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

A High-Temperature and Wide-Permittivity Range Measurement System Based on Ridge Waveguide.

Sensors (Basel, Switzerland)·2025
Same author

Design and Implementation of C-Band Large-Power Planar Butler Matrix in SRS.

Sensors (Basel, Switzerland)·2024
Same author

Chemiluminescent screening of specific hybridoma cells via a proximity-rolling circle activated enzymatic switch.

Communications biology·2022
Same author

Acute granular lymphoblastic leukemia with prominent nucleoli and large cytoplasmic granules.

International journal of laboratory hematology·2022
Same author

Arc-Induced Nitrate Reagent Ion for Analysis of Trace Explosives on Surfaces Using Atmospheric Pressure Arc Desorption/Ionization Mass Spectrometry.

Analytical chemistry·2022
Same author

Gene interaction analysis of psoriasis in Chinese Han population.

Molecular genetics & genomic medicine·2022

Related Experiment Video

Updated: Jun 14, 2025

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

492

Mobile Network Coverage Prediction Using Multi-Modal Model Based on Deep Neural Networks and Semantic Segmentation.

Sheng Zeng1, Yuhang Ji1, Weiwei Chen1

  • 1College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China.

Sensors (Basel, Switzerland)
|August 29, 2024
PubMed
Summary
This summary is machine-generated.

A new deep neural network and semantic segmentation model (DNN-SS) improves mobile network coverage prediction accuracy. This model simplifies large-scale predictions by not requiring base station details or path loss models.

Keywords:
DNNcoverage predictionmulti-modal modelsatellite mapsematic segmentation

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

Related Experiment Videos

Last Updated: Jun 14, 2025

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

492
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

Area of Science:

  • Telecommunications Engineering
  • Machine Learning
  • Geospatial Analysis

Background:

  • Existing mobile network coverage prediction models often rely on complex parameters like base station height and transmission power, or path loss models.
  • These dependencies increase the computational complexity for large-scale coverage predictions, limiting their practical application.

Purpose of the Study:

  • To develop a novel, multi-modal model, DNN-SS, that enhances the accuracy and efficiency of mobile network coverage prediction.
  • To reduce the complexity of large-scale coverage predictions by eliminating the need for detailed base station information and path loss models.

Main Methods:

  • The DNN-SS model integrates a deep neural network (DNN) for numerical feature extraction and semantic segmentation (SS) of satellite imagery for environmental feature extraction.
  • A geospatial-temporal moving average filter is applied for data preprocessing.
  • The model is trained on a combined dataset of numerical and environmental features.

Main Results:

  • On campus testing, DNN-SS achieved a Root Mean Square Error (RMSE) of 1.97 dB and a Mean Absolute Error (MAE) of 1.41 dB for random location predictions, outperforming existing models by over 10%.
  • For a specific test area, the model demonstrated strong performance with an RMSE of 4.32 dB and MAE of 3.45 dB.
  • Crucially, DNN-SS achieved these results without requiring base station height, transmission power, antenna gain, or path loss models.

Conclusions:

  • The proposed DNN-SS model offers a more efficient and accurate approach to mobile network coverage prediction, particularly for large-scale deployments.
  • By leveraging deep learning and semantic segmentation, the model simplifies the prediction process and reduces reliance on traditional, complex parameters.
  • DNN-SS presents a promising solution for network operators seeking to optimize coverage planning and resource management.