Enhancing Security of Medical Image Data in the Cloud Using Machine Learning Technique

Abstract

To prevent medical data leakage to third parties, algorithm developers have enhanced and modified existing models and tightened the cloud security through complex processes. This research utilizes PlayFair and K-Means clustering algorithm as double-level encryption/ decryption technique with ArnoldCat maps towards securing the medical images in cloud. K-Means is used for segmenting images into pixels and auto-encoders to remove noise (denoising); the Random Forest regressor, tree-method based ensemble model is used for classification. The study obtained CT scan-images as datasets from 'Kaggle' and classifies the images into 'Non-Covid' and 'Covid' categories. The software utilized is Jupyter-Notebook, in Python. PSNR with MSE evaluation metrics is done using Python. Through testing-and-training datasets, lower MSE score ('0') and higher PSNR score (60%) were obtained, stating that, the developed decryption/ encryption model is a good fit that enhances cloud security to preserve digital medical images.

Legal aspects of the development of optical medicine for severe systemic diseases

“…Any changes in the social space caused by the introduction of new technologies do not occur in isolation, and therefore have various socio-economic consequences. The development and application of the latest trends and technologies, automated technical systems in the healthcare sector have a powerful potential, as they actualize the social role of law, whose task is to properly regulate and protect emerging relations that have been in a regulatory vacuum until recently [11][12][13][14][15] .…”

Model of Smart Locating Application for Small Businesses

“…Version 2.0 introduced improvements to GFSK increasing the speed to 1 Mbps in BR mode and featured an enhanced data rate (EDR) that used differential phase-shift keying allowing raw data rates of 2 Mbps in case of π/4 differential phase-shift keying (π/4 DQPSK) or 3 Mbps with 8-point differential phase-shift keying (8DPSK). In Bluetooth 3.0, high-speed transfers via 802.11 using Bluetooth pairing were added [39][40][41][42][43][44]. Later versions mainly concerned Bluetooth Low Energy, designed for sport and fitness devices, accessories, and location services using beacons, control, and automation systems [45].…”

“…Apart from being a tool for smart cities, this technology also involves a listener that can precisely monitor shopping and street activity by tracking smartphones in their radius using WiFi and Bluetooth. It detects them without the need to connect to any access point, eliminating the participation of owners of mobile devices [43][44][45][46]. As a commercial solution, Meshlium's cost varies and can range from around USD 2000 to over USD 5000 for a full kit, including additional sensors [47].…”