This PhD research formulates the problem of mining contextual behavioral rules for individual users utilizing their smartphone data. In particular, we propose a dynamic time-series segmentation technique for behavioral data clustering, a machine learning rule-based classification technique for context-aware usage behavior modeling and prediction, and a recency-based rule learning approach for dynamic updating and management of the discovered behavioral rules, to achieve our goal.
J.R.Quinlan, C4.5: Programs for machine learning, Machine Learning (1993).
2.
I.H.Sarker, A.Colman, M.A.Kabir and J.Han, Individualized time-series segmentation for mining mobile phone user behavior, The Computer Journal, Oxford University, UK61(3) (2018), 349–368.
3.
I.H.Sarker, M.A.Kabir, A.Colman and J.Han, Identifying recent behavioral data length in mobile phone log, in: Proceedings of the 2017 ACM EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services. (MobiQuitous 2017), Melbourne, Australia, 2017.
4.
I.H.Sarker, M.A.Kabir, A.Colman and J.Han, Understanding recency-based behavior model for individual mobile phone users, in: Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers, USA, ACM, 2017, pp. 916–921.
5.
I.H.Sarker and F.D.Salim, Mining user behavioral rules from smartphone data through association analysis, in: Proceedings of the 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), Melbourne, Australia, Springer, 2018, pp. 450–461.
