skip to main content
10.1145/3704323.3704381acmotherconferencesArticle/Chapter ViewAbstractPublication PagesiccprConference Proceedingsconference-collections
research-article

An Automatic Diagnosis Method for Chronic Obstructive Pulmonary Disease (COPD) Based on the Integration of MFCC and LPCC Feature Parameters

Published: 07 January 2025 Publication History

Abstract

Chronic Obstructive Pulmonary Disease (COPD) is a common lung disease characterized by the main feature of restricted airflow. The diagnosis of chronic obstructive pulmonary disease (COPD) currently relies primarily on comprehensive clinical presentation, history of exposure to risk factors, physical signs, and laboratory examination. In order to address the complexity, time consumption, and potential treatment delay associated with existing diagnostic methods, a feature extraction method combining Linear Predictive Cepstral Coefficient (LPCC) and Mel Frequency Cepstral Coefficient (MFCC) has been proposed for automatic classification and diagnosis of COPD patients using various machine learning models. Initially, the respiratory sound features of COPD patients are extracted using the LPCC and MFCC feature extraction methods. Subsequently, representative feature dimensions are selected from the extracted features based on Fisher’s criterion for feature fusion. Finally, K-nearest neighbor method, support vector machine, and decision tree models are used for classification training and testing based on the fused features. Experimental results show an average recognition rate of 94.7% when 80% of samples from the Respiratory Database are used for training. Compared to traditional single-feature extraction methods, this approach not only improves the accuracy in diagnosing COPD but also reduces interference from noise in diagnostic results while significantly reducing computation time. It possesses faster diagnostic capabilities which can reduce medical resource wastage and misdiagnosis risks.

References

[1]
Liu T, CAI B Q. Introduction of the Global Strategy for the diag-nosis, management and prevention of chronic obstructive pulmonary disease (2011 revision) [J]. Chin J Respiratory & Critical Care,2012,11(01):1-12.
[2]
Zhang L, Miao M L, Jiang X Q, et al. Progress in the application of respiratory rehabilitation in chronie obstructive pulmonary disease[J]. Chinese Journal of Clinical Health, 2021, 24(05) : 612-617.
[3]
Kanwade A, Bairagi V. Classification of COPD and Nor-mal Lung Airways using Feature Extraction of Electromyo-graphic Signals[J]. Journal of King Saud University - Com-puter and Information Sciences, 2017, 31(4).
[4]
Ma X B, Zhang L X, Li Y, et al. Predicting chronic obstructive pulmonary disease based on optimized decision tree[J]. Journal of Shandong Normal University (Natural Science Edition),2017,32(2):18-29.
[5]
Fang Y L, Wang H, Di R T, et al. Multidimensional feature extraction and integrated diagnosis of COPD[J]. Application Research of Computers,2019,36(10):2925-2929.
[6]
Pei Z W,Zhu P. Research on lung sound signal recognition based on ICEEMDAN-MLP[J]. Electronic Design Engineering,2021,29(1):96-100.
[7]
Wang W. Speaker recognition of text-independent continuous natural speech and its implementation based on DSP[D]. PLA University of Information Engineering,2004.
[8]
YAO Rui, ZENG Zeqing, DU Junjie. Voice Activity Detection Method Based on the Noise Classification and Double Adaptive Threshold Decision. Advanced Engineering Sciences, 2018, 50(4): 170-178.
[9]
Yan W Y, Li L, Yang Y G, et al. Application of the computer-based respiratory sound analysis system based on Mel-frequency cepstral coefficient and dynamic time warping in healthy children[J]. Chinese Journal of Pediatrics, 2016,54 (8): 605-609.
[10]
Zhang W k. The Research of Fusion LPCC and MFCC Feature Parameters in Speech Recognition Technology[D] Xiangtan University, 2016.
[11]
Li H, Xu X l, Wu G X, et al. Research on Speech Emotional Feature Extraction Based on MFCC [J] Journal of Electronic Measurement and Instrumentation, 2017,31 (3): 448-453.
[12]
Wang B. An emproved LPCC parameter extrac-tion method research [J]. Electronic Design Engineering, 2012,20 (6):29-30,33.
[13]
Huang X B, Zhang L, Cao L, et al. Intelligent speech recognition methods of different frequency bands based on LPCC [J]. Electronic Design Engineering, 2020,28 (2):22-25,30.
[14]
Cai H, Zhang J, Huang Z T. Fisher Method for Analysis of Sound Acoustics and Its Application [J] Journal of Data Acquisition and Processing, 2000,15(4):471-475.
[15]
Shen K W, Li W J, Yue K Q. SVM with LPCC and MFCC for OSAHS snoring recognition [J]. Journal of Hangzhou Dianzi University(Natural Sciences), 2020,40(6):6.
[16]
Rocha BM, Filos D, Mendes L, Vogiatzis I, Perantoni E, Kaimakamis E, Natsiavas P, Oliveira A, Jácome C, Marques A, Paiva RP, A Respiratory Sound Database for the Development of Automated Classification In Precision Medicine Powered by pHealth and Connected Health (pp. 51-55). (2018).
[17]
Wang S Q, Hua G, Xu Y G,et al. Anal-ysis of inconsistency of AUC [J]. Journal of Jiangsu Nor-mal University (Natural Science Edition), 2013,31 (03): 31-34.
[18]
Wang J, Wu H Q, Song Z Q. Receiver operating characteristic curve (ROC) and its application in imaging [J]. Radiology practice, 2000 (03) : 201-202.
[19]
Lu J W. Automatic Mining Method for Sensitive Data of COPD Diagnosis Information Based on Neural Network Model[J]. Techniques of Automation and Applications, 2021,40 (11) : 80-85.
[20]
Mini P P, Thomas T, Gopikakumari R. EEG based direct speech BCI system using a fusion of SMRT and MFCC/LPCC features with ANN classifier[J]. Biomedical Signal Processing and Control, 2021, 68(2):102625.

Index Terms

  1. An Automatic Diagnosis Method for Chronic Obstructive Pulmonary Disease (COPD) Based on the Integration of MFCC and LPCC Feature Parameters

        Recommendations

        Comments

        Information & Contributors

        Information

        Published In

        cover image ACM Other conferences
        ICCPR '24: Proceedings of the 2024 13th International Conference on Computing and Pattern Recognition
        October 2024
        448 pages
        ISBN:9798400717482
        DOI:10.1145/3704323
        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        Published: 07 January 2025

        Check for updates

        Author Tags

        1. Chronic obstructive pulmonary disease
        2. Linear prediction cepstral coefficient
        3. Mel frequency cepstral coefficient
        4. Machine learning
        5. Auxiliary diagnosis

        Qualifiers

        • Research-article

        Funding Sources

        Conference

        ICCPR 2024

        Contributors

        Other Metrics

        Bibliometrics & Citations

        Bibliometrics

        Article Metrics

        • 0
          Total Citations
        • 14
          Total Downloads
        • Downloads (Last 12 months)14
        • Downloads (Last 6 weeks)14
        Reflects downloads up to 17 Feb 2025

        Other Metrics

        Citations

        View Options

        Login options

        View options

        PDF

        View or Download as a PDF file.

        PDF

        eReader

        View online with eReader.

        eReader

        Full Text

        View this article in Full Text.

        Full Text

        Figures

        Tables

        Media

        Share

        Share

        Share this Publication link

        Share on social media