Fr-WCSO- DRN: Fractional Water Cycle Swarm Optimizer-Based Deep Residual Network for Pulmonary Abnormality Detection from Respiratory Sound Signals

Abstract

Respiratory sounds disclose significant information regarding the lungs of patients. Numerous methods are developed for analyzing the lung sounds. However, clinical approaches require qualified pulmonologists to diagnose such kind of signals appropriately and are also time consuming. Hence, an efficient Fractional Water Cycle Swarm Optimizerbased Deep Residual Network (FrWCSO-based DRN) is developed in this research for detecting the pulmonary abnormalities using respiratory sounds signals. The proposed FrWCSO is newly designed by the incorporation of Fractional Calculus (FC) and Water Cycle Swarm Optimizer WCSO. Meanwhile, WCSO is the combination of Water Cycle Algorithm (WCA) with Competitive Swarm Optimizer (CSO). The respiratory input sound signals are pre-processed and the important features needed for the further processing are effectively extracted. With the extracted features, data augmentation is carried out for minimizing the over fitting issues for improving the overall detection performance. Once data augmentation is done, feature selection is performed using proposed FrWCSO algorithm. Finally, pulmonary abnormality detection is performed using DRN where the training procedure of DRN is performed using the developed FrWCSO algorithm. The developed method achieved superior performance by considering the evaluation measures, namely True Positive Rate (TPR), True Negative Rate (TNR) and testing accuracy with the values of 0.963, 0.932, and 0.948, respectively.

Advanced modeling and optimizing for surface sterilization process of grape vine (Vitis vinifera) root stock 3309C through response surface, artificial neural network, and genetic algorithm techniques

“…Pre-processing is done on the pulmonary incoming sound patterns in order to successfully extract the key elements required for future processing. With the help of the collected features, data augmentation is done to improve detection performance overall by reducing overfitting challenges [ 40 ]. Although RSM can detect curvature in the response in addition to linear effects, it cannot combine nominal data, such as cultivars; as a result, it creates separate individual models for each cultivar, making the data analysis in plant tissue culture studies more time-consuming and difficult.…”

Attention Feature Fusion Network via Knowledge Propagation for Automated Respiratory Sound Classification

“…While these diseases are not curable, various therapeutic interventions can significantly alleviate symptoms and enhance the quality of life for affected individuals [1] . Consequently, early detection of respiratory abnormalities is of paramount importance [2] .…”