EKGNet: A 10.96{\mu}W Fully Analog Neural Network for Intra-Patient Arrhythmia Classification

Abstract--We present an integrated approach by combining analog computing and deep learning for electrocardiogram (ECG) arrhythmia classification. Experimental evaluations on PhysionNet's MIT-BIH and PTB Diagnostics datasets demonstrate the effectiveness of the proposed Despite the challenges associated with The electrocardiogram (ECG) is crucial for monitoring analog circuits, such as susceptibility to noise and device heart health in medical practice [1], [2]. However, accurately variation, they can be effectively utilized for inferring neural detecting and categorizing different waveforms and network algorithms. The presence of inherent system noise in morphologies in ECG signals is challenging, similar to other analog circuits can be leveraged to enhance robustness and time-series data. Moreover, manual analysis is time-consuming improve classification accuracy, aligning with the desirable and prone to errors. Given the prevalence and potential lethality properties of AI algorithms [24]-[26]. of irregular heartbeats, achieving accurate and cost-effective In this paper, we propose EKGNet, a fully analog neural diagnosis of arrhythmic heartbeats is crucial for effectively network with low power consumption (10.96μW) that achieves managing and preventing cardiovascular conditions [3], [4].