# Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection

arXiv: https://arxiv.org/abs/1701.01077 · HTML: https://mlsanity.com/paper/1701.01077/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jan 2017.

## Built on by (most cited first, 7 of 7)

- [Adversarial Deep Feature Extraction Network for User Independent Human Activity Recognition](https://mlsanity.com/paper/2110.12163/) (2021)
- [TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation](https://mlsanity.com/paper/2209.09092/) (2022)
- [Resource-aware Time Series Imaging Classification for Wireless Link Layer Anomalies](https://mlsanity.com/paper/2104.00972/) (2021)
- [IoT Solutions with Multi-Sensor Fusion and Signal-Image Encoding for Secure Data Transfer and Decision Making](https://mlsanity.com/paper/2106.01497/) (2021)
- [Heterogeneous Noisy Short Signal Camouflage in Multi-Domain Environment Decision-Making](https://mlsanity.com/paper/2106.02044/) (2021)
- [A Novel Local-Global Feature Fusion Framework for Body-weight Exercise Recognition with Pressure Mapping Sensors](https://mlsanity.com/paper/2309.07888/) (2023)
- [Topological Persistence Guided Knowledge Distillation for Wearable Sensor Data](https://mlsanity.com/paper/2407.05315/) (2024)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have become the state-of-the-art in various computer vision tasks, but they are still premature for most sensor data, especially in pervasive and wearable computing. A major reason for this is the limited amount of annotated training data. In this paper, we propose the idea of leveraging the discriminative power of pre-trained deep CNNs on 2-dimensional sensor data by transforming the sensor modality to the visual domain. By three proposed strategies, 2D sensor output is converted into pressure distribution imageries. Then we utilize a pre-trained CNN for transfer learning on the converted imagery data. We evaluate our method on a gait dataset of floor surface pressure mapping. We obtain a classification accuracy of 87.66%, which outperforms the conventional machine learning methods by over 10%.