- Documentation: https://ast-monitor.readthedocs.io/en/latest
- Tested OS: Windows, Ubuntu, Fedora, Alpine, Arch, macOS. However, that does not mean it does not work on others
This repository is devoted to AST-Monitor, i.e., a low-cost and efficient embedded device for monitoring the realization of sport training sessions that are dedicated to monitoring cycling training sessions. AST-Monitor is a part of the Artificial Sport Trainer (AST) system. The first bits of AST-Monitor were presented in the following paper.
The initial page of the application depicts basic parameters of an athlete's activity: current speed and current heart rate. If a training session is conducted, total distance, total time of the session and total ascent are displayed as well.The second page of the application is devoted to an interactive map, which depicts athlete's current position.
Note: the position is currently hardcoded and does not respond according to GPS data.
The third page of the application depicts interval training data. During an interval training, total duration of the current phase is displayed along with current heart rate, average heart rate, Digital Twin proposed heart rate and the difference between the current and the proposed heart rate.
The fourth and final page of the application is intended for loading and starting interval trainings located in the folder "AST-Monitor/development/trainings". In order to be parsed correctly, trainings must be written in domain-specific language AST-TDL and converted to JavaScript Object Notation (JSON). After successful loading of an interval training, the training plan is displayed on this page.
The complete hardware part is shown in the figure from which it can be seen that the AST-computer is split into the following pieces:
- a platform with fixing straps that attach to a bicycle,
- the Raspberry Pi 4 Model B micro-controller with Raspbian OS installed,
- a five-inch LCD touch screen display,
- a USB ANT+ stick,
- Adafruit's Ultimate GPS HAT module.
A Serial Peripheral Interface (SPI) protocol was dedicated to communication between the Raspberry Pi and the GPS peripheral. A specialized USB ANT+ stick was used to capture the HR signal. The screen display was connected using a modified (physically shortened) HDMI cable, while the touch feedback was implemented using physical wires. The computer was powered during the testing phase using the Trust's (5 VDC) power bank. The AST-Monitor prototype is still a little bulky, but a more discrete solution is being searched for, including the sweat drainer of the AST. Internal components of AST-Monitor are depicted in the following scheme.
List of dependencies:
Package | Version | Platform |
---|---|---|
PyQt5 | ^5.15.6 | All |
matplotlib | ^3.5.1 | All |
geopy | ^2.2.0 | All |
openant | ^1.2.0 | All |
pyqt-feedback-flow | ^0.1.0 | All |
tcxreader | ^0.4.1 | All |
sport-activities-features | ^0.3.6 | All |
Additional note: adafruit-circuitpython-gps package must be installed in order to work with the GPS sensor:
$ pip install adafruit-circuitpython-gps
Install AST-Monitor with pip:
$ pip install ast-monitor
In case you want to install directly from the source code, use:
$ git clone https://github.com/firefly-cpp/AST-Monitor.git
$ cd AST-Monitor
$ poetry build
$ python setup.py install
To install AST-Monitor on Fedora Linux, please use:
$ dnf install python3-ast-monitor
To install AST-Monitor on Alpine Linux, please use:
$ apk add py3-ast-monitor
To install AST-Monitor on Arch Linux, please use an AUR helper:
$ yay -Syyu python-ast-monitor
Our project was deployed on a Raspberry Pi device using Raspberry Pi OS.
The hardware configuration of AST-Monitor using Raspberry Pi OS is described in HARDWARE_CONFIGURATION.md.
from PyQt5 import QtWidgets
import sys
try:
from ast_monitor.model import AST
except ModuleNotFoundError:
sys.path.append('../')
from ast_monitor.model import AST
# Paths to the files with heart rates and GPS data.
hr_data = '../sensor_data/hr.txt'
gps_data = '../sensor_data/gps.txt'
if __name__ == '__main__':
app = QtWidgets.QApplication(sys.argv)
window = AST(hr_data, gps_data)
window.show()
sys.exit(app.exec_())
This package is distributed under the MIT License. This license can be found online at http://www.opensource.org/licenses/MIT.
This framework is provided as-is, and there are no guarantees that it fits your purposes or that it is bug-free. Use it at your own risk!
Lukaฤ, L., Fister Jr., I., Fister, I. "Digital Twin in Sport: From an Idea to Realization." Applied Sciences 12.24 (2022): 12741.
Fister Jr, I., Fister, I., Iglesias, A., Galvez, A., Deb, S., & Fister, D. (2021). On deploying the Artificial Sport Trainer into practice. arXiv preprint arXiv:2109.13334.
Fister Jr, I., Salcedo-Sanz, S., Iglesias, A., Fister, D., Gรกlvez, A., & Fister, I. (2021). New Perspectives in the Development of the Artificial Sport Trainer. Applied Sciences, 11(23), 11452. DOI: 10.3390/app112311452
Iztok Fister Jr. ๐ ๐ ๐ป ๐ง ๐งโ๐ซ ๐ฆ |
luckyLukac ๐ ๐ ๐ป ๐จ |
Oromion ๐ฆ |
alenrajsp ๐ ๐ป |
Tatookie ๐ ๐ |