A novel adaptive weight bi-directional long short-term memory (AWBi-LSTM) classifier model for heart stroke risk level prediction in IoT

Abstract

Stroke prediction has become one of the significant research areas due to the increasing fatality rate. Hence, this article proposes a novel Adaptive Weight Bi-Directional Long Short-Term Memory (AWBi-LSTM) classifier model for stroke risk level prediction for IoT data. To efficiently train the classifier, Hybrid Genetic removes the missing data with Kmeans Algorithm (HKGA), and the data are aggregated. Then, the features are reduced with independent component analysis (ICA) to reduce the dataset size. After the correlated features are identified using the T-test-based uniform distribution-gradient search rule-based elephant herding optimization for cluster analysis (GSRBEHO) (T-test-UD-GSRBEHO). Next, the fuzzy rule-based decisions are created with the T-test-UDEHOA correlated features to classify the risk levels accurately. The feature values obtained from the fuzzy logic are given to the AWBi-LSTM classifier, which predicts and classifies the risk level of heart disease and diabetes. After the risk level is predicted, the data is securely stored in the database. Here, the MD5-Elliptic Curve Cryptography (MD5-ECC) technique is utilized for secure storage. Testing the suggested risk prediction model on the Stroke prediction dataset reveals potential efficacy. By obtaining an accuracy of 99.6%, the research outcomes demonstrated that the proposed model outperforms the existing techniques.

Keywords

• Internet of Things (IoT)
• Stroke prediction
• Improved restricted Boltzmann machine (IRBM)
• Correlated features
• Elephant herd optimization algorithm (EHOA)