Noise-Aware Optimization for Mobile Crowdsensing-Based Travel Time Estimation.

Predicting the estimated time of arrival (ETA) is crucial for ride-hailing platforms and autonomous vehicle systems. Although deep neural network-based models have demonstrated high accuracy in ETA prediction, their loss functions often assume standard noise distribution, which fails to account for the noise distribution in real-world mobile crowdsensing travel orders. This study investigates the dynamic noise distribution in practical travel orders and identifies two key types of noise in ETA prediction: intrinsic noise at the start or end of the order and accumulated noise during travel. To address this issue, we propose a novel method called Noise-aware Optimization (NAO) for ETA prediction that generates dynamic noise distributions from real-world datasets and optimizes the ETA model through maximum likelihood estimation accordingly. We provide two specific forms of NAO for ETA prediction with Gaussian and Laplace noise distributions, respectively, to facilitate practical applications. Additionally, we compare commonly used regression loss functions with NAO under a probability interpretation to illustrate the principle of NAO. Our experiments conducted on the DiDi platform in two large cities demonstrate the superior effectiveness of NAO over other loss functions.