# The Devil Is in the Details: An Efficient Convolutional Neural Network for Transport Mode Detection

arXiv: https://arxiv.org/abs/2109.09504 · HTML: https://mlsanity.com/paper/2109.09504/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 41 references that are in the map.
- First posted on arXiv 16 Sep 2021.

## Builds on (most cited first, 5 of 5)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Particular object retrieval with integral max-pooling of CNN activations](https://mlsanity.com/paper/1511.05879/) (2015)
- [Inferring transportation modes from GPS trajectories using a convolutional neural network](https://mlsanity.com/paper/1804.02386/) (2018)
- [Transportation Modes Classification Using Feature Engineering](https://mlsanity.com/paper/1807.10876/) (2018)

## Built on by (most cited first, 2 of 2)

- [Advancing Object Detection in Transportation with Multimodal Large Language Models (MLLMs): A Comprehensive Review and Empirical Testing](https://mlsanity.com/paper/2409.18286/) (2024)
- [DeepStay: Stay Region Extraction from Location Trajectories using Weak Supervision](https://mlsanity.com/paper/2306.06068/) (2023)

## Abstract (arXiv)

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.