Big Data Classification Using RCOA-Enhanced Recurrent Neural Network (RNN)

The ever-increasing amount of massive data in the health care sector necessitates the development of novel approaches to enable efficient analysis and categorization. Traditional methods often fall short of achieving the appropriate level of effectiveness because of their incapacity to manage datasets that are both sophisticated and extensive. To get around this problem, we build a Recurrent Neural Network (RNN) for data classification that is enhanced using the Rider Chicken Optimisation Algorithm (RCOA). In order to efficiently distribute processing of data duties across master and slave systems, the system operates under the Diamonds structure. We use RCOA, a hybrid of Rider Optimisation Algorithm (ROA) and Chicken Swarm Optimisation (CSO), to choose important features that improve the performance of classification. This is achieved by enhancing the RNN's ability to handle data with a high degree of dimensionality. This novel method creates a solid framework for handling healthcare's massive data sets, which is particularly useful for identifying angiographic hazards related to diseases. It offers a scalable and economical solution for data-driven healthcare decision-making. RCOA-RNN outperformed all other approaches with 91.6% accuracy for the Switzerland dataset and 94.4% for the skin disease dataset. In large data classification problems, it is resilient and effective.