| FazBrowse GitHub Viewer | Trending | | Home |
| Tools: [Original HTTPS Page] |
Applied research in sensors, human movement and signal processing.
Rightstep Health conducts research and experimental engineering focused on measuring and interpreting biomechanical signals.
Our work combines wearable and body-mounted sensors, signal processing, data analysis and software engineering to investigate human movement, mechanical loading and musculoskeletal health.
Our areas of research and development include:
This research developed a method for estimating loading rate from acceleration signals in the frequency domain.
The method separates active movement and impact-loading components into frequency bands, allowing mechanical loading to be examined at specific body locations rather than relying only on measurements taken at the point of ground contact.
The study analysed acceleration measurements from the feet, shanks, thighs and pelvis alongside ground reaction force data during walking.
Read the publication on PubMed
Our research and experimental engineering are supported by Nexus N3, our open tooling platform for sensor integration, data acquisition, edge processing and research workflows.
Nexus N3 provides reusable hardware, software and developer tools for connecting sensors, capturing data and developing sensor-driven research and operational systems.
Repositories published through this organisation may include:
Each repository will describe its research question, methodology, data sources, assumptions and known limitations.
Raw sensor data is only the starting point.
Our research explores how acceleration, vibration and related biomechanical signals can be transformed into measures that describe movement, loading and the response of different parts of the body.
This includes investigating:
Public repositories in this organisation primarily contain research and experimental work.
Unless explicitly stated otherwise, software, algorithms, datasets and analyses published here:
Results should be interpreted within the scope and limitations documented by each project.
Research data will only be published where its release is ethically, legally and contractually permitted.
Public data will be open, synthetic, appropriately de-identified, anonymised or otherwise specifically authorised for release.
Learn more at rightstep-health.com.
Experimental PyTorch workflows for classifying knee vibroarthrography signals using time-frequency images and CNN/ResNet models.
Desktop research application for capturing, visualising, analysing and replaying vibroarthrography (VAG) signals from the Nexus N3 HDR Dot BLE sensor.
Research notebooks for analysing wearable accelerometer-derived bone loading during exercise on Earth and in microgravity from ESA’s 85th Parabolic Flight Campaign.
Research notebooks for classifying knee and hip osteoarthritis gait patterns from wearable inertial-sensor data using feature engineering and machine learning.
Research notebooks for estimating gait loading rate from wearable accelerometry in the frequency domain and comparing it with force-plate measurements.
R&D in wearable sensors, biomechanical signal processing and vibroarthrography, supported by the Nexus N3 open tooling platform.
This organization has no public members. You must be a member to see who’s a part of this organization.
Loading…
Loading…
| Back | FazBrowse Home | New Git URL |