Classification Of Respiratory Sounds Research Articles

SPRSound: Open-Source SJTU Paediatric Respiratory Sound Database.

It has proved that the auscultation of respiratory sound has advantage in early respiratory diagnosis. Various methods have been raised to perform automatic respiratory sound analysis to reduce subjective diagnosis and physicians' workload. However, these methods highly rely on the quality of respiratory sound database. In this work, we have developed the first open-access paediatric respiratory sound database, SPRSound. The database consists of 2,683 records and 9,089 respiratory sound events from 292 participants. Accurate label is important to achieve a good prediction for adventitious respiratory sound classification problem. A custom-made sound label annotation software (SoundAnn) has been developed to perform sound editing, sound annotation, and quality assurance evaluation. A team of 11 experienced paediatric physicians is involved in the entire process to establish golden standard reference for the dataset. To verify the robustness and accuracy of the classification model, we have investigated the effects of different feature extraction methods and machine learning classifiers on the classification performance of our dataset. As such, we have achieved a score of 75.22%, 61.57%, 56.71%, and 37.84% for the four different classification challenges at the event level and record level.

Incorporating support vector machine to the classification of respiratory sounds by Convolutional Neural Network

Classification of respiratory sounds (RS) by artificial intelligence (AI) methods has been studied by many groups, and a preferred method belonging to Deep Neural Networks (DNN) is Convolutional Neural Networks (CNN), where the Softmax function is one of the most popular classifiers used in the last layer of the network. However, there have also been studies examining the use of linear support vector machine (SVM) instead of Softmax in an artificial neural network architecture. This work focuses on incorporating SVM to CNN in multi-class RSs classification. Moreover, two-layer CNN model was added to the VGG16 model using transfer learning and similarly, the classification successes were compared with Softmax and SVM. The dataset used in this work has been obtained by clinical experts from a total of 294 subjects (105 diagnosed as normal and the rest of the patients have adventitious sound namely, 116 crackle and 73 rhonchi). During the classification phase, two-layer CNN architecture and SVM were added to this architecture, then various classifiers are implemented, namely CNN-Softmax, CNN-SVM, VGG16-CNN-Softmax, VGG16-CNN-SVM with 10-fold cross validation. In addition, state-of-art models (DenseNet 201, VGG16, InceptionV3, ResNet 101) and VGG16-CNN-KNN have also been applied to the dataset. It is found that the best classification accuracy figures have been found as 83% with VGG16-CNN-SVM model.

An optimal asthma disease detection technique for voice signal using hybrid machine learning technique

AbstractCurrent clinical practice in the treatment of chronic respiratory diseases does not have an effective method that allows patients and caregivers to constantly monitor the severity of respiratory symptoms. This is the “asthma breath” that occurs in the respiratory tract. In this article, we propose an optimal asthma disease detection technique for voice signal using hybrid machine learning (OADD‐HML) technique. In OADD‐HML technique, we used the improved weed optimization (IWO) algorithm for asthma detection and forecasting. We analyze whether the scattered signal pattern follows the frequency of normal and abnormal breathing sounds. Second, we illustrate an enhanced hunting search (EHS) algorithm for feature extraction and selection process. Then, deep Q neural network (DQNN) classifier used to identify the asthma, crackle, and normal speech. After performing the function recovery and classification using DQNN, the respiratory number classes will be identified. The test results show several classifications of specific OADD‐HML breathing sounds, respectively, using accuracy, sensitivity, and specificity. Comparison results of asthma and non‐asthma classification of respiratory sounds suggest that the particular method works better than usual existing state‐of‐art.

COVID-19 disease diagnosis with light-weight CNN using modified MFCC and enhanced GFCC from human respiratory sounds.

In the last 2 years, medical researchers and clinical scientists have paid close attention to the problem of respiratory sound classification to classify COVID-19 disease symptoms. In the physical world, very few AI-based (Artificial Intelligence) techniques are often used to detect COVID-19/SARS-CoV-2 respiratory disease symptoms from the human respiratory system-generated acoustic sounds such as acoustic voice sound, breathing (inhale and exhale) sounds, and cough sound. We propose a light-weight Convolutional Neural Network (CNN) with Modified-Mel-frequency Cepstral Coefficient (M-MFCC) using different depths and kernel sizes to classify COVID-19 and other respiratory sound disease symptoms such as Asthma, Pertussis, and Bronchitis. The proposed network outperforms conventional feature extraction models and existing Deep Learning (DL) models for COVID-19/SARS-CoV-2 classification accuracy in the range of 4–10%. The model’s performance is compared with the COVID-19 crowdsourced benchmark dataset and gives a competitive performance. We applied different receptive fields and depths in the proposed model to get different contextual information that should aid in classification. And our experiments suggested 1 times 12 receptive fields and a depth of 5-Layer for the light-weight CNN to extract and identify the features from respiratory sound data. The model is also trained and tested with different modalities of data to showcase its effectiveness in classification.

Respiratory Sound Classification by Applying Deep Neural Network with a Blocking Variable

Respiratory Sound Classification by Applying Deep Neural Network with a Blocking Variable

Responding to Challenge Call of Machine Learning Model Development in Diagnosing Respiratory Disease Sounds

In this study, a machine learning model was developed for automatically detecting respiratory system sounds such as sneezing and coughing in disease diagnosis. The automatic model and approach development of breath sounds, which carry valuable information, results in early diagnosis and treatment. A successful machine learning model was developed in this study, which was a strong response to the called the Pfizer digital medicine challenge on the OSFHOME open access platform. Environmental sound called ESC-50 and AudioSet sound files were used to prepare the dataset. In this dataset, which consisted of three parts, features that effectively showed coughing and sneezing sound analysis were extracted from training, testing and validating samples. Based on the Mel frequency cepstral coefficients (MFCC) feature extraction method, mathematical and statistical features were prepared. Three different classification techniques were considered to perform successful respiratory sound classification in the dataset containing more than 3800 different sounds. Support vector machine (SVM) with radial basis function (RBF) kernels, ensemble aggregation and decision tree classification methods were used as classification techniques. In an attempt to classify coughing and sneezing sounds from other sounds, SVM with RBF kernels was achieved with 83% success.

Respiratory Sound Classification: From Fluid-Solid Coupling Analysis to Feature-Band Attention

Based on respiratory sound production mechanisms, we study the relationship between airflow characteristics in the bronchi and sound pressure spectrum curves to implement an end-to-end respiratory sound classification system with a feature-band attention module. First, we analyse fluid-solid coupling simulations of the bronchi and execute acoustic simulations to obtain the spectrum curves of the bronchi at the sound pressure level. Then, based on the spectrum characteristics of the bronchi, we propose an attention strategy to refine the acoustic features with adaptive weights. In addition, we introduce a feature-band attention module to ResNet-based networks with a squeeze-and-excitation block. Finally, we perform experiments on the ICBHI public database to classify respiratory sounds into one of four classes: normal, wheezes, crackles, and both (wheezes and crackles). The results show that our proposed system exhibits superior performance compared with the baseline system. This type of feature learning strategy is useful for exploring the distinct characteristics of different types of respiratory sounds.

Lightweight Skip Connections With Efficient Feature Stacking for Respiratory Sound Classification

As the number of deaths from respiratory diseases due to COVID-19 and infectious diseases increases, early diagnosis is necessary. In general, the diagnosis of diseases is based on imaging devices (e.g., computed tomography and magnetic resonance imaging) as well as the patient’s underlying disease information. However, these examinations are time-consuming, incur considerable costs, and in a situation like the ongoing pandemic, face-to-face examinations are difficult to conduct. Therefore, we propose a lung disease classification model based on deep learning using non-contact auscultation. In this study, two respiratory specialists collected normal respiratory sounds and five types of abnormal sounds associated with lung disease, including those associated with four lung lesions in the left and right anterior chest and left and right posterior chest. For preprocessing and feature extraction, the noise was removed using three pass filters (low, band, and high), and respiratory sound features were extracted using the Log-Mel Spectrogram-Mel Frequency Cepstral Coefficient followed by feature stacking. Then, we propose a lung disease classification model of dense lightweight convolutional neural network-bidirectional gated recurrent unit skip connections using depthwise separable convolution based on the extracted respiratory sound information. The performance of the classification model was compared with both the baseline and the lightweight models. The results indicate that the proposed model achieves high performance and has an accuracy of 92.3%, sensitivity of 92.1%, specificity of 98.5%, and f1-score of 91.9%. Using the proposed model, we aim to contribute to the early detection of diseases during the COVID-19 pandemic.

Accurate respiratory sound classification model based on piccolo pattern

Auscultation, or listening to body sounds with a stethoscope, is the most basic and instructive part of the physical examination. Although it is a quick and effective way of diagnosing respiratory tract disorders, the precision of the diagnosis demands a considerable deal of clinical knowledge. As a result, we've created a computerized diagnostic system that will detect breathing sounds automatically, assisting physicians and trainees in the specialization process. Automated respiratory sound classification is a complex issue for advanced biomedical signal processing. Therefore, variable models and methods have been introduced to overcome this problem. This research aims to introduce a high accurate sound classification model using a nonlinear histogram-based generator. To reach this aim, piccolo pattern (it uses S-box of the piccolo cipher as a pattern), statistical moments, tunable q-factor wavelet transform (TQWT), iterative neighborhood component analysis (INCA), and conventional classifiers are used together. This model uses TQWT to create levels. Piccolo pattern is employed to generate textural features (it is the main feature generator of this model), and statistics are deployed to extract statistical features. INCA chooses the relevant features. Decision tree (DT), support vector machine (SVM), and k nearest neighbors (KNN) classifiers are applied to the selected feature vectors to calculate results. Three cases are defined using ICHBI 2017 dataset to calculate results comprehensively. The defined cases contain seven, three, and eight categories, respectively.Furthermore, five performance calculation metrics are employed to evaluate the presented piccolo-pattern-based model comprehensively. The introduced piccolo pattern-based model reaches 99.45%, 99.31%, and 99.19% accuracies for Case 1, Case 2, and Case 3 by employing KNN. These accuracies denote the success of the piccolo pattern-based model. Furthermore, this model attains higher accuracies than the previously presented deep learning-based methods for respiratory sound classification.

An automated Covid-19 respiratory sound classification method based on novel local symmetric Euclidean distance pattern and ReliefF iterative MRMR feature selector

Covid-19 is a new variety of coronavirus that affects millions of people around the world. This virus infected millions of people and hundreds of thousands of people have passed away. Due to the panic caused by Covid-19, recently several researchers have tried to understand and to propose a solution to Covid-19 problem. Especially, researches in machine learning (ML) have been proposed to detect Covid-19 by using X-ray images. In this study, 10 classes of respiratory sounds, including respiratory sounds diagnosed with Covid-19 disease, were collected and ML methods were used to tackle this problem. The proposed respiratory sound classification method has been proposed in this study from feature generation network through hybrid and iterative feature selection to classification phases. A novel multileveled feature generating network is presented by gathering multilevel one-dimensional wavelet transform and a novel local symmetric Euclidean distance pattern (LSEDP). An automated hybrid feature selection method is proposed using ReliefF and ReliefF Iterative Maximum Relevancy Minimum Redundancy (RIMRMR) to select the optimal number of features. Four known classifiers were used to test the capability of our approach for lung disease detection in respiratory sounds. K nearest neighbors (kNN) method has achieved an accuracy of 91.02%.

Classification of Lung Sounds and Disease Prediction using Dense CNN Network

Respiratory illnesses are a main source of death in the world and exact lung sound identification is very significant for the conclusion and assessment of sickness. Be that as it may, this method is vulnerable to doctors and instrument limitations. As a result, the automated investigation and analysis of respiratory sounds has been a field of great research and exploration during the last decades. The classification of respiratory sounds has the potential to distinguish anomalies and diseases in the beginning phases of a respiratory dysfunction and hence improve the accuracy of decision making. In this paper, we explore the publically available respiratory sound database and deploy three different convolutional neural networks (CNN) and combine them to form a dense network to diagnose the respiratory disorders. The results demonstrate that this dense network classifies the sounds accurately and diagnoses the corresponding respiratory disorders associated with them.

Respiratory sound classification for crackles, wheezes, and rhonchi in the clinical field using deep learning

Auscultation has been essential part of the physical examination; this is non-invasive, real-time, and very informative. Detection of abnormal respiratory sounds with a stethoscope is important in diagnosing respiratory diseases and providing first aid. However, accurate interpretation of respiratory sounds requires clinician’s considerable expertise, so trainees such as interns and residents sometimes misidentify respiratory sounds. To overcome such limitations, we tried to develop an automated classification of breath sounds. We utilized deep learning convolutional neural network (CNN) to categorize 1918 respiratory sounds (normal, crackles, wheezes, rhonchi) recorded in the clinical setting. We developed the predictive model for respiratory sound classification combining pretrained image feature extractor of series, respiratory sound, and CNN classifier. It detected abnormal sounds with an accuracy of 86.5% and the area under the ROC curve (AUC) of 0.93. It further classified abnormal lung sounds into crackles, wheezes, or rhonchi with an overall accuracy of 85.7% and a mean AUC of 0.92. On the other hand, as a result of respiratory sound classification by different groups showed varying degree in terms of accuracy; the overall accuracies were 60.3% for medical students, 53.4% for interns, 68.8% for residents, and 80.1% for fellows. Our deep learning-based classification would be able to complement the inaccuracies of clinicians' auscultation, and it may aid in the rapid diagnosis and appropriate treatment of respiratory diseases.

Classification of respiratory sounds using improved convolutional recurrent neural network

Currently, auscultation using a stethoscope is performed for the diagnosis of respiratory diseases. Auscultation is a simple and non-invasive diagnostic method; however, the diagnostic results depend on the experience of the doctor, thereby rendering quantitative diagnosis difficult. Therefore, we herein propose a new automatic classification method based on deep learning algorithms for respiratory sounds to support the diagnosis of respiratory diseases. The proposed method comprises two stages. First, a spectrogram is generated by applying a short-time Fourier transform to the respiratory sound data. Subsequently, the obtained spectrogram is classified into normal and abnormal (three classes: crackle, wheeze, and both) respiratory sounds using an improved convolutional recurrent neural network. By classifying the respiratory sounds using the proposed method, the following results are obtained: sensitivity, 0.63; specificity,0.83; average score, 0.73; harmonic score, 0.72. Furthermore, the proposed method yields better accuracy compared with other methods.

GTCC-based BiLSTM deep-learning framework for respiratory sound classification using empirical mode decomposition

GTCC-based BiLSTM deep-learning framework for respiratory sound classification using empirical mode decomposition

Automatic diagnosis of COVID-19 disease using deep convolutional neural network with multi-feature channel from respiratory sound data: Cough, voice, and breath

The problem of respiratory sound classification has received good attention from the clinical scientists and medical researcher’s community in the last year to the diagnosis of COVID-19 disease. The Artificial Intelligence (AI) based models deployed into the real-world to identify the COVID-19 disease from human-generated sounds such as voice/speech, dry cough, and breath. The CNN (Convolutional Neural Network) is used to solve many real-world problems with Artificial Intelligence (AI) based machines. We have proposed and implemented a multi-channeled Deep Convolutional Neural Network (DCNN) for automatic diagnosis of COVID-19 disease from human respiratory sounds like a voice, dry cough, and breath, and it will give better accuracy and performance than previous models. We have applied multi-feature channels such as the data De-noising Auto Encoder (DAE) technique, GFCC (Gamma-tone Frequency Cepstral Coefficients), and IMFCC (Improved Multi-frequency Cepstral Coefficients) methods on augmented data to extract the deep features for the input of the CNN. The proposed approach improves system performance to the diagnosis of COVID-19 disease and provides better results on the COVID-19 respiratory sound dataset.

Classification of Respiratory Sounds by scSE-CRNN from Triple Types of Respiratory Sound Images

Classification of Respiratory Sounds by scSE-CRNN from Triple Types of Respiratory Sound Images

Automatic COVID-19 disease diagnosis using 1D convolutional neural network and augmentation with human respiratory sound based on parameters: cough, breath, and voice.

The issue in respiratory sound classification has attained good attention from the clinical scientists and medical researcher's group in the last year to diagnosing COVID-19 disease. To date, various models of Artificial Intelligence (AI) entered into the real-world to detect the COVID-19 disease from human-generated sounds such as voice/speech, cough, and breath. The Convolutional Neural Network (CNN) model is implemented for solving a lot of real-world problems on machines based on Artificial Intelligence (AI). In this context, one dimension (1D) CNN is suggested and implemented to diagnose respiratory diseases of COVID-19 from human respiratory sounds such as a voice, cough, and breath. An augmentation-based mechanism is applied to improve the preprocessing performance of the COVID-19 sounds dataset and to automate COVID-19 disease diagnosis using the 1D convolutional network. Furthermore, a DDAE (Data De-noising Auto Encoder) technique is used to generate deep sound features such as the input function to the 1D CNN instead of adopting the standard input of MFCC (Mel-frequency cepstral coefficient), and it is performed better accuracy and performance than previous models.ResultsAs a result, around 4% accuracy is achieved than traditional MFCC. We have classified COVID-19 sounds, asthma sounds, and regular healthy sounds using a 1D CNN classifier and shown around 90% accuracy to detect the COVID-19 disease from respiratory sounds.ConclusionA Data De-noising Auto Encoder (DDAE) was adopted to extract the acoustic sound signals in-depth features instead of traditional MFCC. The proposed model improves efficiently to classify COVID-19 sounds for detecting COVID-19 positive symptoms.

Multi-Time-Scale Features for Accurate Respiratory Sound Classification

The COVID-19 pandemic has amplified the urgency of the developments in computer-assisted medicine and, in particular, the need for automated tools supporting the clinical diagnosis and assessment of respiratory symptoms. This need was already clear to the scientific community, which launched an international challenge in 2017 at the International Conference on Biomedical Health Informatics (ICBHI) for the implementation of accurate algorithms for the classification of respiratory sound. In this work, we present a framework for respiratory sound classification based on two different kinds of features: (i) short-term features which summarize sound properties on a time scale of tenths of a second and (ii) long-term features which assess sounds properties on a time scale of seconds. Using the publicly available dataset provided by ICBHI, we cross-validated the classification performance of a neural network model over 6895 respiratory cycles and 126 subjects. The proposed model reached an accuracy of 85%±3% and an precision of 80%±8%, which compare well with the body of literature. The robustness of the predictions was assessed by comparison with state-of-the-art machine learning tools, such as the support vector machine, Random Forest and deep neural networks. The model presented here is therefore suitable for large-scale applications and for adoption in clinical practice. Finally, an interesting observation is that both short-term and long-term features are necessary for accurate classification, which could be the subject of future studies related to its clinical interpretation.

Respiratory Sound Classification for Remote Diagnosis

With rapid development of electronic control technology in internet technology in modern medical industry and with the development of electronic stethoscope we are one step closer to the remote diagnosis as the hardware part of it is readily available but there are limited software system that can classify stethoscope sound. Diagnosis or classification requires recognizing patterns. If the quantity of input is huge, it becomes difficult to identify these patterns. The collected data is often a non linear data, the conventional models fail to identify patterns. These challenges can be tacle with the use of latest technologies like Machine learning. Till date, many approaches were successful and now, with the use of Neural networks the loss factor is close to nil In this paper machine learning algorithm is implemented on Mel- spectrogram images in the convolutional neural network (CNN). Since considering MFCC features to classify sounds is generally accepted classification method for audio, its scale is used to find patterns in Spectrogram of samples using CNN. Sound is classified in four classes: (1) healthy (2) Containing Wheezes (3) Containing Crackles and (4) Containing both. Accuracy results of the experiments were around 63%-65%.

Collaborative framework for automatic classification of respiratory sounds

There are several diseases (e.g. asthma, pneumonia etc.) affecting the human respiratory apparatus altering its airway path substantially, thus characterising its acoustic properties. This work unfolds an automatic audio signal processing framework achieving classification between normal and abnormal respiratory sounds. Thanks to a recent challenge, a real-world dataset specifically designed to address the needs of the specific problem is available to the scientific community. Unlike previous works in the literature, the authors take advantage of information provided by several stethoscopes simultaneously, i.e. elaborating at the acoustic sensor network level. To this end, they employ two features sets extracted from different domains, i.e. spectral and wavelet. These are modelled by convolutional neural networks, hidden Markov models and Gaussian mixture models. Subsequently, a synergistic scheme is designed operating at the decision level of the best-performing classifier with respect to each stethoscope. Interestingly, such a scheme was able to boost the classification accuracy surpassing the current state of the art as it is able to identify respiratory sound patterns with a 66.7% accuracy.