CINXE.COM
Transfer Learning based Diagnosis and Analysis of Lung Sound Aberrations
<!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <meta http-equiv="X-UA-Compatible" content="ie=edge"> <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.7.0/css/font-awesome.min.css"> <link rel="stylesheet" href="../bootstrap.css"> <link rel="stylesheet" href="../style.css"> <link rel="icon" type="image/png" href="https://wireilla.com/w.ico" alt="logo" size="96x96"> <title>Transfer Learning based Diagnosis and Analysis of Lung Sound Aberrations</title> </head> <body> <nav class="navbar navbar-expand-md navbar-light bg-white fixed-top mb-3 py-1" style="opacity:0.7;"> <div class="container"> <a class="navbar-brand" href="https://wireilla.com/ijbb/index.html"><img src="../WI-simple-logo.jpg" type="image/png" alt="Brand-Logo" width="150px"; height="50px"></a> <button class="navbar-toggler" data-toggle="collapse" data-target="#navbarCollapse"><span class="navbar-toggler-icon"></span></button> <div class="collapse navbar-collapse float-text-end" id="navbarCollapse"> <ul class="navbar-nav ml-auto px-3"> <li class="nav-item"> <a class="nav-link" href="../index.html"><b>Scope & Topics</b></a> </li> <li class="nav-item"> <a class="nav-link" href="../editorial.html"><b>Editorial Board</b></a> </li> <li class="nav-item"> <a class="nav-link" href="../submission.html"><b>Paper Submission</b></a> </li> <li class="nav-item"> <a class="nav-link" href="../indexing.html"><b>Indexing</b></a> </li> <li class="nav-item"> <a class="nav-link" href="../archives.html"><b>Archives</b></a> </li> <li class="nav-item"> <a class="nav-link" href="../contact.html"><b>Contact</b></a> </li> </ul> </div> </div> </nav> <!-- Showcase slider --> <section id="showcase"> <div id="myCarousel" class="carousel slide" data-ride="carousel"> <div class="carousel-inner"> <div class="carousel-item carousel-image-2 active"> <div class="container-fluid"> <div class="carousel-caption mb-5 d-sm-block carousel_mb" style="background-color: #495150;opacity: 0.7;border-radius: 15px;"> <h3 class=" text-white" style="padding:5px;"><b>International Journal on Bioinformatics & Biosciences (IJBB) </b></h3> <p align="center" class=" text-white"><b>ISSN : 1839-9614</b></p> </div> </div> </div> </div> </div> </section> <section id="network-design-1" class="py-5 text-dark"> <div class="container"> <div class="row"> <div class="col"> <h4 style="text-align:center">Transfer Learning based Diagnosis and Analysis of Lung Sound Aberrations</h4><br> <div class="col-md-12"> <h4>Authors</h4> </div> <div class="col-md-12"> Hafsa Gulzar<sup>1</sup>, Jiyun Li<sup>1*</sup>, Arslan Manzoor<sup>2</sup>, Sadaf Rehmat<sup>3</sup>, Usman Amjad<sup>4</sup> and Hadiqa Jalil Khan<sup>4</sup>, <sup>1</sup>Donghua University, China, <sup>2</sup>University of Catania, Italy, <sup>3</sup>PIEAS, Pakistan, <sup>4</sup>Islamia University of Bahawalpur, Pakistan </div> <br> <div class="col-md-12"> <h4>Abstract</h4> <p style="text-align:justify">With the development of computer -systems that can collect and analyze enormous volumes of data, the medical profession is establishing several non-invasive tools. This work attempts to develop a non-invasive technique for identifying respiratory sounds acquired by a stethoscope and voice recording software via machine learning techniques. This study suggests a trained and proven CNN-based approach for categorizing respiratory sounds. A visual representation of each audio sample is constructed, allowing resource identification for classification using methods like those used to effectively describe visuals. We used a technique called MelFrequency Cepstral Coefficients (MFCCs). Here, features are retrieved and categorized via VGG16 (transfer learning) and prediction is accomplished using 5-fold cross-validation. Employing various data splitting techniques, Respiratory Sound Database obtained cutting- edge results, including accuracy of 95%, precision of 88%, recall score of 86%, and F1 score of 81%. The ICBHI dataset is used to train and test the model. </p> <h4>Keywords</h4> <p style="text-align:justify">Machine Learning, Convolutional Neural Networks (Cnn), TransferLearning, Cross Validation, Mfcc, Vgg16.</p> </div> <div class="col-md-12 mb-5"> <a class="btn btn-success " style="background-color:#7c90a1" target="blank" href="http://wireilla.com/papers/ijbb/V13N1/13123ijbb03.pdf">Full Article</a> <a class="btn btn-success " style="background-color:#7c90a1" target="blank" href="../vol13.html">Volume 13</a> </div> </div> </div> </div> </section> <!-- Footer Section /--> <section id="footer-section" class="text-white py-3 text-left"> <div class="container"> <div class="row"> <div class="card-body col-md-2"></div> <div class="card-body col-md-3 text-left"> <h6 class="mb-3"style="font-size: 15px;">About Wireilla</h6> <p><a href="../contact.html" class=" text-white">Contact Wireilla</a></p> </div> <div class="card-body follow col-md-3 text-left"> </div> <div class="card-body col-md-3 text-left "> <h6 class="mb-3 ">Home</h6> <a href="http://wireilla.com/ " target="_blank" alt="airccse logo "><img src="../WI-simple-logo.jpg " alt="client-logo " size="35x35 "></a> </div> </div> <div><p align="center">All Rights Reserved - Wireilla Scientific Publications, New South Wales, Australia</p></div> </div> </div> </section> <script src="../jquery.min.js"></script> <script src="../popper.min.js"></script> <script src="../bootstrap.min.js"></script> <script src="https://ajax.googleapis.com/ajax/libs/jquery/1.12.4/jquery.min.js"></script> <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js"></script> </body> </html>