A Novel Machine Learning Technique for Selecting Suitable Image Encryption Algorithms for IoT Applications

The Internet of Things connects billions intelligent devices that can interact with one another without human intervention, and during communication, a large amount data is exchanged between the devices. As result, it critical to secure digital using an encryption technique provides suitable degree security. Numerous existing techniques do not offer sufficient Therefore, figure out which most appropriate for particular kind data. When comes manually deciding use, process might take long time. In this research, we present novel selecting Encryption Algorithms (EAs) based on application pattern recognition machine learning techniques. To accomplish goal, also prepare dataset. Several techniques, such as Support Vector Machines (SVMs), Linear Regression (LR), K -Nearest Neighbour (KNN), Naïve Bayes (NB), Decision Trees (DT), Random Forests (RF), are evaluated. Based evaluation, SVM has been chosen best option intended because its classification accuracy 98.7%. experimental results, including accuracy, precision, recall, F1-score, used gauge performance suggested technique. proposed compared demonstrate effectiveness.