Power-Efficient Analog Hardware Architecture of the Learning Vector Quantization Algorithm for Brain Tumor Classification

• Published in: IEEE transactions on very large scale integration (VLSI) systems 2024-11, Vol.32 (11), p.1969-1982
• Main Authors: Alimisis, Vassilis, Anastasios Serlis, Emmanouil, Papathanasiou, Andreas, Eleftheriou, Nikolaos P., Sotiriadis, Paul P.
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Analog circuits; Architecture; Biomedical engineering; Brain; Brain cancer; Brain tumor dataset; Classification; Classification algorithms; current comparator (CC); Current comparators; distance calculation circuit (DCC); Euclidean geometry; Hardware; learning vector quantization (LVQ) algorithm; Learning vector quantization networks; low-power architectures; Machine learning; Noise; Tumors; Vector quantization; Vectors
• ISSN: 1063-8210; 1557-9999
• DOI: 10.1109/TVLSI.2024.3447903

This study introduces a design methodology pertaining to analog hardware architecture for the implementation of the learning vector quantization (LVQ) algorithm. It consists of three main approaches that are separated based on the distance calculation circuit (DCC) and, more specifically; Euclidean distance, Sigmoid function, and Squarer circuits. The main building blocks of each approach are the DCC and the current comparator (CC). The operational principles of the architecture are extensively elucidated and put into practice through a power-efficient configuration (operating less than 650 nW) within a low-voltage setup (0.6 V). Each specific implementation is tested on a brain tumor classification task achieving more than 96.00% classification accuracy. The designs are realized using a 90-nm CMOS process and developed utilizing the Cadence IC Suite for both schematic and physical design. Through a comparative analysis of postlayout simulation outcomes with an equivalent software-based classifier and related works, the accuracy of the applied modeling and design methodologies is validated.