Detection of drowsiness based on HOG features and SVM classifiers

Pauly, Leo; Sankar, Deepa

doi:10.1109/icrcicn.2015.7434232

Cited by 49 publications

(26 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, Karolinska Sleepiness Scale (KSS) was set as the reference point of fatigue, which was divided into two categories: alert condition (KSS 1-6) and fatigue condition (KSS 7-9), in line with Pauly and Shankar (2015). The EEG data were then mapped onto the reference points and analyzed using the ROC curve.…”

Section: Resultsmentioning

confidence: 99%

Effect Of Driving Duration On Eeg Fluctuations

Puspasari¹,

Iridiastadi

Sutalaksana

et al. 2017

IJTech

View full text Add to dashboard Cite

Road accidents are a major issue in Indonesia, and their number increases every year. Based on previous studies, mental fatigue is one of the biggest factors leading to road accidents and is majorly affected by mental workload. Driving duration is one of the factors that triggers mental fatigue. The prior literature cites electroencephalogram (EEG) measurement as the gold standard for measuring fatigue. However, there has been only limited study to examine the EEG indicators that are affected by driving duration, and the prior research still contains disagreements regarding the best EEG parameter for use in measuring fatigue. Therefore, this study aimed to evaluate the effect of driving duration on EEG fluctuation and determine the best EEG parameter related to fatigue. Seven participants were asked to spend three hours driving in a medium-fidelity simulator. A one-way ANOVA and correlation analysis were performed to measure the effect of driving duration on the EEG indicators and determine the correlation of the indicators. A Receiver Operating Characteristics (ROC) curve was also utilized to determine the variable with the greatest correlation with the subjective sleepiness indices. The results showed that at the end of three hours' driving, there was an increment in delta and theta activities, followed by a decrement in alpha and beta activities. In addition, the correlation of all bands was significant, with positive results for the alpha-beta and theta-delta bands, and a negative result in relation to each other. Furthermore, the results from the ROC curve revealed the Relative Power Ratio (RPR) of theta, the RPR of alpha, and the ratio of θ/α+β to be the best indicators among others, demonstrating a high degree of accuracy (above 85%).

show abstract

Section: Resultsmentioning

confidence: 99%

Effect Of Driving Duration On Eeg Fluctuations

Puspasari¹,

Iridiastadi

Sutalaksana

et al. 2017

IJTech

View full text Add to dashboard Cite

show abstract

“…The tools were applied to confirm that the driving tasks induced the participants' fatigue. The subjective measurements were SOFI [11], the KSS [7][8], and the subjective Fatigue Rating [9][10]. SOFI was applied to measure the subjective fatigue before and after driving using a scale of 0 = not at all to 6 = very high degree, with 3 as an intermediary level.…”

Section: Subjective Data Collectionmentioning

confidence: 99%

“…The KSS, as a tool to measure sleepiness, is based on a scale of 1 = very alert to 9 = very sleepy, fighting sleep, an effort to keep awake, with 5 as a neutral condition [8]; the KSS value was collected before the experiment started and every 10 minutes during the experiments. The Subjective Fatigue rating uses a 0 to 10 scale [10].…”

Section: Subjective Data Collectionmentioning

confidence: 99%

“…According to reports in the literature, physiological changes can be measured as fatigue indicators using both subjective and objective tools [5,6]. The subjective tools attempt to capture self-perception of the sleepiness/fatigue level at a certain time based on standardized questionnaires, such as the Karolinska Sleepiness Scale (KSS), the Stanford Sleepiness Scale (SSS), the Epworth Sleepiness Scale (EPS), the Fatigue Visual Analogue Scale (F-VAS), the Fatigue Rating, and the Swedish Occupational Fatigue Index (SOFI) [6][7][8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Analysis of EEG Changes during Prolonged Simulated Driving for the Assessment of Driver Fatigue

Zuraida¹,

Iridiastadi²,

Sutalaksana³

et al. 2019

J. Eng. Technol. Sci.

View full text Add to dashboard Cite

Fatigue during driving is the main contributing factor to road accidents. It is influenced by time on task (TOT) and time of day (TOD). Recent electroencephalogram (EEG) research on fatigue assessment has shown a promising result in explaining the fatigue phenomenon. However, different findings exist regarding the best EEG parameters related to fatigue. This study examined EEG changes according to the effect of TOT and TOD and determined the best parameters to distinguish fatigue status. To generate driver fatigue, prolonged driving in the morning and at night in a simulator was conducted. The EEG signal was collected from 28 male participants at frontal and occipital areas. The EEG power (brainwave) was determined from the first and last 5 minutes of the driving task and after a break of 30 minutes. The results of this study showed a general tendency of EEG power changing throughout the driving sessions. However, changes related to fatigue were only found for the night sessions, as confirmed by θ power and the subjective fatigue measurement result. This study showed that TOT (as a factor that induces fatigue) was explained by θ from the frontal area, whereas TOD was differentiated by α, θ, θ/β, (θ+α)/β and (θ+α)/(β+α).

show abstract

“…Here, the ResNet-50 [20] architecture was adopted, with a modified fully connected layer. The system outperformed AlexNet [13], GoogleNet [21], VGGFace fine-turning [14], and HOG-SVM [22].…”

Section: A Driver Drowsiness Detection Systemsmentioning

confidence: 95%

Detecting inter-sectional accuracy differences in driver drowsiness detection algorithms

Ngxande

Tapamo

Burke

2020

2020 International SAUPEC/RobMech/PRASA Conference

View full text Add to dashboard Cite

Convolutional Neural Networks (CNNs) have been used successfully across a broad range of areas including data mining, object detection, and in business. The dominance of CNNs follows a breakthrough by Alex Krizhevsky which showed improvements by dramatically reducing the error rate obtained in a general image classification task from 26.2% to 15.4%. In road safety, CNNs have been applied widely to the detection of traffic signs, obstacle detection, and lane departure checking. In addition, CNNs have been used in data mining systems that monitor driving patterns and recommend rest breaks when appropriate. This paper presents a driver drowsiness detection system and shows that there are potential social challenges regarding the application of these techniques, by highlighting problems in detecting dark-skinned drivers faces. This is a particularly important challenge in African contexts, where there are more dark-skinned drivers. Unfortunately, publicly available datasets are often captured in different cultural contexts, and therefore do not cover all ethnicities, which can lead to false detections or racially biased models. This work evaluates the performance obtained when training convolutional neural network models on commonly used driver drowsiness detection datasets and testing on datasets specifically chosen for broader representation. Results show that models trained using publicly available datasets suffer extensively from over-fitting, and can exhibit racial bias, as shown by testing on a more representative dataset. We propose a novel visualisation technique that can assist in identifying groups of people where there might be the potential of discrimination, using Principal Component Analysis (PCA) to produce a grid of faces sorted by similarity, and combining these with a model accuracy overlay.

show abstract

Detection of drowsiness based on HOG features and SVM classifiers

Cited by 49 publications

References 16 publications

Effect Of Driving Duration On Eeg Fluctuations

Effect Of Driving Duration On Eeg Fluctuations

An Analysis of EEG Changes during Prolonged Simulated Driving for the Assessment of Driver Fatigue

Detecting inter-sectional accuracy differences in driver drowsiness detection algorithms

Contact Info

Product

Resources

About