What question did this study set out to answer?

This research aims to develop a privacy-preserving framework for real-time detection, classification, and tracking of human and vehicle movements using seismic sensor data.

July 23, 2026Mediterranean Geoscience ReviewsOpen Access

Privacy-preserving detection, classification, and tracking of human and vehicle movements using seismic sensor networks

View Full Paper

Ask AI

Bookmark

Authors

YOYuki Oi AAAhmad B. Ahmad TTTakeshi Tsuji

Discussion

Member takes

Overview

Randomized trial demonstrates effective object tracking in urban environments, indicating a potential for privacy-focused monitoring solutions.

Key Points

This research aims to develop a privacy-preserving framework for real-time detection, classification, and tracking of human and vehicle movements using seismic sensor data.
Utilized seismometer networks to capture ground-vibration data from vehicles and pedestrians.
Trained a convolutional neural network on time-frequency spectrograms for classification.
Evaluated two localization methods: particle motion-based approach and Time-Difference-Of-Arrival (TDOA).
Achieved 98.6% test accuracy in classifying human and vehicle movements.
Localized objects within several meters, especially with the particle motion method near the sensor array.
Effectively mitigated misclassifications through rule-based post-processing considering temporal continuity.

Cite This Study

Oi et al. (2026) studied this question.

synapsesocial.com/papers/6a61b004faa9903c5116aa3f https://doi.org/10.1007/s42990-026-00266-x

View Full Paper

Ask AI

Bookmark

July 23, 2026Mediterranean Geoscience ReviewsOpen Access

Privacy-preserving detection, classification, and tracking of human and vehicle movements using seismic sensor networks

View Full Paper

Ask AI

Bookmark

Authors

YOYuki Oi AAAhmad B. Ahmad TTTakeshi Tsuji

Discussion

Member takes

Overview

Randomized trial demonstrates effective object tracking in urban environments, indicating a potential for privacy-focused monitoring solutions.

Key Points

This research aims to develop a privacy-preserving framework for real-time detection, classification, and tracking of human and vehicle movements using seismic sensor data.
Utilized seismometer networks to capture ground-vibration data from vehicles and pedestrians.
Trained a convolutional neural network on time-frequency spectrograms for classification.
Evaluated two localization methods: particle motion-based approach and Time-Difference-Of-Arrival (TDOA).
Achieved 98.6% test accuracy in classifying human and vehicle movements.
Localized objects within several meters, especially with the particle motion method near the sensor array.
Effectively mitigated misclassifications through rule-based post-processing considering temporal continuity.

Cite This Study

Oi et al. (2026) studied this question.

synapsesocial.com/papers/6a61b004faa9903c5116aa3f https://doi.org/10.1007/s42990-026-00266-x

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark