English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present an integrated approach by combining analog computing and deeplearning for electrocardiogram (ECG) arrhythmia classification. We proposeEKGNet, a hardware-efficient and fully analog arrhythmia classificationarchitecture that archives high accuracy with low power consumption. Theproposed architecture leverages the energy efficiency of transistors operatingin the subthreshold region, eliminating the need for analog-to-digitalconverters (ADC) and static random access memory (SRAM). The system designincludes a novel analog sequential Multiply-Accumulate (MAC) circuit thatmitigates process, supply voltage, and temperature variations. Experimentalevaluations on PhysioNet's MIT-BIH and PTB Diagnostics datasets demonstrate theeffectiveness of the proposed method, achieving average balanced accuracy of95% and 94.25% for intra-patient arrhythmia classification and myocardialinfarction (MI) classification, respectively. This innovative approach presentsa promising avenue for developing low-power arrhythmia classification systemswith enhanced accuracy and transferability in biomedical applications.

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