Graph-Based Feature Weight Optimisation and Classification of Continuous Seismic Sensor Array Recordings.
Graph-Based Feature Weight Optimisation and Classification of Continuous Seismic Sensor Array Recordings.
复制标题
DOI：
10.3390/s23010243
复制
发表时间：
2022-12-26
期刊：
影响因子：
--
通讯作者：
Shi Q
中科院分区：
文献类型：
--
作者：
Li J;Stankovic L;Stankovic V;Pytharouli S;Yang C;Shi Q
由暴雨、人为活动或地震引起的斜坡不稳定性可以用地震事件来表征。为了最大限度地减少死亡率和基础设施的损坏，因此，对表征边坡破坏的地震信号特性的良好理解对于有效地将记录的地震事件与连续记录进行分类至关重要。然而，有有限的贡献对理解的重要性，从连续的噪声记录从多个通道/传感器的地震信号的分类特征选择。本文首先提出了一种基于Neyman-Pearson引理和多通道相干偏移（MCM）的多通道事件检测方法。此外，本文采用基于图的特征权重优化作为特征选择，利用信号的物理特性，以提高信号分类。具体来说，我们交替优化的特征权重和分类标签与图平滑和半定规划（SDP）。实验结果表明，与传统的短时平均/长时平均（STA/LTA）检测方法相比，在专家解释下，该方法在5天内多识别出614个地震事件。此外，特征选择，特别是通过基于图的特征权重优化，提供了更集中的特征集，其特征数量不到原始数量的一半，同时提高了分类性能;例如，通过特征选择，图拉普拉斯正则化分类器（GLR）将落石和滑坡地震的灵敏度分别从89%和85%提高到92%和88%。
Slope instabilities caused by heavy rainfall, man-made activity or earthquakes can be characterised by seismic events. To minimise mortality and infrastructure damage, a good understanding of seismic signal properties characterising slope failures is therefore crucial to classify seismic events recorded from continuous recordings effectively. However, there are limited contributions towards understanding the importance of feature selection for the classification of seismic signals from continuous noisy recordings from multiple channels/sensors. This paper first proposes a novel multi-channel event-detection scheme based on Neyman–Pearson lemma and Multi-channel Coherency Migration (MCM) on the stacked signal across multi-channels. Furthermore, this paper adapts graph-based feature weight optimisation as feature selection, exploiting the signal’s physical characteristics, to improve signal classification. Specifically, we alternatively optimise the feature weight and classification label with graph smoothness and semidefinite programming (SDP). Experimental results show that with expert interpretation, compared with the conventional short-time average/long-time average (STA/LTA) detection approach, our detection method identified 614 more seismic events in five days. Furthermore, feature selection, especially via graph-based feature weight optimisation, provides more focused feature sets with less than half of the original number of features, at the same time enhancing the classification performance; for example, with feature selection, the Graph Laplacian Regularisation classifier (GLR) raised the rockfall and slide quake sensitivities to 92% and 88% from 89% and 85%, respectively.
登录
查看更多内容
影响因子：
3.3
作者：
Huggel, Christian;Clague, John J.;Korup, Oliver
通讯作者：
Korup, Oliver
DOI：
10.1109/tgrs.2020.3032664
发表时间：
2021-09-01
影响因子：
8.2
作者：
Li, Jiangfeng;Stankovic, Lina;Stankovic, Vladimir
通讯作者：
Stankovic, Vladimir
影响因子：
2.8
作者：
Tonnellier, Alice;Helmstetter, Agnes;Joswig, Manfred
通讯作者：
Joswig, Manfred
使用基于主成分分析的人工神经网络改进微震事件和采石场爆炸分类
影响因子：
4
作者：
Shang, Xueyi;Li, Xibing;Chen, Guanghui
通讯作者：
Chen, Guanghui
DOI：
10.1109/tgrs.2020.3019520
发表时间：
2021-07-01
影响因子：
8.2
作者：
Saad, Omar M.;Chen, Yangkang
通讯作者：
Chen, Yangkang