Sensor‑Driven Framework for Predicting Human Thermal Comfort and Heat Stress in Connected Vehicle Environments.

  The passage outlines a system that employs sensors and deep learning, a form of artificial intelligence, to forecast how comfortable individuals feel inside a vehicle and assess their potential for experiencing heat stress. This system gathers real-time data from sensors that track variables such as temperature, humidity, airflow, and the physical indicators of the occupants. It then utilizes AI models to interpret how these elements influence a person's comfort and risk of heat stress. Consequently, the vehicle's climate control system can automatically adjust to maintain passenger comfort and safety.[8] Additionally, the system conserves energy by optimizing heating and cooling based on these forecasts. In essence, it enhances the in-car experience by swiftly adapting to changing conditions and individual variations in temperature perception. The proposed sensor‑driven CNN‑LSTM framework demonstrated high predictive accuracy, robust real‑world performance, and energy‑efficient HVAC adaptation. Its integration with connected vehicle networks enables intelligent, human‑centric climate control, advancing comfort prediction and heat stress prevention in next‑generation automotive systems.

[1] Y. J. Ju, J. R. Lim, and E. S. Jeon, “Prediction of AI-Based Personal Thermal Comfort in a Car Using Machine-Learning Algorithm,” Electronics, vol. 11, no. 3, p. 340, Jan. 2022, doi: 10.3390/electronics11030340.   [2] T. Reuscher, K. Poovendran, and D. Abel, “Model predictive zonal temperature control of a vehicle cabin,” Institute Of Electrical Electronics Engineers, July 2021, pp. 37–43. doi: 10.1109/aim46487.2021.9517692.   [3] X. Zhou et al., “Dual-phase prediction model of passenger thermal sensation using facial thermal imaging and environmental factors,” Case Studies in Thermal Engineering, vol. 58, p. 104439, Apr. 2024, doi: 10.1016/j.csite.2024.104439.   [4] M. Colley, S. Hartwig, A. Zeqiri, T. Ropinski, and E. Rukzio, “AutoTherm: A Dataset and Benchmark for Thermal Comfort Estimation Indoors and in Vehicles,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 8, no. 3, pp. 1–49, Aug. 2024, doi: 10.1145/3678503.   [5] M. Savelonas, I. Vernikos, D. Mantzekis, E. Spyrou, A. Tsakiri, and S. Karkanis, “Hybrid Representation of Sensor Data for the Classification of Driving Behaviour,” Applied Sciences, vol. 11, no. 18, p. 8574, Sept. 2021, doi: 10.3390/app11188574.   [6] N. Baharudin, B. Manshoor, M. Mohamed Salleh, A. N. A. Ahmad, M. A. S. Sabrudin, and M. Mondal, “Examining the Influence of Vehicle Speed on Thermal Comfort and Temperature Control in Vehicle Cabins,” J. Adv. Res. Fluid Mech. Therm. Sc., vol. 132, no. 1, pp. 141–157, June 2025, doi: 10.37934/arfmts.132.1.141157.   [7] S. Vallabhuni and K. Debasis, “Hybrid deep learning for IoT-based health monitoring with physiological event extraction.,” DIGITAL HEALTH, vol. 11, p. 20552076251337848, May 2025, doi: 10.1177/20552076251337848.   [8] M. Duzgun, B. Ozarisoy, H. Altan, and S. Moshaver, “Analysis of Technological Systems for Improving Drivers’ Thermal Comfort,” Engineering Reports, vol. 7, no. 4, Apr. 2025, doi: 10.1002/eng2.70128.