Machine learning and pattern recognition methods in chemistry from multivariate and data driven modeling /

Machine Learning and Pattern Recognition Methods in Chemistry from Multivariate and Data Driven Modeling outlines key knowledge in this area, combining critical introductory approaches with the latest advanced techniques. Beginning with an introduction of univariate and multivariate statistical anal...

Descripción completa

Detalles Bibliográficos
Clasificación:Libro Electrónico
Autor principal: Ghasemi, Jahan B. (Editor )
Formato: Electrónico eBook
Idioma:Inglés
Publicado: Amsterdam : Elsevier, 2022.
Temas:
Chemistry > Data processing.
Machine learning.
Pattern recognition systems.
Multivariate analysis.
Chimio-informatique.
Apprentissage automatique.
Reconnaissance des formes (Informatique)
Analyse multivari�ee.
Chemistry > Data processing
Machine learning
Multivariate analysis
Pattern recognition systems
Acceso en línea:Texto completo
Tabla de Contenidos:
  • Intro
  • Machine Learning and Pattern Recognition Methods in Chemistry from Multivariate and Data Driven Modeling
  • Copyright
  • Contents
  • Contributors
  • Preface
  • Chapter 1: Soft constraints in curve resolution problems
  • 1. Introduction
  • 2. Basic concepts and theory
  • 2.1. Penalty alternating least-squares (P-ALS) algorithm
  • 2.2. Multi-way penalty alternating least-squares (P-ALS) algorithm
  • 2.3. Grid search algorithm for applying soft constraints
  • 3. Applications
  • 4. Conclusions
  • References
  • Chapter 2: Multivariate predictive modeling and validation
  • 1. Regression
  • 1.1. Multiple linear regression (MLR)
  • 1.2. Principal component regression (PCR)
  • 1.3. Partial least-squares regression (PLS)
  • 1.3.1. PLS for a single response (PLS-1)
  • 1.3.2. PLS for a multivariate response (PLS-2)
  • 1.4. Other regression techniques
  • 2. Classification
  • 2.1. Linear discriminant analysis (LDA)
  • 2.2. Partial least-squares discriminant analysis (PLS-DA)
  • 2.3. Soft independent modeling of class analogies (SIMCA)
  • 3. Validation
  • References
  • Chapter 3: Multivariate pattern recognition by machine learning methods
  • 1. Introduction
  • 2. Feature extraction
  • 3. Task prediction
  • 3.1. Classic approaches
  • 3.2. Regression
  • 3.3. Classification
  • 3.4. Logistic regression
  • 3.5. SVM
  • 3.6. Random forest
  • 3.7. Deep learning-based models
  • 3.8. Classic neural network
  • 3.9. Convolutional neural network
  • 4. Conclusion
  • 4.1. Advanced topics
  • References
  • Chapter 4: Tuning the apparent thermodynamic parameters of chemical systems
  • 1. Introduction
  • 2. General strategy for tuning the apparent constant (Karimvand, Maeder, & Abdollahi, 2019)
  • 3. The application of proposed strategy in practice
  • 3.1. Case study 1
  • 3.2. Case study 2: Analysis of experimental data (Rasouli, Maeder, & Abdollahi, 2021)
  • References
  • Chapter 5: The analytical/measurement sources of multivariate errors. A case study: Detecting microplastics in sand
  • 1. Introduction
  • 1.1. Adding ``microplastics�� to the dictionary
  • 1.2. Persistent, ubiquitous-And miscounted?
  • 1.3. Hyperspectral imaging as a method for microplastics detection
  • 1.4. Chemometrics
  • 1.5. Principal component analysis
  • 1.6. Classification
  • 1.6.1. SIMCA
  • 1.6.2. PLS-DA
  • 1.6.3. Validation
  • 1.7. Objectives of this book chapter
  • 2. Materials and methods
  • 2.1. Acrylonitrile butadiene styrene (ABS) pellet
  • 2.2. Sample preparation
  • 2.3. Near infrared hyperspectral imaging
  • 2.4. Data analysis and software
  • 3. Results and discussion
  • 3.1. Raman microscopy
  • 3.2. NIR-HSI spectra
  • 3.3. Exploratory chemometric techniques: PCA
  • 3.4. Classification
  • 3.5. SIMCA
  • 3.6. PLS-DA
  • 4. Spectral insights on the problem
  • 5. Future work
  • Acknowledgments
  • References
  • Chapter 6: Autoencoders in generative modeling, feature extraction, regression, and classification
  • 1. What is an autoencoder?

Ejemplares similares