Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 1, 2026SHILAP Revista de lepidopterologíaOpen Access

A Low-Power, Analog-Integrated, Current-Mode, and Fully Tunable Artificial Neural Network Classifier Architecture for Biomedical Engineering Applications

View Full Paper
Ask AI
Bookmark
Share

Authors

VAVassilis AlimisisAPAndreas PapathanasiouVMVasileios Moustakas

Discussion

Loading...

Member takes

Overview

Randomized trial evaluates a low-power analog artificial neural network for biomedical classification, indicating efficient energy use in diagnostics.

Key Points

  • This work aims to develop a low-power current-mode analog artificial neural network for biomedical classification tasks.
  • Implemented in TSMC 65-nm CMOS process
  • Evaluated on two biomedical classification tasks
  • Incorporated analog components for feature correlation and weight adaptation.
  • Achieved worst-case classification accuracy of 91.7%
  • Power consumption below 1311 nW
  • Demonstrated robustness to Process-Voltage-Temperature variations.

Cite This Study

Alimisis et al. (2026) studied this question.

synapsesocial.com/papers/69f44223967e944ac5565e71https://doi.org/10.1109/ojcas.2026.3665625
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A Review on the Role of Machine Learning in Enabling IoT Based Healthcare Applications2021 · 213 citations
  2. 2ACTIVATION FUNCTIONS IN NEURAL NETWORKS2020 · 1,211 citations
  3. 3Design of Programmable Analog Calculation Unit by Implementing Support Vector Regression for Approximate Computing2018 · 52 citations
  4. 4A Low-power, Mixed-mode Neural Network Classifier for Robust Scene Classification2019 · 64 citations