Haitao Zhao – författare

This book covers the essential concepts and strategies within traditional and cutting-edge feature learning methods thru both theoretical analysis and case studies. Good features give good models and it is usually not classifiers but features that determine the effectiveness of a model. In this book, readers can find not only traditional feature learning methods, such as principal component analysis, linear discriminant analysis, and geometrical-structure-based methods, but also advanced feature learning methods, such as sparse learning, low-rank decomposition, tensor-based feature extraction, and deep-learning-based feature learning. Each feature learning method has its own dedicated chapter that explains how it is theoretically derived and shows how it is implemented for real-world applications. Detailed illustrated figures are included for better understanding. This book can be used by students, researchers, and engineers looking for a reference guide for popular methods of feature learning and machine intelligence.

This book describes the reliability research results and experience of BeiDou navigation satellite in engineering development. According to the characteristics of high reliability and high availability, this book discusses the reliability requirements, reliability design, reliability modeling, and reliability analysis of navigation satellite and constellation, focusing on the demonstration and decomposition of reliability requirements, constellation availability design, satellite availability design, and availability analysis. Based on the characteristics of batch production of navigation satellites, the particularity of reliability work is analyzed, and the reliability assurance works during batch production such as process reliability, data consistency comparison, storage reliability, and redundant satellite demonstration are introduced.