# Evaluating Spiking Neural Network On Neuromorphic Platform For Human Activity Recognition

arXiv: https://arxiv.org/abs/2308.00787 · HTML: https://mlsanity.com/paper/2308.00787/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 41 references that are in the map.
- First posted on arXiv 1 Aug 2023.

## Builds on (most cited first, 16 of 16)

- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (2018)
- [End-to-End Learning of Representations for Asynchronous Event-Based Data](https://mlsanity.com/paper/1904.08245/) (2019)
- [Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware](https://mlsanity.com/paper/1812.01739/) (2018)
- [Training Deep Spiking Neural Networks](https://mlsanity.com/paper/2006.04436/) (2020)
- [FANN-on-MCU: An Open-Source Toolkit for Energy-Efficient Neural Network Inference at the Edge of the Internet of Things](https://mlsanity.com/paper/1911.03314/) (2019)
- [Sub-mW Neuromorphic SNN audio processing applications with Rockpool and Xylo](https://mlsanity.com/paper/2208.12991/) (2022)
- [An electronic neuromorphic system for real-time detection of High Frequency Oscillations (HFOs) in intracranial EEG](https://mlsanity.com/paper/2009.11245/) (2020)
- [Hang-Time HAR: A Benchmark Dataset for Basketball Activity Recognition using Wrist-Worn Inertial Sensors](https://mlsanity.com/paper/2305.13124/) (2023)
- [Wearable-based Human Activity Recognition with Spatio-Temporal Spiking Neural Networks](https://mlsanity.com/paper/2212.02233/) (2022)
- [The Contribution of Human Body Capacitance/Body-Area Electric Field To Individual and Collaborative Activity Recognition](https://mlsanity.com/paper/2210.14794/) (2022)
- [Motor control by precisely timed spike patterns](https://mlsanity.com/paper/1605.09023/) (2016)
- [Exploring Automatic Gym Workouts Recognition Locally On Wearable Resource-Constrained Devices](https://mlsanity.com/paper/2301.05748/) (2023)
- [ColibriES: A Milliwatts RISC-V Based Embedded System Leveraging Neuromorphic and Neural Networks Hardware Accelerators for Low-Latency Closed-loop Control Applications](https://mlsanity.com/paper/2302.07957/) (2023)
- [Dual-modality Smart Shoes for Quantitative Assessment of Hemiplegic Patients' Lower Limbs' Muscle Strength](https://mlsanity.com/paper/2305.13977/) (2023)

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

- [When In-memory Computing Meets Spiking Neural Networks -- A Perspective on Device-Circuit-System-and-Algorithm Co-design](https://mlsanity.com/paper/2408.12767/) (2024)
- [Low-power Spike-based Wearable Analytics on RRAM Crossbars](https://mlsanity.com/paper/2502.06736/) (2025)

## Abstract (arXiv)

Energy efficiency and low latency are crucial requirements for designing wearable AI-empowered human activity recognition systems, due to the hard constraints of battery operations and closed-loop feedback. While neural network models have been extensively compressed to match the stringent edge requirements, spiking neural networks and event-based sensing are recently emerging as promising solutions to further improve performance due to their inherent energy efficiency and capacity to process spatiotemporal data in very low latency. This work aims to evaluate the effectiveness of spiking neural networks on neuromorphic processors in human activity recognition for wearable applications. The case of workout recognition with wrist-worn wearable motion sensors is used as a study. A multi-threshold delta modulation approach is utilized for encoding the input sensor data into spike trains to move the pipeline into the event-based approach. The spikes trains are then fed to a spiking neural network with direct-event training, and the trained model is deployed on the research neuromorphic platform from Intel, Loihi, to evaluate energy and latency efficiency. Test results show that the spike-based workouts recognition system can achieve a comparable accuracy (87.5%) comparable to the popular milliwatt RISC-V bases multi-core processor GAP8 with a traditional neural network ( 88.1%) while achieving two times better energy-delay product (0.66 simicrojoulesecond vs. 1.32 simicrojoulesecond).