A Lung Sound Classification System Based on Data Augmenting Using ELM-Wavelet-AE

Ari, Berna; Alçın, Ömer Faruk; Şengür, Abdulkadir

doi:10.55525/tjst.1063039

Cited by 4 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various feature extraction techniques, such as Mel-Spectrograms, Mel-Frequency Cepstral Coefficients (MFCCs), and scalograms, have been employed in ML and DL algorithms for respiratory sound detection [13] , [14] , [15] , [16] . However, the efficacy of traditional ML-based methods depends substantially on the quality of the hand-crafted features.…”

Section: Introductionmentioning

confidence: 99%

Attention Feature Fusion Network via Knowledge Propagation for Automated Respiratory Sound Classification

Crisdayanti,

Nam,

Jung

et al. 2024

IEEE Open J. Eng. Med. Biol.

View full text Add to dashboard Cite

Goal: In light of the COVID-19 pandemic, the early diagnosis of respiratory diseases has become increasingly crucial. Traditional diagnostic methods such as computed tomography (CT) and magnetic resonance imaging (MRI), while accurate, often face accessibility challenges. Lung auscultation, a simpler alternative, is subjective and highly dependent on the clinician's expertise. The pandemic has further exacerbated these challenges by restricting face-to-face consultations. This study aims to overcome these limitations by developing an automated respiratory sound classification system using deep learning, facilitating remote and accurate diagnoses. Methods: We developed a deep convolutional neural network (CNN) model that utilizes spectrographic representations of respiratory sounds within an image classification framework. Our model is enhanced with attention feature fusion of low-to-high-level information based on a knowledge propagation mechanism to increase classification effectiveness. This novel approach was evaluated using the ICBHI benchmark dataset and a larger, self-collected Pediatric dataset comprising outpatient children aged 1 to 6 years. Results: The proposed CNN model with knowledge propagation demonstrated superior performance compared to existing state-of-the-art models. Specifically, our model showed higher sensitivity in detecting abnormalities in the Pediatric dataset, indicating its potential for improving the accuracy of respiratory disease diagnosis. Conclusions: The integration of a knowledge propagation mechanism into a CNN model marks a significant advancement in the field of automated diagnosis of respiratory disease. This study paves the way for more accessible and precise healthcare solutions, which is especially crucial in pandemic scenarios.

show abstract

Section: Introductionmentioning

confidence: 99%

Attention Feature Fusion Network via Knowledge Propagation for Automated Respiratory Sound Classification

Crisdayanti,

Nam,

Jung

et al. 2024

IEEE Open J. Eng. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…Feature extraction was performed using the Correlation-Similarity Analysis (F-DFA) to classify the EMG signals and RMS methods with non-overlapping windows to measure statistical similarity. The extracted features were classified by machine learning methods such as decision trees and k-NN [19,20]. On the other hand, Tuncer et al [21] developed a new model for prosthetic hand control based on the discrete wavelet transform and the triplet model.…”

Section: Introductionmentioning

confidence: 99%

EMG Signal Classification Using Deep Learning and Time Domain Descriptors-Based Feature Extraction for Hand Grip Movement Recognition

Arı¹

2023

View full text Add to dashboard Cite

Electromyogram (EMG) signals are very important in recognizing hand and finger movements and controlling prosthesis movements. In recent years, EMG signals have become popular in designing and controlling human-machine interactions and rehabilitation equipment such as robotic prostheses. This study aims to develop an innovative model based on EMG signal in the classification of basic hand grip movements that can improve prosthetic hand movements for individuals who have lost some limbs for various reasons. The proposed approach consists of Time Domain Descriptors (TDD), convolutional neural network (CNN), Long short-term memory (LSTM) techniques, Selection Minimum Redundancy Maximum Relationship (MRMR), and Support Vector Machine (SVM). First, it is applied to TDD, CNN, and LSTM models to extract features from EMG signals. It is then applied as input to MRMR to select the most effective features from the obtained features. Finally, SVM is applied to classify different hand grip movements. The effectiveness of the proposed model was evaluated with the EMG hand gestures dataset in the publicly available UCI repository. In experimental studies, a 95.63% accuracy rate was achieved in the first two of the five subjects and 100% accuracy in the remaining three subjects. As a result, it achieved an average specificity of 99.66% and an accuracy of 98.34% for five subjects. In addition, the experimental results of the proposed hybrid model show that when compared to the most advanced methods using the same dataset, the model achieves a higher classification rate and produces superior results compared to several previous studies. Therefore, this study reveals that it can be used as a low-cost control unit that can accurately classify hand grips from EMG signals with high accuracy.

show abstract

Performance evaluation of lung sounds classification using deep learning under variable parameters

Wang,

Sun

2024

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

It is desired to apply deep learning models (DLMs) to assist physicians in distinguishing abnormal/normal lung sounds as quickly as possible. The performance of DLMs depends on feature-related and model-related parameters heavily. In this paper, the relationship between performance and feature-related parameters of a DLM, i.e., convolutional neural network (CNN) is analyzed through experiments. ICBHI 2017 is selected as the lung sounds dataset. The sensitivity analysis of classification performance of the DLM on three parameters, i.e., the length of lung sounds frame, overlap percentage (OP) of successive frames and feature type, is performed. An augmented and balanced dataset is acquired by the way of white noise addition, time stretching and pitch shifting. The spectrogram and mel frequency cepstrum coefficients of lung sounds are used as features to the CNN, respectively. The results of training and test show that there exists significant difference on performance among various parameter combinations. The parameter OP is performance sensitive. The higher OP, the better performance. It is concluded that for fixed sampling frequency 8 kHz, frame size 128, OP 75% and spectrogram feature is optimum under which the performance is relatively better and no extra computation or storage resources are required.

show abstract

A Lung Sound Classification System Based on Data Augmenting Using ELM-Wavelet-AE

Cited by 4 publications

References 40 publications

Attention Feature Fusion Network via Knowledge Propagation for Automated Respiratory Sound Classification

Attention Feature Fusion Network via Knowledge Propagation for Automated Respiratory Sound Classification

EMG Signal Classification Using Deep Learning and Time Domain Descriptors-Based Feature Extraction for Hand Grip Movement Recognition

Performance evaluation of lung sounds classification using deep learning under variable parameters

Contact Info

Product

Resources

About