Behavior Analysis with Machine Learning Using R

Behavior Analysis with Machine Learning Using R provides a practical guide to solving behavior analysis problems using machine learning and deep learning concepts and algorithms. It covers data exploration, visualization, preprocessing, data representation, model training and evaluation, and demonstrates applications in behavior analysis tasks. No prior knowledge in machine learning is assumed, and basic experience with R and statistics is beneficial.

Format: Hardback
Length: 400 pages
Publication date: 26 November 2021
Publisher: Taylor & Francis Ltd

Behavior Analysis with Machine Learning Using R is a comprehensive guide that delves into the realm of machine learning and deep learning, applying these concepts and algorithms to a wide range of behavior analysis problems. It emphasizes the practical aspects of solving these problems by utilizing data collected from sensors or stored in electronic records. The included examples showcase various data analysis tasks, including data exploration, visualization, preprocessing, data representation, model training, and evaluation, all conducted using the R programming language and real-life behavioral data.

While the examples primarily focus on behavior analysis applications, the underlying concepts and methods covered in the book have broader applications across different domains. No prior knowledge in machine learning is assumed, although a basic understanding of R and basic knowledge in statistics and high school-level mathematics are beneficial.

The book offers a wealth of features, enabling readers to build supervised machine learning models to predict indoor locations based on WiFi signals, recognize physical activities from smartphone sensors and 3D skeleton data, detect hand gestures from accelerometer signals, and more. It also provides the ability to program one's own ensemble learning methods and utilize Multi-View Stacking to fuse signals from heterogeneous data sources. Unsupervised learning algorithms are employed to discover criminal behavioral patterns, while deep learning neural networks with TensorFlow and Keras are used to classify muscle activity from electromyography signals and detect smiles in images.

Furthermore, the book enables readers to evaluate the performance of their models in traditional and multi-user settings, as well as build anomaly detection models such as Isolation Forests and autoencoders to detect abnormal fish behaviors. This book is designed for undergraduate/graduate students, researchers, and practitioners interested in leveraging machine learning and deep learning to address behavior analysis challenges.

Weight: 850g
Dimension: 161 x 241 x 28 (mm)
ISBN-13: 9781032067049