Machine Learning-based Distributed Big data Analytics Framework for IoT Applications

Abstract

The emerging trend of the Internet of Things (IoT) leads to more real-time applications and it raises the accumulation of more structured and unstructured data. The processing of unstructured and structured data for different distributed applications becomes arduous. Moreover, the accuracy, load balancing, and latency of the services are also challenging. Some of the state-of-art works failed to achieve those parameters. In context with these, we proposed a machine learning-based novel approach that utilizes an SVM classifier. The SVM classifier can be used for the classification and data analytic purposes of features extracted from the data processing step. Data processing employs two steps such as data extraction and data scaling. The data extraction is performed by the adoption of the Principal Component Discriminant power-based Linear Discriminant analysis (PCDP-LDA) technique. The big data framework of the proposed model is evaluated using a tool called Weka. Meanwhile, the data scaling is performed by the Naïve Bayes approach and divides the extracted features into blocks. Experimental analysis is performed and compared with existing approaches. Our proposed approach provides more effective classification and data analytic accuracy than the other approaches. Our approach also provides better latency, and load balancing of data in the distributed big data analysis.