idearibosome/multimodal-activity-recorder

Multimodal recorder for activity recognition

Multimodal Recorder for Activity Recognition

This repository contains codes that enable retrieving human activity recognition data from multiple sensors simultaneously.

Supported platforms

• Windows 7+ (x86/x64)
• macOS 10.10+
• iOS 10.0+
• Android 5.0+ (API Level 21+)

Supported sensors

• Hardware-integrated sensors
  • Accelerometer (Android/iOS)
  • Ambient temperature (Android)
  • Gyroscope (Android/iOS)
  • Light sensor (Android)
  • Magnetometer (Android/iOS)
  • Pressure (Android)
  • Proximity (Android/iOS)
• Kinect v2 (Windows)
• BITalino BLE (macOS/iOS/Android)
• Fitbit Versa/Ionic (Windows/macOS/iOS/Android)

Dependencies

• Qt 5.9+
• (Kinect) Kinect SDK v2.0
• (Recognizer) PySide2

Project files

• Server: MultiModalRecorderServer.pro
• Client: MultiModalRecorderClient.pro
• Viewer: MultiModalRecorderViewer.pro

License

It is licensed under LGPLv3 with additional regulations. Please refer to the LICENSE file for more information.

Acknowledgement

This work was supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (R7124-16-0004, Development of Intelligent Interaction Technology Based on Context Awareness and Human Intention Understanding).

multimodal-activity-recorder's Issues

Test issue

Test issue

(Android) Operate each modality as a Service

백그라운드에서도 동작하도록, Service object에서 작동되도록 해야함

Refactor data parsers

Is your feature request related to a problem? Please describe.
Some data parsers cannot be accessed on specific operating systems.

Describe the solution you'd like
Data parsers should be separated from modality classes, because some modality classes are available only on specific operating systems.