Signal Classification Using a Mechanically Coupled MEMS Neural Network

Nikfarjam, Hamed; Abbasalipour, Amin; Tesfay, Mehari; Hasan, Mohammad H.; Pourkamali, Siavash; Jafari, Roozbeh; Alsaleem, Fadi

doi:10.1109/sensors47087.2021.9639616

Cited by 5 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Novel, non-conventional computing technologies can be one of the answers. In [7], a mechanically coupled MEMS neural network is proposed for signal classification. It is a proof-ofconcept design, but it demonstrated that certain nonlinearity attributes of the MEMS (Micro Electronic Mechanical Systems) system fit well with the requirements of neural network, and that makes MEMS a high potential direction for improving energy efficiency in wearable devices.…”

Section: Novel Computing Technologiesmentioning

confidence: 99%

Optimization of low power consumption in wearable health monitoring devices and algorithm design

Zhu

2024

ACE

View full text Add to dashboard Cite

This paper surveys state-of-the-art approaches designed to decrease the power consumption of wearable health monitoring devices, thereby optimizing battery life. Specifically, this paper examines a concept proposed by researchers in a separate investigation, which involves active computation offloading. This entails developing an algorithm that efficiently distributes data processing tasks between wearable health monitoring devices and mobile applications. Researchers have successfully reduced system power consumption by up to 20% by intelligently offloading computations based on existing device characteristics. In contrast, another ECG remote monitoring system focuses on designing the lowest power sensor while keeping the system low cost and scalable. Lastly, this paper provides ideas to further lower power by state-of-the-art chip design, algorithmic and system design techniques.

show abstract

Section: Novel Computing Technologiesmentioning

confidence: 99%

Optimization of low power consumption in wearable health monitoring devices and algorithm design

Zhu

2024

ACE

View full text Add to dashboard Cite

show abstract

“…Moreover, the three layers (input layer, reservoir layer, and output layer) were always set up separately at the hardware level, resulting in a discrete system with a large volume. Some improvements have been proposed, such as using bias time multiplexing to divide input and mask 13,14 , using hybrid nonlinearity (HNL) to enhance RC ability for classification tasks 15,16 , and using structural design to obtain MEMS neurons 17,18 . However, drawbacks need to be considered, such as feedback still existing resulting in a separate system, poor long-term memory capacity (MC), and pending tasks have to be designed (basically simple classification tasks) especially for the using device, respectively.…”

Section: Introductionmentioning

confidence: 99%

MEMS reservoir computing system with stiffness modulation for multi-scene data processing at the edge

Zou,

Guo,

Yang

et al. 2023

Preprint

View full text Add to dashboard Cite

Reservoir computing (RC) is a bio-inspired neural network structure which can be implemented in hardware with ease. It has been applied across various fields such as memristors, and electrochemical reactions, among which the micro-electro-mechanical systems (MEMS) is supposed to be the closest to integrate sensing and computing. This paper introduces a novel MEMS reservoir computing system based on stiffness modulation, where natural signals directly influence the system stiffness as input. Under this innovative concept, information can be processed locally without the need for advanced data collection and pre-processing. We present an integrated RC system characterized by small volume and low power consumption, eliminating complicated setups in traditional MEMS RC for data discretization and transduction. We performed nonlinearity tuning for the resonator and optimized the post-processing algorithm by introducing a digital mask operator. Consequently, our MEMS RC is capable of both classification and forecasting, surpassing the capabilities of our previous non-delay-based architecture. The system successfully processed word classification and chaos forecasting with high accuracy, demonstrating its adaptability for multi-scene data processing. Our approach has initiated edge computing, enabling emergent applications in MEMS for local computations.

show abstract