ε-duyarsız Kuadratik Kayıp Fonksiyonu ile EKG Verilerinin Sıkıştırılması

ElektroKardiyoGram (EKG), kalbin çalışması esnasında ortaya çıkan elektriksel aktivitenin grafiksel bir gösterim şeklidir. Kalp hastalıklarının teşhisinde ve analizinde önemli bir rol oynamaktadır. Kalp hastalıklarının önceden etkin bir şekilde tespiti ve teşhisi için, EKG sinyalleri sürekli kaydedilmesi gerekir. Bununla birlikte, depolama ve aktarımın zorlaştığı bir seviyede büyük miktarda veri üreten kayıtlar, ortam gürültüsünden dolayı da bozulabilir. Bu nedenlerden dolayı, gürültülü bir ortamda bile etkin sonuçlar verebilecek bir EKG veri sıkıştırma algoritmasına ihtiyaç vardır. Bu çalışma EKG sinyallerinin sıkıştırılması için ε-duyarsız kuadratik kayıplı Destek Vektör Regresyon (ε-kuadratik DVR) tekniğini önermektedir. Kayıp fonksiyonları ile gürültü dağılımları arasında iyi bilinen bir ilişki vardır. Önerilen ε-duyarsız kuadratik kayıp fonksiyonu ise Gauss gürültüsüne karşı en uygun çözümü sunar. Bilgisayar simülasyon sonuçları, önerilen kayıp fonksiyonunun Gauss gürültüsü ile bozulmuş EKG verilerinin sıkıştırılması için çekici bir aday olduğunu göstermektedir.

ECG Data Compression Using ε-insensitive Quadratic Loss Function

ElectroCardioGram (ECG) is a graphical representation of the electricalactivity that occurred during the heartbeat. It plays a significant role in the diagnosisand analysis of heart diseases. ECG signals must be recorded continuously for theeffective detection and diagnosis of heart diseases. However, such records as itproduces large amounts of data at a level that makes it difficult storage andtransmission can also be impaired due to the ambient noise. Thanks to the reasonsmentioned above, an efficient ECG data compression algorithm is required even in anoisy environment. This study proposes ε-insensitive quadratic loss based SupportVector Regression (ε-quadratic SVR) technique for the compression of ECG signals.There is a well-known relationship between loss functions and noise distributions.The proposed ε-insensitive quadratic loss function provides the optimal solutionagainst Gaussian noise. Computer simulation results show that the proposed lossfunction is an attractive candidate for ECG data compression in the presence ofGaussian noise.

PDF

___

Wei, J. J., Chang, C. J., Chou, N. K., Jan, G. J. 2001. ECG data compression using truncated singular value decomposition. IEEE Transactions on Information Technology in Biomedicine, 5(2001), 290-299.
Jalaleddine, S. M., Hutchens, C. G., Strattan, R. D., Coberly, W. A. 1990. ECG data compression techniques-a unified approach. IEEE transactions on Biomedical Engineering, 37(1990), 329-343.
Manikandan, M. S., Dandapat, S. 2014. Waveletbased electrocardiogram signal compression methods and their performances: a prospective review. Biomedical Signal Processing and Control, 14(2014), 73-107.
Singh, B., Kaur, A., Singh, J. 2015. A review of ecg data compression techniques. International journal of computer applications, 116(2015), 39-44.
Olmos, S., MillAn, M., Garcia, J., Laguna, P. 1996. ECG data compression with the Karhunen-Loeve transform. In Computers in Cardiology, Indianapolis, 8-11 September, USA, 253-256.
Reddy, B. S., Murthy, I. S. N. 1986. ECG data compression using Fourier descriptors. IEEE Transactions on Biomedical Engineering, 4(1986), 428-434.
Benzid, R., Messaoudi, A., Boussaad, A. 2008. Constrained ECG compression algorithm using the block-based discrete cosine transform. Digital Signal Processing, 18(2008), 56-64.
Shinde, A. A., Kanjalkar, P. 2011. The comparison of different transform based methods for ECG data compression, Uluslararası konferans, ICSCCN-IEEE, 21-22 June, Thuckafay, India, 332- 335.
Addison, P. S. 2005. Wavelet transforms and the ECG: a review. Physiological measurement, 26(2005), R155.
Karal, O. 2018. Destek Vektör Regresyon ile EKG Verilerinin Sıkıştırılması, Journal of the Faculty of Engineering and Architecture of Gazi University (In press).
Karal, O. 2017. Maximum likelihood optimal and robust Support Vector Regression with lncosh loss function. Neural Networks, 94(2017), 1-12.
Cortes, C., Vapnik, V. 1995. Support-vector networks, Mach. Learn., 20(3), 273-297, 1995.
Smola, A. J., Schölkopf, B. 2004. A tutorial on support vector regression. Statistics and computing, 14(2004), 199-222.
Mahmoodian, H., Ebrahimian, L. 2016. Using support vector regression in gene selection and fuzzy rule generation for relapse time prediction of breast cancer. Biocybernetics and Biomedical Engineering, 36(2016), 466-472.
Valizadeh, M., Sohrabi, M. R. 2018. The application of artificial neural networks and support vector regression for simultaneous spectrophotometric determination of commercial eye drop contents. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 193(2018), 297-304.
Huber, M. B., Lancianese, S. L., Nagarajan, M. B., Ikpot, I. Z., Lerner, A. L., Wismuller, A. 2011. Prediction of biomechanical properties of trabecular bone in MR images with geometric features and support vector regression. IEEE Transactions on Biomedical Engineering, 58(2011), 1820-1826.
Guermoui, M., Mekhalfi, M. L., Ferroudji, K. 2013. Heart sounds analysis using wavelets responses and support vector machines. In Systems, Signal Processing and their Applications (WoSSPA), IEEE, May 2013, 8th International Workshop on, 233-238.
Hu, Q., Zhang, S., Yu, M., Xie, Z. 2016. Short-term wind speed or power forecasting with heteroscedastic support vector regression. IEEE Trans. Sustainable Energy, 7(2016), 241-249.
Khosravi, A., Koury, R. N. N., Machado, L., Pabon, J. J. G. 2018. Prediction of wind speed and wind direction using artificial neural network, support vector regression and adaptive neurofuzzy inference system. Sustainable Energy Technologies and Assessments, 25(2018), 146- 160.
Guermoui, M., Rabehi, A., Gairaa, K., Benkaciali, S. 2018. Support vector regression methodology for estimating global solar radiation in Algeria. The European Physical Journal Plus, 133(2018), 22.
Das, U. K., Tey, K. S., Seyedmahmoudian, M., Mekhilef, S., Idris, M. Y. I., Van Deventer, W., Stojcevski, A. 2018. Forecasting of photovoltaic power generation and model optimization: A review. Renewable and Sustainable Energy Reviews, 81(2018), 912-928.
Yaslan, Y., Bican, B. 2017. Empirical mode decomposition based denoising method with support vector regression for time series prediction: a case study for electricity load forecasting. Measurement, 103(2017), 52-61.
Nava, N., Matteo, T. D., Aste, T. 2018. Financial Time Series Forecasting Using Empirical Mode Decomposition and Support Vector Regression. Risks, 6(2018), 7.
Massana, J., Pous, C., Burgas, L., Melendez, J., Colomer, J. 2016. Short-term load forecasting for non-residential buildings contrasting artificial occupancy attributes. Energy and Buildings, 130(2016), 519-531.
Moody, G. B., Mark, R. G. 2001. The impact of the MIT-BIH arrhythmia database. IEEE Engineering in Medicine and Biology Magazine, 20(2001), 45-50.