Evaluation of Strategies for Integrated Classification of Visual-Manual and Cognitive Distractions in Driving

Kaber, David B.

doi:10.1177/0018720816647607

Cited by 13 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, the preferability of SVM has also been reported by numerous prior studies on fatigue detection based on psychophysiological measures (Li et al, 2020; Maior et al, 2020; Shen et al, 2008; C. Zhang et al, 2009). A possible interpretation of these consistent findings is that SVM is suitable for high‐dimensional non‐Gaussian distribution data, and many psychophysiological data have these characteristics (Y. Zhang & Kaber, 2016). However, some researchers pointed out that SVM had difficulty in training large‐scale datasets (Lin & Lin, 2003).…”

Section: Discussionmentioning

confidence: 83%

Detection of mental fatigue state using heart rate variability and eye metrics during simulated flight

Qin

Liu

et al. 2021

Hum Ftrs & Erg Mfg Svc

View full text Add to dashboard Cite

Pilot mental fatigue is a growing concern in the aviation field due to its significant contributions to human errors and aviation accidents. Long work hours, sleep loss, circadian rhythm disruption, and workload are well‐known reasons, but there is a need to accurately detect pilot mental fatigue to improve aviation safety. However, due to the highly restricted cockpit environment and the complex nature of mental fatigue, feasible in‐flight detection remains under‐investigated. The objective of this study is to define a promising approach for mental fatigue detection based on psychophysiological measurements in flying‐relevant environments. Eleven participants engaged in a simulated flight experiment, where several conventional heart rate variability (HRV) and ocular indices were examined to study their relevance to mental fatigue. Additionally, a Toeplitz Inverse Covariance‐Based Clustering (TICC) method was performed to determine the ground truth, after which supervised machine learning was adopted to enable automated mental fatigue detection using HRV and eye metrics. Results showed that HRV and eye metrics were sensitive to the mental fatigue induced by prolonged flight‐relevant tasks. The TICC method helped determine the ground truth for mental fatigue and identify its three distinct levels. Furthermore, a supervised learning‐based detection of mental fatigue was achieved using a support vector machine with the greatest detection accuracy of 91.8%. The findings and methodology of this study provide new insights into the fatigue countermeasures in restricted cockpit environment and lay the groundwork for further explorations into the mental fatigue induced by prolonged flight missions.

show abstract

Section: Discussionmentioning

confidence: 83%

Detection of mental fatigue state using heart rate variability and eye metrics during simulated flight

Qin

Liu

et al. 2021

Hum Ftrs & Erg Mfg Svc

View full text Add to dashboard Cite

show abstract

“…erefore, we decided to apply dimension optimization techniques on only the external measures. It should, however, be noted that the internal process indices made a signi cant contribution to the cognitive distraction classi cations accuracies reported in [3,14]. Excluding internal process indices could result in lower overall classi cation accuracy when cognitive distraction is part of a driving scenario.…”

Section: Baseline Methodsmentioning

confidence: 99%

“…Zhang et al [3] applied a Supportive Vector Machine (SVM) analysis to the data set described above to classify driver distraction states, including none, visual-manual, cognitive, and combined distraction states. ey showed near perfect prediction accuracies with both overt behavior measures and internal process indices used as SVM inputs.…”

Section: Baseline Methodsmentioning

confidence: 99%

“…T he automotive sector is always looking for solutions to optimize driver safety and driving experiences. With the abundance of sensors in today's vehicle, more data has become available to support advanced driver assistant features such as fatigue detection [1], emotion detection [2], distraction detection [3,4] and future maneuver/intention prediction [5,6,7]. Various streams of data are captured from the vehicle, driver, and surrounding objects equipped with connected components (e.g., DSRC or 5G).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

“Fitting Data”: A Case Study on Effective Driver Distraction State Classification

Zhao

Kaber

Uryasev

et al. 2019

SAE Technical Paper Series

Self Cite

View full text Add to dashboard Cite

he goal of this project was to investigate how to make driver distraction state classi cation more e cient by applying selected machine learning techniques to existing datasets. e data set used in this project included both overt driver behavior measures (e.g., lane keeping and headway measures) and indices of internal cognitive processes (e.g., driver situation awareness responses) collected under four distraction conditions, including no-distraction, visual-manual distraction only, cognitive distraction only, and dual distraction conditions. e baseline classi cation method that we employed was a support vector machine (SVM) to rst identify driver states of visual-manual distraction and then to identify any cognitive-related distraction among the visual-manual distraction cases and other non-visual manual distraction cases. e new aspect of this research is optimization of the classi cation e ort, which involved cardinality constraints on 16 overt driver behavior measures. A spline transformation was also implemented to achieve better classi cation performance. In addition to testing our optimization approach with the SVM, we also explored logistic regression. Results revealed the splinetransformed variables to produce a good "out-of-sample" performance for both the SVM and logistic regression. Beyond this, the cardinality constraints were important for selection of the most in uential variables in driver state classi cation accuracy and preventing data over tting. Regarding the objective of eciency in distraction classi cation, with only two input variables our optimized approach achieved state classi cation accuracies similar to accuracies achieved with "brute-force" application of SVM with all 16 overt driver behavior measures as inputs. Interestingly, with splined-transformed variables, reducing the number of input variables to 2 only led to a marginal decrease in classi cation accuracy (75.38% to 74.16%). e optimization methods explored in this paper could be applied to other in-vehicle real-time data to reduce computational demands in using machine learning methods for driver state classi cation.

show abstract

“…Liang interpreted a sequential analysis as indicating that from a risk state identification perspective, it is not necessary to detect cognitive distraction if visual distraction is present as the latter dominates. A recent work [39] compared alternate SVM based classification approaches in a simulation context with experimentally defined periods of visual-manual, cognitive, and combined distraction. A "two-stage" classifier first considered visualmanual distraction and then detecting dual or cognitive distraction states was evaluated against a "direct-mapping" classifier developed to identify all distraction states at the same time.…”

Section: Cognitive Load and Secondary Tasksmentioning

confidence: 99%

What Can Be Predicted from Six Seconds of Driver Glances?

Fridman

Toyoda²,

Seaman

et al. 2017

Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

We consider a large dataset of real-world, on-road driving from a 100-car naturalistic study to explore the predictive power of driver glances and, specifically, to answer the following question: what can be predicted about the state of the driver and the state of the driving environment from a 6second sequence of macro-glances? The context-based nature of such glances allows for application of supervised learning to the problem of vision-based gaze estimation, making it robust, accurate, and reliable in messy, real-world conditions. So, it's valuable to ask whether such macro-glances can be used to infer behavioral, environmental, and demographic variables? We analyze 27 binary classification problems based on these variables. The takeaway is that glance can be used as part of a multi-sensor real-time system to predict radio-tuning, fatigue state, failure to signal, talking, and several environment variables.

show abstract

Evaluation of Strategies for Integrated Classification of Visual-Manual and Cognitive Distractions in Driving

Cited by 13 publications

References 33 publications

Detection of mental fatigue state using heart rate variability and eye metrics during simulated flight

Detection of mental fatigue state using heart rate variability and eye metrics during simulated flight

“Fitting Data”: A Case Study on Effective Driver Distraction State Classification

What Can Be Predicted from Six Seconds of Driver Glances?

Contact Info

Product

Resources

About