Behavior Analysis with Machine Learning and R: Book Intro

This is the video intro for the book "Behavior Analysis with Machine Learning and R: A Sensors and Data Driven Approach" by Enrique Garcia Ceja.

Learn how to leverage the power of machine learning to analyze behavioral patterns from sensors data and electronic records. This book shows you how to explore, preprocess, encode, and visualize behavioral data. Learn how to train supervised and unsupervised learning models in R and evaluate them in multi-user settings.

Table of contents:

1. Introduction
1.1 What is Machine Learning?
1.2 Types of Machine Learning
1.3 Terminology
1.3.1 Tables
1.3.2 Variable Types
1.3.3 Predictive Models
1.4 Data Analysis Pipeline
1.5 Evaluating Predictive Models
1.6 Simple Classification Example
1.6.1 K-fold Cross-Validation Example
1.7 Simple Regression Example
1.8 Underfitting and Overfitting
1.9 Bias and Variance
2. Predicting Behavior with Classification Models
2.1 k-nearest Neighbors
2.1.1 Indoor Location with Wi-Fi Signals
2.2 Performance Metrics
2.2.1 Confusion Matrix
2.3 Decision Trees
2.3.1 Activity Recognition with Smartphones
2.4 Naive Bayes
2.4.1 Activity Recognition with Naive Bayes
2.5 Dynamic Time Warping
2.5.1 Hand Gesture Recognition
2.6 Dummy Models
2.6.1 Most-frequent-class Classifier
2.6.2 Uniform Classifier
2.6.3 Frequecy-based Classifier
2.6.4 Other Dummy Classifiers
3. Predicting Behavior with Ensemble Learning
3.1 Bagging
3.1.1 Activity recognition with Bagging
3.2 Random Forest
3.3 Stacked Generalization
3.4 Multi-view Stacking for Home Tasks Recognition
4. Exploring and Visualizing Behavioral Data
4.1 Talking with Field Experts
4.2 Summary Statistics
4.3 Class Distributions
4.4 User-Class Sparsity Matrix
4.5 Boxplots
4.6 Correlation Plots
4.6.1 Interactive Correlation Plots
4.7 Timeseries
4.7.1 Interactive Timeseries
4.8 Multidimensional Scaling (MDS)
4.9 Heatmaps
4.10 Automated EDA
5. Preprocessing Behavioral Data
5.1 Missing Values
5.1.1 Imputation
5.2 Smoothing
5.3 Normalization
5.4 Imbalanced Classes
5.4.1 Random Oversampling
5.4.2 SMOTE
5.5 Information Injection
5.6 One-hot Encoding
6. Discovering Behaviors with Unsupervised Learning
6.1 K-means Clustering
6.1.1 Grouping Student Responses
6.2 The Silhouette Index
6.3 Mining Association Rules
6.3.1 Finding Rules for Criminal Behavior
7. Encoding Behavioral Data
7.1 Feature Vectors
7.2 Timeseries
7.3 Transactions
7.4 Images
7.5 Recurrence Plots
7.5.1 Computing Recurence Plots
7.5.2 Recurrence Plots of Hand Gestures
7.6 Bag-of-Words
7.6.1 BoW for Complex Activities
7.7 Graphs
7.7.1 Complex Activities as Graphs
8. Predicting Behavior with Deep Learning
8.1 Introduction to Artificial Neural Networks
8.1.1 Sigmoid and ReLU Units
8.1.2 Assembling Units into Layers
8.1.3 Deep Neural Networks
8.1.4 Learning the Parameters
8.1.5 Parameter Learning Example in R
8.1.6 Stochastic Gradient Descent
8.2 Keras and TensorFlow with R
8.2.1 Keras Example
8.3 Classification with Neural Networks
8.3.1 Classification of Electromyography Signals
8.4 Overfitting
8.4.1 Early Stopping
8.4.2 Dropout
8.5 Fine-Tuning a Neural Network
8.6 Convolutional Neural Networks
8.6.1 Convolutions
8.6.2 Pooling Operations
8.7 CNNs with Keras
8.7.1 Example 1
8.7.2 Example 2
8.8 Smiles Detection with a CNN
9. Multi-User Validation
9.1 Mixed Models
9.1.1 Skeleton Action Recognition with Mixed Models
9.2 User-Independent Models
9.3 User-Dependent Models
9.4 User-Adaptive Models
9.4.1 Transfer Learning
9.4.2 A User-Adaptive Model for Activity Recognition
10. Pending Title
Appendix A: Setup your Environment
Appendix B: Datasets

#machinelearning #R #dataanalysis #deeplearning