Uyarlamalı Filtrelemeyle EKG Gürültü Temizleme için Yazılım Aracı

Abstract

Elektrokardiyogram (EKG), kalp fonksiyonlarını kontrol etmek ve bazı hastalıkları teşhis etmek için kullanılan biyomedikal bir sinyaldir. Değerlendirmelerin doğru bir şekilde yapılabilmesi için ilgili sinyallerin gürültüden iyi bir şekilde arındırılmış olması gerekir. Bu amaçla birçok yöntem geliştirilmiştir. Gerçekleştirilen çalışmada, EKG gürültü temizleme için birçok uyarlamalı algoritmayı bir araya getirerek yeni bir yazılım aracı tasarlanmıştır. Kullanıcı dostu grafiksel bir arayüze sahip bu araç, sinyal yükleme, ön işleme, görselleştirme ve tek veya karşılaştırmalı gürültü temizleme işlemlerini içermektedir. Geliştirilen aracın bazı güçlü ve farklı yönleri, birçok uyarlanabilir algoritma içermesi, sinyallere belirtilen özelliklere sahip farklı gürültü türleri ekleyebilmesi, tek veya karşılaştırmalı gürültü temizleme işlemleri gerçekleştirebilmesi, birçok değerlendirme parametresini hesaplayıp sunabilmesi, karşılaştırmalı analizde en başarılı yöntemi önerebilmesi ve sinyallerin ayrıntılı spektrumlarını göstermesidir. Ayrıca, bu araç uyarlamalı algoritmalar, gürültüler ve gürültü temizleme işlemleri hakkında ayrıntılı teorik bilgiler de sağlamaktadır. Bunun yanında zengin içeriğiyle, gürültü temizleme süreçlerinde uyarlanabilir algoritmaların eğitiminde de faydalıdır.

Keywords

• EKG Gürültü Temizleme
• Uyarlamalı Filtreleme
• Yazılım Aracı

A Software Tool for ECG Denoising with Adaptive Filtering

Abstract

The electrocardiogram (ECG) is a biomedical signal used to check heart functions and diagnose some diseases. In order for these assessing to be made correctly, the relevant signals must be well cleared of noise. Many methods have been developed for this purpose. In this study we designed a new software tool by collecting many adaptive algorithms for ECG denoising. This tool was developed with a user-friendly graphical interface and comprises the loading of signals, their preprocessing, visualization, and single or comparative denoising. Some of the strengths and different aspects of the developed tool are that it contains many adaptive algorithms, can add different noise types with specified characteristics to the signals, can perform single or comparative denoising operations, can calculate and present many evaluation parameters, can recommend the most successful method in comparative analysis, and shows detailed spectrums of signals. Additionally, this tool provides detailed theoretical information about adaptive algorithms, noises and denoising processing. With its rich content, it is also useful in education of adaptive algorithms in denoising processes.

Keywords

• ECG Denoising
• Adaptive Filtering
• Software Tool

References

1. Chatterjee S, Thakur RS, Yadav RN, Gupta L, Raghuvanshi DK. Review of noise removal techniques in ECG signals. IET Signal Process 2020;14(9):569-90. doi:10.1049/iet-spr.2020.0104.
2. Malghan PG, Hota MK. A review on ECG filtering techniques for rhythm analysis. Research on Biomedical Engineering 2020;36(2):171-86. doi:10.1007/s42600-020-00057-9.
3. Mir HY, Singh O. ECG denoising and feature extraction techniques - a review. Journal of Medical Engineering & Technology 2021;45(8):672-84. doi:10.1080/03091902.2021.1955032.
4. Devi GNS, Mittal VK. Enhancing ECG signal in noisy environment: A review. In: Gupta N, Ghatak S, Gupta A, Mukherjee AL, editors. Artificial intelligence on medical data. Springer; 2023, p. 427-37. doi:10.1007/978-981-19-0151-5_36.
5. Widrow B, Glover JR, McCool JM, Kaunitz J, Williams CS, Hearn RH, et al. Adaptive noise cancelling: Principles and applications. Proceedings of the IEEE 1975;63(12):1692-716. doi:10.1109/PROC.1975.10036.
6. Haykin S. Adaptive filter theory. 4th ed. Prentice Hall; 2002.
7. Rahman MZU, Shaik RA, Reddy DVRK. Noise cancellation in ECG signals using computationally simplified adaptive filtering techniques: Application to biotelemetry. Signal Processing: An International Journal (SPIJ) 2009;3:120-31.
8. Rahman MZU, Shaik RA, Reddy DVRK. Efficient sign based normalized adaptive filtering techniques for cancelation of artifacts in ECG signals: Application to wireless biotelemetry. Signal Processing 2011;91(2):225-39. doi:10.1016/j.sigpro.2010.07.002.

9. Islam MZ, Sajjad GMS, Rahman MH, Dey AK, Biswas MAM, Hoque AKMJ. Performance comparison of modified LMS and RLS algorithms in de-noising of ECG signals. International Journal of Engineering and Technology 2012;2:466-8.
10. Rahman MZU, Shaik RA, Reddy DVRK. Efficient and simplified adaptive noise cancelers for ECG sensor based remote health monitoring. IEEE Sensors Journal 2012;12(3):566-73. doi:10.1109/JSEN.2011.2111453.
11. Gowri T, Kumar PR, Reddy DVRK. An efficient variable step size least mean square adaptive algorithm used to enhance the quality of electrocardiogram signal. In: Thampi S, Gelbukh A, Mukhopadhyay J, editors. Advances in signal processing and intelligent recognition systems. Springer; 2014, p. 463-75. doi:10.1007/978-3-319-04960-1_41.
12. Gowri T, Kumar PR, Reddy DVRK, Rahman MZU. Denoising artifacts from cardiac signal using normalized variable step size LMS algorithm. Sensors & Transducers Journal 2015;187:138-45.
13. Gowri T, Kumar PR, Reddy DVRK. Performance of variable step size LMS adaptive algorithm for the removal of artifacts from electrocardiogram using DSP processor. In: 2017 International Conference on Intelligent Sustainable Systems (ICISS), Palladam, India. 2017, p. 342-6. doi:10.1109/ISS1.2017.8389427.
14. Salman MN, Rao PT, Rahman MZU. Cardiac signal enhancement using normalised variable step algorithm for remote healthcare monitoring systems. International Journal of Medical Engineering and Informatics 2017;9(2):145-61. doi:10.1504/IJMEI.2017.083091.
15. Basha SNJ, Zia-Ur-Rahman M, Rao DBRM. Noise removal from electrocardiogram signals using leaky and normalized version of adaptive noise canceller. International Journal of Computer Science & Communication Networks 2011;1:81-4.
16. Gowri T, Swomya I, Rahman ZU, Dodda RKR. Adaptive powerline interference removal from cardiac signals using leaky based normalized higher order filtering techniques. In: 2013 1st International Conference on Artificial Intelligence, Modelling and Simulation, Kota Kinabalu, Malaysia. 2013, p. 294-8. doi:10.1109/AIMS.2013.54.
17. Karthik GVS, Sugumar SJ. High resolution cardiac signal extraction using novel adaptive noise cancelers. In: 2013 International Mutli-Conference on Automation, Computing, Communication, Control and Compressed Sensing (iMac4s), Kottayam, India. 2013, p. 564-8. doi:10.1109/iMac4s.2013.6526474.
18. Salman MN, Rao PT, Rahman MZU. Novel logarithmic reference free adaptive signal enhancers for ECG analysis of wireless cardiac care monitoring systems. IEEE Access 2018;6:46382-95. doi:10.1109/ACCESS.2018.2866303.
19. Sulthana A, Zia-Ur-Rahman M. Adaptive signal enhancement in clinical cardiac care systems using normalized median LMS variants. Indian Journal of Public Health Research & Development 2019;10:23-8.
20. Sulthana A, Rahman MZU, Mirza SS. An efficient Kalman noise canceller for cardiac signal analysis in modern telecardiology systems. IEEE Access 2018;6:34616-30. doi:10.1109/ACCESS.2018.2848201.
21. Balasubramanian S, Naruka MS. A noise removal methodology for effective ECG enhancement in heart disease prediction & analysis. International Journal of Health Sciences 2022;6(S1):11578-93. doi:10.53730/ijhs.v6nS1.7813.
22. Salman MN, Rao PT, Rahman MZU. Efficient and low complexity noise cancellers for cardiac signal enhancement using proportionate adaptive algorithms. Indian Journal of Science and Technology 2016;9(37):1-11. doi:10.17485/ijst/2016/v9i37/92836.
23. Mallam M, Rao KCB. Efficient reference-free adaptive artifact cancellers for impedance cardiography based remote health care monitoring systems. SpringerPlus 2016;5:770. doi:10.1186/s40064-016-2461-5.
24. Rahman MZU, Shaik RA, Reddy DVRK. A non-linearities based noise canceler for cardiac signal enhancement in wireless health care monitoring. In: 2012 IEEE Global Humanitarian Technology Conference, Seattle, WA, USA. 2012, p. 288-92. doi:10.1109/GHTC.2012.46.
25. Sulthana A, Rahman ZU. Artifact cancellation from cardiac signals in health care systems using a zoned adaptive algorithm. International Journal of Engineering and Advanced Technology (IJEAT) 2019;8:988-93.
26. Gowri T, Kumar PR, Reddy DVRK, Rahman UZ. Removal of artifacts from electrocardiogram using efficient dead zone leaky LMS adaptive algorithm. In: Nagar A, Mohapatra D, Chaki N, editors. Proceedings of 3rd International Conference on Advanced Computing, Networking and Informatics. Springer; 2016, p. 619-30. doi:10.1007/978-81-322-2538-6_64.
27. Faiz MMU, Kale I. Removal of multiple artifacts from ECG signal using cascaded multistage adaptive noise cancellers. Array 2022;14:100133. doi:10.1016/j.array.2022.100133.
28. Satheeskumaran S, Sabrigiriraj M. A new LMS based noise removal and DWT based R-peak detection in ECG signal for biotelemetry applications. National Academy Science Letters 2014;37:341-9. doi:10.1007/s40009-014-0238-3.
29. Venkatesan C, Karthigaikumar P. An efficient noise removal technique using modified error normalized LMS algorithm. National Academy Science Letters 2018;41(3):155-9. doi:10.1007/s40009-018-0635-0.
30. Jiao Y, Cheung RYP, Mok MPC. Modified Log-LMS adaptive filter with low signal distortion for biomedical applications. In: 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, San Diego, CA, USA. 2012, p. 5210-3. doi:10.1109/EMBC.2012.6347168.
31. Khan S, Anwar SM, Abbas W, Qureshi R. A novel adaptive algorithm for removal of power line interference from ECG signal. Science International 2016;28:139-43.
32. Zia-Ur-Rahman M, Reddy DVRK, Sangeetha Y. Stationary and non-stationary noise removal from cardiac signals using a constrained stability least mean square algorithm. In: 2011 International Conference on Communications and Signal Processing, Kerala, India. 2011, p. 485-8. doi:10.1109/ICCSP.2011.5739366.
33. Boge A, Vijaya V, Rao KK. Clearing artifacts using constrained stability least mean square algorithm from cardiac signals. International Journal of Scientific & Engineering Research 2012;3:1-6.
34. Rehman U, Jadhav VS. Noise removal from ECG using modified CSLMS algorithm. International Journal of Electronics, Communication & Instrumentation Engineering 2014;4:53-60.
35. Ebrahimzadeh E, Pooyan M, Jahani S, Bijar A, Setaredan SK. ECG signals noise removal: Selection and optimization of the best adaptive filtering algorithm based on various algorithms comparison. Biomedical Engineering: Applications, Basis and Communications 2015;27(4):1550038. doi:10.4015/S1016237215500386.
36. Choi M, Jeong JJ, Kim SH, Kim SW. Reduction of motion artifacts and improvement of R peak detecting accuracy using adjacent non-intrusive ECG sensors. Sensors 2016;16(5):715. doi:10.3390/s16050715.
37. Seo M, Choi M, Lee JS, Kim SW. Adaptive noise reduction algorithm to improve R peak detection in ECG measured by capacitive ECG sensors. Sensors 2018;18(7):2086. doi:10.3390/s18072086.
38. Vatansever F. Noise cancellation with LMS variants. Uludağ University Journal of the Faculty of Engineering 2021;26(1):153-70. doi:10.17482/uumfd.797087.
39. The MathWorks Inc. MATLAB [Computer software]. 2022. Available from: https://www.mathworks.com/products/matlab.html.
40. Moody GB, Mark RG. The impact of the MIT-BIH arrhythmia database. IEEE Engineering in Medicine and Biology Magazine 2001;20(3):45-50. doi:10.1109/51.932724. [Database: Moody G, Mark R. MIT-BIH Arrhythmia Database, v1. 2005. doi:10.13026/C2F305].
41. Moody GB, Muldrow WE, Mark RG. A noise stress test for arrhythmia detectors. Computers in Cardiology 1984;11:381-4. [Database: Moody G, Mark R. MIT-BIH Noise Stress Test Database, v1. 1999. doi:10.13026/C2HS3T].