Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Architecture
Signal Classification Based On Analog Computing Using Mems Network, Mohammad Okour
Signal Classification Based On Analog Computing Using Mems Network, Mohammad Okour
Durham School of Architectural Engineering and Construction: Dissertations, Thesis, and Student Research
The rising complexity of machine learning algorithms and Artificial Intelligence in many applications, such as smart building, has prompted the development of alternate computing options. Because of their compact size, low power consumption, and diverse functionality, microelectromechanical systems (MEMS) have emerged as a possible candidate. This thesis focuses on using MEMS networks as computing units to classify a simple signal classification task using neural network methodology. The study intends to show the potential of using MEMS as an analog computing unit by discussing the advantage of the bi-stability pull-in behavior and hysteresis to create an accurate classifier of these waveforms. …
Simulation For A Mems-Based Ctrnn Ultra-Low Power Implementation Of Human Activity Recognition, Muhammad Emad-Ud-Din, Mohammad H. Hasan, Roozbeh Jafari, Siavash Pourkamali, Fadi M. Alsaleem
Simulation For A Mems-Based Ctrnn Ultra-Low Power Implementation Of Human Activity Recognition, Muhammad Emad-Ud-Din, Mohammad H. Hasan, Roozbeh Jafari, Siavash Pourkamali, Fadi M. Alsaleem
Durham School of Architectural Engineering and Construction: Faculty Publications
This paper presents an energy-efficient classification framework that performs human activity recognition (HAR). Typically, HAR classification tasks require a computational platform that includes a processor and memory along with sensors and their interfaces, all of which consume significant power. The presented framework employs microelectromechanical systems (MEMS) based Continuous Time Recurrent Neural Network (CTRNN) to performHAR tasks very efficiently. In a real physical implementation, we show that the MEMS-CTRNN nodes can perform computing while consuming power on a nano-watts scale compared to the micro-watts state-of-the-art hardware. We also confirm that this huge power reduction doesn’t come at the expense of reduced …
Exploiting Pull-In/Pull-Out Hysteresis In Electrostatic Mems Sensor Networks To Realize A Novel Sensing Continuous-Time Recurrent Neural Network, Mohammad H. Hasan, Amin Abbasalipour, Hamed Nikfarjam, Siavash Pourkamali, Muhammad Emad-Un-Din, Roozbeh Jafari, Fadi Alsaleem
Exploiting Pull-In/Pull-Out Hysteresis In Electrostatic Mems Sensor Networks To Realize A Novel Sensing Continuous-Time Recurrent Neural Network, Mohammad H. Hasan, Amin Abbasalipour, Hamed Nikfarjam, Siavash Pourkamali, Muhammad Emad-Un-Din, Roozbeh Jafari, Fadi Alsaleem
Durham School of Architectural Engineering and Construction: Faculty Publications
The goal of this paper is to provide a novel computing approach that can be used to reduce the power consumption, size, and cost of wearable electronics. To achieve this goal, the use of microelectromechanical systems (MEMS) sensors for simultaneous sensing and computing is introduced. Specifically, by enabling sensing and computing locally at the MEMS sensor node and utilizing the usually unwanted pull in/out hysteresis, we may eliminate the need for cloud computing and reduce the use of analog-to-digital converters, sampling circuits, and digital processors. As a proof of concept, we show that a simulation model of a network of …