# Validation of Inertial Sensor-Based Step Detection Algorithms for Edge Device Deployment

## TL;DR

This paper compares step detection algorithms using inertial sensors for edge devices, finding that Peak Detection performs best overall and upper arm placement is most accurate.

## Contribution

The study validates and compares five step detection algorithms for edge devices, revealing performance differences across scenarios and sensor placements.

## Key findings

- Peak Detection achieved the best overall performance with an average F1-score of 0.82.
- Upper arm sensor mounting yielded the highest accuracy (F1 = 0.84), outperforming ankle placement.

## Abstract

Step detection based on measurements of inertial measurement units (IMUs) is fundamental for human activity recognition, indoor navigation, and health monitoring applications. This study validates and compares five fundamentally different step detection algorithms for potential implementation on edge devices. A dedicated measurement system based on the Raspberry Pi Pico 2W microcontroller with two IMU sensors (Waveshare Pico-10DOF-IMU and Adafruit ST-9-DOF-Combo) was designed. The implemented algorithms include Peak Detection, Zero-Crossing, Spectral Analysis, Adaptive Threshold, and SHOE (Step Heading Offset Estimator). Validation was performed across 84 measurement sessions covering seven test scenarios (Timed Up and Go test, natural and fast walking, jogging, and stair climbing) and four sensor mounting locations (thigh pocket, ankle, wrist, and upper arm). Results demonstrate that Peak Detection achieved the best overall performance, with an average F1-score of 0.82, while Spectral Analysis excelled in stair scenarios (F1 = 0.86–0.92). Surprisingly, upper arm mounting yielded the highest accuracy (F1 = 0.84), outperforming ankle placement. The TUG clinical test proved most challenging (average F1 = 0.68), while fast walking was easiest (F1 = 0.87). Additionally, a preliminary application to 668 clinical TUG recordings from the open-access FRAILPOL database revealed algorithm-specific failure modes when continuous gait assumptions are violated. These findings provide practical guidelines for algorithm selection in edge computing applications and activity monitoring systems.