Enhanced Efficient and Security in Big Data Using TDES And Machine Learning Technique

Abstract

Big Data Analytics (BDA) is an important technology used in many industries, including banking and investments, finance, news and entertainment, transport, education, production, energy and utilities, and medical health care. Big Data in medical healthcare is described as a collection of exceptionally big and complicated sets of electronic healthcare data. Because of the huge amount and complexity of the data, it is impossible to maintain it using traditional software for practical application. The term "Bigdata," created in 1990, refers to the study of huge and complicated datasets. Bigdata problems include data storage, data capture, data processing, data querying, data visualisation, and data transmission. It can only perform wonders if the most crucial information is gathered by it. Predictive analytics, user behaviour analytics, and other Bigdata analytics are being used to extract meaningful information from the massive volume of Bigdata. Bigdata may be used to prevent sickness, identify crime, and aid in commerce, financial institutions, and other fields by studying new patterns and associations. Machine Learning is an area of computer science which is used to find hidden patterns in massive amounts of complicated data. Machine learning is a technique in which a model is taught to learn from data, and it is therefore widely utilised in practically every sector in order to uncover a valuable pattern in Bigdata. This approach produces results without the need for human intervention. Businesses now understand that Bigdata is only helpful if meaningful information is extracted from it using an effective machine learning method. Furthermore, Triple Data Encryption Standard is employed for encryption to improve speed. Attribute Based Access Control is used to offer authentication and to give allowed access. TDES method is compared to current ways such as Data Encryption Standard and Advanced Encryption Standard in terms of file size and time as basis for performance evaluation. In addition, the classification method MKSVM is evaluated to Support Vector Machine and Neural Network in terms of quality, specific, and reliability. These phase evaluates the performance of Attribute Based Access Control. When compared to current approaches, the comparative study demonstrated that the suggested TDES encryption methodology achieved the shortest execution time with the most secure data.