In this digital world, large volume of data is transmitted across various sectors like production industry, healthcare, IoT devices, sales, and other organizations. In this paper, an Elephant Herd Principal Component Optimization (EHPCO) technique is used as a feature selection model to analyse the features of the data that are collected from the IoT devices. The improved perturbation technique is used the privacy preserving of data streams from the IoT devices. The machine learning classifiers are used to analyse its performance based on the proposed feature selection technique. Experimental results show that the proposed HPCO technique outperforms to improve the performance of the machine learning classifiers in terms of TPR, FPR, and accuracy. The DBN classifier obtains more than 86% of accuracy when compared with other algorithms like SVM, MLP, DT, and RF. When the certain features are extracted using the proposed EHPCO technique, the performance of the classifier is improved much in terms of accuracy. The analysis is made for four datasets such as, HPMD, FRDD, EZSD, and SSTD.

No abstract

Several concerns are raised due to the widespread technology of Internet of Things and big data, which possess private and protection of information. Several researchers have analyzed different privacy preserving techniques, which still cannot provide equal stability between the data privacy and the utility and improvement in the scalability and efficiency. Data mining is one of the prominent technologies, which extracts reliable and useful knowledge from vast amount of information. Henceforth, mining of data stream have become a most popular and important research issue. Due to fast growth in the data generation, the mechanism of privacy preserving with high utility and security becomes more necessary. In this research, an improved efficient perturbation method for data stream named privacy-preserving rotation-based condensation algorithm with geometric transformation is proposed that delivers high data utility when compared with other existing techniques. This improved method gives high resilience against the attacks during the process of data reconstruction. Simulation result shows that the proposed method can acquire data privacy and improves accuracy during mining of data streams in which the analysis is performed for different datasets in which the proposed technique obtains more than 95% when compared with original dataset.