Nanotechnology-Based Sensitive Biosensors for COVID-19 Prediction Using Fuzzy Logic Control

• Published in: Journal of nanomaterials 2021-11, Vol.2021, p.1-8
• Main Authors: Maheshwari, Vikas, Mahmood, Md Rashid, Sravanthi, Sumukham, Arivazhagan, N., ParimalaGandhi, A., Srihari, K., Sagayaraj, R., Udayakumar, E., Natarajan, Yuvaraj, Bachanna, Prashant, Sundramurthy, Venkatesa Prabhu
• Format: Article
• Language: English
• Subjects: Accuracy; Big Data; Biosensors; Classification; COVID-19; Data structures; Datasets; Decision making; Decision trees; Diagnosis; Fuzzy control; Fuzzy logic; Genetic algorithms; Internet of medical things; Missing data; Nanotechnology; Pandemics; Sensitivity
• ISSN: 1687-4110; 1687-4129
• DOI: 10.1155/2021/3383146

Increasing the growth of big data, particularly in healthcare-Internet of Things (IoT) and biomedical classes, tends to help patients by identifying the disease early through methods for the analysis of medical data. Hence, nanotechnology-based IOT biosensors play a significant role in the medical field. Problem. However, the consistency continues to decrease where missing data occurs in such medical data from nanotechnology-based IOT biosensors. Furthermore, each region has its own special features, which further lowers the accuracy of prediction. The proposed model initially reconstructs lost or partial data in order to address the challenge of handling the medical data structures with incomplete data. Methods. An adaptive architecture is proposed to enhance the computing capabilities to predict the disease automatically. The medical databases are managed by unpredictable environments. This optimized paradigm for diagnosis produces the fuzzy, genetically categorized decision tree algorithm. This work uses a normalized classifier namely fuzzy-based decision tree (FDT) algorithm for classifying the data collected via nanotechnology-based IOT biosensors, and this helps in the identification of nondeterministic instances from unstructured datasets relating to the medical diagnosis. The FDT algorithm is further enhanced by using genetic algorithms for effective classification of instances. Finally, the proposed system uses two larger datasets to verify the predictive precision. In order to describe a fuzzy decision tree algorithm based upon the fitness function value, a modified decision classification rule is used. The structure and unstructured databases are configured for processing. Results and Conclusions. This evaluation of test patterns helps to track the efficiency of FDT with optimized rules during the training and testing stages. The proposed method is validated against nanotechnology-based IOT biosensors data in terms of accuracy, sensitivity, specificity, and F-measure. The results of the simulation show that the proposed method achieves a higher rate of accuracy than the other methods. Other metrics relating to the model with and without feature selection show an improved sensitivity, specificity, and F-measure rate than the existing methods.