Ensemble Machine Learning Based Blockchain Model for Privacy Preserving of Medical data in Fog Computing
V. K. Sheetal, Vidya Sagar S. D., Piyush Kumar Pareek · 2023
The advent of COVID-19 highlights the need for big data-driven medical applications, the Internet of Medical Things, and smart healthcare. The biological information collected is strictly private. This enormous quantity of biological information is, however, beyond the capacity of current health care systems. Therefore, cloud computing has become the norm for archiving and sharing data. The combined information is then put to use in a variety of ways, including research and the identification of previously unknown facts. Textual forms (such as test results, prescriptions, and diagnoses) are the norm for biological data. Unfortunately, there are a number of security dangers and assaults that may be made against such data, including infringements on privacy and confidentiality. The security of biological data has come a long way, yet the majority of current methods still cause considerable delays and cannot support real-time replies. To improve the healthcare system, this study suggests a unique fog-enabled blockchain based privacy-preserving approach that makes use of machine learning. The suggested model efficiently carries out Medical Entity Recognition as it is built on four different machine learning models. In terms of detection rate and accuracy, the suggested model is 97% and 98%, respectively, better than the state-of-the-art replicas, as shown by the experiments. The sanitization approach outdoes the state-of-the-art by 8 percentage points when it comes to preserving utilities.