DOAJ Open Access 2022

In-sensor neural network for high energy efficiency analog-to-information conversion

Sudarsan Sadasivuni Sumukh Prashant Bhanushali Imon Banerjee Arindam Sanyal

Abstrak

Abstract This work presents an on-chip analog-to-information conversion technique that utilizes analog hyper-dimensional computing based on reservoir-computing paradigm to process electrocardiograph (ECG) signals locally in-sensor and reduce radio frequency transmission by more than three orders-of-magnitude. Instead of transmitting the naturally sparse ECG signal or extracted features, the on-chip analog-to-information converter analyzes the ECG signal through a nonlinear reservoir kernel followed by an artificial neural network, and transmits the prediction results. The proposed technique is demonstrated for detection of sepsis onset and achieves state-of-the-art accuracy and energy efficiency while reducing sensor power by $$159\times $$ 159 × with test-chips prototyped in 65 nm CMOS.

Topik & Kata Kunci

Medicine Science

Penulis (4)

Sudarsan Sadasivuni

Sumukh Prashant Bhanushali

Imon Banerjee

Arindam Sanyal

Format Sitasi

APA MLA BibTeX

Sadasivuni, S., Bhanushali, S.P., Banerjee, I., Sanyal, A. (2022). In-sensor neural network for high energy efficiency analog-to-information conversion. https://doi.org/10.1038/s41598-022-23100-4

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →

Lihat di Sumber doi.org/10.1038/s41598-022-23100-4

Informasi Jurnal

Tahun Terbit: 2022
Sumber Database: DOAJ
DOI: 10.1038/s41598-022-23100-4
Akses: Open Access ✓