References | Method | Disadvantage | Advantage |
---|---|---|---|
[4] | An enhanced optimized Genetic Algorithm feature selection technique is applied to provide relevant information from a high-dimensional Anopheles Gambia dataset and test its classification by SVM-Kernel algorithms | Complicated model | High accuracy in classification |
[5] | Provide a patient remote monitoring system with the aim of effectively managing hospital resources through patient monitoring at home | Insufficient accuracy of diagnostic information, high classification error | High classification speed, removing outliers, using IoT |
[10] | An innovative IoT-based system for identifying medications and monitoring prescription medication | Insufficient accuracy of diagnostic information high classification error | High computational speed, simple model, removing outliers |
[11] | A remote monitoring and decision support system to assist physicians in diagnosing, remote monitoring, treating, prescribing, rehabilitating, and advancing patients with Parkinson’s disease | Complicated model, long computation time | High classification accuracy, simple model |
[12] | An IoT-based health monitoring system considering the role of smart data in the smart home for patient-centered remote health monitoring | Insufficient accuracy of diagnostic information, high classification error | High classification accuracy |
[13] | An IoT-based mobile gateway (e.g. mobile/tablet /PDA, etc.) for health scenarios | Complicated model, long computation time | High accuracy in classification |
[14] | IoT-based health monitoring system for children with Autism | Complicated model, long computation time | High accuracy in classification |
[15] | An industrial IoT-based monitoring framework for healthcare | High error, complicated model and low computational speed | Optimal accuracy in classification |
[16] | Smart Architecture for In-Home Healthcare | Insufficient accuracy of diagnostic information, high classification error | High computational speed, simple model, removing outliers |
[17] | An IoT-based patient monitoring framework in the intensive care unit | Complicated model, long computation time | High accuracy in classification |
[18] | Medication reminder and monitoring system for health using IoT | Insufficient accuracy of diagnostic information, high classification error | High computational speed, simple model, removing outliers |
[19] | IoT based patient monitoring system | Complicated model, long computation time | High accuracy in classification |
[20] | Patient monitoring system using IoT | Insufficient accuracy of diagnostic information, high classification error | High accuracy in classification |
[21] | A smart patient monitoring system to monitor patients’ health | High error, complicated model and low computational speed | Optimal classification speed, removing outliers and using IoT platform |
[22] | New generation technology and IoT for managing and analyzing big data | Insufficient accuracy of diagnostic information, high classification error | Optimal accuracy in classification |
[23] | An IoT-based healthcare monitoring and analysis system | High error, complicated model and low computational speed | Optimal accuracy in classification |
[24] | Approach uses a long-term and short-term memory network and extends it to two mechanisms (i.e., time and attention-based) | long computational speed, complicated model | Optimal accuracy in classification |
[25] | A comprehensive analysis of Long-Short Term Memory (LSTM) based DL models | Long computational speed | High classification accuracy |
[26] | A novel optimized hybrid investigative combines an optimized genetic algorithm with Principal Component Analysis and Independent Component Analysis (GA-O-PCA and GAO-ICA) | Complicated model | Optimal classification accuracy |
[27] | Using clustering techniques, deep neural networks, online hybrid similarity criteria as a method for analysis | Long computation time | High classification accuracy |