Convolutional neural network optimized by differential evolution for electrocardiogram classification

被引:8
作者
Chen, Shan Wei [1 ,2 ]
Wang, Shir Li [1 ,3 ]
Qi, XiuZhi [4 ]
Ng, Theam Foo [5 ]
Ibrahim, Haidi [6 ]
机构
[1] Univ Pendidikan Sultan Idris, Fac Comp & Meta Technol, Tanjong Malim 35900, Perak, Malaysia
[2] Baoji Univ Arts & Sci, Dept Educ, Baoji 721012, Peoples R China
[3] Univ Pendidikan Sultan Idris, Data Intelligent & Knowledge Management DILIGENT, Tanjong Malim 35900, Perak, Malaysia
[4] Baoji Univ Arts & Sci, Dept Arts, Baoji 721012, Peoples R China
[5] Univ Sains Malaysia, Ctr Global Sustainabil Studies, Minden 11800, Penang, Malaysia
[6] Univ Sains Malaysia, Sch Elect & Elect Engn, Engn Campus, Nibong Tebal 14300, Penang, Malaysia
关键词
Differential evolution; Convolutional neural network; Electrocardiogram classification; CNN;
D O I
10.1007/s11042-023-15407-9
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The Coronavirus disease 2019, or COVID-19, has shifted the medical paradigm from face-to-face to telehealth. Telehealth has become a vital resource to contain the virus spread and ensure the continued care of patients. In terms of preventing cardiovascular diseases, automating electrocardiogram (ECG) classification is a promising telehealth intervention. The healthcare service ensures that patient care is appropriate, comfortable, and accessible. Convolutional neural networks (CNNs) have demonstrated promising results in ECG categorization, which require high accuracy and short training time to ensure healthcare quality. This study proposes a one-dimensional-CNN (1D-CNN) arrhythmia classification based on the differential evolution (DE) algorithm to optimize the accuracy of ECG classification and training time. The performance of 1D-CNNs of different activation functions are optimized based on the standard DE algorithm. Finally, based on MIT-BIH and SCDH arrhythmia databases, the performances of optimized and unoptimized 1D-CNN are compared and analysed. Results show that the 1D-CNN optimized by the DE has higher accuracy in heartbeats classification. The optimized 1D-CNN improves from 97.6% to 99.5% on MIT-BIH and from 80.2% to 88.5% on SCDH. Therefore, the optimized 1D-CNN shows improvements of 1.9% and 8.3% in the two datasets, respectively. In addition, compared with the unoptimized 1D-CNN based on the same parameter settings, the optimized 1D-CNN has less training time. Under the conditions of ReLU function and 10 epochs, the training takes 9.22 s on MIT-BIH and 10.35 s on SCDH, reducing training time by 67.2% and 64.2%, respectively.
引用
收藏
页码:45811 / 45837
页数:27
相关论文
共 31 条
  • [1] A deep convolutional neural network model to classify heartbeats
    Acharya, U. Rajendra
    Oh, Shu Lih
    Hagiwara, Yuki
    Tan, Jen Hong
    Adam, Muhammad
    Gertych, Arkadiusz
    Tan, Ru San
    [J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2017, 89 : 389 - 396
  • [2] Multi-stream CNN for facial expression recognition in limited training data
    Aghamaleki, Javad Abbasi
    Chenarlogh, Vahid Ashkani
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (16) : 22861 - 22882
  • [3] Electrocardiogram Classification Using Reservoir Computing With Logistic Regression
    Angel Escalona-Moran, Miguel
    Soriano, Miguel C.
    Fischer, Ingo
    Mirasso, Claudio R.
    [J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2015, 19 (03) : 892 - 898
  • [4] Differential Evolution: A review of more than two decades of research
    Bilal
    Pant, Millie
    Zaheer, Hira
    Garcia-Hernandez, Laura
    Abraham, Ajith
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2020, 90
  • [5] Robust Heartbeat Detection From Multimodal Data via CNN-Based Generalizable Information Fusion
    Chandra, B. S.
    Sastry, C. S.
    Jana, S.
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2019, 66 (03) : 710 - 717
  • [6] Arrhythmic Heartbeat Classification Using 2D Convolutional Neural Networks
    Degirmenci, M.
    Ozdemir, M. A.
    Izci, E.
    Akan, A.
    [J]. IRBM, 2022, 43 (05) : 422 - 433
  • [7] Examination of the ECG signal classification technique DEA-ELM using deep convolutional neural network features
    Diker, Aykut
    Sonmez, Yasin
    Ozyurt, Fatih
    Avci, Engin
    Avci, Derya
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (16) : 24777 - 24800
  • [8] [丁青锋 Ding Qingfeng], 2017, [智能系统学报, CAAI Transactions on Intelligent Systems], V12, P431
  • [9] Biometric human recognition system based on ECG
    El Rahman, Sahar A.
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (13) : 17555 - 17572
  • [10] Automatic Prediction of Atrial Fibrillation Based on Convolutional Neural Network Using a Short-term Normal Electrocardiogram Signal
    Erdenebayar, Urtnasan
    Kim, Hyeonggon
    Park, Jong-Uk
    Kang, Dongwon
    Lee, Kyoung-Joung
    [J]. JOURNAL OF KOREAN MEDICAL SCIENCE, 2019, 34 (07)