Data Augmentation of IMU Signals and Evaluation via a Semi-Supervised Classification of Driving Behavior
This work addresses a domain-specific problem for car insurance companies needing behavior classification from IMU data, but it is incremental as it applies existing methods to a specific data type.
The paper tackled the problem of classifying driving behavior as aggressive or normal using limited labeled IMU data by employing a semi-supervised learning approach with RCGAN for data augmentation, resulting in improved classification in 79% of cases compared to using no generated data.
Over the past years, interest in classifying drivers' behavior from data has surged. Such interest is particularly relevant for car insurance companies who, due to privacy constraints, often only have access to data from Inertial Measurement Units (IMU) or similar. In this paper, we present a semi-supervised learning solution to classify portions of trips according to whether drivers are driving aggressively or normally based on such IMU data. Since the amount of labeled IMU data is limited and costly to generate, we utilize Recurrent Conditional Generative Adversarial Networks (RCGAN) to generate more labeled data. Our results show that, by utilizing RCGAN-generated labeled data, the classification of the drivers is improved in 79% of the cases, compared to when the drivers are classified with no generated data.