Abstract
Conference Title: 2017 International Conference on Informatics, Health & Technology (ICIHT) Conference Start Date: 2017, Feb. 21 Conference End Date: 2017, Feb. 23 Conference Location: Riyadh, Saudi Arabia The rapid advancement of wearable devices and smartphones, allowed practitioners and specialists to keep track of physical, biological and behavioral activities. Nowadays, this self tracking, a.k.a. quantified self (QS), is widely used in big data science due to the large volume of data being generated from these devices. The wearable devices that are being used today for self-tracking can collect enormous amounts of data for an individual from only one activity such as collecting the heart rates for an individual; it generates around 9 gigabytes of data per person per month. The collected data from an individual or from a group might lead to extraordinary advancement in vast scientific fields if it has been collected, organized, and analysed in a proper manner. Examples of the advantages include, but not limited to, helping to improve health of targeted individuals, predicting future incidents or events, helping decision makers in governments and organizations in taking the right decisions at the right time according to data collected and analyzed from crows, that is to name a few. In this paper, we analyze existing approaches of utilizing and handling QS as big data, and the state of the art mining approaches in this emerging domain comparing two primary findings from previous studies and how it impacts individual’s health, especially among adults who suffer from obesity and diabetes. We also did and analyze a survey among self-trackers in Saudi Arabia to have an understating of the QS movement in the country and how it can be improved for healthcare purposes.