Vaishali Baviskar
ABSTRACT
Deep learning models have paved the way towards generating high-efficiency classification systems for multiple applications. These applications include lung disease classification, electrocardiogram classification, electroencephalogram classification; forest cover classification, etc. All these applications rely on efficient feature selection capabilities of deep learning models. Models like convolutional neural network (CNN), recurrent neural networks (RNNs), long-short-term-memory (LSTM) etc. are used for this purpose. These models tend to evaluate all possible feature combinations via iterative window-based feature processing. Thereby trying to cover indefinite number of feature combinations in order to classify a definite number of features into a definite number of classes. All these models have a stopping-criteria, which depends upon the error rate difference of previous current iteration. If the error rate is less than a particular threshold, and number of iterations are above a certain predefined value, then training of these networks is stopped. This property of deep learning models limits their real-time performance, because training stops even if the accuracy is lower than expected. The reason for this low accuracy is high dimensionality of search space, due to which selection of the most optimum features is skipped. In order to reduce the probability of such conditions, this text proposes a bio-inspired Genetic Algorithm model for accuracy-based feature selection. The selected features are given to different deep learning models like LSTM RNN, and their internal performance is evaluated. Here, heart failure disease dataset from kaggle is used, and it is observed that due to pre-feature selection process, overall accuracy of these models is improved by 10, while precision, recall fMeasure scores are improved by 15 for heart disease data sets. The specificity and sensitivity performance is improved by 20 when compared with RNN and LSTM models individually.
- Fakheraldin Abdalla, Longwen Wu, Hikmat Ullah, Guanghui Ren, Alam Noor, Hassan Mkindu, and Yaqin Zhao. 2020. Deep convolutional neural network application to classify the ECG arrhythmia. Signal, Image and Video Processing 14 (10 2020). https://doi.org/10.1007/s11760-020-01688-2Google Scholar
- Lana Abdulrazaq Abdullah and Muzhir Shaban Al-ani. 2020. CNN-LSTM Based Model for ECG Arrhythmias and Myocardial Infarction Classification. Advances in Science, Technology and Engineering Systems Journal 5, 5(2020), 601–606. https://doi.org/10.25046/aj050573Google ScholarCross Ref
- Andronicus A Akinyelu. 2020. Bio-inspired technique for improving machine learning speed and big data processing. In 2020 International Joint Conference on Neural Networks (IJCNN). 1–8. https://doi.org/10.1109/IJCNN48605.2020.9206762Google ScholarCross Ref
- Fajr Alarsan and Mamoon Younes. 2019. Analysis and classification of heart diseases using heartbeat features and machine learning algorithms. Journal of Big Data 6 (08 2019). https://doi.org/10.1186/s40537-019-0244-xGoogle Scholar
- Ahmed Alghamdi, Mohamed Hammad, Hassan Ugail, Asmaa Abdel-Raheem, Khan Muhammad, Hany Khalifa, and Ahmed Abd El-Latif. 2020. Detection of myocardial infarction based on novel deep transfer learning methods for urban healthcare in smart cities. Multimedia Tools and Applications (03 2020). https://doi.org/10.1007/s11042-020-08769-xGoogle Scholar
- Lahcen El Bouny, Mohammed Khalil, and Abdellah Adib. 2020. ECG Heartbeat Classification Based on Multi-Scale Wavelet Convolutional Neural Networks. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 3212–3216. https://doi.org/10.1109/ICASSP40776.2020.9054749Google Scholar
- Konstantinos Charalampous and Antonios Gasteratos. 2013. Bio-inspired Deep Learning Model for Object Recognition. https://doi.org/10.1109/IST.2013.6729661Google Scholar
- Ashraf Darwish. 2018. Bio-inspired computing: Algorithms review, deep analysis, and the scope of applications. Future Computing and Informatics Journal 3, 2 (2018), 231–246. https://doi.org/10.1016/j.fcij.2018.06.001Google ScholarCross Ref
- Zümray Dokur and Tamer Ölmez. 2020. Heartbeat classification by using a convolutional neural network trained with Walsh functions. Neural Computing and Applications 32 (08 2020). https://doi.org/10.1007/s00521-020-04709-wGoogle ScholarDigital Library
- Zahra Ebrahimi, Mohammad Loni, Masoud Daneshtalab, and Arash Gharehbaghi. 2020. A Review on Deep Learning Methods for ECG Arrhythmia Classification. Expert Systems with Applications: X 7 (06 2020), 100033. https://doi.org/10.1016/j.eswax.2020.100033Google Scholar
- Xumei Fan, William Sayers, Shu-jun Zhang, Zhiwu Han, Luquan Ren, and Hassan Chizari. 2020. Review and Classification of Bio-inspired Algorithms and Their Applications. Journal of Bionic Engineering 17 (05 2020), 611–631. https://doi.org/10.1007/s42235-020-0049-9Google Scholar
- Jing-Shan Huang, Binqiang Chen, Nian-Yin Zeng, Xin-Cheng Cao, and Yang Li. 2020. Accurate classification of ECG arrhythmia using MOWPT enhanced fast compression deep learning networks. Journal of Ambient Intelligence and Humanized Computing (05 2020). https://doi.org/10.1007/s12652-020-02110-yGoogle Scholar
- Shweta Jambukia, Vipul Dabhi, and Harshadkumar Prajapati. 2015. Classification of ECG signals using machine learning techniques: A survey. https://doi.org/10.1109/ICACEA.2015.7164783Google Scholar
- Ali Khan, Muzammil Hussain, and Muhammad Malik. 2021. Cardiac Disorder Classification by Electrocardiogram Sensing Using Deep Neural Network. Complexity 2021 (03 2021), 1–8. https://doi.org/10.1155/2021/5512243Google Scholar
- Lazhar Khriji, Marwa Fradi, Mohsen Machhout, and Abdulnasir Hossen. 2020. Deep Learning-Based Approach for Atrial Fibrillation Detection. In The Impact of Digital Technologies on Public Health in Developed and Developing Countries, Mohamed Jmaiel, Mounir Mokhtari, Bessam Abdulrazak, Hamdi Aloulou, and Slim Kallel (Eds.). Springer International Publishing, Cham, 100–113.Google Scholar
- Zhishuai Liu, Guihua Yao, Qing Zhang, Junpu Zhang, and Xueying Zeng. 2020. Wavelet Scattering Transform for ECG Beat Classification. Computational and Mathematical Methods in Medicine 2020 (2020).Google Scholar
- Mufti Mahmud, M Shamim Kaiser, and Amir Hussain. 2020. Deep Learning in Mining Biological Data. arxiv:2003.00108 [q-bio.QM]Google Scholar
- Esma mansour benssassi and Juan Ye. 2021. Generalisation and robustness investigation for facial and speech emotion recognition using bio-inspired spiking neural networks. Soft Computing 25 (02 2021). https://doi.org/10.1007/s00500-020-05501-7Google ScholarDigital Library
- Saumendra Kumar Mohapatra, Geetika Srivastava, and Mihir Narayan Mohanty. 2019. Arrhythmia Classification Using Deep Neural Network. In 2019 International Conference on Applied Machine Learning (ICAML). 296–300. https://doi.org/10.1109/ICAML48257.2019.00062Google Scholar
- Mohammad Sadegh Norouzzadeh, Dan Morris, Sara Beery, Neel Joshi, Nebojsa Jojic, and Jeff Clune. 2019. A deep active learning system for species identification and counting in camera trap images. CoRR abs/1910.09716(2019). arxiv:1910.09716http://arxiv.org/abs/1910.09716Google Scholar
- Pramendra Prajapati and Vijay Sharma. 2020. Detection and Classification of ECG Noises using Decomposition on MixedCodebook for Quality Analysis. Healthcare Technology Letters 7 (01 2020). https://doi.org/10.1049/htl.2019.0096Google Scholar
- Paweł Pławiak and U Rajendra Acharya. 2020. Novel Deep Genetic Ensemble of Classifiers for Arrhythmia Detection Using ECG Signals. Neural Computing and Applications 32 (08 2020), 11137–11161. https://doi.org/10.1007/s00521-018-03980-2Google ScholarDigital Library
- Milad Salem, Dr Taheri, and Jiann-Shiun Yuan. 2018. ECG Arrhythmia Classification Using Transfer Learning from 2-Dimensional Deep CNN Features. https://doi.org/10.1109/BIOCAS.2018.8584808Google Scholar
- Xinjing Song, Gongping Yang, Kuikui Wang, Yuwen Huang, Feng Yuan, and Yilong Yin. 2020. Short Term ECG Classification with Residual-Concatenate Network and Metric Learning. Multimedia Tools and Applications 79 (08 2020). https://doi.org/10.1007/s11042-020-09035-wGoogle Scholar
- Rutger van de Leur, Lennart Blom, Efstratios Gavves, Irene Hof, Jeroen Van der Heijden, Nick Clappers, Pieter Doevendans, Rutger Hassink, and René van Es. 2020. Automatic Triage of 12‐Lead ECGs Using Deep Convolutional Neural Networks. Journal of the American Heart Association 9 (05 2020). https://doi.org/10.1161/JAHA.119.015138Google Scholar
- Glenn van steenkiste, Gunther van Loon, and Guillaume Crevecoeur. 2020. Transfer Learning in ECG Classification from Human to Horse Using a Novel Parallel Neural Network Architecture. Scientific Reports 10 (01 2020), 186. https://doi.org/10.1038/s41598-019-57025-2Google Scholar
- Jenny Venton, Philip J. Aston, Nadia A. S. Smith, and Peter M. Harris. 2020. Signal to Image to Classification: Transfer Learning for ECG. In 2020 11th Conference of the European Study Group on Cardiovascular Oscillations (ESGCO). 1–2. https://doi.org/10.1109/ESGCO49734.2020.9158037Google ScholarCross Ref
- Surbhi Vijh, Prashant Gaurav, and Hari Pandey. 2020. Hybrid bio-inspired algorithm and convolutional neural network for automatic lung tumor detection. Neural Computing and Applications (09 2020), 1–14. https://doi.org/10.1007/s00521-020-05362-zGoogle ScholarDigital Library
- Yuwei Zhang, Yuan Zhang, Benny Lo, and Wenyao Xu. 2019. Wearable ECG signal processing for automated cardiac arrhythmia classification using CFASE‐based feature selection. Expert Systems 37 (06 2019). https://doi.org/10.1111/exsy.12432Google Scholar
Recommendations
Intrusion Detection Using Big Data and Deep Learning Techniques
ACM SE '19: Proceedings of the 2019 ACM Southeast ConferenceIn this paper, Big Data and Deep Learning Techniques are integrated to improve the performance of intrusion detection systems. Three classifiers are used to classify network traffic datasets, and these are Deep Feed-Forward Neural Network (DNN) and two ...
ECG signal classification to detect heart arrhythmia using ELM and CNN
AbstractThe cardiovascular disease is the one of the major cause of death in the today’s world. The Holter recorder is used to monitor the Electrocardiogram (ECG) signal to record the heart activity which is a popular method to detect the disease. ...
ECG signal classification via combining hand-engineered features with deep neural network features
AbstractThe electrocardiogram (ECG) has been proven to be the most common and effective approach to investigate cardiovascular diseases because that it is simple, noninvasive and inexpensive. However, the differences among ECG signals are difficult to be ...
Comments