Optimized DEC: An effective cough detection framework using optimal weighted Features-aided deep Ensemble classifier for COVID-19

Highlights

• To extract the most informative features of cough audio signal by the concept inference of Mel Frequency Cepstral Coefficients (MFCC), spectral and statistical features, this aids to increase the cough detection performance.

• To concatenate all the resultant features to select the weighted based optimal features. It is upgraded into the weighted features, where the weight factor is optimally determined using novel Modified Cat and Mouse Based Optimizer (MCMBO) algorithm that resolves the dimensionality issues.

• To frame the Optimized Deep Ensemble Classifier (ODEC) model for classifying the features into presence or absence of COVID19. Here, it possesses Deep Neural Network (DNN), Long-Short Term Memory (LSTM), and Radial Basis Function (RBF) to do the classification task, in turn the hidden neurons and epochs are tuned with the help of Modified Cat and Mouse Based Optimizer (MCMBO) algorithm.

• To analyze the performance with different metrics and compared over classical heuristic algorithms and other classifier models. The comparative analysis provides the effective results to enhance the robustness of the system.

Abstract

Since the year 2019, the entire world has been facing the most hazardous and contagious disease as Corona Virus Disease 2019 (COVID-19). Based on the symptoms, the virus can be identified and diagnosed. Amongst, cough is the primary syndrome to detect COVID-19. Existing method requires a long processing time. Early screening and detection is a complex task. To surmount the research drawbacks, a novel ensemble-based deep learning model is designed on heuristic development. The prime intention of the designed work is to detect COVID-19 disease using cough audio signals. At the initial stage, the source signals are fetched and undergo for signal decomposition phase by Empirical Mean Curve Decomposition (EMCD). Consequently, the decomposed signal is called “Mel Frequency Cepstral Coefficients (MFCC), spectral features, and statistical features”. Further, all three features are fused and provide the optimal weighted features with the optimal weight value with the help of “Modified Cat and Mouse Based Optimizer (MCMBO)”. Lastly, the optimal weighted features are fed as input to the Optimized Deep Ensemble Classifier (ODEC) that is fused together with various classifiers such as “Radial Basis Function (RBF), Long-Short Term Memory (LSTM), and Deep Neural Network (DNN)”. In order to attain the best detection results, the parameters in ODEC are optimized by the MCMBO algorithm. Throughout the validation, the designed method attains 96% and 92% concerning accuracy and precision. Thus, result analysis elucidates that the proposed work achieves the desired detective value that aids practitioners to early diagnose COVID-19 ailments.