| 韦子辉,陈江鹏,王子瑞,赵新月,董鹏.基于半监督自训练GMM-SVM的NLOS识别方法[J].电子测量与仪器学报,2026,40(5):166-178 |
| 基于半监督自训练GMM-SVM的NLOS识别方法 |
| NLOS recognition based on semi-supervised self-training GMM-SVM |
| |
| DOI： |
| 中文关键词: NLOS 信道冲激响应 自编码器 注意力机制 支持向量机 |
| 英文关键词:NLOS channel impulse response autoencoder attention mechanism support vector machine |
| 基金项目:国家自然科学基金（62173122）、中央引导地方科技发展资金(246Z0402G)项目资助 |
|
|
| Author | Institution |
| Wei Zihui | 1.School of Quality and Technical Supervision, Hebei University, Baoding 071002, China; 2.Nationa l &Local Joint Engineering
Research Center of Metrology Instrument and System, Hebei University, Baoding 071002, China; 3.Hebei Key Laboratory of
Energy Metering and Safety Testing Technology, Hebei University, Baoding 071002, China;4.Engineering Research Center of
Zero-carbon Energy Buildings and Measurement Techniques, Ministry of Education, Baoding 071000, China |
| Chen Jiangpeng | 1.School of Quality and Technical Supervision, Hebei University, Baoding 071002, China; 2.Nationa l &Local Joint Engineering
Research Center of Metrology Instrument and System, Hebei University, Baoding 071002, China; 3.Hebei Key Laboratory of
Energy Metering and Safety Testing Technology, Hebei University, Baoding 071002, China;4.Engineering Research Center of
Zero-carbon Energy Buildings and Measurement Techniques, Ministry of Education, Baoding 071000, China |
| Wang Zirui | 1.School of Quality and Technical Supervision, Hebei University, Baoding 071002, China; 2.Nationa l &Local Joint Engineering
Research Center of Metrology Instrument and System, Hebei University, Baoding 071002, China; 3.Hebei Key Laboratory of
Energy Metering and Safety Testing Technology, Hebei University, Baoding 071002, China;4.Engineering Research Center of
Zero-carbon Energy Buildings and Measurement Techniques, Ministry of Education, Baoding 071000, China |
| Zhao Xinyue | 1.School of Quality and Technical Supervision, Hebei University, Baoding 071002, China; 2.Nationa l &Local Joint Engineering
Research Center of Metrology Instrument and System, Hebei University, Baoding 071002, China; 3.Hebei Key Laboratory of
Energy Metering and Safety Testing Technology, Hebei University, Baoding 071002, China;4.Engineering Research Center of
Zero-carbon Energy Buildings and Measurement Techniques, Ministry of Education, Baoding 071000, China |
| Dong Peng | 1.School of Quality and Technical Supervision, Hebei University, Baoding 071002, China; 2.Nationa l &Local Joint Engineering
Research Center of Metrology Instrument and System, Hebei University, Baoding 071002, China; 3.Hebei Key Laboratory of
Energy Metering and Safety Testing Technology, Hebei University, Baoding 071002, China;4.Engineering Research Center of
Zero-carbon Energy Buildings and Measurement Techniques, Ministry of Education, Baoding 071000, China |
|
| 摘要点击次数: 189 |
| 全文下载次数: 75 |
| 中文摘要: |
| 在超宽带（UWB）无线通信系统中，非视距（NLOS）和视距（LOS）环境的准确识别对于提高定位精度和系统性能至关重要。为此提出了一种基于注意力机制结构（ATTENTION）改进稀疏自编码器（SAE）的特征提取方法，SAE通过稀疏编码学习稳定有效的特征表达，注意力机制则通过动态权重分配突出重要信息，两者结合能实现更加精准的特征降维；采用了结合高斯混合模型（GMM）和自训练支持向量机（SVM）的半监督分类策略来执行LOS/NLOS的状态识别，高斯混合模型用于建模提取的特征空间生成概率分布参数，随后利用自训练支持向量机来增强边缘部分分类的准确性和鲁棒性。实验结果表明，通过比较不同降维方法与LOS/NLOS分类器组合在NLOS识别任务中的性能，本研究提出的SAE-ATTENTION特征提取策略与GMM-SVM分类模型组合，在识别准确率和可靠性方面表现出显著优势。在静态实验和动态实验中，该方法的NLOS识别准确率分别达到95.20%和93.05%，有效提升了模型在有限标记样本条件下的泛化能力。 |
| 英文摘要: |
| In ultra-wideband wireless communication systems, the accurate identification of non-line-of-sight and line-of-sight environments is crucial for enhancing positioning accuracy and system performance. To this end, a feature extraction method based on an attention mechanism structure is proposed to enhance the sparse autoencoder. The SAE learns stable and effective feature representations through sparse coding, while the attention mechanism highlights crucial information via dynamic weight allocation. Their integration enables more precise feature dimensionality reduction. A semi-supervised classification strategy combining Gaussian Mixture Models and self-training Support Vector Machines is employed for LOS/NLOS state recognition. The GMM models the generative probability distribution parameters of the extracted feature space, while the self-training SVM enhances classification accuracy and robustness in marginal regions. Experimental results demonstrate that, when comparing the performance of different dimensionality reduction methods combined with LOS/NLOS classifiers in the NLOS recognition task, the proposed SAE-ATTENTION feature extraction strategy coupled with the GMM-SVM classification model exhibits significant advantages in recognition accuracy and reliability. In static and dynamic experiments, this approach achieved NLOS recognition accuracies of 95.20% and 93.05% respectively, effectively enhanced the model’s generalisation capability under conditions of limited labelled samples. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
