Abstract
Electrocardiogram (ECG) is a most primitive and important test to analyse the status of the heart functioning. During this test, different types of noises and artefacts get involved in the captured electrical signal which affects the performance of overall diagnosis. In general, computer aided decision system (CADS) performs three operations viz. pre-processing, feature extraction and classification to reach a decision for analyzing an ECG signal. Among three waves of an ECG signal, QRS-complex is to be examined most critically to diagnose existence of a possible cardiovascular disease. But detection of exact locations of QRS complexes is still a challenging task as they are hidden by various noises and artefacts. Therefore, in this paper emerging tools such as wavelet transform (WT), adaptive autoregressive modelling (AARM) and vector machines (VMs) like support vector machine (SVM) and relevance vector machine (RVM) are proposed to be used for pre-processing, feature extraction and classification, respectively for utilizing distinct advantages of each. For instance, WT provides better time–frequency resolution, AARM possesses parameters that vary with time leading to the measurement of time-varying spectra and VMs models the non-linear data stably. Also, RVM has been proposed to be used for the first time here for ECG signal analysis as it needs much less kernel functions. SVM has been used for comparison purpose only. The performance of the proposed methodology is evaluated on the basis of widely used performance parameters such as sensitivity (Se), positive predictivity (Pp), accuracy (Acc) and detection rate (Dr). Highlight of the proposed methodology is that it yields consistently high values of all the widely used and critical performance parameters i.e. Se of 99.95%, Pp of 99.95%, Dr of 99.95%, and Acc of 99.93%. These results are highest amongst other techniques existing in the literature, indicating its usefulness for handling real-time heart related emergent cases.
Similar content being viewed by others
References
Alickovic E, Suabsi A (2015) Effect of multiscale PCA de-noising in ECG beat classification for diagnosis of cardiovascular diseases. J Cir Sysand Sig Proc 34:513–533
Al-Kamal FS, Hassan ES, El-Naby MA et al (2015) An efficient transceiver scheme for SC-FDMA systems based on discrete wavelet transform and discrete cosine transform. Wirel Pers Commun 83:3133–3155
Anurudhya K, Mohan NM (2019) Analysis of a contactless ECG monitoring system. IETE J Res. https://doi.org/10.1080/03772063.2018.1562386
Arnold M, Miltner WHR, Witte H, Bauer R, Braun C (1998) Adaptive AR modeling of nonstationary time series by means of Kalman filtering. IEEE Trans Biomed Eng 45:553–562
Benitez ZADS, Gaydecki PA, Fitzpatrick AP (2000) A new QRS detection algorithm based on the hilbert transform. In: The 2000 IEEE International Conference on Computers in Cardiology, pp 379–382
Biopac Systems (2020) The premier data acquisition & analysis program. resource document. https://www.biopac.com/wp-content/uploads/AcqKnowledge-Products.pdf
Biswal B (2017) ECG signal analysis using modified S-transform. Heal Tech Lett 4:68–72
Chashmi AJ, Amirani MC (2021) An automatic ECG arrhythmia diagnosis system using support vector machines optimized with GOA and entropy-based feature selection procedure. IJMEI. https://doi.org/10.1504/IJMEI.2022.119309
Das M, Ari S (2013) Analysis of ECG signal denoising method based on S-transform. IRBM 34:362–370
ECG (2020) National Instruments, vernier_ecg_for_ni_elvis.pdf. Accessed on 17 Apr 2020
Feng Y, Wu X, Hu Y (2018) Forecasting research on the wireless mesh network throughput based on the support vector machine. Wirel Pers Commun 99:581–593. https://doi.org/10.1007/s11277-017-5135-x
Finet P, Gibaud B, Dameron O, Jeannès RLB (2018) Interoperable infrastructure and implementation of a health data model for remote monitoring of chronic diseases with comorbidities. IRBM 39:151–159
Gupta V, Mittal M (2018a) R-peak based arrhythmia detection using Hilbert transform and principal component analysis. Int Innov Appl Comput Intell PowerEnergy Controls Impact Humanity 5:5. https://doi.org/10.1109/cipech.2018.8724191
Gupta V, Mittal M (2018b) Blood pressure and ECG signal interpretation using neural network. Int J Appl Eng Res 13:127–132
Gupta V, Mittal M (2019a) A comparison of ECG signal pre-processing using FrFT, FrWT and IPCA for improved analysis. IRBM 40:145–156
Gupta V, Mittal M (2019b) R-peak detection in ECG signal using Yule-Walker and principal component analysis. IETE J Res. https://doi.org/10.1080/03772063.2019.1575292
Gupta V, Mittal M (2019c) Investigation of normal and abnormal blood pressure signal using Hilbert transform, Z-transform, and modified Z-transform. Int J Comput Med Healthc (IJCMH)
Gupta V, Mittal M (2020) Efficient R-peak detection in electrocardiogram signal based on features extracted using hilbert transform and burg method. J Inst Eng India Ser B. https://doi.org/10.1007/s40031-020-00423-2
Gupta V, Mittal M (2021a) R-peak detection for improved analysis in health informatics. Inter J Medical Eng Infor (IJMEI). https://doi.org/10.1504/IJMEI.2021.10035358
Gupta V, Mittal M (2021b) A novel method of cardiac arrhythmia detection in electrocardiogram signal. Int J Med Eng Inf 12:489–499. https://doi.org/10.1504/IJMEI.2020.109943
Gupta V, Mittal M, Mittal V (2019) R-peak detection using chaos analysis in standard and real time ECG databases. IRBM 40:341–354
Gupta V, Mittal M, Mittal V (2020a) Chaos theory: an emerging tool for arrhythmia detection. Sens Imaging 21:1–22
Gupta V, Monika M, Vikas M (2020b) R-peak detectionbased chaos analysis of ECG signal. Analog Integr Circ Sig Process 102:479–490
Gupta V, Mittal M, Mittal V (2020c) Performance evaluation of various pre-processing techniques for R-peak detection in ECG signal. IETE J Res. https://doi.org/10.1080/03772063.2020.1756473
Gupta V et al (2020d) Attractor plot as an emerging tool in ECG signal processing for improved health informatics. In: International Conference on Future Technologies 2020d (ICOFT 2020d) in Manufacturing, Automation, Design and Energy (MADE@NITPY) NIT Puducherry Karaikal India December, pp 28–30
Gupta V, Mittal M, Mittal V, Gupta A (2021) ECG signal analysis using CWT, spectrogram and autoregressive technique. Iran J Comput Sci. https://doi.org/10.1007/s22077-021-00071-1
Halder B, Mitra S, Mitra M (2019) Classification of complete myocardial infarction using rule-based rough set method and rough set explorer system. IETE J Res. https://doi.org/10.1080/03772063.2019.1588175
Honig M, Messerschmidt D (1984) Adaptive filters: structures, algorithms and applications. Kluwer, Boston
Jin-liang Y, Yong-li Z, Guo-qin Y (2012) Research on relevance vector machine and its application to fault diagnosis of transformers. Asia-Pac Power Energy Eng Conf. https://doi.org/10.1109/APPEEC.2012.6307637
Jog NK (2013) Electronics in medicine and biomedical instrumentation, 2nd edn. PHI, pp 85–109
Jung WH, Lee SG (2017) An arrhythmia classification method in utilizing the weighted KNN and the fitness rule. IRBM. https://doi.org/10.1016/j.irbm.2017.04.002
Kaya Y, Pehlivan H (2015) Feature selection using genetic algorithms for premature ventricular contraction classification. Int Conf Electr Electr Eng ELECO). https://doi.org/10.1109/ELECO.2015.7394628
Kora P, Krishna KSR (2016) ECG based heart arrhythmia detection using wavelet coherence and bat algorithm. Sens Imaging 17:1–16
Lin C, Yeh CH, Wang CY, Shi W, Serafico BMF, Wang CH, Juan CH, Young HWV, Lin YJ, Yeh HM, Lo MT (2018) Robust fetal heart beat detection via R-peak intervals distribution. Trans Biomed Eng 66:3310–3319
Liu L, Yang J, Meng W (2019) Detecting malicious nodes via gradient descent and support vector machine in Internet of Things. Comput Electr Eng. https://doi.org/10.1016/j.compeleceng.2019.06.013
Mehta SS, Lingayat NS (2008a) SVM-based algorithm for recognition of QRS complexes in electrocardiogram. IRBM 29:310–317
Mehta SS, Lingayat NS (2008b) Development of SVM based ECG pattern recognition technique. IETE J Res 54:5–11
Mehta SS, Lingayat NS (2008c) SVM based QRS detection in electrocardiogram using signal entropy. IETE J Res 54:231–240
Mehta SS, Shete DA, Lingayat NS, Chouhan VS (2010) K-means algorithm for the detection and delineation of QRS-complexes in Electrocardiogram. IRBM 31:48–54
Meo M, Muñoz AH, Zarzoso V, Meste O,Latcu GD et al (2015) F-wave amplitude stability on multiple electrocardiogram leads in atrial fibrillation. Computing in Cardiology, Nice, France. ffhal-01217233f.
Meshgini S, Aghagolzadeh A, Seyedarabi H (2013) Face recognition using Gabor-based direct linear discriminant analysis and support vector machine. Comput Electr Eng 39:727–745
Miyasaka Y, Barnes ME, Gersh BJ et al (2006) Secular trends in incidence of atrial fibrillation in Olmsted County, Minnesota, 1980 to 2000, and implications on the projections for future prevalence. Circulation 114:119–125
Morillo CA, Banerjee A, Perel P, Wood D, Jouven X (2017) Atrial fibrillation: the current epidemic. J Geriatr Cardiol 14:195–203. https://doi.org/10.11909/j.issn.1671-5411.2017.03.011
Nallathambi G, Príncipe JC (2014) Integrate and fire pulse train automaton for QRS detection. IEEE Tran Biomed Eng 61:317–326
Nayak C, Saha SK, Kar R, Mandal D (2018) An efficient QRS complex detection using optimally designed digital differentiator. Circ Sys Sig Process 38:716–749
Newbold P, Granger CWJ (1974) Experience with forecasting univariate time series and the combination of forecasts (with discussion). J R Stat Soc A 137:131–165
Padmavathi K, Ramakrishna KS (2015) Detection of atrial fibrillation using autoregressive modelling. Int J Electr Comput Eng (IJECE) 5:64–70
Pandit D, Zhang L, Liu C, Chattopadhyay S, Aslam N, Lim CP (2017) A lightweight QRS detector for single lead ECG signals using a max-min difference algorithm. Comput Methods Prog Biomed 144:61–75
Patro KK, Prakash AJ, Rao MJ, Kumar PR (2020) An efficient optimized feature selection with machine learning approach for ECG biometric recognition. IETE J Res. https://doi.org/10.1080/03772063.2020.1725663
Preethi D, Valarmathi RS (2019) A novel classification and synchronous noise removal during fetal heart rate monitoring. IETE J Res. https://doi.org/10.1080/03772063.2019.1567276
Raja J, Shanmugam P, Pitchai R (2021) An automated early detection of glaucoma using support vector machine based visual geometry group 19 (VGG-19) convolutional neural network. Wirel Pers Commun. https://doi.org/10.1007/s11277-020-08029-z
Rajankar SO, Talbar SN (2019) An electrocardiogram signal compression techniques: a comprehensive review. Analog Integr Circ Sig Process 98:59–74
Rao GH, Rekha S (2019) A 0.8-V, 55.1-dB DR, 100 Hz low- pass filter with low-power PTAT for bio-medical applications. IETE J Res. https://doi.org/10.1080/03772063.2019.1682074
Rekik S, Ellouze N (2017) Enhanced and optimal algorithm for QRS detection. IRBM 38:56–61
Scholkopf B, Mullert KR (1999) Fisher discriminant analysis with kernels. In: Proceedings of the 1999 IEEE Signal Processing Society Workshop Neural Networks for Signal Processing IX, Madison, WI, USA, pp 41–48
Shah SMS, Shah FA, Hussain SA, Batool S (2020) Support vector machines-based heart disease diagnosis using feature subset, wrapping selection and extraction methods. Comput Electr Eng. https://doi.org/10.1016/j.compeleceng.2020.106628
Shanmathi N, Jagannath M (2018) Computerised decision support system for remote health monitoring: a systematic review. IRBM 39:359–367
Sharma T, Sharma KK (2016) QRS complex detection in ECG signals using the synchrosqueezed wavelet transform. IETE J Res 62:885–892
Sharma T, Sharma KK (2017) QRS complex detection in ECG signals using locally adaptive weighted total variation denoising. Comput Biol Med 87:187–199
Sharma LD, Sunkaria RK (2020) Myocardial infarction detection and localization using optimal features based lead specific approach. IRBM 41:58–70
Sharma M, Tan RS, Acharya UR (2018) A novel automated diagnostic system for classification of myocardial infarction ECG signals using an optimal biorthogonal filter bank. Comput Biol Med 102:341–356
Sharma M, Tan RS, Acharya UR (2019a) A new method to identify coronary artery disease with ECG signals and time-frequency concentrated antisymmetric biorthogonal wavelet filter bank. Pattern Recogn Lett 125:235–240
Sharma A, Patidar S, Upadhyay A, Acharya UR (2019b) Accurate tunable-Q wavelet transform based method for QRS complex detection. Comput Electr Eng 75:101–111. https://doi.org/10.1016/j.compeleceng.2019.01.025
Singh RS, Saini BS, Sunkaria RK (2018) Times varying spectral coherence investigation of cardiovascular signals based on energy concentration in healthy young and elderly subjects by the adaptive continuous morlet wavelet transform. IRBM 39:54–68
Singh J, Sharma M, Acharya UR (2019) Hypertension diagnosis index for discrimination of high-risk hypertension ECG signals using optimal orthogonal Wavelet Filter Bank. Int J Environ Res Public Health 16:40–68
Time frequency resolution (2020) https://sapienlabs.org/time-frequency-analysis-and-wavelets/. Accessed 12 Aug 2020
Tipping ME (2000) The relevance vector machine. In: Solla SA, Leen TK, Müller K-R (eds) Advances in neural information processing systems, 12th edn. MIT Press, Cambridge
Tipping ME (2001) Sparse Bayesian learning and the relevance vector machine. J Mach Learn Res 1:211–244
Trevethan R (2017) Sensitivity, specificity, and predictive values: foundations, pliabilities, and pitfalls in research and practice. Front Public Health. https://doi.org/10.3389/fpubh.2017.00307
Vimala C, Priya PA (2019) Artificial neural networkbased wavelet transform technique for image quality enhancement. Comput Electr Eng 76:258–267
Wang Z, Zhu J, Yan T, Yang L (2019) A new modified wavelet-based ECG denoising. Comput Assist Surg 24:174–183
Wax M (1988) Order selection for AR models by predictive least squares. IEEE Trans Acoust Speech Signal Process 36:581–588
What is Relevance Vector Machine (2020) https://www.igi-global.com/dictionary/relevance-vector-machine/45879. Accessed 07 Aug 2020
Wu X, Xu X, Wan S, Qi L (2021) Private estimation of symptom distribution for infectious disease analysis in edge computing. IEEE Int Conf Embed Ubiquitous Comput. https://doi.org/10.1109/EUC53437.2021.00014
Xiaotong W, Mohammad RK, Lianyong Q, Genlin J, Wanchun D, Xiaolong X (2020) Locally private frequency estimation of physical symptoms for infectious disease analysis in Internet of Medical Things. Comput Commun 162:139–151. https://doi.org/10.1016/j.comcom.2020.08.015
Yakut O, Bolat ED (2018) An improved QRS complex detection method having low computational load. Biom Sig Proc Control 42:230–241
Yazdani S, Vesin JM (2016) Extraction of QRS fiducial points from the ECG using adaptive mathematical morphology. Dig Sig Proc 56:100–109
Yazdani A, Fallet S, Vasin JM (2018) A novel short-term event extraction algorithm for biomedical signals. IEEE Trans Biomed Eng 65:754–762
Yu WM, Du T, Lim KB (2004) Comparison of the support vector machine and relevant vector machine in regression and classification problems. ICARCV Control Autom Robot vis Conf. https://doi.org/10.1109/icarcv.2004.1469035
Zhou M, Du W, Qin K et al (2018) Distinguish crude and sweated chinese herbal medicine with support vector machine and random forest methods. Wirel Pers Commun 102:1827–1838
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gupta, V. Wavelet transform and vector machines as emerging tools for computational medicine. J Ambient Intell Human Comput 14, 4595–4605 (2023). https://doi.org/10.1007/s12652-023-04582-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-023-04582-0