http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
HeartNetEC: a deep representation learning approach for ECG beat classifi cation
Sri Aditya Deevi,Christina Perinbam Kaniraja,Vani Devi Mani,Deepak Mishra,Shaik Ummar,Cejoy Satheesh 대한의용생체공학회 2021 Biomedical Engineering Letters (BMEL) Vol.11 No.1
One of the most crucial and informative tools available at the disposal of a Cardiologist for examining the condition of apatient’s cardiovascular system is the electrocardiogram (ECG/EKG). A major reason behind the need for accurate reconstructionof ECG comes from the fact that the shape of ECG tracing is very crucial for determining the health condition ofan individual. Whether the patient is prone to or diagnosed with cardiovascular diseases (CVDs), this information can begathered through examination of ECG signal. Among various other methods, one of the most helpful methods in identifyingcardiac abnormalities is a beat-wise categorization of a patient’s ECG record. In this work, a highly efficient deep representationlearning approach for ECG beat classification is proposed, which can significantly reduce the burden and time spentby a Cardiologist for ECG Analysis. This work consists of two sub-systems: denoising block and beat classification block. The initial block is a denoising block that acquires the ECG signal from the patient and denoises that. The next stage is thebeat classification part. This processes the input ECG signal for finding out the different classes of beats in the ECG throughan efficient algorithm. In both stages, deep learning-based methods have been employed for the purpose. Our proposedapproach has been tested on PhysioNet’s MIT-BIH Arrhythmia Database, for beat-wise classification into ten importanttypes of heartbeats. As per the results obtained, the proposed approach is capable of making meaningful predictions andgives superior results on relevant metrics.