CMOS Perceptron for Vesicle Fusion Classification

Abstract

Edge computing (processing data close to its source) is one of the fastest developing areas of modern electronics and hardware information technology. This paper presents the implementation process of an analog CMOS preprocessor for use in a distributed environment for processing medical data close to the source. The task of the circuit is to analyze signals of vesicle fusion, which is the basis of life processes in multicellular organisms. The functionality of the preprocessor is based on a classifier of full and partial fusions. The preprocessor is dedicated to operate in amperometric systems, and the analyzed signals are data from carbon nanotube electrodes. The accuracy of the classifier is at the level of 93.67%. The implementation was performed in the 65 nm CMOS technology with a 0.3 V power supply. The circuit operates in the weak-inversion mode and is dedicated to be powered by thermal cells of the human energy harvesting class. The maximum power consumption of the circuit equals 416 nW, which makes it possible to use it as an implantable chip. The results can be used, among others, in the diagnosis of precancerous conditions.

Study of the Complexity of CMOS Neural Network Implementations Featuring Heart Rate Detection

“…The preprocessor additionally uses other modules, e.g., single-and multi-output current mirrors (CMs) [25], the size and number of which depend on the structure of the classifier. The implementation details of the modules and the preprocessor itself are described in paper [5]. The physical parameters of the modules are summarized in Table 1.…”

“…Another constraint emerged as a limitation, wherein the RCM module could produce a finite number of multipliers. Each combination of a 12-bit input corresponded to a real value ranging from 0.02 to 1.46 [5]. The training process was carried out with an upper limit of the weight values of 1.5 and no limit on the lower weight values (values below 0.02 were acceptable).…”

“…However, a special place among these devices belongs to applicationspecific integrated circuits (ASICs). There are many examples presenting acceleration with dedicated integrated circuits in relation to convolutional neural networks [2], imaging technologies [3], cryptography in soft processors [4] or biomedical signal processing [5]. In this work, the authors focus mainly on biomedical data processing and medical applications.…”