Ortak vektör yöntemiyle bağırsak sesinin tespiti ve sınıflandırılması

Öz

Bağırsak aktivitesinin bir ölçüsü olan bağırsak sesi (BS) dinleme yoluyla gözlemlenebilir. BS’den yararlanarak, bağırsak hastalıklarının erken, zararsız ve pratik tespiti için birçok çalışma yapılmıştır. Temel olarak, tekil (SB) ve çoklu (MB) patlamaya benzeyen bağırsak sesleri, basit mikrofonlarla gözlemlenebilir olmasına rağmen, ani değişen karakteri, sessiz dönemlerin (QP) uzun olması ve mide, kas, nefes gibi diğer seslerle karışabilmesi nedenleriyle doğru tespit edilemeyebilir. Bu çalışmada, önişleme adımlarından sonra bağırsak seslerine özgü karakteristik zaman-frekans öznitelikleri bir araya getirilerek bir dağılım matrisi (P) oluşturulmuş ve bu matrisinin sıfır veya sıfıra yakın öz değerlerine karşılık gelen öz vektörlerden farksızlık alt uzayını geren ortak değişim matrisi (Q) elde edilmiştir. Bir kaydın hangi sınıfa ait olduğunu belirlemek için ortak değişim matrisi ile yeni uzaya olan izdüşümünün hangi sınıfın ortak vektörüne yakınsadığına bakmak yeterli olacaktır. Deneysel çalışmalarda, birer dakikalık kayıtlardaki SB, MB, QP ve BS-değil sınıflarının ortalama oranları sırasıyla %2,3, %0,3, %92,9 ve %4,5 iken, eğitimde hiç kullanılmamış bir dakikalık kayıtlarla yapılan testlerde, tekil patlamaların (SB) %87,5'i, çoklu patlamaların (MB) %35,7'si, BS-değil kısımlarının %84,3'ünün doğru sınıflara atandığı görülmüştür. Sonuç olarak, tüm sınıfların dağılımlarına bakarak sınıflar içi örnekleri birbirine yaklaştıran, sınıflar arası örnekleri ise birbirinden uzaklaştıran bu yeni yansıtım uzayı (Q) kullanılarak, tıp uzmanlarına danışılmadan eğitim setinden bağımsız olarak bağırsak sesleri diğer seslerden büyük oranda ayrıştırılabilir.

Anahtar Kelimeler

• Bağırsak sesi tanıma
• sınıflandırma
• biyosensörler
• ortak vektör
• Bowel sound recognition
• classification
• biosensors
• common vector.

Detection and classification of bowel sound with common vector method

Öz

Bowel sound (BS), a measure of bowel activity, can be observed through listening. By utilizing BS, many studies have been conducted for the early, harmless and practical detection of intestinal diseases. Basically, single (SB) and multiple (MB) burst-like bowel sounds, although observable with simple microphones, may not be accurately detected due to their abrupt character, long quiet periods (QP), and may be confused with other sounds such as stomach, muscle, breath. In this study, after the preprocessing steps, a distribution matrix (P) was formed by bringing together the characteristic time-frequency features specific to bowel sounds, and a common variation matrix (Q) stretching the indifference subspace was obtained from the eigenvectors corresponding to zero or near zero eigenvalues of this matrix. In order to determine which class a record belongs to, it will be sufficient to look at the common vector of which class its projection to the new space converges with the co-change matrix. In experimental studies, the average rates of SB, MB, QP, and non-BS classes in one-minute recordings were 2.3%, 0.3%, 92.9%, and 4.5%, respectively, while in tests performed with one-minute recordings that were never used in training, 87.5% of single bursts (SB), 35.7% of multiple bursts (MB), 84.3% of non-BS parts were assigned to the correct classes. As a result, by using this new reflection space (Q), which brings the in-class samples closer to each other and distances the inter-class samples from each other by looking at the distributions of all classes, bowel sounds can be largely separated from other sounds, regardless of the training set, without consulting medical professionals.

Anahtar Kelimeler

• Bowel sound recognition
• classification
• biosensors
• common vector.

Kaynakça

1. 1. Cannon, W. B., Auscultation of the rhythmic sounds produced by the stomach and intestines, American Journal of Physiology-Legacy Content, 14 (4), 339–353, 1905.
2. 2. Georgoulis, B., Bowel sounds, Proceedings of The Royal Society of Medicine, 60 (9), 917–920, 1967.
3. 3. Watson, W. C. and Knox, E. C., Phonoenterography: the recording and analysis of bowel sounds, Gut, 8 (1), 88–94, 1967.
4. 4. Dalle, D., Devroede, G., Thibault, R., and Perrault, J., Computer analysis of bowel sounds, Computers In Biology And Medicine, 4 (3), 247–256, 1975.
5. 5. Arnbjörnsson, E., Normal and pathological bowel sound patterns, Annales Chirurgiae Et Gynaecologiae, 75 (6), 314–318, 1986.
6. 6. Vantrappen, G., Janssens, J., Coremans, G., and Jian, R., Gastrointestinal motility disorders, Digestive Diseases and Sciences, 31 (9 Suppl), 5S-25S, 1986.
7. 7. Mansy, H. A. and Sandler, R. H., Bowel-sound signal enhancement using adaptive filtering, IEEE Engineering In Medicine And Biology Magazine, The Quarterly Magazine of the Engineering In Medicine & Biology Society, 16 (6), 105–117, 1997.
8. 8. Li, M., Yang, J., and Wang, X., Research on auto-identification method to the typical bowel sound signal, 2011 4th International Conference on Biomedical Engineering and Informatics (BMEI), 2011.

9. 9. Hadjileontiadis, L. J. and Panas, S. M., on modeling impulsive bioacoustic signals with symmetric /spl alpha/-stable distributions, application in discontinuous adventitious lung sounds and explosive bowel sounds, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286), 1998.
10. 10. Xizheng, Z., Ling, Y., and Weixiong, W., An New Filtering Methods in the Wavelet Domain for Bowel Sounds, International Journal Of Advanced Computer Science And Applications (IJACSA), 1 (5), 2010.
11. 11. Hadjileontiadis, L. J., Kontakos, T. P., Liatsos, C. N., Mavrogiannis, C. C., Rokkas, T. A., and Panas, S. M., Enhancement of the diagnostic character of bowel sounds using higher-order crossings, Proceedings of the First Joint BMES/EMBS Conference. 1999 IEEE Engineering in Medicine and Biology 21st Annual Conference and the 1999 Annual Fall Meeting of the Biomedical Engineering Society (Cat. N), 1999.
12. 12. Hadjileontiadis, L. J., Liatsos, C. N., Mavrogiannis, C. C., Rokkas, T. A., and Panas, S. M., Enhancement of bowel sounds by wavelet-based filtering, IEEE Transactions on Bio-Medical Engineering, 47 (7), 876–886, 2000.
13. 13. Hadjileontiadis, L. J., Wavelet-based enhancement of lung and bowel sounds using fractal dimension thresholding--Part I, methodology, IEEE Transactions on Bio-Medical Engineering, 52 (6), 1143–1148, 2005.
14. 14. Hadjileontiadis, L. J., Wavelet-based enhancement of lung and bowel sounds using fractal dimension thresholding-part II, application results, IEEE Transactions on Biomedical Engineering, 52 (6), 1050–1064, 2005.
15. 15. Ranta, R., Heinrich, C., Louis-Dorr, V., Wolf, D., and Guillemin, F., Wavelet-based bowel sounds denoising, segmentation and characterization, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2001.
16. 16. Ranta, R., Louis-Dorr, V., Heinrich, C., Wolf, D., and Guillemin, F., Principal component analysis and interpretation of bowel sounds, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2004.
17. 17. Sakata, O., Suzuki, Y., Matsuda, K., and Satake, T., Temporal changes in occurrence frequency of bowel sounds both in fasting state and after eating, Journal of Artificial Organs, the Official Journal of the Japanese Society for Artificial Organs, 16 (1), 83–90, 2013.
18. 18. Yin, Y., Jiang, H., Feng, S., Liu, J., Chen, P., Zhu, B., and Wang, Z., Bowel sound recognition using SVM classification in a wearable health monitoring system, SCIENCE CHINA Information Sciences, 61 (8), 084301, 2018.
19. 19. Kölle, K., Fougner, A., Ellingsen, R., Carlsen, S., and Stavdahl, Ø., Feasibility of early meal detection based on abdominal sound, IEEE Journal of Translational Engineering In Health And Medicine, PP, 2019. 20. Huang, Y., Song, I., Rana, P., and Koh, G., Fast diagnosis of bowel activities, 2017 International Joint Conference on Neural Networks (IJCNN), 2017.
20. 21. Yin, Y., Jiang, H., Yang, W., and Wang, Z., Intestinal motility assessment based on Legendre fitting of logarithmic bowel sound spectrum, Electronics Letters, 52 (16), 1364–1366, 2016.
21. 22. Emoto, T., Shono, K., Abeyratne, U. R., Okahisa, T., Yano, H., Akutagawa, M., Konaka, S., and Kinouchi, Y., ARMA-based spectral bandwidth for evaluation of bowel motility by the analysis of bowel sounds, Physiological Measurement, 34 (8), 925–936, 2013.
22. 23. Kim, K. S., Seo, J. H., Ryu, S. H., Kim, M. H., and Song, C. G., Estimation algorithm of the bowel motility based on regression analysis of the jitter and shimmer of bowel sounds, Computer Methods And Programs In Biomedicine, 104 (3), 426–434, 2011.
23. 24. Kim, K.-S., Park, H.-J., Kang, H. S., and Song, C.-G., Awareness system for bowel motility estimation based on artificial neural network of bowel sounds, 4th International Conference on Awareness Science and Technology, 2012.
24. 25. Kölle, K., Aftab, M. F., Andersson, L. E., Fougner, A. L., and Stavdahl, Ø., Data driven filtering of bowel sounds using multivariate empirical mode decomposition, BioMedical Engineering OnLine, 18 (1), 28, 2019. 26. Ulusar, U. D., Recovery of gastrointestinal tract motility detection using Naive Bayesian and minimum statistics, Computers In Biology And Medicine, 51, 223–228, 2014.
25. 27. Longfu, Z., Yi, S., Sun, H., Zheng, L., Dapeng, H., and Yonghe, H., Identification of bowel sound signal with spectral entropy method, 2015 12th IEEE International Conference on Electronic Measurement Instruments (ICEMI), 2015.
26. 28. Yin, Y., Yang, W., Jiang, H., and Wang, Z., Bowel sound based digestion state recognition using artificial neural network, 2015 IEEE Biomedical Circuits and Systems Conference (BioCAS), 2015.
27. 29. Sheu, M., Lin, P., Chen, J., Lee, C., and Lin, B., Higher-Order-Statistics-Based Fractal Dimension for Noisy Bowel Sound Detection, IEEE Signal Processing Letters, 22 (7), 789–793, 2015.
28. 30. Lin, B., Sheu, M., Chuang, C., Tseng, K., and Chen, J., Enhancing Bowel Sounds by Using a Higher Order Statistics-Based Radial Basis Function Network, IEEE Journal Of Biomedical And Health Informatics, 17 (3), 675–680, 2013.
29. 31. Dimoulas, C., Kalliris, G., Papanikolaou, G., and Kalampakas, A., Novel wavelet domain Wiener filtering de-noising techniques, Application to bowel sounds captured by means of abdominal surface vibrations, Biomedical Signal Processing And Control, 1 (3), 177–218, 2006.
30. 32. Dimoulas, C., Kalliris, G., Papanikolaou, G., and Kalampakas, A., Long-term signal detection, segmentation and summarization using wavelets and fractal dimension, a bioacoustics application in gastrointestinal-motility monitoring, Computers In Biology And Medicine, 37 (4), 438–462, 2007.
31. 33. Dimoulas, C., Kalliris, G., Papanikolaou, G., Petridis, V., and Kalampakas, A., Bowel-sound pattern analysis using wavelets and neural networks with application to long-term, unsupervised, gastrointestinal motility monitoring, Expert Systems With Applications, 34 (1), 26–41, 2008.
32. 34. Dimoulas, C. A., Papanikolaou, G. V., and Petridis, V., Pattern classification and audiovisual content management techniques using hybrid expert systems, A video-assisted bioacoustics application in Abdominal Sounds pattern analysis, Expert Systems With Applications, 38 (10), 13082–13093, 2011.
33. 35. Dimoulas, C. A., Audiovisual Spatial-Audio Analysis by Means of Sound Localization and Imaging, A Multimedia Healthcare Framework in Abdominal Sound Mapping, IEEE Transactions on Multimedia, 18 (10), 1969–1976, 2016.
34. 36. Sakata, O. and Suzuki, Y., Optimum Unit Time on Calculating Occurrence Frequency of Bowel Sounds for Real-Time Monitoring of Bowel Peristalsis, International Journal of Signal Processing Systems, 465–468, 2016.
35. 37. Kim, K.-S., Seo, J.-H., and Song, C.-G., Non-invasive algorithm for bowel motility estimation using a back-propagation neural network model of bowel sounds, BioMedical Engineering OnLine, 10, 69, 2011.
36. 38. Chien, C.-H., Huang, H.-T., Wang, C.-Y., and Chong, F.-C., Two-dimensional static and dynamic display system of bowel sound magnitude map for evaluation of intestinal motility, Biomedical Engineering, Applications, Basis And Communications, 21 (05), 333–342, 2009.
37. 39. Ulusar, U. D., Canpolat, M., Yaprak, M., Kazanir, S., and Ogunc, G., Real-time monitoring for recovery of gastrointestinal tract motility detection after abdominal surgery, 2013 7th International Conference on Application of Information and Communication Technologies, 2013.
38. 40. Öztaş, A. S., Türk, E., Uluşar, Ü. D., Canpolat, M., Yaprak, M., Kazanır, S., Öğünç, G., Doğru, V., and Canagir, O. C., Bioacoustic sensor system for automatic detection of bowel sounds, 2015 Medical Technologies National Conference (TIPTEKNO), 2015.
39. 41. Türk, E., Öztaş, A. S., Uluşar, Ü. D., Canpolat, M., Kazanır, S., Yaprak, M., Öğünç, G., Doğru, V., and Canagir, O. C., Wireless bioacoustic sensor system for automatic detection of bowel sounds, 2015 19th National Biomedical Engineering Meeting (BIYOMUT), 2015.
40. 42. Al-Turjman, F., Edge Computing, From Hype to Reality, Springer International Publishing, 133–144 (2019).
41. 43. Güvenç, H., Wireless ECG Device with Arduino, 2020 Medical Technologies Congress (TIPTEKNO), (2020).
42. 44. Du, X., Allwood, G., Webberley, K. M., Osseiran, A., Wan, W., Volikova, A., and Marshall, B. J., A mathematical model of bowel sound generation, The Journal of the Acoustical Society of America, 144 (6), EL485–EL491, 2018.
43. 45. Hadjileontiadis, L. J. and Rekanos, I. T., Enhancement of explosive bowel sounds using Kurtosis-based filtering, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439), 2003.
44. 46. Rekanos, I. T. and Hadjileontiadis, L. J., An iterative kurtosis-based technique for the detection of nonstationary bioacoustic signals, Signal Processing, 86 (12), 3787–3795, 2006.
45. 47. Hadjileontiadis, L. J. and Rekanos, I. T., Detection of explosive lung and bowel sounds by means of fractal dimension, IEEE Signal Processing Letters, 10 (10), 311–314, 2003.
46. 48. Cevikalp, H., Neamtu, M., Wilkes, M., and Barkana, A., Discriminative common vectors for face recognition, IEEE Transactions on Pattern Analysis And Machine Intelligence, 27 (1), 4–13, 2005.
47. 49. Güvenç, H., Ortak vektör yöntemiyle öznitelik çıkarımı, 2009.
48. 50. Mamun, K. A. A. and McFarlane, N., Integrated real time bowel sound detector for artificial pancreas systems, Sensing And Bio-Sensing Research, 7, 84–89, 2016.
49. 51. Wang, F., Wu, D., Jin, P., Zhang, Y., Yang, Y., Ma, Y., Yang, A., Fu, J., and Feng, X., A flexible skin-mounted wireless acoustic device for bowel sounds monitoring and evaluation, Science China Information Sciences, 62 (10), 202402, 2019.