Components of Artificial Neural Networks Realized in CMOS Technology to be Used in Intelligent Sensors in Wireless Sensor Networks.

Tomasz Talaśka

doi:10.3390/s18124499

Abstract

The article presents novel hardware solutions for new intelligent sensors that can be used in wireless sensor networks (WSN). A substantial reduction of the amount of data sent by the sensor to the base station in the WSN may extend the possible sensor working time. Miniature integrated artificial neural networks (ANN) applied directly in the sensor can take over the analysis of data collected from the environment, thus reducing amount of data sent over the RF communication block. A prototype specialized chip with components of the ANN was designed in the CMOS 130 nm technology. An adaptation mechanism and a programmable multi-phase clock generator—components of the ANN—are described in more detail. Both simulation and measurement results of selected blocks are presented to demonstrate the correctness of the design.

Highlights

In typical wireless sensor networks, the role of particular sensors is to register a given signal from the environment, perform an initial data preprocessing and to transfer it to a base station where an artificial neural network (ANN) may be used to carry out a more detailed analysis
We mainly focus on the adaptation mechanism along with the controlling multiphase clock generator—the topic of the presented work
We present two circuits, crucial from the point of view of the implementation of artificial neural networks at the transistor level

Summary

Introduction

In typical wireless sensor networks, the role of particular sensors is to register a given signal from the environment, perform an initial data preprocessing and to transfer it to a base station where an artificial neural network (ANN) may be used to carry out a more detailed analysis. Signal processing performed at the sensor level typically includes an anti-aliasing filtering, analog-to-digital conversion, and optionally data compression to reduce the amount of data transferred over the wireless network. One of the problems associated with WSN development is high energy required to transfer data. To reduce the described problem, we propose a solution, in which to a much greater extent than data processing will take place directly at the sensor level.

Objectives

Methods

Results

Discussion

Conclusion