Automatic Classification of Dry Cough and Wet Cough Based on Improved Reverse Mel Frequency Cepstrum Coefficients_Journal of Biomedical Engineering

Authors：

 ZHUChunmei ^1,2 , LIUBaojun ¹ , LIPing ¹ , MOHongqiang ² , ZHENGZeguang ³

1. Mechanical & Electrical Engineering Department, University of Electronic Science and Technology of China, Zhongshan Institute, Zhongshan 528403, China;
2. College of Automation Science and Engineering, South China University of Technology, Guangzhou 510641, China;
3. First Affiliated Hospital of Guangzhou Medical College, Guangzhou 510120, China;

Corresponding author：

ZHUChunmei, Email: cmzhu@zsc.edu.cn

Keywords：

computer-aided diagnosis; automatic classification of cough; feature extraction; reverse Mel frequency cepstrum coefficients

DOI：

10.7507/1001-5515.20160042

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Automatic classification of different types of cough plays an important role in clinical. In the previous research of cough classification or cough recognition, traditional Mel frequency cepstrum coefficients (MFCC) which extracts feature mainly from low frequency band is usually used as feature expression. In this paper, by analyzing the distributions of spectral energy of dry/wet cough, it is found that spectral difference of two types of cough exits mainly in middle frequency band and high frequency band. To better reflect the spectral difference of dry cough and wet cough, an improved method of extracting reverse MFCC is proposed. In this method, reverse Mel filter-bank in which filters are allocated in reverse Mel scale is adopted and is improved by placing filters only in the frequency band with high spectral energy. As a result, features are mainly extracted from the frequency band where two types of cough show both high spectral energy and distinguished difference. Detailed process of accessing improved reverse MFCC was introduced and hidden Markov models trained by 60 dry cough and 60 wet cough were used as cough classification model. Classification experiment results for 120 dry cough and 85 wet cough showed that, compared to traditional MFCC, better classification performance was achieved by the proposed method and the total classification accuracy was raised from 89.76% to 93.66%.

Citation： ZHUChunmei, LIUBaojun, LIPing, MOHongqiang, ZHENGZeguang. Automatic Classification of Dry Cough and Wet Cough Based on Improved Reverse Mel Frequency Cepstrum Coefficients. Journal of Biomedical Engineering, 2016, 33(2): 239-243, 254. doi: 10.7507/1001-5515.20160042 Copy

1.	YOUSAF N, MONTEIRO W, MATOS S, et al. Cough frequency in health and disease[J]. Eur Respir J, 2013, 41(1):241-243.
2.	BARRY S J, DANE A D, MORICE A H, et al. The automatic recognition and counting of cough[J]. Cough, 2006, 2(1):8-17.
3.	SWARNKAR V, ABEYRATNE U R, AMRULLOH Y, et al. Neural network based algorithm for automatic identification of cough sounds[C]//EMBC 2013:35th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society. Osaka, Japan:2013:1764-1767.
4.	MATOS S, BIRRING S S, PAVORD I D, et al. Detection of cough signals in continuous audio recordings using hidden Markov models[J]. IEEE Trans Biomed Eng, 2006, 53(6):1078-1083.
5.	MATOS S, BIRRING S S, PAVORD I D, et al. An automated system for 24-h monitoring of cough frequency:the leicester cough monitor[J]. IEEE Trans Biomed Eng, 2007, 54(8):1472-1479.
6.	SHIN S H, HASHIMOTO T, HATANO S. Automatic detection system for cough sounds as a symptom of abnormal health condition[J]. IEEE Transactions on Information Technology in Biomedicine, 2009, 13(4):486-493.
7.	MARTINEK J, KLCO P, VRABEC M, et al. Cough sound analysis[J]. Acta Medica Martiniana, 2013, 13(1):15-20.
8.	DRUGMAN T, URBAIN J, BAUWENS N, et al. Objective study of sensor relevance for automatic cough detection[J]. IEEE J Biomed Health Inform, 2013, 17(3):699-707.
9.	BIRRING S S, FLEMING T, MATOS S, et al. The leicester cough monitor:preliminary validation of an automated cough detection system in chronic cough[J]. Eur Respir J, 2008, 31(5):1013-1018.
10.	WILHELM F H, ROTH W T, SACKNER M A. The LifeShirt. An advanced system for ambulatory measurement of respiratory and cardiac function[J]. Behav Modif, 2003, 27(5):671-691.
11.	HOLLIER C A, HARMER A R, MAXWELL L J, et al. Validation of respiratory inductive plethysmography (LifeShirt) in obesity hypoventilation syndrome[J]. Respir Physiol Neurobiol, 2014, 194(1):15-22.
12.	SMITH J A, EARIS J E, WOODCOCK A A. Establishing a gold standard for manual cough counting:video versus digital audio recordings[J]. Cough, 2006, 2(1):6.
13.	PIIRILA P, SOVIJARVI A R. Objective assessment of cough[J]. European Respiratory Journal, 1995, 8(11):1949-1956.
14.	SHIELDS M D, DOHERTY G M. Chronic cough in children[J]. Paediatr Respir Rev, 2013, 14(2):100-106.
15.	李文, 莫鸿强, 田联房, 等.采用MFCC和DTW的咳嗽干湿性自动分类技术[J].计算机工程与应用, 2010, 46(13):209-212.
16.	SWARNKAR V, ABEYRATNE U R, CHANG A B, et al. Automatic identification of wet and dry cough in pediatric patients with respiratory diseases[J]. Ann Biomed Eng, 2013, 41(5):1016-1028.
17.	CHATRZARRIN H. Feature extraction for the differentiation of dry and wet cough sounds[D]. Ottawa:Carleton University, 2011.
18.	KORPÁŠ J, SADLOÑOVÁ J, VRABEC M. Analysis of the cough sound:an overview[J]. Pulm Pharmacol, 1996, 9(5-6):261-268.
19.	ZHU Chunmei, TIAN Lianfang, LI Xiangyang, et al. Recognition of cough using features improved by sub-band energy transformation[C]//BMEI 2013:6th International Conference on Biomedical Engineering and Informatics. Hangzhou, China:2013:251-255.
20.	PICONE J W. Signal modeling techniques in speech recognition[J]. Proceedings of the IEEE, 1993, 81(9):1215-1247.
21.	CHAKROBORTY S, ROY A, MAJUMDAR S, et al. Capturing complementary information via reversed filter bank and parallel implementation with MFCC for improved text-independent speaker identification[C]//International Conference on Computing:Theory and Application, 2007. Kolkata:2007:463-467.
22.	RABINER L R. A tutorial on hidden Markov models and selected applications in speech recognition[J]. Proceedings of the IEEE, 1989, 77(2):257-286.

1. YOUSAF N, MONTEIRO W, MATOS S, et al. Cough frequency in health and disease[J]. Eur Respir J, 2013, 41(1):241-243.
2. BARRY S J, DANE A D, MORICE A H, et al. The automatic recognition and counting of cough[J]. Cough, 2006, 2(1):8-17.
3. SWARNKAR V, ABEYRATNE U R, AMRULLOH Y, et al. Neural network based algorithm for automatic identification of cough sounds[C]//EMBC 2013:35th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society. Osaka, Japan:2013:1764-1767.
4. MATOS S, BIRRING S S, PAVORD I D, et al. Detection of cough signals in continuous audio recordings using hidden Markov models[J]. IEEE Trans Biomed Eng, 2006, 53(6):1078-1083.
5. MATOS S, BIRRING S S, PAVORD I D, et al. An automated system for 24-h monitoring of cough frequency:the leicester cough monitor[J]. IEEE Trans Biomed Eng, 2007, 54(8):1472-1479.
6. SHIN S H, HASHIMOTO T, HATANO S. Automatic detection system for cough sounds as a symptom of abnormal health condition[J]. IEEE Transactions on Information Technology in Biomedicine, 2009, 13(4):486-493.
7. MARTINEK J, KLCO P, VRABEC M, et al. Cough sound analysis[J]. Acta Medica Martiniana, 2013, 13(1):15-20.
8. DRUGMAN T, URBAIN J, BAUWENS N, et al. Objective study of sensor relevance for automatic cough detection[J]. IEEE J Biomed Health Inform, 2013, 17(3):699-707.
9. BIRRING S S, FLEMING T, MATOS S, et al. The leicester cough monitor:preliminary validation of an automated cough detection system in chronic cough[J]. Eur Respir J, 2008, 31(5):1013-1018.
10. WILHELM F H, ROTH W T, SACKNER M A. The LifeShirt. An advanced system for ambulatory measurement of respiratory and cardiac function[J]. Behav Modif, 2003, 27(5):671-691.
11. HOLLIER C A, HARMER A R, MAXWELL L J, et al. Validation of respiratory inductive plethysmography (LifeShirt) in obesity hypoventilation syndrome[J]. Respir Physiol Neurobiol, 2014, 194(1):15-22.
12. SMITH J A, EARIS J E, WOODCOCK A A. Establishing a gold standard for manual cough counting:video versus digital audio recordings[J]. Cough, 2006, 2(1):6.
13. PIIRILA P, SOVIJARVI A R. Objective assessment of cough[J]. European Respiratory Journal, 1995, 8(11):1949-1956.
14. SHIELDS M D, DOHERTY G M. Chronic cough in children[J]. Paediatr Respir Rev, 2013, 14(2):100-106.
15. 李文, 莫鸿强, 田联房, 等.采用MFCC和DTW的咳嗽干湿性自动分类技术[J].计算机工程与应用, 2010, 46(13):209-212.
16. SWARNKAR V, ABEYRATNE U R, CHANG A B, et al. Automatic identification of wet and dry cough in pediatric patients with respiratory diseases[J]. Ann Biomed Eng, 2013, 41(5):1016-1028.
17. CHATRZARRIN H. Feature extraction for the differentiation of dry and wet cough sounds[D]. Ottawa:Carleton University, 2011.
18. KORPÁŠ J, SADLOÑOVÁ J, VRABEC M. Analysis of the cough sound:an overview[J]. Pulm Pharmacol, 1996, 9(5-6):261-268.
19. ZHU Chunmei, TIAN Lianfang, LI Xiangyang, et al. Recognition of cough using features improved by sub-band energy transformation[C]//BMEI 2013:6th International Conference on Biomedical Engineering and Informatics. Hangzhou, China:2013:251-255.
20. PICONE J W. Signal modeling techniques in speech recognition[J]. Proceedings of the IEEE, 1993, 81(9):1215-1247.
21. CHAKROBORTY S, ROY A, MAJUMDAR S, et al. Capturing complementary information via reversed filter bank and parallel implementation with MFCC for improved text-independent speaker identification[C]//International Conference on Computing:Theory and Application, 2007. Kolkata:2007:463-467.
22. RABINER L R. A tutorial on hidden Markov models and selected applications in speech recognition[J]. Proceedings of the IEEE, 1989, 77(2):257-286.

Journal of Biomedical Engineering

Automatic Classification of Dry Cough and Wet Cough Based on Improved Reverse Mel Frequency Cepstrum Coefficients

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content