Method to implement K-NN machine learning to classify data privacy in IoT environment

Abstract

<span>Internet of Things technology allows many devices to connect with each other. The interaction could be between humans and devices or between devices itself. In fact, the data are traveling between the devices through the media within the boundary, and it could be traveling outside the boundary when it required to be analyzed or stored in the cloud through the internet. Due the transmission media and internet, the data are vulnerable to attacks. Thus, the data need to be encrypted strongly for the purpose of protection. Usually, most of the encryption techniques will consume computer resources. In this work, we divide the data that are used in the IoT environment into three levels of sensitivity which are low, medium and high sensitive data to leverage the computer resources such as time of encryption and decryption, battery usage and so on. A framework is proposed in this work to encrypt the data depends on the level of sensitivity using the machine learning K nearest neighbors (K-NN).</span>

Clustering similar time series data for the prediction the patients with heart disease

“…The generated medical recommendations will definitely be made the decision to detect if the given patient required to get the medical test toward the next upcoming day or not. More details are presented in the following subsections [27], [30].…”

“…In this research, the similar sliding windows are clustered into two groups: either the patient needs to get the medical test or not needed to take it. A method of short-time disease risk prediction is suggested, and the important method contributions are summarized as shown [24]- [27]: i) The time series data is partitioned into smaller overlapped sliding windows depending on the sliding window size utilized in the data analysis; ii) A clustering method is carried out on all-time series sliding windows to identify the similar sliding windows. The clustering similar method is based on euclidean distance helps to recognize the similar sliding windows that are close in the distance of space; iii) A clustering similar sliding windows are dealt as training samples belong to suggested model; iv) Least square-support vector machine is applied to generate suitable recommendations for the patients which are having chronic heart diseases in regards to the requirement of taken the medical test or not toward the next upcoming day; v) A comparison has already been done among our suggested model and the researches that already established to solve the identical concern to prove that our technique is superior.…”

The IoT and registration of MRI brain diagnosis based on genetic algorithm and convolutional neural network

“…This study focuses on real-time surveillance with the low cost-effective security solution. Make the most of computer resources such encryption and decryption time, battery usage, and so on, divide the data utilized in the IoT environment into three categories of sensitivity: low, medium, and high sensitive data [33]. In this paper, a framework is provided for encrypting data based on the level of sensitivity utilizing machine learning K-nearest neighbors (K-NN).…”

Optimal ElGamal Encryption with Hybrid Deep-Learning-Based Classification on Secure Internet of Things Environment

“…Once an attacker accumulates these data and leverages them maliciously, high security risks will naturally occur in the IoT compared with the prevailing ecosystem. Passive assaults, such as spam messages transmit through smart TVs or refrigerators, might lead to damaging these gadgets, and more aggressive assaults can threaten the life of users [ 3 ], for instance, through hacking medical devices or vehicle interaction mechanisms. In addition, user data gathered on IoT networks cause an invasion of privacy; for instance, the analysis of electricity consumption patterns leveraging a smart meter can expose the lifestyle of a person [ 4 , 5 ].…”