Deadline for Manuscript Submissions: 31 November 2025

 

Special Issue Editors

Dr. Zari Farhadi  Website  E-Mail: z.farhadi@tabrizu.ac.ir, z.farhadi88@yahoo.com
University of Tabriz, Iran
Interests: high dimensional data statistical learning methods, machine learning, deep learning, artificial Inteligence, and data science

Dr. Muhammad Fazal Ijaz  Website  E-Mail: mfazal@mit.edu.au
Melbourne Institute of Technology, Australia
Interests: human-centered AI, medical image analysis, medical artificial intelligence, the Internet of Things, and data mining

 

Special Issue Information

Dear Colleagues,

Recent advances in artificial intelligence (AI), machine learning (ML), and deep learning (DL) have revolutionized the analysis and interpretation of sound and vibration signals across engineering, healthcare, and industrial applications. These technologies enable automated signal processing, feature extraction, regression modeling, and classification for enhanced diagnostics, predictive maintenance, and real-time monitoring.

This Special Issue is dedicated to cutting-edge research on AI-driven approaches for sound and vibration analysis, covering both theoretical developments and practical implementations. We welcome contributions that explore innovative algorithms, computational techniques, analytical, numerical, and experimental methods with direct relevance to practical engineering, data science, computer science challenges, and data-driven solutions to address challenges in noise and vibration control, fault detection, and beyond.

Topics of Interest Include (but are not limited to):

-AI/ML/DL for vibration signal processing (e.g. denoising, segmentation, time-frequency analysis, Wigner-Ville distribution analysis, envelope extraction, modal analysis.)

-Feature extraction and selection (e.g., Mel-frequency cepstral coefficients, time-domain statistical features, nonlinear features)

-Optimization methods (e.g., genetic algorithms for feature selection, convex optimization for active control)

-Generative AI models (e.g., generative adversarial networks for synthetic vibration data generation, variational autoencoders for anomaly simulation, diffusion models for rare event synthesis)

-Regression models (e.g. predictive maintenance and parameter estimation, etc.)

-Classification algorithms (e.g fault detection and anomaly identification, etc.)

-Explainable AI (XAI) for interpretable sound and vibration analysis

-Transformer-based models (e.g., vibration forecasting, long-sequence anomaly detection, cross-machine transfer learning)

-Deep learning architectures (e.g. CNNs, RNNs, LSTMs, BiLSTMs, Transformers for deep networks)

-General machine learning

-Real-time AI applications (e.g., edge computing for predictive maintenance, FPGA-based vibration control, low-latency anomaly detection)

-Sensor fusion and IoT-enabled

-Transfer learning

-Hybrid Graph Neural Networks (GNN) (e.g. structural vibration analysis and damage detection, etc.)

-Hybrid Deep Learning models (e.g., CNN-LSTM for spatiotemporal analysis, Transformer-GNN architectures, neuro-fuzzy systems)

-Reinforcement Learning (e.g, computer vision, audio, language)

We encourage submissions from multidisciplinary fields, including mechanical engineering, computer engineering, data science, computer science, biomedical acoustics, medical engineering, civil infrastructure, and smart manufacturing, where AI/ML techniques enhance the understanding and utilization of sound and vibration data.

 

Keywords

Vibration signal processing, Feature extraction, Deep learning, Transformer models, Structural health monitoring, Signal segmentation, Fault classification, Regression analysis, Structural damage detection, Dimensionality reduction