Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yuchao Hou has a total of 53 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    SE-ResNet-Based Breast Cancer Histopathological Image Classification on the BreaKHis Dataset

    by Yan Hao, Yuchao Hou

    Breast cancer histopathological image classification is an important task in computer-aided pathological image analysis. Handcrafted feature-based methods require substantial feature engineering, while conventional CNN architectures may have limited adaptive feature weighting and multi-level feature fusion. This paper presents an SE-ResNet-based model for binary classification of breast histopathological images into benign and malignant categories. A 3 × 1 asymmetric convolution was adopted as a parameter-efficient alternative to the corresponding 3 × 3 configuration. SE attention was integrated with residual blocks for adaptive channel recalibration, and bilinear upsampling was used to fuse multi-level feature maps. Experiments were conducted on the BreaKHis dataset containing 7909 images at four magnifications (40×, 100×, 200×, 400×). The comparative experiments across five patient-disjoint trials showed that the 3 × 1 kernel, a batch size of 24 and the SE-ResNet configuration achieved the highest mean image-level accuracy, patient-level accuracy, sensitivity, specificity, precision, and F1-score among their respective tested configurations. Under the magnification-independent classification setting, the model achieved 92.95 ± 0.08% image-level accuracy and 91.88 ± 1.35% patient-level accuracy. These results support the feasibility of the proposed architecture for benign/malignant classification on the BreaKHis dataset.

  • Top Cited Papers

    AsyncFed-SAR: Towards Communication-Efficient Asynchronous Federated Learning for SAR Image Target Recognition

    by Yuchao Hou, Dongming Lv, Minghui Liwang, Jie Wang, Zijian Li, Xiaoyu Xia, Di Wu, Youliang Tian, Tony Q.S. Quek, Xianbin Wang

    Synthetic aperture radar (SAR) image target recognition plays a pivotal role in applications such as disaster response, environmental monitoring, and agricultural monitoring. However, aggregating imagery data across multiple sensors faces significant challenges due to privacy concerns and communication constraints. While federated learning (FL) enables joint training without data sharing, conventional synchronous FL suffers from severe straggler issues in airborne SAR networks under dynamic and unstable communication conditions. To address this challenge, we propose AsyncFed-SAR, an efficient asynchronous FL framework tailored for SAR image target recognition. Specifically, AsyncFed-SAR adopts an adaptive online sensor selection (OSS) strategy inspired by reinforcement learning principles. This method designs a novel model quality score as a reward and introduces a virtual queue to ensure fairness, thereby maintaining robust performance even in communication-constrained environments. To further mitigate model staleness introduced by asynchronous updates, we propose a gradient delay compensation (GDC) strategy, which approximates the stale gradient contributions through a lightweight Hessian estimation based on the gradient outer product. Theoretical analysis provides convergence guarantees and demonstrates the framework's capability to reduce total training time. Extensive experiments on the MSTAR and FUSAR-Ship datasets validate that AsyncFed-SAR significantly outperforms baseline methods in generalization and robustness while achieving lower training time and faster convergence.


  • Top Cited Papers

    EfficientSARNet: A Lightweight, High-Performance, and Fast SAR Image Target Recognition Network

    by Yuchao Hou, Liang Zhang, Jie Wang, Hongtao Li, Xiaoqi Duan, Kaiwen Huang, Youliang Tian

    Synthetic aperture radar (SAR) image target recognition aims to identify objects captured in radar imagery accurately and efficiently. This core technology is widely used in various applications, including military and civilian contexts. However, SAR image target recognition models are typically deployed on edge devices with limited computational resources and real-time processing requirements, posing significant challenges to the model size, recognition accuracy, and inference speed. Existing SAR image target recognition methods struggle to achieve outstanding performance in all these aspects simultaneously. To address these challenges, we propose EfficientSARNet, a novel efficient model designed for SAR image target recognition. Specifically, we design a light-weight multi-branch (LWMB) feature extraction module to capture local diversity features efficiently. Additionally, we introduce an efficient linear self-attention module, proximal linear self-attention (PLSA), which leverages feature positional information for re-weighting to facilitate the capture of global features. EfficientSARNet is innovatively designed by both simply and efficiently stacking PLSA and LWMB modules in various stages to capture both global and local features, achieving light-weight, high performance, and fast SAR image target recognition under limited computational resources. Extensive experiments and thorough analysis on multiple subsets of the moving and stationary target acquisition and recognition (MSTAR) dataset and the OpenSARUrban dataset demonstrate that EfficientSARNet not only surpasses state-of-the-art algorithms in recognition accuracy but also shows advantages in metrics such as Parameters, MACs, and Throughput.


  • Top Cited Papers

    Privacy-preserving federated SAR image target recognition with adaptive resource management in space-air-ground integrated networks

    by Yuchao Hou, Bo Yu, Zhiqin Yang, Jie Wang, Wei Xiang, Di Wu, Minghui Liwang, Xiaoyu Xia, Zijian Li, Youliang Tian, et al.


  • Open Access

    Federated Dynamic Aggregation Selection Strategy-Based Multi-Receptive Field Fusion Classification Framework for Point Cloud Classification

    by Yuchao Hou, Biaobiao Bai, Shuai Zhao, Yue Wang, Jie Wang, Zijian Li

    Recently, large-scale deep learning models have been increasingly adopted for point cloud classification. However, these methods typically require collecting extensive datasets from multiple clients, which may lead to privacy leaks. Federated learning provides an effective solution to data leakage by eliminating the need for data transmission, relying instead on the exchange of model parameters. However, the uneven distribution of client data can still affect the model’s ability to generalize effectively. To address these challenges, we propose a new framework for point cloud classification called Federated Dynamic Aggregation Selection Strategy-based Multi-Receptive Field Fusion Classification Framework (FDASS-MRFCF). Specifically, we tackle these challenges with two key innovations: (1) During the client local training phase, we propose a Multi-Receptive Field Fusion Classification Model (MRFCM), which captures local and global structures in point cloud data through dynamic convolution and multi-scale feature fusion, enhancing the robustness of point cloud classification. (2) In the server aggregation phase, we introduce a Federated Dynamic Aggregation Selection Strategy (FDASS), which employs a hybrid strategy to average client model parameters, skip aggregation, or reallocate local models to different clients, thereby balancing global consistency and local diversity. We evaluate our framework using the ModelNet40 and ShapeNetPart benchmarks, demonstrating its effectiveness. The proposed method is expected to significantly advance the field of point cloud classification in a secure environment.


  • Top Cited Papers
    Open Access

    FedC-DAC: A Federated Clustering With Dynamic Aggregation and Calibration Method for SAR Image Target Recognition

    by Yuchao Hou, Shuai Zhao, Xiaoyu Xia, Minghui Liwang, Zijian Li, Nan Xu, Di Wu, Youliang Tian, Tony Q.S. Quek

    Federated learning (FL), owing to its distributed training paradigm and inherent privacy-preserving properties, has shown great potential in multi-sensor SAR target recognition. However, heterogeneous data distributions across clients and hierarchical heterogeneity among sensors can induce local model drift. The existing FL methods mitigate the impact of data heterogeneity but assume uniform differences in client data heterogeneity and ignore the inherent multi-level data heterogeneity of SAR images. To address this limitation, we propose FedC-DAC, a clustered FL framework designed to explicitly capture and utilize heterogeneity at multiple levels. The method integrates GMM-guided soft grouping to reveal latent sensor similarities, introduces intra-cluster dynamic aggregation to enhance representation sharing while mitigating overfitting, and applies cross-cluster calibration to align feature distributions and reduce global inconsistency. Experimental results on representative SAR benchmark datasets show consistent gains over representative FL baselines in Accuracy, Kappa, and F1 under strong heterogeneity, and performance close to centralized training when distributions are near uniform. These results demonstrate improved robustness and generalization for distributed SAR recognition.


  • LPP-CNN: A Lightweight Privacy-Preserving Object Classification Framework for Military Vehicle Images

    by Junyu Lai, Jie Wang, Yuchao Hou, Peiheng Jia

    In this article, we propose a lightweight privacy-preserving convolutional neural network (LPP-CNN) framework for military vehicle image classification. Existing target classification methods primarily focus on improving accuracy and recognition efficiency but often overlook security threats during data transmission and processing, making them unsuitable for high-risk battlefield scenarios. Although some approaches incorporate image security through homomorphic encryption (HE), the low efficiency and operational complexity of such techniques hinder their applicability in battlefield environments. To this end, we design a solution that integrates additive secret sharing (ASS) with edge computing by encrypting images into two ciphertexts, which are then processed independently by two edge servers to prevent data leakage during upload. The encrypted data is subsequently processed by the LPP-CNN embedded with secure computation protocols. Finally, results are combined and decrypted to achieve target classification. This method ensures efficient and accurate military vehicle classification while significantly enhancing data privacy and security. Theoretical analysis demonstrates improved response speed and reduced communication overhead. Experimental evaluations show that under a classification accuracy not less than 94%, the computational efficiency of secure comparison (SComp), secure ReLU (SReLU), and secure MaxPool protocols (SMaxPool protocols) increases by 32, 4, and 0.5 times, respectively, while communication costs decrease by 2, 2, and 13 times. The overall framework achieves a 33% improvement in computational efficiency compared to existing solutions. Compared to state-of-the-art methods, our framework not only meets battlefield requirements for high-precision object classification but also substantially strengthens data privacy and security, aligning more effectively with real-world military application demands.


  • Top Cited Papers

    Toward Secure SAR Image Generation via Federated Angle-Aware Generative Diffusion Framework

    by Yuchao Hou, Yue Wang, Xiaoyu Xia, Youliang Tian, Zijian Li, Tony Q. S. Quek

    Acquiring synthetic aperture radar (SAR) images is inherently difficult and laborious. To mitigate this data scarcity, generative models for SAR images aim to learn underlying data distributions from large-scale datasets, ensuring robust performance. Generative models mitigate data scarcity but rely on centralized frameworks, posing privacy risks and limiting deployment in Internet of Things (IoT) scenarios. To tackle the aforementioned challenges, we introduce an innovative federated angle-aware generative diffusion (FAGD) framework for secure SAR image generation. This framework integrates three key innovations: federated learning (FL), the angle-aware generative diffusion (AAGDiff) model, and the local data knowledge distillation (LDKD) strategy. Specifically, we introduce the FL framework, which enables clients to collaboratively train a generative model by transmitting model weights, thereby eliminating raw data exchange and enhancing security. We then propose the AAGDiff model for client-side high-quality generation, leveraging denoising diffusion probabilistic models (DDPMs) to synthesize high-quality SAR images from noise using an angle-conditioned encoder, enabling the generation of SAR images at different target azimuth angles. Additionally, the LDKD strategy alleviates overfitting during federated training under Non-Independent and Non-Identically Distributed (non-IID) data distributions by allowing the model to distill knowledge primarily from less frequent classes, thus enhancing generalization and robustness. Evaluated extensively on MSTAR and OpenSARShip datasets, the proposed framework ensures secure SAR image generation while achieving superior target recognition performance. Overall, the FAGD framework offers an effective and scalable solution for privacy-preserving SAR image synthesis.


  • Remote Sensing Image Scene Classification Based on Deep Learning Feature Fusion

    by Liqi Wang, Cheng Zhang, Yuchao Hou, Xiuhui Tan, Rong Cheng, Xiang Gao, Yanping Bai

    In view that traditional manual feature extraction method cannot effectively extract the overall deep image information, a new method of scene classification based on deep learning feature fusion is proposed for remote sensing images. First, the Grey Level Co-occurrence Matrix (GLCM) and Local Binary Patterns (LBP) are used to extract the shallow information of texture features with relevant spatial characteristics and local texture features as well; second, the deep information of images is extracted by the AlexNet migration learning network, and a 256-dimensional fully connected layer is added as feature output while the last fully connected layer is removed; and the two features are adaptively integrated, then the remote sensing images are classified and identified by the Grid Search optimized Support Vector Machine (GS-SVM). The experimental results on 21 types of target data of the public dataset UC Merced and 7 types of target data of RSSCN7 produced average accuracy rates of 94.77% and 93.79%, respectively, showing that the proposed method can effectively improve the classification accuracy of remote sensing image scenes. Image classification, Convolutional Neural Network (CNN), Grey Level Co-occurrence Matrix (GLCM), Local Binary Patterns (LBP), migration learning, Support Vector Machine (SVM). 68U10, 68T05 COPYRIGHT: © Global Science Press