PROJECT TITLE :

Inexact Arithmetic Circuits for Energy Efficient loT Sensors Data Processing - 2018

ABSTRACT:

Developing moveable autonomous systems is extremely requested for numerous application domains like Web of Things (ton), wearable devices, and biomedical applications. Portable systems sometimes contain autonomous and networked sensors; every sensor hosts multiple input channels (e.g. tactile) closely coupled to embedded computing unit and power provide. The embedded computing unit should locally extract meaningful data by employing subtle methods. This imposes challenges on real time operation and adds a burden relating to power consumption. Approximate or inexact computing represents a promising resolution for energy efficient knowledge processing; it tunes the accuracy of computation on the particular application requirements in order to reduce power consumption. During this paper, inexact arithmetic circuits have been utilized to improve the energy efficiency for sensors digital data processing. The proposed inexact circuits achieve up to 80% power saving when compared to the precise one, and similar solutions presented in literature with a most loss of 1.39 dB in output SNR when applied to FIR filters