Improved Accuracy in Speech Recognition System for Detection of Covid-19 using K Nearest Neighbour and Comparing with Artificial Neural Network

Abstract

Aim: This study focuses on the detection of Covid-19 via the use of cutting-edge speech recognition technology known as K Nearest Neighbor (KNN), and comparing its accuracy with that of an Artificial Neural Network (ANN). Both the Materials and the Methods: In this case, speech recognition through the use of KNN is deemed to be group 1, while speech recognition via the use of an artificial neural network is considered to be group 2. ANN is comprised of several different components that are responsible for gathering the input signals and predefined functions that are responsible for creating the output signals. KNN works by calculating the distance between the query and the data and then picking the samples that are geographically closest to the requests. These various samples using algorithms were computationally assessed by a sampling test with 5% of alpha error and 0.95 of confidence interval. The results of this analysis are shown below. The findings show that ANN performs at a level of mean accuracy of 83.5%, whereas KNN performs at a level of mean accuracy of 91.49% with an error significance value of 0.03 (p 0.05). The findings that were acquired using KNN have shown much improved performance in terms of accuracy compared to those obtained using ANN.