Rethinking Temporal Models for TinyML: LSTM versus 1D-CNN in Resource-Constrained Devices

TL;DR

This paper compares LSTM and 1D-CNN models for time series classification on resource-constrained devices, finding 1D-CNN more efficient and equally or more accurate for TinyML applications.

Contribution

It provides a hardware-aware feasibility analysis showing 1D-CNN's advantages over LSTM for TinyML deployment on microcontrollers.

Findings

1D-CNN achieves ~95% accuracy, LSTM around 89%.

1D-CNN uses 35% less RAM and 25% less Flash memory.

1D-CNN enables real-time inference at 27.6 ms, compared to 2038 ms for LSTM.

Abstract

Time series classification underpins applications such as human activity recognition, healthcare monitoring, and gesture detection in the IoT domain. Tiny Machine Learning enables models to run directly on low-power microcontroller units, improving efficiency, ensuring privacy, and reducing cost by avoiding reliance on cloud or edge computing. While Long Short-Term Memory networks are widely used for capturing temporal dependencies, their high computational and memory demands make real-time MCU deployment impractical. In this work, we conduct a hardware-aware feasibility study of LSTM versus 1D Convolutional Neural Networks across five benchmark datasets. Results show that 1D-CNN consistently achieves comparable or higher accuracy around 95% than LSTM which is around 89%, while requiring 35% less RAM, approx. 25% less Flash, and enabling real-time inference that is 27.6 ms vs. 2038 ms. Being so lightweight, 1D-CNN is particularly suitable for on-device processing in wearables and other low-power, battery-operated systems, establishing it as a practical and resource-efficient choice for TinyML deployment.