An Automated Lung Sound Preprocessing and Classification System Based OnSpectral Analysis Methods

Serbes, Görkem; Ulukaya, Sezer; Kahya, Yasemin P.

doi:10.1007/978-981-10-7419-6_8

Cited by 72 publications

(47 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [24], low-level features were used for the feature extraction, and the features then conveyed to the Decision Tree classifier, and lung sounds were classified to an accuracy of 49.62%. In [25], the wavelet decomposition and STFT were combined as a feature set, producing a best accuracy level of 57.88% using the SVM classifier. In [26], two methods were proposed for lung sound classification.…”

Section: Experi̇mental Setup and Resultsmentioning

confidence: 99%

Classification of Lung Sounds With CNN Model Using Parallel Pooling Structure

2020

View full text Add to dashboard Cite

The recognition of various lung sounds recorded using electronic stethoscopes plays a significant role in the early diagnoses of respiratory diseases. To increase the accuracy of specialist evaluations, machine learning techniques have been intensely employed during the past 30 years. In the current study, a new pretrained Convolutional Neural Network (CNN) model is proposed for the extraction of deep features. In the CNN architecture, an average-pooling layer and a max-pooling layer are connected in parallel in order to boost classification performance. The deep features are utilized as the input of the Linear Discriminant Analysis (LDA) classifier using the Random Subspace Ensembles (RSE) method. The proposed method was evaluated against a challenge dataset known as ICBHI 2017. The deep features and the LDA with RSE method provided the best accuracy score when compared to other existing methods using the same dataset, improving the classification accuracy by 5.75%. INDEX TERMS Lung sound, CNN model, parallel pooling, deep features, RSE method.

show abstract

Section: Experi̇mental Setup and Resultsmentioning

confidence: 99%

Classification of Lung Sounds With CNN Model Using Parallel Pooling Structure

2020

View full text Add to dashboard Cite

show abstract

“…A method based on standard signal-processing techniques is described in [9]. The preprocessing phase here consists of a band-pass filter which is in charge of removing undesired frequencies due to heart sounds and other noise components.…”

Section: Related Workmentioning

confidence: 99%

“…In this context, machine learning techniques have shown to provide an invaluable computational tool for detecting disease-related anomalies in the early stages of a respiratory dysfunctions (e.g., [8][9][10]). In particular, deep learning (DL) based methods promise to support enhanced detection of respiratory diseases from auscultation sound data, given their well-recognized ability of learning complex non-linear functions from large, high-dimensional data.…”

Section: Introductionmentioning

confidence: 99%

Deep Auscultation: Predicting Respiratory Anomalies and Diseases via Recurrent Neural Networks

Perna

Tagarelli

2019

2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)

104

View full text Add to dashboard Cite

Respiratory diseases are among the most common causes of severe illness and death worldwide. Prevention and early diagnosis are essential to limit or even reverse the trend that characterizes the diffusion of such diseases. In this regard, the development of advanced computational tools for the analysis of respiratory auscultation sounds can become a game changer for detecting disease-related anomalies, or diseases themselves. In this work, we propose a novel learning framework for respiratory auscultation sound data. Our approach combines state-of-the-art feature extraction techniques and advanced deep-neural-network architectures. Remarkably, to the best of our knowledge, we are the first to model a recurrent-neural-network based learning framework to support the clinician in detecting respiratory diseases, at either level of abnormal sounds or pathology classes. Results obtained on the ICBHI benchmark dataset show that our approach outperforms competing methods on both anomaly-driven and pathology-driven prediction tasks, thus advancing the state-of-the-art in respiratory disease analysis. arXiv:1907.05708v1 [eess.AS]

show abstract

“…However, such a setting is ill-posed as one class is combination of two existing classes, thus without necessarily distinctive spectral content. Given the difficulty of the specific problem [7,8] and towards a better formalisation, this work limits the problem space addressing the most important one here (classification of normal versus abnormal respiratory sounds) leaving further differentiation (crack, wheeze, crack + wheeze) to a subsequent module.…”

Section: Problem Formulationmentioning

confidence: 99%

“…In our previous work [6], we employed a wavelet packet-based feature set along with a graph-based classification scheme. Similarly to related researches using the standardised task [7,8], we attempted to create a single model explaining the distribution followed by the data coming from all stethoscopes. However, these were placed on different chest locations.…”

Section: Introductionmentioning

confidence: 99%

Collaborative framework for automatic classification of respiratory sounds

Ntalampiras¹

2020

IET signal process.

View full text Add to dashboard Cite

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.

show abstract

An Automated Lung Sound Preprocessing and Classification System Based OnSpectral Analysis Methods

Cited by 72 publications

References 19 publications

Classification of Lung Sounds With CNN Model Using Parallel Pooling Structure

Classification of Lung Sounds With CNN Model Using Parallel Pooling Structure

Deep Auscultation: Predicting Respiratory Anomalies and Diseases via Recurrent Neural Networks

Collaborative framework for automatic classification of respiratory sounds

Contact Info

Product

Resources

About