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

You might also read

Related Articles

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

Sort by
Same author

Synergistic Impact of Turkey Red Oil and Sodium Oleate on the Separation of Dolomite from Apatite.

Langmuir : the ACS journal of surfaces and colloids·2026
Same author

Dual Marker Co-Expressed Exosome-Based Liquid Biopsy Electrochemical Assay for Enhanced-Accuracy Diagnosis of Prostate Cancer.

ACS sensors·2026
Same author

Controllable Synthesis of Silicalite-1 with Tailored c-Axis Length via KHSO<sub>4</sub> and Seed Co-Additive Strategy.

Materials (Basel, Switzerland)·2026
Same author

CHD1L maintains genome integrity by facilitating okazaki fragment maturation.

Nucleic acids research·2026
Same author

Quantifying the combined effects of substrate microstructure and environmental factors on microalgal biofilm growth: a novel kinetic modeling approach.

Bioresource technology·2026
Same author

GSEA model outcomes in pharmaceutical workforce development: a retrospective pilot study (2023-2025).

Frontiers in public health·2026

Related Experiment Video

Updated: Jan 19, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.6K

MCSM-Wri: A Small-Scale Motion RecognitionMethod Using WiFi Based on Multi-ScaleConvolutional Neural Network.

Shiyuan Ma1, Tingpei Huang2, Shibao Li3

  • 1College of Computer & Communication Engineering, China University of Petroleum, Qingdao 266580, China. S17070758@s.upc.edu.cn.

Sensors (Basel, Switzerland)
|September 28, 2019
PubMed
Summary

This study introduces MCSM-Wri, a WiFi-based system for recognizing handwritten letters. It achieves high accuracy for small-scale motion recognition, outperforming existing methods.

Keywords:
WiFi signalschannel state informationconvolutional neural networkhandwritten letters recognition

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K
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

9.8K

Related Experiment Videos

Last Updated: Jan 19, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.6K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K
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

9.8K

Area of Science:

  • Computer Science
  • Electrical Engineering
  • Signal Processing

Background:

  • Small-scale motion recognition using WiFi is challenging due to minimal signal impact.
  • Distinguishing between uppercase and lowercase letters with similar writing trajectories requires advanced techniques.
  • Existing WiFi-based motion recognition systems struggle with the nuances of fine motor actions.

Purpose of the Study:

  • To develop a device-free handwritten letter recognition system utilizing WiFi Channel State Information (CSI).
  • To address the challenges of low impact and similar trajectories in small-scale motion recognition.
  • To improve the accuracy and robustness of WiFi-based handwritten character recognition.

Main Methods:

  • Leveraged WiFi Channel State Information (CSI) for device-free recognition.
  • Implemented data preprocessing to enhance feature information for recognition.
  • Developed a ten-layer Convolutional Neural Network (CNN) to handle multi-scale characteristics and subtle signal changes.
  • Collected a dataset of 6240 handwritten letter instances (52 types) from 6 volunteers in two environments.

Main Results:

  • The MCSM-Wri system achieved high accuracy rates: 95.31% (lab), 96.68% (utility room), and 97.70% (combined).
  • The proposed CNN effectively addressed recognition issues caused by small-scale actions and size variations.
  • Significantly outperformed existing methods like Wi-Wri and SignFi, with accuracy improvements ranging from 8.96% to 18.13%.

Conclusions:

  • MCSM-Wri demonstrates a highly accurate and effective approach for WiFi-based handwritten letter recognition.
  • The system's CNN architecture is adept at handling the complexities of small-scale motion recognition.
  • This research offers a promising advancement in device-free human-computer interaction and environmental perception technologies.