Exploiting Pull-In/Pull-Out Hysteresis in Electrostatic MEMS Sensor Networks to Realize a Novel Sensing Continuous-Time Recurrent Neural Network
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,...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-03-01
|
Series: | Micromachines |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-666X/12/3/268 |
_version_ | 1797413364250443776 |
---|---|
author | Mohammad H Hasan Amin Abbasalipour Hamed Nikfarjam Siavash Pourkamali Muhammad Emad-Ud-Din Roozbeh Jafari Fadi Alsaleem |
author_facet | Mohammad H Hasan Amin Abbasalipour Hamed Nikfarjam Siavash Pourkamali Muhammad Emad-Ud-Din Roozbeh Jafari Fadi Alsaleem |
author_sort | Mohammad H Hasan |
collection | DOAJ |
description | 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 three commercially available MEMS accelerometers can classify a train of square and triangular acceleration signals inherently using pull-in and release hysteresis. Furthermore, we develop and fabricate a network with finger arrays of parallel plate actuators to facilitate coupling between MEMS devices in the network using actuating assemblies and biasing assemblies, thus bypassing the previously reported coupling challenge in MEMS neural networks. |
first_indexed | 2024-03-09T05:16:37Z |
format | Article |
id | doaj.art-0d4271e346514ad1b0f291f2e995de35 |
institution | Directory Open Access Journal |
issn | 2072-666X |
language | English |
last_indexed | 2024-03-09T05:16:37Z |
publishDate | 2021-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Micromachines |
spelling | doaj.art-0d4271e346514ad1b0f291f2e995de352023-12-03T12:44:40ZengMDPI AGMicromachines2072-666X2021-03-0112326810.3390/mi12030268Exploiting Pull-In/Pull-Out Hysteresis in Electrostatic MEMS Sensor Networks to Realize a Novel Sensing Continuous-Time Recurrent Neural NetworkMohammad H Hasan0Amin Abbasalipour1Hamed Nikfarjam2Siavash Pourkamali3Muhammad Emad-Ud-Din4Roozbeh Jafari5Fadi Alsaleem6Department of Earth and Space Sciences, Columbus State University, Columbus, GA 31909, USADepartment of Electrical and Computer Engineering, University of Texas at Dallas, Dallas, TX 75080, USADepartment of Electrical and Computer Engineering, University of Texas at Dallas, Dallas, TX 75080, USADepartment of Electrical and Computer Engineering, University of Texas at Dallas, Dallas, TX 75080, USADepartment of Computer Science and Engineering, Texas A&M University, College Station, TX 77843, USADepartment of Computer Science and Engineering, Texas A&M University, College Station, TX 77843, USADurham School of Architectural Engineering and Construction, University of Nebraska—Lincoln, Omaha, NE 68182, USAThe 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 three commercially available MEMS accelerometers can classify a train of square and triangular acceleration signals inherently using pull-in and release hysteresis. Furthermore, we develop and fabricate a network with finger arrays of parallel plate actuators to facilitate coupling between MEMS devices in the network using actuating assemblies and biasing assemblies, thus bypassing the previously reported coupling challenge in MEMS neural networks.https://www.mdpi.com/2072-666X/12/3/268neuromorphic computingMEMSSensor NetworkCTRNN |
spellingShingle | Mohammad H Hasan Amin Abbasalipour Hamed Nikfarjam Siavash Pourkamali Muhammad Emad-Ud-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 Micromachines neuromorphic computing MEMS Sensor Network CTRNN |
title | Exploiting Pull-In/Pull-Out Hysteresis in Electrostatic MEMS Sensor Networks to Realize a Novel Sensing Continuous-Time Recurrent Neural Network |
title_full | Exploiting Pull-In/Pull-Out Hysteresis in Electrostatic MEMS Sensor Networks to Realize a Novel Sensing Continuous-Time Recurrent Neural Network |
title_fullStr | Exploiting Pull-In/Pull-Out Hysteresis in Electrostatic MEMS Sensor Networks to Realize a Novel Sensing Continuous-Time Recurrent Neural Network |
title_full_unstemmed | Exploiting Pull-In/Pull-Out Hysteresis in Electrostatic MEMS Sensor Networks to Realize a Novel Sensing Continuous-Time Recurrent Neural Network |
title_short | Exploiting Pull-In/Pull-Out Hysteresis in Electrostatic MEMS Sensor Networks to Realize a Novel Sensing Continuous-Time Recurrent Neural Network |
title_sort | exploiting pull in pull out hysteresis in electrostatic mems sensor networks to realize a novel sensing continuous time recurrent neural network |
topic | neuromorphic computing MEMS Sensor Network CTRNN |
url | https://www.mdpi.com/2072-666X/12/3/268 |
work_keys_str_mv | AT mohammadhhasan exploitingpullinpullouthysteresisinelectrostaticmemssensornetworkstorealizeanovelsensingcontinuoustimerecurrentneuralnetwork AT aminabbasalipour exploitingpullinpullouthysteresisinelectrostaticmemssensornetworkstorealizeanovelsensingcontinuoustimerecurrentneuralnetwork AT hamednikfarjam exploitingpullinpullouthysteresisinelectrostaticmemssensornetworkstorealizeanovelsensingcontinuoustimerecurrentneuralnetwork AT siavashpourkamali exploitingpullinpullouthysteresisinelectrostaticmemssensornetworkstorealizeanovelsensingcontinuoustimerecurrentneuralnetwork AT muhammademaduddin exploitingpullinpullouthysteresisinelectrostaticmemssensornetworkstorealizeanovelsensingcontinuoustimerecurrentneuralnetwork AT roozbehjafari exploitingpullinpullouthysteresisinelectrostaticmemssensornetworkstorealizeanovelsensingcontinuoustimerecurrentneuralnetwork AT fadialsaleem exploitingpullinpullouthysteresisinelectrostaticmemssensornetworkstorealizeanovelsensingcontinuoustimerecurrentneuralnetwork |