Doesn't suit? No problem! You can return items for up to 30 days
You won't go wrong with a gift voucher. The gift recipient can choose anything from our offer.
Up to 30 days for returns
This open access book provides a thorough examination of advanced network-based data analysis approaches, with a focus on Network-Based Dimensionality Reduction and Analysis (NDA) and Generalized Network-Based Dimensionality Reduction and Analysis (GNDA). Covering both theoretical and practical aspects, it describes how to use these cutting-edge techniques to extract underlying variables and uncover hidden patterns within complex data structures.
These non-parametric network-based approaches do not rely on data distribution assumptions, giving them a considerable advantage over existing dimensionality reduction and clustering methods. NDA and GNDA are robust and scalable, and are able to handle datasets of varying sizes and complexities. They excel at managing nonlinear relationships in data, increasing representation accuracy. Furthermore, they improve interpretability by making data easier to see and understand using geometric representations. Highly flexible and adaptable, NDA and GNDA use automated feature selection processes to reliably estimate latent variables and expand the types of similarity measures that can be used. They also present community-based modularity identification, which enables a more thorough examination of high-dimensional datasets.
Including numerous real-world examples, and implemented codes in R and MATLAB, the book will be an invaluable resource for researchers, software developers and practitioners looking to use network-based techniques for advanced data analysis and dimensionality reduction.
Hi! I'm Libroamiko, your book advisor.
How can I help you?