Social Signal Processing for Android

SSJ is an extensible android framework for social signal processing in an out of lab envirnoment. It packages common signal processing tools in a flexible, mobile friendly Java library which can be easily integrated into Android Apps.

Features

• Realtime signal processing using independent components as processing steps in a pipeline
• Synchronized data streams
• Support for most standard Android sensors (camera, microphone, IMU, GPS, ...)
• Support for external sensors via Bluetooth (e.g. Myo, Empatica, MS Band 2, Angel Sensor, ...)
• Advanced signal processing functionality, including machine learning approaches (Neural Networks, SVM, NaiveBayes)
• On device model training capabilities (batch and online learning)
• I/O functionality: local storage, WiFi, Bluetooth
• Live data visualization (using GraphView library)
• SSJ Creator: Android App for building, editing and running SSJ pipelines without writing a single line of code

Downloads

• SSJ Creator can be downloaded from the play store.
• To use libssj in your own application, simply add the following code at the end of your module's gradle file:

  dependencies {
      implementation 'com.github.hcmlab:libssj:0.7.6'
  }

About

The SSJ framework is beeing developed at the Lab for Human Centered Multimedia of the University of Augsburg. The authors of the framework are: Ionut Damian, Michael Dietz, Frank Gaibler, Daniel Langerenken, Simon Flutura, Vitalijs Krumins and Antonio Grieco. If you want to get in touch, you can email us at:

SSJ has been inspired by the OpenSSI framework. SSJ is not a one-to-one port of SSI to Java, it is an approximation. Nevertheless, it borrows a lot of programming patterns from SSI and preserves the same vision for signal processing which makes SSI great. It than packages everything in a flexible, mobile friendly Java library which can be easily integrated into Android Apps.

Related Publications

If you use SSJ for a research project, please reference the following papers:

• Ionut Damian, Michael Dietz, Elisabeth André, The SSJ Framework: Augmenting Social Interactions Using Mobile Signal Processing and Live Feedback, Frontiers in ICT, 2018
  paper | BibTex
• Ionut Damian, Michael Dietz, Frank Gaibler, Elisabeth André, Social Signal Processing for Dummies, In Proceedings of International Conference on Multimodal Interaction (ICMI), ACM, 2016
  paper | BibTex | dl.acm.org

License

This library is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 3 of the License, or any later version. This library is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.