Research by Prof. Paul P. Sotiriadis's Group received the IC Design Contest Award in the SMACD 2025
We are pleased to announce that the paper entitled "An Energy-Efficient Analog Integrated Neural Network for Cirrhosis Patient Survival Prediction" received the IC Design Contest Award in the 21st International Conference of Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuits Design (SMACD), which took place in Istanbul, Türkiye on 7-10 July, 2025.
The Award-Winning paper was co-authored by Konstantinos Cheliotis (Diploma Student, ECE-NTUA and Researcher Archimedes/Athena RC), Dr. Vassilis Alimisis (Collaborating Researcher, ECE-NTUA and Postdoctoral Researcher Archimedes/Athena RC), Vasileios Moustakas (PhD Student, ECE-NTUA and Researcher Archimedes/Athena RC), Zisis Foufas (Graduate, ECE-NTUA), Anna Mylona (Diploma Student, ECE- NTUA and Researcher Archimedes/Athena RC) and Paul P. Sotiriadis (Professor, ECE-NTUA; Lead Researcher, Archimedes/ Athena RC; IEEE, AIIA & AAIA Fellow ).
ABSTRACT: In this study, an energy-efficient analog integrated artificial neural network architecture is introduced. It comprises circuits operating in the sub-threshold region, including a ReLU circuit, a Sigmoid function circuit, an analog multiplier, and a current comparator. A Cirrhosis patient survival dataset is used to validate the proper operation of the proposed classifier. This classifier achieves an accuracy of 91.45% while consuming only 924 nW. The design is implemented and validated using the TSMC 90 nm CMOS process, with its post-layout performance benchmarked against both software implementations and existing works in literature. The architecture's robustness is verified through Monte Carlo simulations and corner analysis.
