Classification Techniques for Diagnosing Respiratory Sounds in Infants and Children

Signals play a fundamental role in science, technology, and communication by conveying information through varying patterns, amplitudes, and frequencies. This paper introduces innovative methodologies for processing electromyographic (EMG) signals to develop artificial intelligence systems capable of decoding muscle activity for controlling arm movements. The study investigates advanced signal processing techniques and machine learning classification algorithms using the GRABMyo dataset, aiming to enhance prosthetic control systems and rehabilitation technologies. A comprehensive analysis was conducted on signal processing techniques, including signal filtering and discrete wavelet transform (DWT), alongside a composite feature set comprising Mean Absolute Value (MAV), Waveform Length (WL), Zero Crossing (ZC), Slope Sign Changes (SSC), Root Mean Square (RMS), Enhanced Waveform Length (EWL), and Enhanced Mean Absolute Value (EMAV). These features, refined through Linear Discriminant Analysis (LDA) for dimensionality reduction, were classified using Support Vector Machine (SVM) algorithms. Signal filtering and DWT improved signal quality, facilitating better feature extraction, while the diverse feature set enhanced classification accuracy. LDA further improved accuracy by isolating the most informative features, and the SVM achieved optimal performance in decoding complex EMG patterns. Machine learning models, including K-Nearest Neighbor (KNN), Naïve Bayes (NB), and the SVM, were evaluated, with the SVM outperforming the others. The significance of these results lies in their potential applications in prosthetic control systems and rehabilitation technologies. By accurately decoding muscle activity, the developed systems can facilitate more intuitive and responsive robotic arm movements, contributing to the advancement of innovative solutions for individuals requiring prosthetic devices or undergoing rehabilitation, hence improving the quality of life for users. This research marks a significant step forward in the integration of advanced signal processing and machine learning in the field of EMG analysis.

This work addresses the problem of lung sound classification, in particular, the problem of distinguishing between wheeze and normal sounds. Wheezing sound detection is an important step to associate lung sounds with an abnormal state of the respiratory system, usually associated with tuberculosis or another chronic obstructive pulmonary diseases (COPD). The paper presents an approach for automatic lung sound classification, which uses different state-of-the-art sound features in combination with a C-weighted support vector machine (SVM) classifier that works better for unbalanced data. Feature extraction methods used here are commonly applied in speech recognition and related problems thanks to the fact that they capture the most informative spectral content from the original signals. The evaluated methods were: Fourier transform (FT), wavelet decomposition using Wavelet Packet Transform bank of filters (WPT) and Mel Frequency Cepstral Coefficients (MFCC). For comparison, we evaluated and contrasted the proposed approach against previous works using different combination of features and/or classifiers. The different methods were evaluated on a set of lung sounds including normal and wheezing sounds. A leave-two-out per-case cross-validation approach was used, which, in each fold, chooses as validation set a couple of cases, one including normal sounds and the other including wheezing sounds. Experimental results were reported in terms of traditional classification performance measures: sensitivity, specificity and balanced accuracy. Our best results using the suggested approach, C-weighted SVM and MFCC, achieve a 82.1% of balanced accuracy obtaining the best result for this problem until now. These results suggest that supervised classifiers based on kernel methods are able to learn better models for this challenging classification problem even using the same feature extraction methods.

In the field of medicine, with the introduction of computer systems that can collect and analyze massive amounts of data, many non-invasive diagnostic methods are being developed for a variety of conditions. In this study, our aim is to develop a non-invasive method of classifying respiratory sounds that are recorded by an electronic stethoscope and the audio recording software that uses various machine learning algorithms.In order to store respiratory sounds on a computer, we developed a cost-effective and easy-to-use electronic stethoscope that can be used with any device. Using this device, we recorded 17,930 lung sounds from 1630 subjects.We employed two types of machine learning algorithms; mel frequency cepstral coefficient (MFCC) features in a support vector machine (SVM) and spectrogram images in the convolutional neural network (CNN). Since using MFCC features with a SVM algorithm is a generally accepted classification method for audio, we utilized its results to benchmark the CNN algorithm. We prepared four data sets for each CNN and SVM algorithm to classify respiratory audio: (1) healthy versus pathological classification; (2) rale, rhonchus, and normal sound classification; (3) singular respiratory sound type classification; and (4) audio type classification with all sound types. Accuracy results of the experiments were; (1) CNN 86%, SVM 86%, (2) CNN 76%, SVM 75%, (3) CNN 80%, SVM 80%, and (4) CNN 62%, SVM 62%, respectively.As a result, we found out that spectrogram image classification with CNN algorithm works as well as the SVM algorithm, and given the large amount of data, CNN and SVM machine learning algorithms can accurately classify and pre-diagnose respiratory audio.

We designed a computer-based respiratory sound analysis system to identify pediatric normal lung sound. To verify the validity of the computer-based respiratory sound analysis system. First we downloaded the standard lung sounds from the network database (website: http: //www.easyauscultation.com/lung-sounds-reference-guide) and recorded 3 samples of abnormal loud sound (rhonchi, wheeze and crackles) from three patients of The Department of Pediatrics, the First Affiliated Hospital of Xiamen University. We regarded such lung sounds as"reference lung sounds". The"test lung sounds"were recorded from 29 children form Kindergarten of Xiamen University. we recorded lung sound by portable electronic stethoscope and valid lung sounds were selected by manual identification. We introduced Mel-frequency cepstral coefficient (MFCC) to extract lung sound features and dynamic time warping (DTW) for signal classification. We had 39 standard lung sounds, recorded 58 test lung sounds. This computer-based respiratory sound analysis system was carried out in 58 lung sound recognition, correct identification of 52 times, error identification 6 times. Accuracy was 89.7%. Based on MFCC and DTW, our computer-based respiratory sound analysis system can effectively identify healthy lung sounds of children (accuracy can reach 89.7%), fully embodies the reliability of the lung sounds analysis system.

Automatic Digital Modulation Recognition (ADMR) is becoming an interesting problem with various civil and military applications. In this paper, an ADMR algorithm in Multi-Carrier Code Division Multiple Access (MC-CDMA) systems using Discrete Transforms (DTs) and Mel-Frequency Cepstral Coefficients (MFCCs) is proposed. This algorithm uses various DT techniques such as the Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT) and Discrete Sine Transform (DST) with MFCCs to extract features from the modulated signal and a Support Vector Machine (SVM) to classify the modulation orders. The proposed algorithm avoids over fitting and local optimal problems that appear in Artificial Neural Networks (ANNs). Simulation results shows the classifier is capable of recognizing the modulation scheme with high accuracy up to 90% - 100% using DWT, DCT and DST for some modulation schemes over a wide Signal-to-Noise Ratio (SNR) range in the presence of Additive White Gaussian Noise (AWGN) and Rayleigh fading channel, particularly at a low Signal-to-Noise ratios (SNRs).

The aim of the study was to inspect the acoustic properties and sleep characteristics of a preapneic snoring sound. The feasibility of forecasting upcoming respiratory events by snoring sound was also investigated. Participants with habitual snoring or a heavy breathing sound during sleep were recruited consecutively. Polysomnography was conducted, and snoring-related breathing sound was recorded simultaneously. Acoustic features and sleep features were extracted from 30-second samples, and a machine learning algorithm was used to establish 2 prediction models. A total of 74 eligible participants were included. Model 1, tested by 5-fold cross-validation, achieved an accuracy of 0.92 and an area under the curve of 0.94 for respiratory event prediction. Model 2, with acoustic features and sleep information tested by Leave-One-Out cross-validation, had an accuracy of 0.78 and an area under the curve of 0.80. Sleep position was found to be the most important among all sleep features contributing to the performance of the 2 models. Preapneic sound presented unique acoustic characteristics, and snoring-related breathing sound could be deployed as a real-time apneic event predictor. The models, combined with sleep information, serve as a promising tool for an early warning system to forecast apneic events. Wang B, Yi X, Gao J, etal. Real-time prediction of upcoming respiratory events via machine learning using snoring sound signal. J Clin Sleep Med. 2021;17(9):1777-1784.

Since the beginning of the recording of lung sounds, many studies have been done on automatic recognition of lung sounds. But, multi-channel recording methods were frequently used in these studies. Whereas single-channel recording methods are more suitable for the auscultation procedure. Therefore, there is a greater need in the literature for studies on single-channel lung sounds. In this study, appropriate features derived from the Mel Frequency Cepstrum Coefficients (MFCC) and classification methods were searched for automatic classification of single channel common lung sounds. In the feature extraction phase, the Hjorth parameters, mean, standard deviation, skewness, kurtosis and entropy values were derived from the MFCC. The features were tested by using Support Vector Machine (SVM), k-Nearest Neighbour (k-NN), Linear Discriminant Analysis (LDA) and Naive Bayes (NBA) algorithms. The results obtained showed that the derived features from MFCC reached 99.05% success when the SFS method was applied.

Emotional speech recognition: Resources, features, and methods

Lung sound classification using cepstral-based statistical features

Classification of infant cry into normal and pathological cries is a socially relevant research problem for a long time. Crying is the only means that an infant use for communication. The state-of-the-art feature vectors, such as Short-Time Fourier Transform (STFT) representations and Mel Frequency Cepstral Coefficients (MFCC) have been earlier reported for this task. However, quasi-periodic sampling of vocal tract spectrum by high pitch-source harmonics of infant cry results in poor spectral resolution in STFT based spectrum and hence, these feature vectors could not produce satisfactory performance. In this work, we compare the performance of various time-averaged feature extraction techniques of window sizes 20, and 55 ms with three different classifiers, namely, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest (RF). The experiments in this work are performed using the 10-fold stratified cross-validation on standard and statistically meaningful Baby Chillanto dataset using various state-of-the-art features vectors. It was observed that the time-averaged dynamic MFCC feature vector gives a classification accuracy of \(98.48\% \). Furthermore, the performance of the proposed feature vectors was also studied using the confusion matrix and found to be better than other features, such as LFCC and CC.KeywordsInfant cry classificationMFCCLFCCCepstral coefficientsTime averageKNNRandom forestSVM

A comprehensive overview on signal processing and artificial intelligence techniques applications in classification of power quality disturbances

Respiratory sound classification has emerged as a promising non-invasive and scalable tool for the early detection of respiratory disorders. While most previous studies have relied on a single feature extraction method-such as Melfrequency cepstral coefficients (MFCC), Mel-spectrograms, or Short-Time Fourier Transform (STFT)-this study provides a comprehensive comparative analysis of these three approaches, evaluated individually, in pairwise combinations, and in a combined three-method configuration. Experiments are conducted on the SPRSound dataset, a pediatric respiratory sound database comprising 6,656 annotated events from seven unbalanced classes. Three architectures are assessed under identical preprocessing and augmentation strategies: a custom convolutional neural network (CNN), and two pre-trained models (VGG16 and InceptionV3) fine-tuned via transfer learning. Results show that STFT consistently delivers the highest performance for CNN and VGG16 models, while MFCC achieves the best accuracy with InceptionV3. Specifically, VGG16 with STFT attained 93.43% accuracy (score: 0.9545), whereas InceptionV3 with MFCC achieved the top performance within its architecture. These findings highlight the importance of aligning feature extraction techniques with model architecture and provide a systematic benchmark for SPRSound-based respiratory sound classification.

Information and communication technology usage in the healthcare sector is not perceptible due to various challenges with increased healthcare needs. With the outburst of COVID-19, when the different countries announced lockdown and social distancing rules, it is crucial to predict a person's symptoms, which will help in the early diagnosis. In such situations, there is a tremendous growth seen in the usage of various technologies, such as remote health monitoring, Wireless Body Area Networks (WBANs), Machine Learning (ML), and Decision Support system (DSS). Hence, the chapter focuses on detecting diseases and associated symptoms using various ML algorithms. A total of 3073 patient data (heartbeat, snore, and body temperature) has been collected. The collected data were preprocessed to remove empty cells and zero values by replacing the mean of the cells. Later, the extracted features were used in Empirical Mode Decomposition (EWD) and Discrete Wavelet Transformation (DWT). Then, the optimized algorithms with the threshold values were identified by consulting doctors for accurate disease prediction. With the testing performance of various ML algorithms, such as Decision Tree Classifier (DTC), K-Nearest Neighbor (KNN), Gradient Descent (SGD), Naive Bayes (NB), Multilayer perceptron (MLP), Support Vector Machine (SVM), and Random Forest (RF), was compared. Performance evaluation parameters are accuracy, precision, F1 score, and recall. The results showed an average of 100% accuracy with SGD and SVM with DWT, whereas EMD, SVM, and MLP outperformed the state-of-the-art algorithms with 99.83% accuracy.

Respiratory sound analysis provides vital information of the present condition of the Lungs. It can be used to assist medical professionals in differential diagnosis. In this paper, we intend to distinguish between normal (without any pathological condition), airway obstruction pathology and parenchymal pathology using respiratory sound recordings taken from RALE database. The proposed method uses Mel-frequency cepstral coefficients (MFCC) as features extracted from respiratory sounds. The extracted features are distinguished using support vector machine classifier (SVM). The classifier performance is analysed by using confusion matrix technique. A mean classification accuracy of 90.77% was reported using the proposed method. The performance analysis of the SVM classifier using confusion matrix revealed that normal, airway obstruction and parenchymal pathology are classified at 94.11%, 92.31% and 88.00% classification accuracy respectively. The analysis reveals that the proposed method shows promising outcome in distinguishing between the normal, airway obstruction and parenchymal pathology.

Murmurs are auscultatory sounds produced by turbulent blood flow in and around the heart. These sounds usually signify an underlying cardiac pathology, which may include diseased valves or an abnormal passage of blood flow. The murmurs are classified based on their occurrence in different parts of the heart cycle; systolic murmurs and diastolic murmurs. This paper investigates features derived from cepstrum of the heart sound signals and use them to train three classifiers; k-nearest neighbor (kNN) classifier, multilayer perceptron (MLP) neural networks and support vector machines (SVM) for classification of heart sounds into normal, systolic murmurs and diastolic murmurs. These features have been compared with features extracted from short-term Fourier transform (STFT) and discrete wavelet transform (DWT) in combination with the above three classifiers. The classification experiments were carried out on the heart sounds samples collected from various web sources. Among various combinations of the above features and classifiers, SVM trained on cepstral features are most promising for murmur classification with an accuracy of around 95%.