Abstract Commuting when there is a significant volume of traffic congestion has been acknowledged as one of the key factors causing stress. Significant levels of stress whilst driving are seen to have a profoundly negative effect on the actions and ability of a driver; this has the capacity to result in risks, hazards and accidents. As such, there is a recognized need to determine drivers’ levels of stress and accordingly predict the key causes responsible for high levels of stress. In this work, the objective is centred on providing an ensemble machine learning framework in order to determine the stress levels of drivers. Moreover, the study also provides a fresh set of data, as gathered from 14 different drivers, with data collection having taken place during driving in Amman, Jordan. Data was gathered via the implementation of a wearable biomedical instrument that was attached to the driver on a continuous basis in order to gather physiological data. The data gathered was accordingly categorised into two different groups: ‘Yes’, which represents the presence of stress, whilst ‘No’ represents the absence of stress. Importantly, in an effort to circumvent the negative impact of driver instances with a minority class on stress predictions, oversampling technique was applied. A two-step ensemble classifier was developed through bringing together the findings from random forest, decision tree, and Repeated Incremental Pruning to Produce Error Reduction (RIPPER) classifiers, which was then inputted into a Multi-Layer Perceptron neural network. The experimental findings highlight that the suggested framework is far more precise and has a more scalable capacity when compared with all classifiers in relation to accuracy, g-mean measures and sensitivity.

References

[1] Abu-Arqoub M., Hadi W., and Ishtaiwi A., “A New Associative Classification Based on RIPPER Algorithm,” Journal of Information and Knowledge Management, vol. 20, no. 1, pp. 2150013, 2021.

[2] Aburub F. and Hadi W., “A New Associative Classification Algorithm for Predicting Groundwater Locations,” Journal of Information and Knowledge Management, vol. 17, no. 4, pp. 1850043, 2018.

[3] AlAgha A., Faris H., Hammo B., and Al-Zoubi A., “Identifying β -Thalassemia Carriers Using A Data Mining Approach: the Case of the Gaza Strip, Palestine,” Artificial Intelligence in Medicine, vol. 88, pp. 70-83, 2018.

[4] Al-Fayoumi M., Alwidian J., and Abusaif M., “Intelligent Association Classification Technique for Phishing Website Detection,” The International Arab Journal of Information Technology, vol. 17, no. 4, pp. 488-496, 2020.

[5] Bakker J., Pechenizkiy M., and Sidorova N., “What’s Your Current Stress Level? Detection of Stress Patterns from GSR Sensor Data,” in Proceedings of 11th International Conference on Data Mining Workshops, Vancouver, pp. 573- 580, 2011.

[6] Barua S., Begum S., and Ahmed M., “Supervised Machine Learning Algorithms to Diagnose Stress for Vehicle Drivers Based on Physiological Sensor Signals,” Studies in Health Technology and Informatics, vol. 211, pp. 241-248, 2015.

[7] Bogner C., Kuhnel A., and Huwe B., “Predicting With Limited Data-Increasing the Accuracy in Vis-Nir Diffuse Reflectance Spectroscopy by Smote,” in Proceedings of 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, Lausanne, pp. 1-4, 2014.

[8] Bundele M. and Banerjee R., “Detection of Fatigue of Vehicular Driver using Skin Conductance and Oximetry Pulse,” in Proceedings of the 11th International Conference on Information Integration and Web-based Applications and Services, New York, pp. 739- 744, 2009.

[9] Bunker R. and Thabtah F., “A Machine Learning Framework for Sport Result Prediction,” Applied Computing and Informatics, vol. 15, no. 1, pp. 27-33, 2019.

[10] Chen B., Xia S., Chen Z., Wang B., and Wang G., “RSMOTE: A Self-Adaptive Robust SMOTE For Imbalanced Problems with Label Noise,” Information Sciences, vol. 553, pp. 397-428, 2021.

[11] De Santos Sierra A., Sanchez-Avila C., Bailador del Pozo G., and Guerra Casanova J., “Stress Detection By Means of Stress Physiological Template,” in Proceedings of 3rd World Congress on Nature and Biologically Inspired Computing, Salamanca, pp. 131-136, 2011.

[12] Deng Y., Wu Z., Chu C., and Yang T., “Evaluating Feature Selection for Stress Identification,” in Proceedings of IEEE 13th International Conference on Information Reuse and Integration, Las Vegas, pp. 584-591, 2012.

[13] El-Khalili N., Alnashashibi M., Hadi W., Banna A., and Issa G., “Data Engineering for Affective Understanding Systems,” Data, vol. 4, no. 2, pp. 52, 2019.

[14] Eyben F., Wöllmer M., Poitschke T., Schuller B., Blaschke C., Färber B., and Nguyen-Thien N., “Emotion on the Road-Necessity, Acceptance, and Feasibility of Affective Computing in the Car,” Advances in Human-Computer Interaction, pp. 1-17, 2010.

[15] Fernández-Caballero A., González P., López M., and Navarro E., “Special Issue on Socio- Cognitive and Affective Computing,” Applied Sciences, vol. 8, no. 8, pp. 1371, 2018.

[16] Ghaderi A., Frounchi J., and Farnam A., “Machine Learning-Based Signal Processing using Physiological Signals for Stress Detection,” in Proceedings of 22nd Iranian Conference on Biomedical Engineering, Tehran, pp. 93-98, 2015.

[17] Hadi W., “Classification of Arabic Social Media Data,” Advances in Computational Sciences and Technology, vol. 8, pp. 29-34, 2015. 828 The International Arab Journal of Information Technology, Vol. 18, No. 6, November 2021

[18] Hadi W., El-Khalili N., AlNashashibi M., Issa G. and AlBanna A., “Application of Data Mining Algorithms for Improving Stress Prediction of Automobile Drivers: A Case Study in Jordan,” Computers in Biology and Medicine, vol. 114, no. 7, pp. 103474, 2019.

[19] Hadi W., Issa G., and Ishtaiwi A., “ACPRISM: Associative Classification Based on PRISM Algorithm,” Information Sciences, vol. 417, pp. 287-300, 2017

[20] Hajian-Tilaki K., “Receiver Operating Characteristic (ROC) Curve Analysis for Medical Diagnostic Test Evaluation,” Caspian Journal of Internal Medicine, vol. 4, no. 2, pp. 627-635, 2013.

[21] Hall M., Frank E., Holmes G., Pfahringer B., Reutemann P., and Witten I., “The WEKA Data Mining Software,” ACM SIGKDD Explorations Newsletter, vol. 11, no. 1, 2009.

[22] Han, J., Kamber M., and Pei J., Data Mining: Concepts and Techniques, Elsevier, 2012.

[23] 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,” Statistical Methods and Applications, vol. 28, pp. 157-185, 2019.

[24] Harmon-Jones E., Gable P., and Price T., “The Influence of Affective States Varying In Motivational Intensity on Cognitive Scope,” Frontiers in Integrative Neuroscience, vol. 6, pp. 73, 2012.

[25] 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.

[26] Hido S., Kashima H., and Takahashi Y., “Roughly Balanced Bagging for Imbalanced Data,” Statistical Analysis and Data Mining: The ASA Data Science Journal, vol. 2, no. 5-6, pp. 412-426, 2009.

[27] Ishaq A., Sadiq S., Umer M., Ullah S., Mirjalili S., Rupapara V., and Nappi M., “Improving the Prediction of Heart Failure Patients’ Survival Using SMOTE and Effective Data Mining Techniques,” IEEE Access, vol. 9, pp. 39707- 39716, 2021.

[28] Jiang Z., Pan T., Zhang C., and Yang J., “A New Oversampling Method Based on the Classification Contribution Degree,” Symmetry (Basel), vol. 13, no. 2, pp. 194, 2021.

[29] Munoz-Organero M. and Corcoba-Magana V., “Predicting Upcoming Values of Stress While Driving,” IEEE Transactions on Intelligent Transportation Systems, vol. 18, no. 7, pp. 1802- 1811, 2017.

[30] Nagaraj K., Bhattacharjee B., Sridhar A., and GS, S. “Detection of Phishing Websites Using A Novel Twofold Ensemble Model,” Journal of Systems and Information Technology, vol. 20, no. 3, pp. 321-357, 2018.

[31] PSD. The statistics of traffic accidents. Retrieved from https://www.psd.gov.jo/images/traffic/traffic2017 Last Visited, 2021.

[32] Qabajeh I., Thabtah F., and Chiclana F., “A Dynamic Rule-Induction Method for Classification in Data Mining,” Journal of Management Analytics, vol. 2, no. 3, pp. 233- 253, 2015.

[33] Rahman T., Zhang M., Voida S., and Choudhury T., “Towards Accurate Non-Intrusive Recollection of Stress Levels Using Mobile Sensing and Contextual Recall,” in Proceedings of the 8th International Conference on Pervasive Computing Technologies for Healthcare, Brussels, pp. 166-169, 2014.

[34] Rigas G., Goletsis Y., Bougia P., and Fotiadis D., “Towards Driver’s State Recognition on Real Driving Conditions,” International Journal of Vehicular Technology, vol. 2011, pp. 1-14, 2011.

[35] Różanowski K., Truszczyński O., Filipczak K., and Madeyski M., “The Level of Driver Personality And Stress Experienced As Factors Influencing Behavior on The Road,” in Sustainable Development, vol. 168, pp. 1009- 1019, 2015.

[36] Schießl C., “Stress And Strain While Driving,” in Proceedings of the Young Researchers Seminar- European Conference of Transport Research Institutes, Brno, pp. 27-30, 2007.

[37] Shearer C., “The CRISP-DM Model: The New Blueprint for Data Mining,” Journal Data Warehousing, vol. 5, no. 4, pp. 13-22, 2000.

[38] Shiwu L., Linhong W., Zhifa Y., Bingkui J., Feiyan Q., and Zhongkai Y., “An Active Driver Fatigue Identification Technique Using Multiple Physiological Features,” in Proceedings of International Conference on Mechatronic Science, Electric Engineering and Computer, Jilin, pp. 733-737, 2011.

[39] Shu C. and Burn D., “Artificial Neural Network Ensembles and Their Application in Pooled Flood Frequency Analysis,” Water Resources Research, vol. 40, no. 9, 2004.

[40] Smart R., Cannon E., Howard A., Frise P., and Mann R., “Can We Design Cars To Prevent Road Rage?,” International Journal of Vehicle Information and Communication Systems, vol. 1, no. 1-2, pp. 44-55, 2005.

[41] Thabtah F., Hadi W., Abdelhamid N., and Issa A., “Prediction Phase in Associative Classification Mining,” International Journal of Software Engineering and Knowledge A New Two-step Ensemble Learning Model for Improving Stress Prediction of... 829 Engineering, vol. 21, no. 6, pp. 855-876, 2011.

[42] Tharwat A., “Classification Assessment Methods,” Applied Computing and Informatics, vol. 17, no. 1, pp. 168-192, 2021.

[43] Villaverde J., Godoy D., and Amandi A., “Learning Styles’ Recognition in E-Learning Environments with Feed-Forward Neural Networks,” Journal of Computer Assisted Learning, vol. 22, no. 3, pp. 197-206, 2006.

[44] WHO. Global status report on road safety 2018. Retrieved from https://www.who.int/violence_injury_prevention/ road_safety_status/2018/en/ Last Visited, 2021.

[45] Zhai J. and Barreto A., “Stress Detection in Computer Users Based on Digital Signal Processing of Noninvasive Physiological Variables,” in Proceedings of International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 1355-1358, New York, 2006. May Al-Nashashibi received the PhD degree from the University of Bradford, Bradford, UK. She is currently an Assistant Professor in the University of Petra, Amman, Jordan. She started her research focusing on Arabic natural language processing and text mining. Currently her research interests are concentrated on applying data mining techniques in the fields of medicine, biology, and chemistry. She has published research papers in reputed international journals/conferences. Wael Hadi is currently the Chair of Information Security at the University of Petra. He Holds a Ph.D. degree from the Arab Academy for Banking and Financial Sciences. His research interest in Data Mining, Machine Learning, and Big Data. Nuha El-Khalili is the Dean of Faculty of Information Technology and the director of the E-learning center at University of Petra. She obtained her PhD from the School of Computing at University of Leeds in the United Kingdom. She has 19 years of experience in teaching Software Engineering courses. Her research interest includes: data engineering for data science, quality assurance for managing academic programs, and e-learning. Ghassan Issa is a Professor of Computer Science. He received his M.S. and Ph.D. in Computer Science from Old Dominion University, Virginia, in 1987 and 1992 respectively. He was a faculty member and Department Chair of Computer Science at Pennsylvania College of Technology (Penn State), USA from 1992-1995. He also served as the Dean of Computer Science at the Applied Science University (Amman, Jordan) from 2003-2005, and the Dean of Information Technology at the University of Petra (Amman, Jordan) from 2008- 2018. Currently he is a Professor and the Dean of the School of Information Technology at Skyline University (Sharjah, UAE). Professor Issa’s research interest include Artificial Intelligence, Machine Learning and Deep Learning Fine Tuning, Case-Based and Analogical learning, and Associative Classification. Abd Alkarim Albanna is the CTO and the co-founder of Jordanian startup called TAKALAM, a company that provides solutions for hearing and speech disorder. He is a member of the Leaders in Innovation Fellowship from the Royal Academy of Engineering (the UK, 2020) and PhD student at Loughborough University England.