Adaptive Vehicle Speed Classification via BMCNN with Reinforcement Learning-Enhanced Acoustic Processing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yuli, Fan, Pengfei, Jiang, Ruiyuan, Gu, Hankang, Jia, Dongyao, Wang, Xinheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914015237636096
author Zhang, Yuli
Fan, Pengfei
Jiang, Ruiyuan
Gu, Hankang
Jia, Dongyao
Wang, Xinheng
author_facet Zhang, Yuli
Fan, Pengfei
Jiang, Ruiyuan
Gu, Hankang
Jia, Dongyao
Wang, Xinheng
contents Traffic congestion remains a pressing urban challenge, requiring intelligent transportation systems for real-time management. We present a hybrid framework that combines deep learning and reinforcement learning for acoustic vehicle speed classification. A dual-branch BMCNN processes MFCC and wavelet features to capture complementary frequency patterns. An attention-enhanced DQN adaptively selects the minimal number of audio frames and triggers early decisions once confidence thresholds are reached. Evaluations on IDMT-Traffic and our SZUR-Acoustic (Suzhou) datasets show 95.99% and 92.3% accuracy, with up to 1.63x faster average processing via early termination. Compared with A3C, DDDQN, SA2C, PPO, and TD3, the method provides a superior accuracy-efficiency trade-off and is suitable for real-time ITS deployment in heterogeneous urban environments.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00839
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Vehicle Speed Classification via BMCNN with Reinforcement Learning-Enhanced Acoustic Processing
Zhang, Yuli
Fan, Pengfei
Jiang, Ruiyuan
Gu, Hankang
Jia, Dongyao
Wang, Xinheng
Sound
Artificial Intelligence
Audio and Speech Processing
Traffic congestion remains a pressing urban challenge, requiring intelligent transportation systems for real-time management. We present a hybrid framework that combines deep learning and reinforcement learning for acoustic vehicle speed classification. A dual-branch BMCNN processes MFCC and wavelet features to capture complementary frequency patterns. An attention-enhanced DQN adaptively selects the minimal number of audio frames and triggers early decisions once confidence thresholds are reached. Evaluations on IDMT-Traffic and our SZUR-Acoustic (Suzhou) datasets show 95.99% and 92.3% accuracy, with up to 1.63x faster average processing via early termination. Compared with A3C, DDDQN, SA2C, PPO, and TD3, the method provides a superior accuracy-efficiency trade-off and is suitable for real-time ITS deployment in heterogeneous urban environments.
title Adaptive Vehicle Speed Classification via BMCNN with Reinforcement Learning-Enhanced Acoustic Processing
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2509.00839