Mining Personalized Climate Preferences for Assistant Driving

TL;DR

This paper presents a novel IoT-based system for personalized climate control and driver behavior recognition in assistant driving, improving comfort and health by leveraging real-world data and machine learning.

Contribution

It introduces an integrated approach combining IoT sensors, machine learning, and personalized recommendations for climate control tailored to individual driver preferences.

Findings

Effective driver behavior recognition with high accuracy.

Personalized climate recommendations improve driver comfort.

System tested on 11,370 km of real-world driving data.

Abstract

Both assistant driving and self-driving have attracted a great amount of attention in the last few years. However, the majority of research efforts focus on safe driving; few research has been conducted on in-vehicle climate control, or assistant driving based on travellers' personal habits or preferences. In this paper, we propose a novel approach for climate control, driver behavior recognition and driving recommendation for better fitting drivers' preferences in their daily driving. The algorithm consists three components: (1) A in-vehicle sensing and context feature enriching compnent with a Internet of Things (IoT) platform for collecting related environment, vehicle-running, and traffic parameters that affect drivers' behaviors. (2) A non-intrusive intelligent driver behaviour and vehicle status detection component, which can automatically label vehicle's status (open windows, turn on air condition, etc.), based on results of applying further feature extraction and machine learning algorithms. (3) A personalized driver habits learning and preference recommendation component for more healthy and comfortable experiences. A prototype using a client-server architecture with an iOS app and an air-quality monitoring sensor has been developed for collecting heterogeneous data and testing our algorithms. Real-world experiments on driving data of 11,370 km (320 hours) by different drivers in multiple cities worldwide have been conducted, which demonstrate the effective and accuracy of our approach.