Vibration Detection of Vehicle Impact Using Smartphone Accelerometer Data and Long-Short Term Memory Neural Network

João Paulo Brognoni Casati; Ruy Alberto  Corrêa Altafim; Ruy Alberto  Pisani Altafim

doi:10.48011/asba.v2i1.1274

João Paulo Brognoni Casati Universidade de São Paulo
Ruy Alberto Corrêa Altafim Universidade de São Paulo, Universidade Federal da Paraíba
Ruy Alberto Pisani Altafim Universidade Federal da Paraíba

DOI: https://doi.org/10.48011/asba.v2i1.1274

Keywords: Artificial neural networks, Deep learning, Long-short term memory, Accelerometer, Trafic analysis, Smart cities

Abstract

Vehicle’s analysis can be useful for a variety of traffic problems, such as monitoring road damages and vehicle type classification. Further, traffic behavior analysis can be useful to monitor traffic jams as a smart cities solution. In this paper, the vibration caused by a vehicle passing through a speed bump was recorded with a docked smartphone. The acquired signals were processed in order to detect the generated impact. In order to analyze this data a LSTM neural network was used due to its classification process over time while the smartphone accelerometer was continuously operating (waiting for a vehicle pass by). This deep learning technique allows the use of raw 3-axis accelerometer data. The results achieved 98% of accuracy with a low level of false positives (less than 1%). Indicating that the methodology is effective in classification of vehicles by their impact vibration.