Hybrid Algorithm for Resource Aware Predictive Scheduling: A case-study to Human Activity Recognition

Analyzing big stream data is a significant task for real-time high-voluminous data. Various research works have evolved to analyze those big stream data. However, state-of-the-art systems have certain limitations, such as scheduling time (ST), resource-aware predictive scheduling efficiency (RAPSE), memory consumption (MC), false positive rate (FPR), etc. This paper proposes a hybrid algorithm for predictive resource-aware scheduling to address the issues. The algorithm integrates Elastic-net regularization with Kernelized Fisher Discriminant (KFD) and Map Reduce classification process for a case study on a high volume of human activity recognition (HAR) dataset. The Elastic-net regularization process selects significant features from the dataset and adds certain performance measures for efficient scheduling by the KFD process. The Map Reduce classifier classifies the data streams assigned to a respective processor by the KFD to achieve a low false positive rate. Experimentation has been validated with state-of-the-art systems using standard challenges such as RAPSE, MC, FPR, and ST. Results have also proven that the proposed system has certain merits in implementation over the other state-of-the-art systems in realtime human activity recognition.