An Industry Framework for Remote Health Monitoring using Machine Learning Models to Predict a Disease

Venkateswarulu, N ; Manike, Chiranjeevi ; Obulesu, O


Remote health monitoring frameworks gained significant attention due to their real intervention and treatment standards. Most conventional works object to developing remote monitoring frameworks for identifying the disease at the earlier stages for an appropriate diagnosis. Still, it faced the problems with complexity in operations, increased cost of resources, misprediction results, which requires more time consumption for data gathering, and reduced convergence rate. Hence, the proposed work intends to design a machine learning based remote health monitoring framework for predicting heart disease and diabetes from the given medical datasets. In this framework, the Industry based smart devices are used to gather the health information of patients, and the obtained information is integrated together by using different nodes that includes the detecting node, visualization node, and prognostic node. Then, the medical dataset preprocessing is performed to normalize the attributes by identifying the missing values and eliminating the irrelevant qualities. Consequently, the Unified Levy Modeled Crow Search Optimization (U-CSO) algorithm is employed to select the optimal features based on the global fitness function, which helps increase the accuracy and reduce the training time of the classifier. Finally, the Most Probabilistic Guided Naïve Distribution (MP-ND) based classification model is utilized for predicting the label as to whether normal or disease affected. During an evaluation, two different datasets, such as PIMA and Hungarian, are used to validate and compare the results of the proposed model by using various performance measures. A Patients' health status can be monitored remotely for disease detection and proper diagnosis.


Artificial intelligence, MP-ND, Smart devices, U-CSO

Full Text: PDF (downloaded 323 times)


  • There are currently no refbacks.
This abstract viewed 630 times