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 Experiment Video

Updated: May 12, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Unsupervised user similarity mining in GSM sensor networks.

Shafqat Ali Shad1, Enhong Chen

  • 1Department of Computer Science and Technology, University of Science and Technology of China, Huangshan Road, Hefei, Anhui 230027, China. shafqat@mail.ustc.edu.cn

Thescientificworldjournal
|April 12, 2013
PubMed
Summary

This study introduces a new method for building user mobility profiles using semantic tagging and GSM network data. It enables effective user similarity mining from raw mobility data, improving applications like route prediction.

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

Agent4CD: Generative Agent for Cognitive Diagnosis in Intelligent Education.

IEEE transactions on neural networks and learning systems·2026
Same author

MENDNet: Memory-Enhanced Dependency Network for Multistock Movement Prediction.

IEEE transactions on neural networks and learning systems·2026
Same author

DisenTS: Disentangled Channel Evolving Pattern Modeling for Multivariate Time Series Forecasting.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

ActionX: pre-training action experts with reinforcement learning for vision-language action models.

Frontiers in neurorobotics·2026
Same author

Rein++: Efficient Generalization and Adaptation for Semantic Segmentation With Vision Foundation Models.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Survey of Computerized Adaptive Testing: A Machine Learning Perspective.

IEEE transactions on pattern analysis and machine intelligence·2026

Area of Science:

  • Data Science
  • Computer Science
  • Network Engineering

Background:

  • Mobility data offers rich spatiotemporal insights for applications like traffic management and social networking.
  • Building user mobility profiles is crucial but challenging due to the complexity of extracting significant places and predicting movements.
  • Existing methods often rely on high-precision location data, which may not always be available or practical.

Purpose of the Study:

  • To propose a novel methodology for user similarity mining based on user mobility profile building.
  • To leverage semantic tagging and GSM network architecture for enhanced mobility data analysis.
  • To address the challenges of extracting meaningful information from low-level, raw mobility data.

Main Methods:

  • Developed an unsupervised clustering approach for mobility profile building.

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

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

Related Experiment Videos

Last Updated: May 12, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

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

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

  • Utilized semantic tagging information provided by users.
  • Employed basic GSM network architecture properties, specifically cell-ID location information.
  • Converted low-level raw mobility data into high-level meaningful information.

    • Main Results:

    • Successfully built user mobility profiles using a novel approach.
    • Demonstrated effective user similarity mining through the proposed methodology.
    • Showcased the conversion of raw cell-ID data into actionable insights for profile building.
    • Achieved profile mining and user similarity mining without relying on GPS, Infrared, or WiFi.

    Conclusions:

    • The proposed methodology offers an effective way to build user mobility profiles and perform user similarity mining.
    • Utilizing GSM network data and semantic tagging provides a viable alternative to traditional location-sensing methods.
    • This approach enhances the utility of mobility data for various applications by extracting high-level meaningful information.