Abstract
The research hypothesis in this study is that different random number generator seeds using 1D Convolutional Neural Networks impact the performance results by more than 15% on the heartbeat classification performance. Furthermore, we address a research question to evaluate the impact level of random values in the initialization of model parameters experimenting on the classification of ventricular heartbeats in electrocardiogram training and evaluating models with various feature sets based on the width of the measured samples surrounding a heartbeat location. Specific test cases consist of differently selected initial neural network parameters guided by manually selected random number seeds while preserving the rest of the training environment and hyper-parameters. We examine the influence of the random number seed on the model’s learning dynamics and ultimate F1 score on the performance of the testing dataset and conclude fluctuations resulting in 24.61% root mean square error from the average. Furthermore, we conclude that optimizing the validation in the training process does not optimize the performance in the testing. The research results contribute a novel viewpoint to the field, paving the way for more efficient and accurate heartbeat classification systems and improving diagnostic and prognostic performance in cardiac health.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bock, S., Weiß, M.: A proof of local convergence for the Adam optimizer. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2019)
De Chazal, P., O’Dwyer, M., Reilly, R.B.: Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Trans. Biomed. Eng. 51(7), 1196–1206 (2004)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249–256. JMLR Workshop and Conference Proceedings (2010)
Hooper, S.M., et al.: Impact of upstream medical image processing on downstream performance of a head CT triage neural network. Radiol.: Artif. Intell. 3(4), e200229 (2021)
Kiranyaz, S., Ince, T., Gabbouj, M.: Real-time patient-specific ECG classification by 1-d convolutional neural networks. IEEE Trans. Biomed. Eng. 63(3), 664–675 (2015)
Li, F., Wu, J., Jia, M., Chen, Z., Pu, Y.: Automated heartbeat classification exploiting convolutional neural network with channel-wise attention. IEEE Access 7, 122955–122963 (2019)
Li, Y., Liang, Y.: Learning overparameterized neural networks via stochastic gradient descent on structured data. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Liu, S., Papailiopoulos, D., Achlioptas, D.: Bad global minima exist and SGD can reach them. Adv. Neural. Inf. Process. Syst. 33, 8543–8552 (2020)
Marrone, S., Olivieri, S., Piantadosi, G., Sansone, C.: Reproducibility of deep CNN for biomedical image processing across frameworks and architectures. In: 2019 27th European Signal Processing Conference (EUSIPCO), pp. 1–5. IEEE (2019)
Moody, G.B., Mark, R.G.: The impact of the MIT-BIH arrhythmia database. IEEE Eng. Med. Biol. Mag. 20(3), 45–50 (2001)
Oxford Medical Education: ECG interpretation. https://oxfordmedicaleducation.com/ecgs/ecg-interpretation/
Ruby, U., Yendapalli, V.: Binary cross entropy with deep learning technique for image classification. Int. J. Adv. Trends Comput. Sci. Eng. 9(10) (2020)
Sarvan, Ç., Özkurt, N.: ECG beat arrhythmia classification by using 1-d CNN in case of class imbalance. In: 2019 Medical Technologies Congress (TIPTEKNO), pp. 1–4. IEEE (2019)
Shi, H., Wang, H., **, Y., Zhao, L., Liu, C.: Automated heartbeat classification based on convolutional neural network with multiple kernel sizes. In: 2019 IEEE Fifth International Conference on Big Data Computing Service and Applications (BigDataService), pp. 311–315. IEEE (2019)
Silva, K.G., Aloise, D., Xavier-de Souza, S., Mladenovic, N.: Less is more: simplified Nelder-mead method for large unconstrained optimization. Yugoslav J. Oper. Res. 28(2), 153–169 (2018)
Wang, Z., Yan, M., Chen, J., Liu, S., Zhang, D.: Deep learning library testing via effective model generation. In: Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 788–799 (2020)
**aolin, L., Cardiff, B., John, D.: A 1d convolutional neural network for heartbeat classification from single lead ECG. In: 2020 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS), pp. 1–2. IEEE (2020)
Xu, X., Liu, H.: ECG heartbeat classification using convolutional neural networks. IEEE Access 8, 8614–8619 (2020)
Zhang, D., Chen, Y., Chen, Y., Ye, S., Cai, W., Chen, M.: An ECG heartbeat classification method based on deep convolutional neural network. J. Healthcare Eng. 2021, 1–9 (2021)
Zhuang, D., Zhang, X., Song, S., Hooker, S.: Randomness in neural network training: characterizing the impact of tooling. Proc. Mach. Learn. Syst. 4, 316–336 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gusev, M., Tudjarski, S., Stankovski, A., Jovanov, M. (2024). The Curious Case of Randomness in Deep Learning Models for Heartbeat Classification. In: Mihova, M., Jovanov, M. (eds) ICT Innovations 2023. Learning: Humans, Theory, Machines, and Data. ICT Innovations 2023. Communications in Computer and Information Science, vol 1991. Springer, Cham. https://doi.org/10.1007/978-3-031-54321-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-54321-0_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-54320-3
Online ISBN: 978-3-031-54321-0
eBook Packages: Computer ScienceComputer Science (R0)