Instantaneous vehicle fuel consumption estimation using smartphones and recurrent neural networks

• Published in: Expert systems with applications Vol. 120; pp. 436 - 447
• Main Authors: Kanarachos, Stratis, Mathew, Jino, Fitzpatrick, Michael E.
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 15.04.2019; Elsevier BV
• Subjects: Air pollution; Balances (scales); Crowd monitoring; Driving conditions; Fuel consumption; Global positioning systems; GPS; Neural networks; Optimisation; Parametric analysis; Pollution monitoring; Recurrent neural networks; Road transportation; Satellite navigation systems; Smartphone data; Smartphones; Soft sensor; Training; Urban areas; Vehicle fuel consumption; Training; Vehicle fuel consumption; Recurrent neural networks; Soft sensor; Smartphone data; Optimisation
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2018.12.006

•Estimation of instantaneous vehicle fuel consumption using smartphone measurements.•Deep Neural Network estimation assessment and comparison to other methods.•Deep Neural Network training evaluation and proposal of a novel hybrid training technique.•Performance loss investigation for less information-rich inputs. The high level of air pollution in urban areas, caused in no small extent by road transport, requires the implementation of continuous and accurate monitoring techniques if emissions are to be minimized. The primary motivation for this paper is to enable fine spatiotemporal monitoring based on crowd sensing, whereby the instantaneous fuel consumption of a vehicle is estimated using smartphone measurements. To this end, a surrogate method based on indirect monitoring using Recurrent Neural Networks (RNNs) that process a smartphone's GPS position, speed, altitude, acceleration and number of visible satellites is proposed. Extensive field trials were conducted to gather smartphone and fuel consumption data at a wide range of driving conditions. Two different RNN types were explored, and a parametric analysis was performed to define a suitable architecture. Various training methods for tuning the RNN were evaluated based on performance and computational burden. The resulting estimator was compared with others found in the literature, and the results confirm its superior performance. The potential impact of the proposed method is noteworthy as it can facilitate accurate monitoring of in-use vehicle fuel consumption and emissions at large scales by exploiting available smartphone measurements.