Cargando…
Advantages and Pitfalls of Pattern Recognition : Selected Cases in Geophysics /
| Clasificación: | Libro Electrónico |
|---|---|
| Autor principal: | |
| Otros Autores: | , |
| Formato: | Electrónico eBook |
| Idioma: | Inglés |
| Publicado: |
San Diego :
Elsevier,
2020.
|
| Colección: | Computational geophysics series ;
v. 3. |
| Temas: | |
| Acceso en línea: | Texto completo |
Tabla de Contenidos:
- Front Cover; Advantages and Pitfalls of Pattern Recognition; Advantages and Pitfalls of Pattern Recognition; Copyright; Contents; Preface; Acknowledgments; I
- From data to methods; 1
- Patterns, objects, and features; 1.1 Objects and patterns; 1.2 Features; 1.2.1 Types; 1.2.2 Feature vectors; 1.2.3 Feature extraction; 1.2.3.1 Delineating segments; 1.2.3.2 Delineating regions; 1.2.4 Transformations; 1.2.4.1 Karhunen-Lo�eve transformation (Principal Component Analysis); 1.2.4.2 Independent Component Analysis; 1.2.4.3 Fourier transform; 1.2.4.4 Short-time Fourier transform and spectrograms
- 1.2.4.5 Discrete wavelet transforms1.2.5 Standardization, normalization, and other preprocessing steps; 1.2.5.1 Comments; 1.2.5.2 Outlier removal; 1.2.5.3 Missing data; 1.2.6 Curse of dimensionality; 1.2.7 Feature selection; Appendix 1 Basic notions on statistics; A1.1 Statistical parameters of an ensemble; A1.2 Distinction of ensembles; 2
- Supervised learning; 2.1 Introduction; 2.2 Discriminant analysis; 2.2.1 Test ban treaty-some history; 2.2.2 The MS-mb criterion for nuclear test identification; 2.2.3 Linear Discriminant Analysis; 2.3 The linear perceptron
- 2.4 Solving the XOR problem: classification using multilayer perceptrons (MLPs)2.4.1 Nonlinear perceptrons; 2.5 Support vector machines (SVMs); 2.5.1 Linear SVM; 2.5.2 Nonlinear SVM, kernels; 2.6 Hidden Markov Models (HMMs)/sequential data; 2.6.1 Background-from patterns and classes to sequences and processes; 2.6.2 The three problems of HMMs; 2.6.3 Including prior knowledge/model dimensions and topology; 2.6.4 Extension to conditional random fields; 2.7 Bayesian networks; Appendix 2; Appendix 2.1 Fisher's linear discriminant analysis; Appendix 2.2 The perceptron; Backpropagation
- Appendix 2.3 SVM optimization of the marginsAppendix 2.4. Hidden Markov models; Appendix 2.4.1. Evaluation; Appendix 2.4.2. Decoding-the Viterbi algorithm; Appendix 2.4.3. Training-the expectation-maximization /Baum-Welch algorithm; 3
- Unsupervised learning; 3.1 Introduction; 3.1.1 Metrics of (dis)similarity; 3.1.2 Clustering; 3.1.2.1 Partitioning clustering; 3.1.2.1.1 Fuzzy clustering; 3.1.2.2 Hierarchical clustering; 3.1.2.3 Density-based clustering; 3.2 Self-Organizing Maps; 3.2.1 Training of an SOM; Appendix 3; Appendix 3.1. Analysis of variance (ANOVA)
- Appendix 3.2 Minimum distance property for the determinant criterionAppendix 3.3. SOM quality; Topological error; Designing the map; II
- Example applications; 4
- Applications of supervised learning; 4.1 Introduction; 4.2 Classification of seismic waveforms recorded on volcanoes; 4.2.1 Signal classification of explosion quakes at Stromboli; 4.2.2 Cross-validation issues; 4.3 Infrasound classification; 4.3.1 Infrasound monitoring at Mt Etna-classification with SVM; 4.4 SVM classification of rocks; 4.5 Inversion with MLP; 4.5.1 Identification of parameters governing seismic waveforms