Computational Enhancement of All Possible Context Generation in Modified-SPEED Algorithm
Araf Farayez, Mamun Bin Ibne Reaz, Norhana Arsad · 2018
With the rising demand for smart devices and smart home systems, automation and activity prediction have become a vital aspect of people's everyday lives. Researchers have focused on developing approaches which detect patterns in user activities and used them to predict future actions. One such system is Modified Sequence Prediction via Enhanced Episode Discovery (M-SPEED) that uses spatiotemporal data of activities of daily lives to analyze user behaviors. But computational overhead of run time and memory causes this algorithm to show poor performance in case of large datasets. This research focuses on modifying the M-SPEED algorithm to improve its capability to run on larger dataset while at the same time improving run time. Proof of algorithm effectiveness is provided to ensure system validity, and simulation is carried out on real life data. The results demonstrate a 66.69% improvement in cumulative memory efficiency and 37% faster run time, confirming the effectiveness of the proposal.