Automatic classification of active sonar data using time-frequency transforms

1992 ◽  
Author(s):  
Francesco Lari ◽  
Avideh Zakhor
Keyword(s):  
Automatic Classification ◽  
Time Frequency ◽  
Active Sonar

Application of Time-Frequency Analysis & Blind Source Separation to Diagnosis of Faults with Generator Rotor System

2014 ◽  
Vol 556-562 ◽  
pp. 2748-2751
Author(s):  
Hong Li Wang ◽  
Bing Xu ◽  
Xue Dong Xue ◽  
Kan Cheng
Keyword(s):  
Blind Source Separation ◽  
Source Separation ◽  
Automatic Classification ◽  
Wave Method ◽  
Nerve Network ◽  
Time Frequency ◽  
Generator Rotor ◽  
Independent Components ◽  
Local Wave

One method for diagnosis of faults with generator rotor is contrived by combining local wave method and blind source separation. Time-frequency image varies with local wave of different fault signals, and this feature is applied to identify different faults. In order to realize automatic classification of faults, blind source separation is employed for separation of independent components in time-frequency image of local wave of different fault signals, so as to derive projection coefficients for a set of source images. On the basis of this, automatic classification of faults is realized with probability nerve network. Taking fault signal of rotor as an example, this method is investigated, and the validity is proved by experimental results.

Comparison of fuzzy-cluster-based time-frequency signatures for automatic classification of underground minelike targets

1999 ◽  
Author(s):  
Steffan Abrahamson ◽  
Anders Ericsson ◽  
Anders Gustafsson ◽  
Hans C. Strifors ◽  
Guillermo C. Gaunaurd
Keyword(s):  
Automatic Classification ◽  
Fuzzy Cluster ◽  
Time Frequency

scholarly journals Automatic classification of seismo-volcanic signals at La Soufrière of Guadeloupe

2020 ◽  
Author(s):  
Alexis Falcin ◽  
Jean-Philippe Metaxian ◽  
Jérôme Mars ◽  
Eléonore Stutzmann ◽  
Roberto Moretti ◽  
...  
Keyword(s):  
Physical Process ◽  
Average Rate ◽  
Spectral Characteristics ◽  
Automatic Classification ◽  
Full Description ◽  
Large Set ◽  
Classification Rate ◽  
Time Frequency ◽  
Accuracy And Precision

<p>Seismic activity at La Soufrière volcano of Guadeloupe is composed of various transient signals, which are classified manually by the Observatoire Volcanologique et Sismologique de Guadeloupe (OVSG-IPGP) considering waveforms recorded at several stations. Although five main types of signals are recognized in the data analysis by the observatory (Moretti et al., 2020), only three main classes readily distinguishable on seismic traces during the daily analytical protocol have been catalogued: Volcano-Tectonic events, Long-Period events and Nested events, each related to a distinct physical process.</p><p>Automatic classification of seismo-volcanic signals of La Soufrière was performed by using an architecture based on supervised learning, available at github.com/malfante/AAA. Seismic waveforms are transformed into a large set of features (34 features for each representation domain) computed from three representation domain of the signal (time, frequency, quefrency). The resulting vectors of features are then used for the modeling. We are using the Random Forest Classifier algorithm from the scikit-learn library.</p><p>At first, we trained the model with the dataset given by the OVSG consisting of 845 available labeled events (542 VT, 217 nested and 86 LP) recorded in the period 2013-2018. We obtained an average classification rate of 72 %. We determined that the VT class includes a variety of signals covering the LP, Nested and VT classes. Reviewing in details the waveforms and the spectral characteristics of the signals belonging to the 3 classes we then introduced Hybrid events and also defined a monochromatic class (so-called Tornillo) of LP signals, thus matching the full description of signals provided in Moretti et al. (2020).</p><p>Then, using the new information, a new model was trained with 5 classes and tested. We obtained a much better classification average rate of 84 %. The classification is excellent for Nested events (93 % of accuracy and precision) and Tornillo events (93% of accuracy and precision). The classification of VT events (90% accuracy, 89% precision) and LP events (86% accuracy, 82% precision) were also very good. The most difficult class to recognize is the Hybrid class (64 % accuracy, 69 % precision). Hybrid events are often mixed with VT and LP events. This may be explained by the nature of this class and the physical process that includes both a fracturing and a resonating component with different modal frequencies.</p><p>Machine learning is a powerful tool to handle large datasets. From a dataset built manually, the processing we applied allowed to obtain a reliable automatic classification by refining class definitions. This has important implications for observatory data processing during unrest and eruptive activity.</p>

Sign in / Sign up

Export Citation Format

Share Document