{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T17:46:19Z","timestamp":1785433579808,"version":"3.56.0"},"reference-count":40,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:00:00Z","timestamp":1783123200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010044","name":"University of Lancashire","doi-asserted-by":"publisher","award":["101479113"],"award-info":[{"award-number":["101479113"]}],"id":[{"id":"10.13039\/100010044","id-type":"DOI","asserted-by":"publisher"}]},{"award":["101479113"],"award-info":[{"award-number":["101479113"]}],"id":[{"id":"https:\/\/ror.org\/010jbqd54","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Respiratory disease classification using lung sound recordings remains challenging due to signal interference, heterogeneous acquisition conditions, and substantial overlap among clinically related acoustic patterns. This study presents a framework for respiratory disease classification using NMF-enhanced log-mel spectrograms and deep neural classifiers. Respiratory sound recordings from two publicly available datasets were harmonized into a unified label space comprising Asthma, Bronchiectasis, Bronchiolitis, COPD, Healthy, Pneumonia and URTI. Following signal standardization and fixed-length segmentation, a non-negative matrix factorization (NMF)-based enhancement stage was applied to increase the salience of respiratory components prior to log-mel spectrogram generation. The proposed classifier was a convolutional recurrent neural network (CRNN) that combined convolutional feature extraction, bidirectional recurrent modelling, and attention-based temporal aggregation. For comparison, RDLINet, a conventional CNN, ResNet, and a YOLO-style backbone were implemented under the same preprocessing and training framework. Experimental results demonstrated that the proposed CRNN achieved the best overall performance, attaining 96.14 \u00b1 0.50% accuracy and 94.05 \u00b1 1.21% Macro-F1 on the unified seven-class cohort. Class-wise analysis, confusion-matrix evaluation, and output-space visualization further showed that the CRNN provided more balanced recognition across disease categories and clearer class separation than competing architectures. These findings indicate that NMF-enhanced spectro-temporal modelling combined with convolutional recurrent learning offers an effective approach for automated multi-class respiratory disease classification.<\/jats:p>","DOI":"10.3390\/s26134268","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T12:01:37Z","timestamp":1783339297000},"page":"4268","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Respiratory Disease Classification Using NMF-Enhanced Log-Mel Spectrograms and Convolutional Recurrent Neural Networks"],"prefix":"10.3390","volume":"26","author":[{"given":"Bowen","family":"Han","sequence":"first","affiliation":[{"name":"School of Engineering and Computing, University of Lancashire, Preston PR1 2HE, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2099-9520","authenticated-orcid":false,"given":"Wei","family":"Quan","sequence":"additional","affiliation":[{"name":"School of Engineering and Computing, University of Lancashire, Preston PR1 2HE, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bogdan","family":"Matuszewski","sequence":"additional","affiliation":[{"name":"School of Engineering and Computing, University of Lancashire, Preston PR1 2HE, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dennis","family":"Corbett","sequence":"additional","affiliation":[{"name":"Department of Paediatric, East Lancashire Hospitals NHS Trust, Blackburn BB2 3HH, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1016\/S2213-2600(20)30105-3","article-title":"Prevalence and attributable health burden of chronic respiratory diseases, 1990\u20132017: A systematic analysis for the Global Burden of Disease Study 2017","volume":"8","author":"Soriano","year":"2020","journal-title":"Lancet Respir. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e069679","DOI":"10.1136\/bmj-2021-069679","article-title":"Burden of chronic obstructive pulmonary disease and its attributable risk factors in 204 countries and territories, 1990\u20132019: Results from the Global Burden of Disease Study 2019","volume":"378","author":"Safiri","year":"2022","journal-title":"BMJ"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1626","DOI":"10.1016\/S1473-3099(22)00510-2","article-title":"Age-sex differences in the global burden of lower respiratory infections and risk factors, 1990\u20132019: Results from the Global Burden of Disease Study 2019","volume":"22","author":"Kyu","year":"2022","journal-title":"Lancet Infect. Dis."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1056\/NEJMra1302901","article-title":"Fundamentals of lung auscultation","volume":"370","author":"Bohadana","year":"2014","journal-title":"N. Engl. J. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1183\/13993003.01132-2015","article-title":"Towards the standardisation of lung sound nomenclature","volume":"47","author":"Pasterkamp","year":"2016","journal-title":"Eur. Respir. J."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"035001","DOI":"10.1088\/1361-6579\/ab03ea","article-title":"An open access database for the evaluation of respiratory sound classification algorithms","volume":"40","author":"Rocha","year":"2019","journal-title":"Physiol. Meas."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/S1386-5056(98)00137-3","article-title":"A wavelet-based reduction of heart sound noise from lung sounds","volume":"52","author":"Hadjileontiadis","year":"1998","journal-title":"Int. J. Med. Inform."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"344","DOI":"10.3109\/03091902.2011.595529","article-title":"Reduction of heart sound interference from lung sound signals using empirical mode decomposition technique","volume":"35","author":"Mondal","year":"2011","journal-title":"J. Med. Eng. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","article-title":"Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences","volume":"28","author":"Davis","year":"1980","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hershey, S., Chaudhuri, S., Ellis, D.P.W., Gemmeke, J.F., Jansen, A., Moore, R.C., Plakal, M., Platt, D., Saurous, R.A., and Seybold, B. (2017). CNN Architectures for Large-Scale Audio Classification. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017), New Orleans, LA, USA, 5\u20139 March 2017, IEEE.","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Piczak, K.J. (2015). Environmental Sound Classification with Convolutional Neural Networks. Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2015), Boston, MA, USA, 17\u201320 September 2015, IEEE.","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.artmed.2018.04.008","article-title":"Lung sounds classification using convolutional neural networks","volume":"88","author":"Bardou","year":"2018","journal-title":"Artif. Intell. Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"103831","DOI":"10.1016\/j.compbiomed.2020.103831","article-title":"Multi-channel lung sound classification with convolutional recurrent neural networks","volume":"122","author":"Messner","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"107367","DOI":"10.1016\/j.compeleceng.2021.107367","article-title":"Classification of respiratory sounds using improved convolutional recurrent neural network","volume":"94","author":"Asatani","year":"2021","journal-title":"Comput. Electr. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1109\/TASLP.2017.2690575","article-title":"Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection","volume":"25","author":"Parascandolo","year":"2017","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"903","DOI":"10.1098\/rspa.1998.0193","article-title":"The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis","volume":"454","author":"Huang","year":"1998","journal-title":"Proc. R. Soc. A"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1109\/TSP.2013.2288675","article-title":"Variational Mode Decomposition","volume":"62","author":"Dragomiretskiy","year":"2014","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1038\/44565","article-title":"Learning the parts of objects by non-negative matrix factorization","volume":"401","author":"Lee","year":"1999","journal-title":"Nature"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1109\/MSP.2008.4408452","article-title":"Nonnegative matrix and tensor factorization","volume":"25","author":"Cichocki","year":"2008","journal-title":"IEEE Signal Process. Mag."},{"key":"#cr-split#-ref_20.1","unstructured":"Smaragdis, P. (2004). Non-negative Matrix Factor Deconvolution"},{"key":"#cr-split#-ref_20.2","unstructured":"Extraction of Multiple Sound Sources from Monophonic Inputs. Independent Component Analysis and Blind Signal Separation (ICA 2004), LNCS 3195, Springer."},{"key":"ref_21","unstructured":"Kohavi, R. (1995, January 20\u201325). A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, Montreal, QC, Canada."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"101046","DOI":"10.1016\/j.patter.2024.101046","article-title":"Avoiding common machine learning pitfalls","volume":"5","author":"Lones","year":"2024","journal-title":"Patterns"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yu, S., Yu, J., Chen, L., Zhu, B., Liang, X., Xie, Y., and Sun, Q. (2025). Advances and Challenges in Respiratory Sound Analysis: A Technique Review Based on the ICBHI2017 Database. Electronics, 14.","DOI":"10.20944\/preprints202506.1527.v1"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Nguyen, T., and Pernkopf, F. (2021). Lung Sound Classification Using Co-tuning and Stochastic Normalization. arXiv.","DOI":"10.1109\/TBME.2022.3156293"},{"key":"ref_25","first-page":"556","article-title":"Algorithms for Non-negative Matrix Factorization","volume":"13","author":"Lee","year":"2001","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2421","DOI":"10.1162\/NECO_a_00168","article-title":"Algorithms for Nonnegative Matrix Factorization with the \u03b2-Divergence","volume":"23","author":"Idier","year":"2011","journal-title":"Neural Comput."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2164","DOI":"10.1162\/neco_a_00980","article-title":"Rank Selection in Nonnegative Matrix Factorization Using Minimum Description Length","volume":"29","author":"Squires","year":"2017","journal-title":"Neural Comput."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wood, S.U.N., and Rouat, J. (2017, January 20\u201324). Real-Time Speech Enhancement with GCC-NMF. Proceedings of the Interspeech 2017, Stockholm, Sweden.","DOI":"10.21437\/Interspeech.2017-1458"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1109\/IEEEDATA.2025.3566012","article-title":"Descriptor: Heart and Lung Sounds Dataset Recorded From a Clinical Manikin Using Digital Stethoscope (HLS-CMDS)","volume":"2","author":"Torabi","year":"2025","journal-title":"IEEE Data Descr."},{"key":"ref_30","unstructured":"FitzGerald, D., and Jaiswal, R. (2012, January 17\u201321). On the Use of Masking Filters in Sound Source Separation. Proceedings of the 15th International Conference on Digital Audio Effects, DAFx-12, York, UK."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"106913","DOI":"10.1016\/j.dib.2021.106913","article-title":"A dataset of lung sounds recorded from the chest wall using an electronic stethoscope","volume":"35","author":"Fraiwan","year":"2021","journal-title":"Data Brief."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/s42979-024-03506-9","article-title":"Multi-task Learning for Lung Sound and Lung Disease Classification","volume":"6","author":"Venkatapathiah","year":"2024","journal-title":"SN Comput. Sci."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Khan, R., Khan, S.U., Saeed, U., and Koo, I.-S. (2024). Auscultation-Based Pulmonary Disease Detection through Parallel Transformation and Deep Learning. Bioengineering, 11.","DOI":"10.3390\/bioengineering11060586"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Wall, C., Zhang, L., Yu, Y., Kumar, A., and Gao, R. (2022). A Deep Ensemble Neural Network with Attention Mechanisms for Lung Abnormality Classification Using Audio Inputs. Sensors, 22.","DOI":"10.3390\/s22155566"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Basu, V., and Rana, S. (2020, January 27\u201329). Respiratory diseases recognition through respiratory sound with the help of deep neural network. Proceedings of the 2020 4th International Conference on Computational Intelligence and Networks (CINE), Kolkata, India.","DOI":"10.1109\/CINE48825.2020.234388"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"4008813","DOI":"10.1109\/TIM.2023.3292953","article-title":"RDLINet: A Novel Lightweight Inception Network for Respiratory Disease Classification Using Lung Sounds","volume":"72","author":"Roy","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1186\/s13634-024-01148-w","article-title":"Performance evaluation of lung sounds classification using deep learning under variable parameters","volume":"2024","author":"Wang","year":"2024","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, H., Yeh, C.H., and Liu, X. (2022). Classify Respiratory Abnormality in Lung Sounds Using STFT and a Fine-Tuned ResNet18 Network. Proceedings of the IEEE BioCAS, Taipei, Taiwan, 13\u201315 October 2022, IEEE.","DOI":"10.1109\/BioCAS54905.2022.9948614"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.3390\/make5040083","article-title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","volume":"5","author":"Terven","year":"2023","journal-title":"Mach. Learn. Knowl. Extr."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4268\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T12:18:14Z","timestamp":1783340294000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4268"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,4]]},"references-count":40,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26134268"],"URL":"https:\/\/doi.org\/10.3390\/s26134268","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,4]]}}}