The Devil Is in the Details: An Efficient Convolutional Neural Network for Transport Mode Detection
This work addresses the problem of heavy computational costs in deep learning models for transport mode detection, which is incremental by optimizing existing methods for applications like carbon footprint tracking.
The paper tackles transport mode detection by proposing an efficient convolutional neural network that achieves comparable performance to state-of-the-art deep models while using 10 to 1,000 times fewer parameters and operations, as demonstrated on GeoLife and SHL 2018 datasets.
Transport mode detection is a classification problem aiming to design an algorithm that can infer the transport mode of a user given multimodal signals (GPS and/or inertial sensors). It has many applications, such as carbon footprint tracking, mobility behaviour analysis, or real-time door-to-door smart planning. Most current approaches rely on a classification step using Machine Learning techniques, and, like in many other classification problems, deep learning approaches usually achieve better results than traditional machine learning ones using handcrafted features. Deep models, however, have a notable downside: they are usually heavy, both in terms of memory space and processing cost. We show that a small, optimized model can perform as well as a current deep model. During our experiments on the GeoLife and SHL 2018 datasets, we obtain models with tens of thousands of parameters, that is, 10 to 1,000 times less parameters and operations than networks from the state of the art, which still reach a comparable performance. We also show, using the aforementioned datasets, that the current preprocessing used to deal with signals of different lengths is suboptimal, and we provide better replacements. Finally, we introduce a way to use signals with different lengths with the lighter Convolutional neural networks, without using the heavier Recurrent Neural Networks.