Gradient Boosting Machine and Efficient Combination of Features for Speech-Based Detection of COVID-19

Dash, Tusar Kanti; Chakraborty, Chinmay; Mahapatra, Soumya Jagannath; Panda, Ganapati

doi:10.1109/jbhi.2022.3197910

Cited by 38 publications

(18 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The examination of multiple performance indices shows that the suggested COVID-19 detection technique may be successfully used by physicians in the present pandemic context. This detection method requires additional training time and computations [33] .…”

Section: Related Workmentioning

confidence: 99%

Utilizing CNN-LSTM techniques for the enhancement of medical systems

Rayan¹,

alruwaili²,

Alaerjan³

et al. 2023

Alexandria Engineering Journal

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Utilizing CNN-LSTM techniques for the enhancement of medical systems

Rayan¹,

alruwaili²,

Alaerjan³

et al. 2023

Alexandria Engineering Journal

View full text Add to dashboard Cite

“…Dash et al [ 2 ] proposed a speech-based respiratory disease detection method for Covid-19 and Asthma, where various features, such as periodicity, spectral, cepstral, and spectral descriptors, are computed and then uniformly fused to obtain relevant statistical features, and these statistical features are then used as inputs for the gradient boosting algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…The most common and effective test for Covid-19 is the reverse transcription-polymerase chain reaction (RT-PCR) test which has a number of drawbacks in addition to having a high degree of accuracy. A few of the drawbacks include the inconvenient nature of having to go to a specialized testing center, the necessity for knowledgeable medical personnel, the use of single-use testing kits, the intrusive nature of the operation, and the delayed wait for results [ 2 ]. Speech signal processing has recently been used in a variety of clinical aspects for the non-invasive diagnosis of problems, which has implications for both the effectiveness of remote health monitoring and the development of remote healthcare infrastructure.…”

Section: Introductionmentioning

confidence: 99%

Machine learning approach for detecting Covid-19 from speech signal using Mel frequency magnitude coefficient

Nayak

Darji

Shah

2023

SIViP

View full text Add to dashboard Cite

The Covid-19 pandemic is one of the most significant global health concerns that have emerged in this decade. Intelligent healthcare technology and techniques based on speech signal and artificial intelligence make it feasible to provide a faster and more efficient timely detection of Covid-19. The main objective of our study is to design speech signal-based noninvasive, low-cost, remote diagnosis of Covid-19. In this study, we have developed system to detect Covid-19 from speech signal using Mel frequency magnitude coefficients (MFMC) and machine learning techniques. In order to capture higher-order spectral features, the spectrum is divided into a larger number of subbands with narrower bandwidths as MFMC, which leads to better frequency resolution and less overall noise. As a consequence of an improvement in frequency resolution as well as a decrease in the quantity of noise that is included with the extraction of MFMC, the higher-order MFMCs are able to identify Covid-19 from speech signals with an increased level of accuracy. The procedures for machine learning are often less complicated than those for deep learning, and they may commonly be carried out on regular computers. However, deep learning systems need extensive computing power and data storage. Twelve, twenty-four, thirty, and forty spectral coefficients are obtained using MFMC in our study, and from these coefficients, performance is accessed using machine learning classifiers, such as random forests and K -nearest neighbor (KNN); however, KNN has performed better than the other model with having AUC score of 0.80.

show abstract

“…Many interesting solutions have been proposed that do not rely solely on diagnosing the disease based on RT-PCR data and chest X-ray tests. A solution was presented by [32] to detect the disease by analyzing the audio data using the Gradient Boosting Machine-based classifier. The methods that have been used in this research were the LGM classifier, Random Forest (RF), SVM, and K-Nearest Neighbor (KNN).…”

Section: Related Workmentioning

confidence: 99%