# Online Human Activity Recognition using Low-Power Wearable Devices

arXiv: https://arxiv.org/abs/1808.08615 · HTML: https://mlsanity.com/paper/1808.08615/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2018.

## Built on by (most cited first, 10 of 10)

- [Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances](https://mlsanity.com/paper/2111.00418/) (2021)
- [Human Activity Recognition models using Limited Consumer Device Sensors and Machine Learning](https://mlsanity.com/paper/2201.08565/) (2022)
- [Impact of On-Chip Interconnect on In-Memory Acceleration of Deep Neural Networks](https://mlsanity.com/paper/2107.02358/) (2021)
- [Analysing the Performance of Stress Detection Models on Consumer-Grade Wearable Devices](https://mlsanity.com/paper/2203.09669/) (2022)
- [Sensor-Aware Classifiers for Energy-Efficient Time Series Applications on IoT Devices](https://mlsanity.com/paper/2407.08715/) (2024)
- [Early Mobility Recognition for Intensive Care Unit Patients Using Accelerometers](https://mlsanity.com/paper/2106.15017/) (2021)
- [Unstructured Handwashing Recognition using Smartwatch to Reduce Contact Transmission of Pathogens](https://mlsanity.com/paper/2107.13405/) (2021)
- [Settling the Communication Complexity for Distributed Offline Reinforcement Learning](https://mlsanity.com/paper/2202.04862/) (2022)
- [Towards Stroke Patients' Upper-limb Automatic Motor Assessment Using Smartwatches](https://mlsanity.com/paper/2212.05062/) (2022)
- [Posture Recognition in the Critical Care Settings using Wearable Devices](https://mlsanity.com/paper/2110.02768/) (2021)

## Abstract (arXiv)

Human activity recognition~(HAR) has attracted significant research interest due to its applications in health monitoring and patient rehabilitation. Recent research on HAR focuses on using smartphones due to their widespread use. However, this leads to inconvenient use, limited choice of sensors and inefficient use of resources, since smartphones are not designed for HAR. This paper presents the first HAR framework that can perform both online training and inference. The proposed framework starts with a novel technique that generates features using the fast Fourier and discrete wavelet transforms of a textile-based stretch sensor and accelerometer. Using these features, we design an artificial neural network classifier which is trained online using the policy gradient algorithm. Experiments on a low power IoT device (TI-CC2650 MCU) with nine users show 97.7% accuracy in identifying six activities and their transitions with less than 12.5 mW power consumption.