Machine Learning in Farm Animal Behavior Using Python

This book is a comprehensive guide in the fields of machine learning and animal behavior. It explores the use of machine learning algorithms to understand the behavior of farm animals based on activity recognition. It begins with an introduction to fundamental concepts of animal behavior and ethology, establishing a foundation before exploring the importance and types of machine learning, including supervised, unsupervised, semi-supervised, and reinforcement learning.

Readers will gain practical experience through hands-on guidance that covers data collection, preprocessing, exploratory data analysis, feature extraction, model training, and evaluation using Python. The book also looks into the use of various sensors and methods for data collection and annotation, emphasizing the importance of high-quality data. Key machine learning concepts and challenges are addressed, focusing on generalization and data-related issues. Advanced topics include feature selection techniques, model selection, hyperparameter tuning, and deep learning algorithms. Practical examples and Python implementations are provided throughout to aid in the understanding and application of these techniques.

The book is a valuable resource for researchers, students, and professionals interested in applying machine learning to animal behavior analysis, offering insights into both theoretical and practical aspects of the field.

Natasa Kleanthous has a B Sc in Management and Information Systems from University of Nicosia, Nicosia, Cyprus, and a M Sc in Computing and Information Systems from Liverpool John Moores University, Liverpool, UK (2017). She completed her PhD at the Faculty of Engineering and Technology, Liverpool John Moores University, UK (2021). Her research interests include machine learning, embedded machine learning, Internet of Things, Virtual Fencing Systems, signal processing, wearable devices, and computer vision. She is a founder of a newly created tech startup (O&P Electronics and Robotics Limited) that investigates the use of machine learning for animal behavior recognition in combination with a virtual fence system in order to develop a suitable smart device to be used in farm industries in Cyprus.

Abir Hussain is a professor of Image and Signal processing at the University of Sharjah, UAE. She is also a visiting professor at Liverpool John Moores University, UK. She completed her PhD study at The University of Manchester (UMIST), UK in 2000 with a thesis title Polynomial Neural Networks for Image and Signal Processing. She has published numerous referred research papers in conferences and journals covering Neural Networks, Signal Prediction, Telecommunication Fraud Detection and Image Compression. She has worked with higher order and recurrent neural networks and their applications to e-health and medical image compression techniques. She has developed with her research students a number of recurrent neural network architectures. She is a PhD supervisor and an external examiner for research degrees including PhD and MPhil. She is one of the initiators and chairs of the Development in e-Systems Engineering (DeSE) conference series.