In addition to the devastating effects of anxiety and stress on the development and exacerbation of the cardiovascular disease, lack of stress control increases drivers' risk of accidents. This paper aims to identify the stress of drivers in various driving situations to warn the driver to control the tense conditions during driving. In order to detect stress while driving, we used the heart signals in the Physionet database. To analyze the conditions of the electrocardiogram (ECG) under various driving situations, linear and non-linear features were used. The characteristics of the RRIs are the only able to identify driver stress in different driving modes relative to rest periods, while the return mapping features, in addition to identifying driver stress while resting, have the ability to identify stress between different driving positions also brought. The results showed that driver's stress level during driving in city 1 and highway 1 with a P-value of 0.028 and also in city 3 and highway 2 with a P-value of 0.041 can be distinguished. The accuracy obtained from the proposed detection method is 98±2% for 100 iterations. The result indicated an efficiency of our proposed method and enhanced the reliability.

[1] Akba A., “Evaluation of Physiological Data Driving Dynamic Stress of Drivers,” Scientific Research and Essays, vol. 6, no. 2, pp. 430-439, 2011.

[2] Al-Nashashibi M., Hadi W., El-Khalili N., Issa G., and AlBanna A., “A New Two-step Ensemble Learning Model for Improving Stress Prediction of Automobile Drivers,” The International Arab Journal of Information Technology, vol. 18, no. 6, pp. 819-829, 2021.

[3] Corcoba-Magaña V., Muñoz-Organero M., and Pañeda X., “Prediction of Motorcyclist Stress Using a Heartrate Strap,” Journal of Ambient 88 The International Arab Journal of Information Technology, Vol. 19, No. 1, January 2022 Intelligence and Smart Environments, pp. 579- 593, 2017.

[4] El Haouij N., Poggi J., Ghozi R., Sevestre- Ghalila S., and Jaïdane M., “Random Forest- Based Approach for Physiological Functional Variable Selection for Driver’s Stress Level Classification,” Journal of the Italian Statistical Society, vol. 28, no. 2, pp. 157-185, 2019.

[5] Franklin S., Larson M., Khan S., Wong N., Leip E., Kannel W., and Levy D., “Does The Relation of Blood Pressure to Coronary Heart Disease Risk Change with Aging?” Circulation, vol. 103, no. 9, pp. 1245-1249, 2001.

[6] Goldberger A., Amara L., Glass L., Hausdorff J., Ivanov P., Mark R., Mietus J., Moody G., Peng C., and Stanley H., “PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals,” Circulation, vol. 101, no. 23, pp. e215-e220, 2010.

[7] Healey J. and Picard R., “Detecting Stress During Real-World Driving Tasks Using Physiological Sensors,” IEEE Transactions on Intelligent Transportation Systems, vol. 6, no. 2, pp. 156- 166, 2005.

[8] https://github.com/hooman650/BioSigKit, Last Visited, 2019.

[9] Ieracitano C., Mammone N., Hussain A., Morabito F., “A Novel Explainable Machine Learning Approach for EEG-Based Braincomputer Interface Systems,” Neural Computing and Applications, pp. 1-14, 2021.

[10] Jeong I., Lee D., Park S., Ko J., and Yoon H., “Automobile Driver's Stress Index Provision System that Utilizes Electrocardiogram,” in Proceedings of IEEE Symposium on Intelligent Vehicle, Istanbul, pp. 652-656, 2007.

[11] Kashani A., ShariatMohaymany A., and Ranjbar A., “Analysis of Factors Associated with Traffic Injury Severity in Rural Roads in Iran,” Journal of Injury and Violence Research, vol. 4, pp. 36- 41, 2012.

[12] Lichtenstein M., Shipley M., and Rose G., “Systolic and Diastolic Blood Pressures As Predictors of Coronary Heart Disease Mortality in Whitehall Study,” BMJ, vol. 291, pp. 243-245, 1985.

[13] Liu D., Ulrich M., Kremer A., ProCon G., and Healey J., “Listen to Your Heart: Stress Prediction Using Consumer Heart Rate Sensors,” in Proceedings of CS229 Machine Learning, USA, pp.1-5, 2013.

[14] Mani A., Montagnese S., Jackson C., Jenkins C., Head I., Stephens R., Moore K., and Morgan1 M., “Decreased Heart Rate Variability in Patients with Cirrhosis Relates to the Presence and Degree of Hepatic Encephalopathy,” American Journal of Physiology-Gastrointestinal and Liver Physiology, vol. 296, no. 2, pp. G330-G338, 2009.

[15] Mandeep S. and Queyam A., “Stress Detection in Automobile Drivers Using Physiological Parameters: A Review,” International Journal of Electronics Engineering, vol. 5, no. 2, pp. 1-5, 2013.

[16] Manivel K. and Ravindran S., “Noise Removal for Baseline Wander and Power Line in Electrocardiograph Signals,” International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, vol. 4, no. 2, pp. 1114-1122, 2015.

[17] Moridani A., Fakhrmoosavy S., and Moridani M., “Vehicle Detention and Tracking in Roadway Traffic Analysis Using Kalman Filter and Features,” International Journal of Imaging and Robotics, vol. 15, no. 2, pp. 45-52, 2015.

[18] Moridani M., Zadeh M., Mazraeh Z., “An Efficient Automated Algorithm for Distinguishing Normal and Abnormal ECG Signal,” IRBM, vol. 40, no. 6, pp. 332-340, 2019.

[19] Moridani M., Setarehdan S., Nasrabadi A., and Hajinasrollah E., “New Algorithm of Mortality Risk Prediction for Cardiovascular Patients Admitted In Intensive Care Unit,” International Journal of Clinical and Experimental Medicine., vol. 8, no. 6, pp. 8916-8926, 2015.

[20] Munla N., Khalil M., Shahin A., and Mourad A., “Driver Stress Level Detection Using HRV Analysis,” International Conference on Advances in Biomedical Engineering, Beirut, pp. 61-64, 2015.

[21] Lee J., Lee H., Shin M., “Driving Stress Detection Using Multimodal Convolutional Neural Networks with Nonlinear Representation of Short-Term Physiological Signals,” Sensors (Basel), vol. 21, no. 7, pp. 2381, 2021.

[22] Ozkan T. and Lajunen T., “A New Addition to DBQ: Positive Driver Behaviors Scale,” Transportation Research Part F Traffic Psychology and Behaviour, vol. 8, no. 4-5, pp. 355-368, 2005.

[23] Patil S. and Hansen J., “Detection of speech Under Physical Stress: Model Development, Sensor Selection, and Feature Fusion,” in Proceedings of 9th Annual Conference of the International Speech Communication Association, Brisbane, pp. 817-820, 2008.

[24] Rastgoo M., Nakisa B., Maire F., Rakotonirainy A., and Chandran V., “Automatic Driver Stress Level Classification Using Multimodal Deep Learning,” Expert Systems with Applications, vol. 138, pp. 112793, 2019.

[25] Shiwu L., Linhong W., Zhifa Y., Bingk J., Feiyan Q., and Zhongkai Y., “Active Driver Fatigue Identification Technique Using Multiple Physiological Features,” in Proceedings of Designing an Intelligent System to Detect Stress Levels During Driving 89 International Conference on Mechatronic Science, Electric Engineering and Computer, Jilin, pp. 733-737, 2011.

[26] Singh R., Conjeti S., and Banerjee R., “An Approach for Real Time Stress-Trend Detection in Physiological Signals in Wearable Computing Systems for Automotive Drivers,” in Proceedings of 14th International IEEE Annual Conference Intelligent Transportation Systems, Washington, pp. 1477-1482, 2011.

[27] Singh R., Conjeti S., and Banerjee R., “Biosignal Based on-Road Stress Monitoring for Automotive Drivers,” in Proceedings of National Conference on Communications, Kharagpur, pp. 1-5, 2012.

[28] World Health Organization. Global status report on road safety 2018 Geneva, Switzerland, 2018. Available: https://www.who.int/violence_injury_prevention/ road_ safety_status/2018/en/ Last Visited, 2020.

[29] Tulppo M., Mäkikallio T., Takala T., Seppänen T., and Huikuri H., “Quantitative Beat-To-Beat Analysis of Heart Rate Dynamics During Exercise,” American Journal of Physiology, vol. 271, pp. 244-252, 1996.

[30] Vargas-Lopez O., Perez-Ramirez C., Valtierra- Rodriguez M., Yanez-Borjas J., and Amezquita- Sanchez J., “An Explainable Machine Learning Approach Based on Statistical Indexes and SVM for Stress Detection in Automobile Drivers Using Electromyographic Signals,” Sensors, vol. 21, no. 9, pp. 3155, 2021.