Quantified self (QS) is a term that exemplifies self-knowledge through self-tracking. The exponential rise in the number and variation of wearables and applications for personal use has facilitated smart-health concepts.… Click to show full abstract
Quantified self (QS) is a term that exemplifies self-knowledge through self-tracking. The exponential rise in the number and variation of wearables and applications for personal use has facilitated smart-health concepts. It has now become effortless for a user to monitor himself and track his routine activities to gain more in-depth insight into his health. However, to study and analyze the massive amount of data gathered by such devices, machine learning needs to be integrated into the decision-making process. In this work, we propose a quantified self-based hybrid model that considers user-health from multiple perspectives to provide relevant recommendations. We further analyze the performance of support vector machine, Naïve Bayes, and a metalevel hybrid model of SVM and Naïve Bayes for the intended work. Based on the results, it is observed that the hybrid model enhances the accuracy by 6% of the weak performing classifier.
               
Click one of the above tabs to view related content.