{"title":"基于心电信号二维尺度图特征的量子卷积神经网络识别心律失常","authors":"S. S, K. T, Issac K, Sudha M","doi":"10.1109/ICITIIT54346.2022.9744224","DOIUrl":null,"url":null,"abstract":"Quantum computing is the main emerging technology solving complex problems and even though error raised will be high, can be computed using customized algorithms. We propose the use of discrete wavelet transform to decompose the ECG signals followed by computing 2D scalogram to obtain time-frequency features and apply Quanvolutional Neural Network to classify those scalogram images to recognize Arrhythmia. This is the first paper to introduce scalogram and Quanvolutional neural networks. We considered using publicly available physio net MIT-BIH arrhythmia database for our research. The proposed model of hybrid quantum classical model comprising quantum convolutional neural networks for the MIT-BIH arrhythmia database resulting in the precision of 98% and Receiver Operating Curve Score of 100%.","PeriodicalId":184353,"journal":{"name":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Quanvolution Neural Network to Recognize arrhythmia from 2D scaleogram features of ECG signals\",\"authors\":\"S. S, K. T, Issac K, Sudha M\",\"doi\":\"10.1109/ICITIIT54346.2022.9744224\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Quantum computing is the main emerging technology solving complex problems and even though error raised will be high, can be computed using customized algorithms. We propose the use of discrete wavelet transform to decompose the ECG signals followed by computing 2D scalogram to obtain time-frequency features and apply Quanvolutional Neural Network to classify those scalogram images to recognize Arrhythmia. This is the first paper to introduce scalogram and Quanvolutional neural networks. We considered using publicly available physio net MIT-BIH arrhythmia database for our research. The proposed model of hybrid quantum classical model comprising quantum convolutional neural networks for the MIT-BIH arrhythmia database resulting in the precision of 98% and Receiver Operating Curve Score of 100%.\",\"PeriodicalId\":184353,\"journal\":{\"name\":\"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)\",\"volume\":\"32 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-02-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICITIIT54346.2022.9744224\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICITIIT54346.2022.9744224","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6
摘要
量子计算是解决复杂问题的主要新兴技术,即使产生的误差很高,也可以使用定制算法进行计算。本文提出利用离散小波变换对心电信号进行分解,计算二维尺度图得到时频特征,并应用量子神经网络对尺度图图像进行分类,实现心律失常的识别。本文首次介绍了尺度图和量子神经网络。我们考虑在我们的研究中使用公开的physio net MIT-BIH心律失常数据库。本文提出的由量子卷积神经网络组成的混合量子经典模型用于MIT-BIH心律失常数据库,其准确率为98%,接收者工作曲线评分为100%。
Quanvolution Neural Network to Recognize arrhythmia from 2D scaleogram features of ECG signals
Quantum computing is the main emerging technology solving complex problems and even though error raised will be high, can be computed using customized algorithms. We propose the use of discrete wavelet transform to decompose the ECG signals followed by computing 2D scalogram to obtain time-frequency features and apply Quanvolutional Neural Network to classify those scalogram images to recognize Arrhythmia. This is the first paper to introduce scalogram and Quanvolutional neural networks. We considered using publicly available physio net MIT-BIH arrhythmia database for our research. The proposed model of hybrid quantum classical model comprising quantum convolutional neural networks for the MIT-BIH arrhythmia database resulting in the precision of 98% and Receiver Operating Curve Score of 100%.