Disease Diagnosis Model for Smart Healthcare Systems Using Artificial Intelligence and the Internet of Things

Main Article Content

Dr.K.Sai Manoj

Abstract

The Internet of Things (IoT), cloud services, and artificial intelligence (AI) have all improved in recent years, converting traditional medical into smart healthcare. The application of important technologies such as AI and IoT to healthcare treatments could improve outcomes. The combination of IoT and AI in the medical industry opens up a world of possibilities. As a result, the current study suggests a new AI- and IoT-based disease detection paradigm for smart medical systems. The model includes phases such as preprocessing, data collection, parameterization, and categorization. IoT devices, such as wearables and detectors, allow for real-time data collecting, which AI systems then use to identify ailments. For illness detection, the suggested method employs a Crow Search Optimization algorithm-based Cascaded Long Short Term Memory (CSO-CLSTM) model. CSO is used to alter the CLSTM model's 'weights' and 'bias' variables to enhance the categorization of health data. This study also employs the isolation Forest (iForest) approach to reduce outliers. The CLSTM model's diagnostic outcomes are greatly improved when CSO is used. The CSO-LSTM model was put to the test using healthcare data. During the testing, the CSO-LSTM model identified diabetes and heart disease with the highest accuracies of 96.16 percent and 97.26 percent, etc. As a result, the suggested CSO-LSTM model can be used in smart health systems as a diagnostic tool.

Article Details

Section
Articles