June 14, 2022Open Access

Assessment Of Driving Stress Through SVM And KNN Classifiers On Multi-Domain Physiological Data

Q: What is the clinical evidence from this study?

Study design: Observational. Population: Driving stress (n=16). Intervention: Support Vector Machine and K-Nearest Neighbors classification vs. Single physiological signal classification. Primary outcome: Stress classification accuracy.

DFDamiano FruetUniversity of Trento CBChiara BaràNational Research Council RPRiccardo PerniceUniversity of Palermo

Key Result

A classification model using Support Vector Machine on multi-domain physiological data achieved a prediction accuracy of 98.4% for detecting driver stress states.

Study Design

Type

Observational (n=16)

Structured PICO

Population

16 subjects with complete multiparametric physiological data acquired during a 50-90 minute driving route to assess stress states.

Exposure

Stress assessment using Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) classifiers on 21 features extracted from physiological time series.

Outcome

Prediction accuracy of driver stress level (restful, highway, city driving)

Multidomain physiological data acquisition combined with SVM or KNN classifiers can accurately detect driver stress levels, achieving up to 98.4% accuracy.

Limitations

The feature selection step remains a supervised and time consuming approach.
The KNN classifier requires large memories to store all available data before starting the training step.
The KNN classifier does not maintain high performance when dealing with large datasets.

Abstract

We propose an objective stress assessment method based on the extraction of features from physiological time series and their classification using Support Vector Machine and K-Nearest Neighbors algorithms. For this purpose, we used an open dataset consisting of multiparametric physiological signals (electrocardiogram, electromyogram, galvanic skin response and breath signal) obtained during the execution of a driving route within the city of Boston with restful, highway and city driving periods indicative of three different stress states. To predict the driver stress level, 21 features were extracted from 122 chunks of raw signals and were subsequently managed by classification algorithms. Our analysis showed a prediction accuracy of 98.4% when all features were used, decreasing when signals from specific physiological systems were not considered. Our results highlighted that multidomain data acquisition by wearable sensors combined with appropriate classification models may represent a promising strategy to detect drivers’ stress status in an unobtrusive and objective way that can in perspective be applicable in several other fields such as in the clinics.

Ask AI

Helpful

Bookmark

View Full Paper

Ask AI

Helpful

Bookmark

View Full Paper

Cite This Study

Fruet et al. (Tue,) conducted a observational in Driving stress (n=16). Support Vector Machine and K-Nearest Neighbors classification vs. Single physiological signal classification was evaluated on Stress classification accuracy. A classification model using Support Vector Machine on multi-domain physiological data achieved a prediction accuracy of 98.4% for detecting driver stress states.

synapsesocial.com/papers/6a35db69e8fad655376e50e8 https://doi.org/https://doi.org/10.1109/melecon53508.2022.9842891

Also Consider

Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: