長時間的駕駛可能因姿勢或是精神渙散而有不舒適感，增加行駛中的風
險，最後可能導致事故發生或者死亡，而生理訊號被認為是偵測駕駛最可
靠的方法。目前市面上多以壓力墊佐問卷結果來評估受試者舒適程度，但
價格昂貴且維護不易，以至於無法推廣到車用市場上。在本論文中，我透
過統計迴歸的方式，讓較為耐用且可替換性高的氣囊取代成本較高的壓力
墊，再藉由層次分析法找到氣囊內壓力值的最佳初始值，讓駕駛於行駛時
有良好的模擬駕駛體驗。而在模擬駕駛中，也發現了壓力訊號舒適與不舒
適的差異性，除此之外也藉由邏輯迴歸，找到與舒適度有關的壓力訊號參
數。
本篇實驗設計了一連串模擬駕駛下的實驗流程，目的是找出與舒適度有
關的壓力訊號參數。首先，分析了八名受試者於一小時模擬駕駛情況下的
壓力訊號變化，並針對訊號制定了幾個參數，再透過問卷的方式得到受試
者感受並做相關性分析，實驗結果中透過雙尾檢定分析各參數和舒適度都
有 70% 左右的相關性，並找出舒適與不舒適訊號的顯著差異，為了提高判
斷受試者舒適性的準確性，使用邏輯迴歸模型進一步分析參數對於舒適度
的預測能力，再將制定的參數進行分析，最後透過向前選擇法，將選擇的
參數組合相對於原始的壓力訊號參數組合的舒適度預測模型更為準確，使
左腿、右腿、臀部這三個部分的模型準確度分別上升了 13%、15%、8%，
找到了藉由生理壓力訊號參數預測駕駛舒適度的方法。

Prolonged driving may lead to discomfort due to postural issues or mental distractions, increasing the risk of accidents or fatalities. Physiological signals are considered the most reliable method for detecting driver discomfort. Currently, pressure mats combined with questionnaires are commonly used to assess the comfort level of participants, but their high cost and maintenance challenges hinder their widespread use in the automotive market. In this study, I employed statistical regression to replace the higher-cost pressure mats with more durable and easily replaceable airbags. Subsequently, using the analytic hierarchy process , I determined the optimal initial pressure values within the airbags, enhancing the driver's simulated driving experience. During simulated driving, disparities between comfortable and uncomfortable pressure signals were observed. Furthermore, through logistic regression, pressure signal parameters related to comfort were identified.

A series of experiments were designed to investigate pressure signal parameters associated with comfort during simulated driving. The analysis of pressure signal variations in eight participants during a one-hour simulated driving scenario and derived several parameters based on the signals. Subsequently, questionnaire responses were collected from the participants to assess their perceived comfort levels. Through correlation analysis, it was found that various parameters exhibited approximately 70\% correlation with comfort. Furthermore, significant differences were identified between pressure signals corresponding to comfort and discomfort. To improve the accuracy of comfort assessment, the application of logistic regression further analyzed the predictive capabilities of the parameters on comfort. The selected parameters were subjected to forward selection, resulting in model improvements of 13\%, 15\%, and 8\% for the left leg, right leg, and hip regions, respectively, compared to the original pressure signal parameters. This indicates that the newly chosen parameter combinations provide more accurate predictions of driver comfort, thus establishing the feasibility of using physiological pressure signal parameters to predict driver comfort during driving simulations.

[1] “Global status report on road safety,” 2021. [Online]. Available: https://www.who.int/
violence_injury_prevention/road_safety_status/2021/en/.
[2] K. Hartman, J. Strasser, and C. Systematics, “Saving lives through advanced vehicle safety
technology: Intelligent vehicle initiative,” United States. Federal Highway Administration,
Tech. Rep., 2005.
[3] E. Grandjean, “Fatigue in industry.” Occupational and Environmental Medicine, vol. 36,
no. 3, pp. 175–186, 1979.
[4] J. F. May and C. L. Baldwin, “Driver fatigue: The importance of identifying causal factors
of fatigue when considering detection and countermeasure technologies,” Transportation
research part F: traffic psychology and behaviour, vol. 12, no. 3, pp. 218–224, 2009.
[5] S. Malik, H. Jürgens, and K. Helbig, “Quantitative analysis of involuntary movements
as a test of comfort of a car seat: A study of man-machine interface,” Journal of Human
Ecology, vol. 2, no. 1, pp. 53–61, 1991.
[6] J. Meyer, B. Arnrich, J. Schumm, and G. Troster, “Design and modeling of a textile pressure
sensor for sitting posture classification,” IEEE Sensors Journal, vol. 10, no. 8, pp.
1391–1398, 2010.
[7] U. Kilincsoy, A. Wagner, P. Vink, and H. Bubb, “Application of ideal pressure distribution
in development process of automobile seats,” Work, vol. 54, no. 4, pp. 895–904, 2016.
[8] R. Votrubec, “Control system of the seat with variable stiffness,” in Proceedings of the
16th International Conference on Mechatronics-Mechatronika 2014. IEEE, 2014, pp.
314–317.
[9] K. Slater, Human comfort. Springfield, Ill., USA: CC Thomas, 1985.
[10] H. T. E. Hertzberg, “The human buttocks in sitting: pressures, patterns, and palliatives,”
SAE Transactions, pp. 39–47, 1972.
[11] K. Ebe and M. J. Griffin, “Qualitative models of seat discomfort including static and dynamic
factors,” Ergonomics, vol. 43, no. 6, pp. 771–790, 2000.
[12] N. J. Mansfield, “Impedance methods (apparent mass, driving point mechanical
impedance and absorbed power) for assessment of the biomechanical response of the
seated person to whole-body vibration,” Industrial Health, vol. 43, no. 3, pp. 378–389,
2005.
[13] “Cloud security questions?” 2010, https://www.geeknev.com/jxwd/290/2900960.html.
[14] J. Peng, X. Wang, and L. Denninger, “Effects of anthropometric variables and seat height
on automobile drivers＇preferred posture with the presence of the clutch,” Human factors,
vol. 60, no. 2, pp. 172–190, 2018.
[15] M. J. Griffin, “Discomfort from feeling vehicle vibration,” Vehicle System Dynamics,
vol. 45, no. 7-8, pp. 679–698, 2007.
[16] M. Li, Z. Gao, F. Gao, T. Zhang, X. Mei, and F. Yang, “Quantitative evaluation of vehicle
seat driving comfort during short and long term driving,” IEEE Access, vol. 8, pp.
111 420–111 432, 2020.
[17] J. Smith, N. Mansfield, D. Gyi, M. Pagett, and B. Bateman, “Driving performance and
driver discomfort in an elevated and standard driving position during a driving simulation,”
Applied ergonomics, vol. 49, pp. 25–33, 2015.
[18] J. M. Porter, D. E. Gyi, and H. A. Tait, “Interface pressure data and the prediction of driver
discomfort in road trials,” Applied ergonomics, vol. 34, no. 3, pp. 207–214, 2003.
[19] M. Varela, D. Gyi, N. Mansfield, R. Picton, A. Hirao, and T. Furuya, “Engineering movement
into automotive seating: Does the driver feel more comfortable and refreshed?”
Applied ergonomics, vol. 74, pp. 214–220, 2019.
[20] Ö. Tunçer, L. Güvenç, F. Coşkun, and E. Karslıgil, “Vision based lane keeping assistance
control triggered by a driver inattention monitor,” in 2010 IEEE International Conference
on Systems, Man and Cybernetics. IEEE, 2010, pp. 289–297.
[21] J. C. Verster and T. Roth, “Standard operation procedures for conducting the on-the-road
driving test, and measurement of the standard deviation of lateral position (sdlp),” International
journal of general medicine, vol. 4, p. 359, 2011.
[22] R. Senaratne, D. Hardy, B. Vanderaa, and S. Halgamuge, “Driver fatigue detection by
fusing multiple cues,” Advances in Neural Networks–ISNN 2007, p. 801–809.
[23] G. M. Sammonds, M. Fray, and N. J. Mansfield, “Effect of long term driving on driver
discomfort and its relationship with seat fidgets and movements (sfms),” Applied ergonomics,
vol. 58, pp. 119–127, 2017.
[24] Z. Mu, J. Hu, and J. Min, “Driver fatigue detection system using electroencephalography
signals based on combined entropy features,” Applied Sciences, vol. 7, no. 2, p. 150, 2017.
[25] J. Verster and T. Roth, “Standard operation procedures for conducting the on-the-road
driving test, and measurement of the standard deviation of lateral position (SDLP),” International
journal of general medicine, vol. 4, pp. 359–71, May. 2011.
[26] F. Abtahi, A. Anund, C. Fors, F. Seoane, and K. Lindecrantz, “Association of drivers’
sleepiness with heart rate variability: A pilot study with drivers on real roads,” EMBEC
& NBC 2017, pp. 149–152, 2018.
[27] R. Bhardwaj, P. Natrajan, and V. Balasubramanian, “Study to determine the effectiveness
of deep learning classifiers for ECG based driver fatigue classification,” IEEE 13th International
Conference on Industrial and Information Systems (ICIIS), pp. 98–102, 2018.
[28] A. Chowdhury, R. Shankaran, M. Kavakli, and M. M. Haque, “Sensor applications and
physiological features in drivers＇drowsiness detection: A review,” IEEE Sensors Journal,
vol. 18, no. 8, pp. 3055–3067, 2018.
[29] H. Nakane, J. Toyama, and M. Kudo, “Fatigue detection using a pressure sensor chair,” in
2011 IEEE International Conference on Granular Computing. IEEE, 2011, pp. 490–495.
[30] M. Ingre, T. Åkerstedt, B. Peters, A. Anund, and G. Kecklund, “Subjective sleepiness,
simulated driving performance and blink duration: examining individual differences,”
Journal of Sleep Research, vol. 15, no. 1, pp. 47–53, 2006. [Online]. Available:
https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1365-2869.2006.00504.x
[31] B. M. Deros, D. D. I. Daruis, and M. J. M. Nor, “Evaluation of static car driver seat
discomfort through objective and subjective methods,” APIEMS2009, Kitakyushu, 2009.
[32] T. L. Saaty, “Decision making with the analytic hierarchy process,” International journal
of services sciences, vol. 1, no. 1, pp. 83–98, 2008.
[33] S. K. Clark and K. D. Wise, “Pressure sensitivity in anisotropically etched thin-diaphragm
pressure sensors,” IEEE Transactions on Electron Devices, vol. 26, no. 12, pp. 1887–1896,
Dec 1979.
[34] C. Ravariu, F. Ravariu, D. Dobrescu, L. Dobrescu, C. Codreanu, and M. Avram, “A designing
roule for a pressure sensor with pzt layer,” in 2001 International Semiconductor
Conference. CAS 2001 Proceedings (Cat. No.01TH8547), vol. 2, Oct 2001, pp. 379–382
vol.2.
[35] A. Gieles, “Subminiature silicon pressure transducer,” in 1969 IEEE International Solid-
State Circuits Conference. Digest of Technical Papers, vol. 12. IEEE, 1969, pp. 108–109.
[36] M. Awais, N. Badruddin, and M. Drieberg, “A hybrid approach to detect driver drowsiness
utilizing physiological signals to improve system performance and wearability,” Sensors,
vol. 17, no. 9, p. 1991, 2017.
[37] K. Fujiwara, E. Abe, K. Kamata, C. Nakayama, Y. Suzuki, T. Yamakawa, T. Hiraoka,
M. Kano, Y. Sumi, F. Masuda et al., “Heart rate variability-based driver drowsiness detection
and its validation with eeg,” IEEE transactions on biomedical engineering, vol. 66,
no. 6, pp. 1769–1778, 2018.
[38] E. Marenzi, G. M. Bertolotti, and A. Cristiani, “Design and development of a monitoring
system for the interface pressure measurement of seated people,” IEEE Transactions on
Instrumentation and Measurement, vol. 62, no. 3, pp. 570–577, 2013.
[39] G. Andreoni, G. C. Santambrogio, M. Rabuffetti, and A. Pedotti, “Method for the analysis
of posture and interface pressure of car drivers,” Applied ergonomics, vol. 33, no. 6, pp.
511–522, 2002.
[40] D. E. Gyi, J. M. Porter, and N. K. Robertson, “Seat pressure measurement technologies:
considerations for their evaluation,” Applied Ergonomics, vol. 29, no. 2, pp. 85–91, 1998.
[41] K. Uenishi, M. Tanaka, H. Yoshida, S. Tsutsumi, and N. Miyamoto, “Driver’s fatigue
evaluation during long term driving for automotive seat development,” SAE Technical
Paper, Tech. Rep., 2002.
[42] M. Kolich, “Reliability and validity of an automobile seat comfort survey,” SAE Technical
Paper, Tech. Rep., 1999.
[43] A. Talukder and M. Z. Hossain, “Prevalence of diabetes mellitus and its associated factors
in bangladesh: application of two-level logistic regression model,” Scientific Reports,
vol. 10, no. 1, p. 10237, 2020.
[44] “Micropressure mpr series,” 2023. [Online]. Available: https:
//sps.honeywell.com/us/en/products/advanced-sensing-technologies/healthcare-sensing/
board-mount-pressure-sensors/micropressure-mpr-series