**6. Conclusions**

Quantifying sedentary behaviour can provide valuable information about individuals' daily life patterns. In this research, we proposed a context-mining model to promote self-awareness by monitoring sedentary behaviour and providing a proactive platform for self-management. Participants reported a high level of satisfaction with active or sedentary behaviour, while moderate satisfaction while recognizing the micro-contexts. Micro-context recognition is a complex process that can take place in a wide variety of settings and is influenced by various environmental factors. Furthermore, our model processes the collected sensory data in real time and inside the smartphone environment, which prove the ubiquity of our solution and demonstrate how it does not require any server-side processing, which can obviously undermine privacy. Ultimately, it relaxes the assumption of a strong reliable communication channel to transfer the bulk amount of collected sensory data. The work is ongoing, and we are applying a deep learning model on environmental sound to learn more concrete contexts and situations. We are also working on a dashboard in our application, which will be able to demonstrate the visual representation of users' progress toward achieving a predetermined standard level of each behaviour for different age groups.

**Acknowledgments:** This research was supported by Zayed University RIF funding # R17063.

**Author Contributions:** Muhammad Fahim, Thar Baker and Asad Masood Khattak are the principal researchers of this research. Babar Shah, Saiqa Aleem and Fracis Chow contributed to the design of the framework. Muhammad Fahim implemented the idea in the Android platform. Asad Masood Khattak contributed to the development of the experimental protocol. All authors contributed equally to finalizing the manuscript.

**Conflicts of Interest:** The authors declare no conflict of interest.
