| 赵子杰,程巍,姬培锋,滕鹏晓,吕君,杨军.应用原型度量的小样本次声信号分类识别方法*[J].,2024,43(6):1193-1202 |
| 应用原型度量的小样本次声信号分类识别方法* |
| A method for classification of few-shot infrasound signals applying prototype network |
| 投稿时间：2023-02-28 修订日期：2024-10-21 |
| 中文摘要: |
| 地震、闪电、火箭发射、爆炸等活动都会伴随着次声信号的产生。为提升次声事件的监测能力，需要对小样本的次声信号进行正确分类识别。针对小样本和可变时长的次声事件的有效识别问题，结合长短期记忆模型提出了一种应用原型网络的次声信号分类方法。使用该方法分别对公开的次声信号数据集和实地采集的地震、爆炸、闪电、火箭再入产生的四类次声信号进行分类实验。实验结果表明，该方法相对于传统方法，简化了特征提取的过程，有效解决了可变时长次声信号的特征分析问题，取得较好的分类结果和泛化效果。 |
| 英文摘要: |
| Events such as earthquakes, lightning, rocket launches, and explosions are accompanied by infrasound signals. In order to improve the monitoring capability of infrasound events, it is necessary to correctly classify small samples of infrasound signals. For the problem of effective identification of infrasound events with small samples and variable duration, a classification method of infrasound signals applying prototype network is proposed in combination with a long and short-term memory model. The method is used to conduct classification experiments on publicly available infrasound signal datasets and four types of infrasound signals generated by earthquakes, explosions, lightning, and rocket re-entry collected in the field. The experimental results show that the method simplifies the process of feature extraction and effectively solves the problem of feature analysis of variable duration infrasound signals compared with the traditional method, and achieves better classification results and generalization effects. |
| DOI：10.11684/j.issn.1000-310X.2024.06.002 |
| 中文关键词: 次声 小样本 原型网络 长短期记忆模型 |
| 英文关键词: Infrasound Few-shot Prototypical Network LSTM |
| 基金项目:国家自然科学基金项目（面上项目，重点项目，重大项目） |
|
| 摘要点击次数: 49 |
| 全文下载次数: 34 |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
