Koios Crowdsensing Platform


A resource efficient and context-aware mobile crowdsensing platform


Mobile crowdsensing is the technique to collect sensor and context data from smartphone/wearables to infer or predict information about a person or group. The method is widely used in psychology, social science, and mHealth research studies. Acquiring sufficient data within energy constraints is one of the challenges in crowdsensing applications, especially those, are used to collect high-frequency data in longitudinal studies. Context information plays a vital role in data collection to minimize energy consumption. For example, it could be unnecessary to collect data when the participant is sleeping. In this particular case, we need to know when a person is sleeping. So, inferring context is one challenge. Another challenge is to find a correlation between different kinds of context so that they can be used to activate or deactivate sensing as per need. The project is intended to build a mobile crowdsensing platform that can be used in various data collection projects, maintaining the right balance between data quality and energy consumption.

Source Code



NetHealth Data


  • Afzal Hossain and Christian Poellabauer, "Efficient Location Sensing in Longitudinal Cohort Studies", Proceedings of 43rd IEEE Conference on Local Computer Networks (LCN), Chicago, IL, October 2018.
  • Afzal Hossain and Christian Poellabauer, "Challenges in Building Continuous Smartphone Sensing Applications", Proceedings of the 9th IEEE International Workshop on Selected Topics in Wireless and Mobile Computing, New York, NY, October 2016.

Project Members

  • Dr. Christian Poellabauer
  • Afzal Hossain