Abstract
•Proposing NVS method using supervised learning for infectious disease data modeling.•Designing supervised learning based on HMM for infectious disease classification.•Enhancing sensitivity, specificity, and accuracy compared to other existing method.
Data modelling and analysis have become a recent trend in medical and healthcare applications for their ease of visualization and handling. To keep up with the vast amount of information generated by such medical and healthcare applications, the need for computer-aided modelling and intelligent data handling is expected to increase the quality of assessment and visualization. Moreover, reliable modelling requires structured data handling for achieving better data visualization. The un-ordered and raw disease/medical data require formal structuring and grouping for improving the visualization process. Existing models consume too much time for processing a huge volume of data. This, in turn, causes a high error rate in classification, which directly affects system performance. In this paper, biosensors gather patient health information and examine the infectious with a high prediction rate. A biosensor rapidly collects patient health data changes and reduces the time complexity of data modelling and analysis. Moreover, a supervised Non-Variant Structuring (NVS) approach for grouping infectious disease data is introduced. This approach helps improve the visualization of sensor-based acquired raw data. In this structuring process, the associativity and disparity features of the infectious disease data are identified for grouping and analyzing the disease-related features. The introduced structuring method employs a supervised learning technique for identifying the associativity and disparity in different instances of accumulation based on a Hidden Markov Model (HMM). This learning technique reduces the chances of non-partial organization of infectious disease data for better modelling and analysis. The performance of the suggested approach is verified with a sensitivity ratio of 98.2%, a specificity ratio of 96.7%, and accuracy ratio of 95.5%, a prediction error rate of 7.8% less, and a classification time of 10.1% less compared to other existing methods.