilance, providing early warning of fatigue and drowsiness in drivers.

scholarly journals Toward Wearable EEG-based Alertness Detection System Using SVM with Optimal Minimum Channels

2018 ◽  
Vol 214 ◽  
pp. 03009 ◽  
Author(s):  
Mihong Yang ◽  
Huiyan Li ◽  
Xiaozhou Sun ◽  
Li Yang ◽  
Hailong Duan ◽  
...  
Keyword(s):  
Traffic Accidents ◽  
Detection System ◽  
The State ◽  
Support Vector ◽  
Drowsy Driving ◽  
Wearable Eeg ◽  
High Fatality Rate ◽  
Minimum Number ◽  
Eeg Recordings

Alertness is the state of attention by high sensory awareness. A lack of alertness is one of the main reasons of serious accidents. Traffic accidents caused by driver’s drowsy driving have a high fatality rate. This paper presents an EEG-based alertness detection system. In order to ensure the convenience and long-term wearing comfort of EEG recordings, the wearable electrode cap will be the principal choice in the future, and the selection of channels will be limited. We first built a 3-D simulated driving platform using Unity3D. Then, we perform an experiment with driving drift task. EEG signals are recorded form frontal and occipital regions. We select data segments using the driving reaction time, classify the state of alertness with a support vector machine (SVM), and select the optimal combination of channels with minimum number of channels. Our results demonstrate that alertness can be classified efficiently with one channel (PO6) at accuracy of 93.52%, with two channels (FP1+PO6) at 95.85% and with three channels (FP1+PO6+PO5 and FP1+PO6+POZ) at 96.11%.

Talocalcaneocentral luxation combined with lateral instability of the talocrural joint in a dog and a cat

2004 ◽  
Vol 17 (01) ◽  
pp. 53-56 ◽  
Author(s):  
P. Schawalder ◽  
H. G. Schmökel ◽  
K. Hurter
Keyword(s):  
Motor Vehicle ◽  
Surgical Techniques ◽  
Motor Vehicle Accidents ◽  
Lateral Instability ◽  
Talocrural Joint ◽  
Vehicle Accidents ◽  
Talocalcaneal Joint ◽  
Surgical Fixation

SummaryTarsal injuries occur commonly in the cat and the dog, often due to motor vehicle accidents. In two cases a talocalcaneocentral luxation was associated with lateral talocrural instability. The surgical fixation of the talocalcaneocentral luxation, employing Kirschner pins in a cat and a DC plate in a dog, together with stabilisation of the lateral talocrural joint resulted in good long-term healing. The main aim of the surgical techniques used in these two cases was to stabilise the joints, without crossing and immobilising the talocalcaneal joint.

Ankle Dislocation without Fracture

Foot & Ankle ◽  
1988 ◽  
Vol 9 (2) ◽  
pp. 64-74 ◽  
Author(s):  
Randall R. Wroble ◽  
James V. Nepola ◽  
Thomas A. Malvitz
Keyword(s):  
Motor Vehicle ◽  
Sports Participation ◽  
Joint Space ◽  
University Of Iowa ◽  
Optimum Treatment ◽  
Vehicle Accidents ◽  
Patient Reported ◽  
Long Term Follow Up ◽  
Ankle Dislocation

Dislocation of the ankle without accompanying malleolar fracture has been regarded as a rare lesion, with few cases reported in the literature. To date, there has been no precedent for accurate descriptions of the mechanisms, optimum treatment, and long-term prognosis of this injury. Our goal was to evaluate these variables by a retrospective review of cases from our institution. We identified eight patients who had sustained ankle dislocation without fracture and were treated at the University of Iowa during the period 1958 to 1986. We interviewed and examined each patient and obtained ankle radiographs at an average of 11.5 years postinjury (range 2 to 24 years). After analyzing our cases and others reported in the literature, we have found that this injury is most common in young people (average age 31 years, range 10 to 73 years) and males (72%), and occurs most frequently in falls, motor vehicle accidents, and sports (86%). Medial displacement occurs most frequently (27%). Disruption of the mortise occurs variably. The most likely mechanism appears to be anterior or posterior extrusion of the talus from the mortise secondary to a force applied to the plantarflexed foot. Final displacement is then determined by the position of the foot and the direction of the force applied. Physical findings are commensurate with the deformity. Neurovascular compromise is uncommon (10%). Closed reduction is almost invariably accomplished easily unless the deformity is accompanied by posterior tibiofibular dislocation. Optimum treatment appears to be immobilization in a short leg cast for 6 weeks with no weightbearing for the first 3 weeks. Long-term follow-up revealed the following. Results were all good to excellent considering the following variables: return to work and sports activities, pain, instability, swelling, and ankle and subtalar joint motion. No patient reported instability and all returned to work and sports participation. We noted mild pain and swelling that was not severe enough to require medication in 25% of patients. Range of motion was normal in all but four patients; none of these lacked more than 10° of motion in any plane. Radiographic abnormalities consisted of minor ligamentous or capsular calcification in all patients, small osteophytes in four patients, and minimal joint space narrowing in one patient. No patient had normal radiographs.

scholarly journals Sleep Disorders and Risk of Motor Vehicle Accident

2021 ◽  
Vol 18 (2) ◽  
pp. 72-77
Author(s):  
Soo Hwan Yim ◽  
Jae Wook Cho ◽  
Jun-Sang Sunwoo ◽  
Daeyoung Kim ◽  
Dae Lim Koo ◽  
...  
Keyword(s):  
Sleep Disorders ◽  
Traffic Accidents ◽  
Motor Vehicle ◽  
Motor Vehicle Accident ◽  
Drowsy Driving ◽  
Vehicle Accidents ◽  
Neurocognitive Functions ◽  
Sleeping Pills ◽  
Obstructive Sleep ◽  
Sedative Drugs

Driving is a complicated process that demands coordination between a range of neurocognitive functions, including attention, visuo-perception, and appropriate judgment, as well as sensory and motor responses. Therefore, several factors may reduce the driving performance of an individual, such as sleepiness, distraction, overspeeding, alcohol consumption, and sedative drugs, all of which increase the hazard of motor vehicle accidents. Among them, drowsy driving is a major cause of traffic accidents, leading to more serious injuries as compared to other causes of major traffic accidents. Although sleep disorders have been highly associated among drowsy drivers, they are often untreated and unrecognized as a disease. In particular, obstructive sleep apnea and narcolepsy are some sleep disorders that are highly related to traffic accidents. Insomnia, which can cause inadequate sleep duration and promote sedative effects from sleeping pills, may also cause traffic accidents. These conditions are especially applicable to commercial bus or truck drivers, nocturnal workers, and shift workers, who are highly vulnerable to drowsy driving. Therefore, assertive screening and management of sleep disorders are necessary in general private drivers and relevant occupational drivers.

scholarly journals Fractures of the femoral head: a narrative review

2021 ◽  
Vol 6 (11) ◽  
pp. 1122-1131
Author(s):  
Maximilian M. Menger ◽  
Benedikt J. Braun ◽  
Steven C. Herath ◽  
Markus A. Küper ◽  
Mika F. Rollmann ◽  
...  
Keyword(s):  
Femoral Head ◽  
Surgical Approach ◽  
Motor Vehicle ◽  
Hip Dislocation ◽  
High Energy ◽  
Femoral Head Fracture ◽  
Concomitant Injuries ◽  
Vehicle Accidents ◽  
Joint Congruity

Fractures of the femoral head are rare injuries, which typically occur after posterior hip dislocation. The Pipkin classification, developed in 1957, is the most commonly used classification scheme to date. The injury is mostly caused by high-energy trauma, such as motor vehicle accidents or falls from a significant height. Emergency treatment consists of urgent closed reduction of the hip joint, followed by non-operative or operative treatment of the femoral head fracture and any associated injuries. There is an ongoing controversy about the suitable surgical approach (anterior vs. posterior) for addressing fractures of the femoral head. Fracture location, degree of displacement, joint congruity and the presence of loose fragments, as well as concomitant injuries are crucial factors in choosing the adequate surgical approach. Long-term complications such as osteonecrosis of the femoral head, posttraumatic osteoarthritis and heterotopic ossification can lead to a relatively poor functional outcome. Cite this article: EFORT Open Rev 2021;6:1122-1131. DOI: 10.1302/2058-5241.6.210034

scholarly journals Investigating the Use of Eye Fixation Data for Emotion Classification in VR

2021 ◽  
Vol 12 (3) ◽  
pp. 1852-1857
Author(s):  
Lim Jia Zheng Et.al
Keyword(s):  
Eye Tracking ◽  
Classification Accuracy ◽  
Preliminary Investigation ◽  
Support Vector ◽  
Tracking Data ◽  
Eye Tracker ◽  
Emotion Classification ◽  
Learning Classifier ◽  
Rbf Kernel ◽  
Tracking Technology

Eye-tracking technology has become popular recently and widely used in research on emotion recognition since its usability. In this paper, we presented a preliminary investigation on a novelty approach for detecting emotions using eye-tracking data in virtual reality (VR) to classify 4-quadrant of emotions according to russell’scircumplex model of affects. A presentation of 3600 videos is used as the experiment stimuli to evoke the emotions of the user in VR. An add-on eye-tracker within the VR headset is used for the recording and collecting device of eye-tracking data. Fixation data is extracted and chosen as the eye feature used in this investigation. The machine learning classifier is support vector machine (SVM) with radial basis function (RBF) kernel. The best classification accuracy achieved is 69.23%. The findings showed that emotion classification using fixation data has promising results in the prediction accuracy from a four-class random classification.

scholarly journals An SVM-Based Framework for Long-Term Learning Systems

2019 ◽  
Vol 33 ◽  
pp. 9915-9916
Author(s):  
Diana Benavides-Prado
Keyword(s):  
Binary Classification ◽  
Upper Bounds ◽  
Support Vector ◽  
Transfer Of Knowledge ◽  
Learning Framework ◽  
Vector Machines ◽  
Novel Method ◽  
Classification Tasks ◽  
Retention Of Knowledge

In our research, we study the problem of learning a sequence of supervised tasks. This is a long-standing challenge in machine learning. Our work relies on transfer of knowledge between hypotheses learned with Support Vector Machines. Transfer occurs in two directions: forward and backward. We have proposed to selectively transfer forward support vector coefficients from previous hypotheses as upper-bounds on support vector coefficients to be learned on a target task. We also proposed a novel method for refining existing hypotheses by transferring backward knowledge from a target hypothesis learned recently. We have improved this method through a hypothesis refinement approach that refines whilst encouraging retention of knowledge. Our contribution is represented in a long-term learning framework for binary classification tasks received sequentially one at a time.

scholarly journals Public Health Surveillance for the Great American Solar Eclipse in Oregon

2018 ◽  
Vol 10 (1) ◽  
Author(s):  
Laurel Boyd ◽  
Meredith Jagger ◽  
Kathryn Kuspis ◽  
Melissa Powell ◽  
Sandy Giffin
Keyword(s):  
Public Health ◽  
Solar Eclipse ◽  
Public Health Surveillance ◽  
Motor Vehicle ◽  
Health Surveillance ◽  
Motor Vehicle Accidents ◽  
The State ◽  
Poison Center ◽  
Vehicle Accidents ◽  
Mass Gatherings

ObjectiveDevelop a public health surveillance plan for the Oregon Public Health Division (OPHD) in anticipation of the expected influx of visitors for the 2017 Great American Solar Eclipse.IntroductionThe Great American Solar Eclipse of 2017 provided a rare opportunity to view a complete solar eclipse on the American mainland. Much of Oregon was in the path of totality and forecasted to have clear skies. Ahead of the event, OPHD aggregated a list of 107 known gatherings in mostly rural areas across the state, some with estimated attendance of up to 30,000 attendees. Temporary food vendors and a range of sanitation solutions (including open latrines) were planned. International travelers were expected, along with large numbers of visitors traveling by car on the day of the eclipse.The potential for multiple simultaneous mass gatherings across the state prompted OPHD to activate an incident management team (IMT) and to create a Health Intelligence Section to design a mass gathering surveillance strategy. Statewide syndromic surveillance (Oregon ESSENCE) has been used to monitor previous mass gatherings (1) and captures statewide emergency department (ED), urgent care, Oregon Poison Center, and reportable disease data.MethodsThe OPHD Health Intelligence Section identified five categories of public health effects associated with large outdoor gatherings based on literature review (2–5) and an internal risk assessment. These included health system status (total visit or call counts), communicable disease (fever, bloody diarrhea and reportable disease counts), injuries and substance abuse (including motor vehicle accidents), and outdoor exposure (heat-related illness, snake bites and asthma-related visits). An event-related category monitored trends in eclipse-related visits or eye-related injuries (looking directly at the sun). Where possible, syndromic trends were assessed in multiple data sources. These categories were used to create dashboards within Oregon ESSENCE and shared in a guidance document for local health departments and hospitals.Health Intelligence monitored syndromes of interest during a period of enhanced surveillance (9/18-9/22), and met daily with members of the OPHD IMT to share surveillance summaries, which were also sent to OPHD leadership and external partners.ResultsDuring the enhance surveillance period, the OPHD Health Intelligence Section did not identify statewide increases in healthcare utilization (total ED visits and calls to the Oregon Poison Center), but did observe increases in visits at select emergency departments in the state. Visits by out-of-state residents (as determined by patient zip code at time of registration) increased during the surveillance period. Fever-related visits increased as well but were not accompanied by reports of illnesses clusters.Increases were noted for motor vehicle accidents, eye-related injuries, and “eclipse”-related visits. Increases in eye-related injuries appeared to be an annual seasonal trend and not related to the eclipse. There were no increases of note in the other queries monitored. Development of new queries (West Nile Virus) was begun based upon mosquito pool surveillance findings. Surveillance highlights were posted publicly in a special edition of the biweekly Oregon ESSENCE Hazard Report (see Image 1).ConclusionsStatewide public health surveillance during the 2017 Great American Solar Eclipse in Oregon did not identify clusters of infectious disease or other opportunities for real-time public health intervention. Nevertheless, surveillance identified increases in motor vehicle accidents, especially among out-of-state residents, due perhaps to increased road travel for the event. Preparations for this event increased capacity of state health department staff to conduct this type of surveillance in the future. Tools created for the eclipse have been used in several IMT activations since the eclipse.References1. Jagger MA, Jaramillo S, Boyd L, Johnson B, Reed KR, Powell M. Mass Gathering Surveillance : New ESSENCE Report and Collaboration Win Gold in OR. 2017;9(1):2579.2. WHO. Public Health for Mass Gatherings: Key Considerations. World Health Organization. 2015.3. Lombardo JS, Sniegoski CA, Loschen WA, Westercamp M, Wade M, Dearth S, et al. Public health surveillance for mass gatherings. Johns Hopkins APL Tech Dig (Applied Phys Lab. 2008;27(4):347–55.4. Polkinghorne BG, Massey PD, Durrheim DN, Byrnes T, MacIntyre CR. Prevention and surveillance of public health risks during extended mass gatherings in rural areas: The experience of the Tamworth Country Music Festival, Australia. Public Health. 2013;127(1):32–8.5. Burdick TE. Wilderness event medicine: Planning for mass gatherings in remote areas. Vol. 3, Travel Medicine and Infectious Disease. 2005. p. 249–58.

Sign in / Sign up

Export Citation Format

Share Document