YAYoussef Akoudad

Youssef Akoudad

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Youssef Akoudad has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • HDNAT: A Transformer-Based Fault Diagnosis Model for Rotating Machinery Across Varying Damage Degrees

    by Wei Gao, Xiuhuang Xie, Dongliang Fu, Jiongmin Yu, Youssef Akoudad

    The goal of cross-domain fault diagnosis for rotating machinery is to enhance the robustness and generalization ability of diagnostic systems, enabling accurate fault diagnosis across different domains. Most existing studies in this field focus on diagnosing the same equipment under varying operating conditions. However, rotating machinery, a critical component in mechanical systems, undergoes inevitable wear during operation, resulting in varying degrees of damage that poses significant challenges for fault diagnosis. To address these challenges arising from wear-induced variations, we propose a cross-damage-degree fault diagnosis framework for rotating machinery. We introduce a novel hybrid domain nested attention Transformer (HDNAT) model, designed to improve fault diagnosis in rotating machinery with different levels of damage. Leveraging the powerful information integration capabilities of multi-domain fusion, the model enhances its ability to extract fault-related features across varying damage degrees. To achieve this, we propose the multi-modal hybrid perception (MMHP) strategy, based on multi-domain fusion, which captures both coarse-grained global dependencies and fine-grained local dependencies within signal features, while simultaneously extracting amplitude and phase information. Furthermore, HDNAT utilizes a nested cross-attention (NCA) mechanism to optimize the fusion of multi-domain information from vibration signals. The NCA mechanism overcomes the limitations of traditional cross-attention, which typically handles only dual-branch inputs, by enabling comprehensive integration of diverse signal information. Extensive experiments conducted on three bearing and gearbox datasets with varying damage degrees demonstrate that HDNAT outperforms state-of-the-art deep learning-based fault diagnosis models.


  • MSSF-Net: A Multimodal Spectral–Spatial Feature Fusion Network for Hyperspectral Unmixing

    by Wei Gao, Yu Zhang, Youssef Akoudad, Jie Chen

    Hyperspectral unmixing (HU) aims to decompose mixed pixels in remote sensing imagery into material-specific spectra and their respective abundance fractions. Recently, autoencoders have made significant advances in HU due to their strong representational capabilities and ease of implementation. However, relying exclusively on feature extraction from a single-modality hyperspectral image can fail to fully utilize both spatial and spectral information, thereby limiting the ability to distinguish objects in complex scenes. To address these limitations, we propose a multimodal spectral-spatial feature fusion network (MSSF-Net) for enhanced HU. MSSF-Net adopts a dual-stream architecture to extract feature representations from complementary input modalities. Specifically, the hyperspectral subnetwork leverages a convolutional neural network (CNN) to capture spatial information, while the light detection and ranging (LiDAR) subnetwork incorporates an enhanced channel attention mechanism (ECAM) to capture the dynamic changes in spatial information across different channels. Furthermore, we introduce a cross-modal fusion (CMF) module that integrates spectral and spatial information across modalities, leading to more robust feature representations. Experimental results indicate that MSSF-Net significantly outperforms existing traditional and deep learning-based methods in terms of unmixing accuracy. The code is available at https://github.com/Octopus-Squidward/MSSF-Net.


  • Metric-Based Meta-Learning Relation Network for Cross-Domain Few-Shot Bearing Fault Diagnosis

    by Wei Gao, Zhiqiang Xu, Youssef Akoudad

    Deep learning techniques have recently shown great promise in the field of bearing fault diagnosis, yet their performance is often limited by practical challenges such as insufficient fault data and varied working conditions in real-world industrial settings. Furthermore, traditional deep transfer learning approaches often require extensive parameter fine-tuning for specific tasks, thus reducing their adaptability in scenarios where rapid deployment is crucial. To address these issues, we propose a novel metric-based meta-learning relation network designed for few-shot bearing fault diagnosis across diverse domains. This method directly targets an industrial need: accurate fault detection with minimal training samples under unseen operational conditions. This capability is critical for predictive maintenance systems in resource-constrained environments. Vibration signals from various working conditions are first transformed into two-dimensional time-frequency images. These samples are then divided into meta-training and meta-testing sets, with each set further split into support and query subsets according to a meta-learning strategy. Following this division, a residual shrinkage non-local feature extraction module is introduced to extract and combine features from both subsets. A neural network with a nonlinear metric is subsequently employed to compute similarity scores between the support and query sets. The proposed method enables rapid and precise bearing fault diagnosis, even with limited data samples and under unknown working conditions, which are typical in maintenance workshops and field operations. Comparative tests on three datasets demonstrate that our approach outperforms existing methods under different working conditions and noise levels, highlighting its potential to reduce unplanned downtime and improve equipment reliability in real industrial applications. The experimental results further confirm the method’s robust generalization and rapid adaptability.


  • Top Cited Papers

    SSAF-Net: A Spatial-Spectral Adaptive Fusion Network for Hyperspectral Unmixing With Endmember Variability

    by Wei Gao, Jingyu Yang, Yu Zhang, Youssef Akoudad, Jie Chen

    Deep learning has recently garnered substantial interest in hyperspectral unmixing due to its exceptional learning capabilities. In particular, unsupervised unmixing methods based on autoencoders have become a research hotspot, with many existing networks focusing on the fusion of spatial and spectral information. However, the diversity of fusion structures makes it challenging to select appropriate modules that meet unmixing requirements, while the issue of endmember variability is often neglected. In this paper, we propose a novel spatial-spectral adaptive fusion network (SSAF-Net) that accounts for endmember variability. The network consists of two cascaded encoders and a deep generative model (DGM) based on a variational autoencoder. The encoders perform local spatial-spectral information fusion through channel and spatial attention mechanisms, respectively, while self-perception loss facilitates global information fusion during the cascading process. In addition, we address endmember variability using a proportional perturbation model (PPM), learning the necessary endmember parameters through an elaborately designed DGM. Our SSAF-Net learns both endmember variability and the corresponding abundances in an unsupervised manner. Experimental results on a synthetic dataset and real-world datasets validate the significant superiority of SSAF-Net compared to other methods. The code for this work is available at https://github.com/yjysimply/SSAF-Net.


  • MA-Stereo: Real-Time Stereo Matching via Multi-Scale Attention Fusion and Spatial Error-Aware Refinement

    by Wei Gao, Yongjie Cai, Youssef Akoudad, Yang Yang, Jie Chen

    Stereo matching is a fundamental task in computer vision. Real-time stereo matching has recently shown great potential in robotics and autonomous driving applications. However, the existing cost aggregation in real-time stereo matching suffers from accuracy limitations in ill-posed regions. Furthermore, most real-time stereo matching methods struggle to predict disparity in object details and edge areas, resulting in relatively blurred and lacking detailed disparity maps. To address these issues, we propose a real-time stereo matching architecture called MA-Stereo, which features a multi-scale attention fusion (MAF) module and an attention-based spatial error-aware refinement (ASER) module. The MAF adaptively fuses context and geometry information through attention mechanism, effectively improving cost aggregation. In addition, the ASER refines the predicted disparity map, fully leveraging high-frequency information and spatial evidence to accurately predict disparities for sharp edges and thin structures. Experimental results on the SceneFlow and KITTI benchmarks demonstrate that MA-Stereo outperforms almost all current state-of-the-art real-time stereo matching methods while maintaining relatively low runtime, achieving a favorable trade-off between accuracy and speed.