Releases: PhysiologicAILab/PhysioKit
Updated signal quality module
New Feature: Further updated signal quality assessment model to SQAPhysMD - trained with contrastive learning,
Pending items:: Video tutorials and recordings of the demos.
Full Changelog: V1.8.8...V2.0.1
V1.8.8
New Feature
- Updated signal quality assessment model to SQA_PhysMD, as published in our recent article: Joshi, J., & Cho, Y. (2024). Imaging Blood Volume Pulse Dataset: RGB-Thermal Remote Photoplethysmography Dataset with High-Resolution Signal-Quality Labels. Electronics, 13(7), 1334. https://doi.org/10.3390/electronics13071334
Pending items:
- Video tutorials and recordings of the demos.
Full Changelog: V1.8.0...V1.8.8
Presented PhysioKit based breathing biofeedback at Haptics soirée event, UCL on 3rd Nov 2023
New Feature:
-
Support for getting biofeedback over the UART - using the same arduino board as the one used for acquisition. This feature is illustrated only with two sensors scenario, however it can be achieved for any number of sensors.
-
Integration with mid-air haptics device for breathing biofeedback.
-
To implement this demo, please follow the steps as below:
- Download the source code (attached below), build the wheel package and install.
- Download the Arduino program and upload the same to Arduino.
- Download the software configuration file.
- Download the experiment configuration file.
- Launch PhysioKit with this command: physiokit --config [path to sw_config.json]
- Connect to the correct COM-Port.
- Load Experiment and specify the downloaded experiment configuration file - i.e. "exp_config_Resp_PPG_BF.json".
- Once the sensors are connected and live acquisition is started, the breathing biofeedback signal will be avilable on PWM Pin=5 of the Arduino.
Pending items:
- Video tutorials and recordings of the demos.
Refinements for Biofeedback
New Feature:
-
Support for getting biofeedback over the UART - using the same arduino board as the one used for acquisition. This feature is illustrated only with two sensors scenario, however it can be achieved for any number of sensors.
-
To implement this demo, please follow the steps as below:
- Install or update the PhysioKit2 package: pip install --upgrade PhysioKit2
- Download the Arduino program and upload the same to Arduino.
- Download the software configuration file.
- Download the experiment configuration file.
- Launch PhysioKit with this command: physiokit --config [path to sw_config.json]
- Connect to the correct COM-Port.
- Load Experiment and specify the downloaded experiment configuration file - i.e. "exp_config_Resp_PPG_BF.json".
- Once the sensors are connected and live acquisition is started, the breathing biofeedback signal will be avilable on PWM Pin=5 of the Arduino.
Pending items:
- Video tutorials and recordings of the demos.
Published at MDPI Sensors journal
Update after the work got published at MDPI sensors journal.
New feature:
- Real time visualization of PPG signal quality in the interface.
- Performance optimization.
Next plan for future release:
- Video tutorials and demo video
Published at MDPI Sensors journal
Update after the work got published at MDPI sensors journal.
New feature:
- Real time visualization of PPG signal quality in the interface.
- Performance optimization.
Next plan for future release:
- Video tutorials and demo video
Published at MDPI Sensors journal
Update after the work got published at MDPI sensors journal.
New feature:
- Real time visualization of PPG signal quality in the interface.
- Data analysis code in analysis_helper folder.
Next plan for future release:
- Video tutorials and demo video
- Performance optimization.
Published at MDPI Sensors journal
First release tag after the work got published at MDPI sensors journal.
Pending items for integration:
- Real time visualization on the UI for PPG signal quality in subplots.
- Sample-wise saving of signal quality data.
Fully Functional Release
Minor corrections in ReadMe
Fully Functional Release
Enhancements and support for latest versions of python and python packages.