Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Classification of Systems-I01:26

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Classification of Systems-II01:31

Classification of Systems-II

Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear.
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation01:24

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation

This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

SNDR Limits of Oscillator-Based Sensor Readout Circuits.

Sensors (Basel, Switzerland)·2018
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

Related Experiment Video

Updated: May 12, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.4K

A KWS System for Edge-Computing Applications with Analog-Based Feature Extraction and Learned Step Size Quantized

Yukai Shen1, Binyi Wu2, Dietmar Straeussnigg3

  • 1Electronics Technology Department, University of Madrid Carlos III, 28911 Leganes, Spain.

Sensors (Basel, Switzerland)
|April 26, 2025
PubMed
Summary
This summary is machine-generated.

This study proposes an ultra-low-power Keyword Spotting (KWS) system for edge devices. The energy-efficient architecture achieves high accuracy for keyword detection with minimal resource usage, even in noisy conditions.

Keywords:
analog feature extractionedge computingkeyword spotting (KWS)quantization-aware training (QAT)recurrent neural network (RNN)

More Related Videos

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.2K
Picometer-Precision Atomic Position Tracking through Electron Microscopy
15:04

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

6.3K

Related Experiment Videos

Last Updated: May 12, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.4K
Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.2K
Picometer-Precision Atomic Position Tracking through Electron Microscopy
15:04

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

6.3K

Area of Science:

  • Edge Computing
  • Low-Power Architectures
  • Speech Recognition

Background:

  • Edge computing requires energy-efficient systems for tasks like keyword spotting.
  • Portable devices have strict power constraints for audio processing.

Purpose of the Study:

  • To propose an ultra-low-power Keyword Spotting (KWS) system for energy-constrained edge applications.
  • To develop a robust and efficient architecture for audio feature extraction and classification.

Main Methods:

  • An analog filter bank for audio feature extraction and a digital Gated Recurrent Unit (GRU) classifier were used.
  • A Learned Step Size (LSQ) and Look-Up Table (LUT)-aware quantization method (W4A8) was applied to the GRU model.
  • Behavioral modeling of the analog front-end (AFE) and robustness testing against noise and parameter variations were performed.

Main Results:

  • The quantized W4A8 GRU model achieved 91.35% accuracy on 12 classes, with <1% degradation from full precision.
  • The system requires only 34.8 kB memory and 62,400 MAC operations per inference.
  • The AFE demonstrated robustness against Gaussian noise and analog circuit impairments.

Conclusions:

  • The proposed KWS system is suitable for ultra-low-power, noise-resilient edge applications.
  • The energy-efficient design balances high accuracy with minimal computational and memory resources.
  • The system's robustness ensures reliable performance in real-world, imperfect conditions.