EGOOSE-LightGBM Model-Based Identity Recognition Using Cough Acoustic Signal Analysis

Abstract

Speech signals-based identity recognition is an active research area, which has a wide range of important applications such as human–computer interaction, forensic investigation, sound surveillance, transaction authentication, and health monitoring. As a special speech event, cough plays a crucial supplementary role in identity recognition scenarios, especially when traditional biometric features are unavailable. However, compared to traditional speaker recognition, very few research efforts have been made by researchers to explore identity recognition using cough acoustic signal analysis. In this work, we propose an EGOOSE-LightGBM model for cougher recognition, in which the hyperparameters of LightGBM are optimized by EGOOSE algorithm. Chaotic mapping, Gaussian mutation, and crisscross optimization are employed in the proposed metaheuristic-type EGOOSE algorithm, which demonstrates superior performance in terms of convergence speed and accuracy compared to GOOSE algorithm. A static-dynamic feature fusion (SDFF) technique is used to fuse cough sound characteristics including Mel frequency cepstral coefficient (MFCC), fundamental frequency, formant, ∆MFCC, and jitter of formant to improve recognition effectiveness and noise robustness. Using the self-recorded cough sounds, we establish a dataset, the size of which is enlarged by data augmentation techniques. Performance improvement of 3.167% is obtained due to the exploitation of cough data augmentation. Experimental results show that EGOOSE-LightGBM outperforms other existing machine learning models such as SVM, XGBoost, RF-Adaboost, LSTM, and LightGBM, achieving remarkable recognition accuracy of 99.500%.