A Novel Deep Learning Structure for Detecting Human Activity and Clothing Insulation

Deep learning is a subset of machine learning that allows for more complex problems to be solved in exchange for higher computational cost and algorithm complexity. One of the research fields that take advantage of the tools deep learning provides is computer vision, which is an AI field that enables computers to retrieve valuable data from images, videos, and other visual inputs. Convolutional neural networks (CNN) and recurrent neural networks (RNN) are two of the most powerful and commonly used algorithms for these applications. A CNN is usually used to analyze single images, while an RNN is used to understand how frames relate to one another in a series of images or videos. Therefore, this chapter explores the basics of CNN and RNN, as well as the different architectures of these networks that have been used to solve several computer vision problems, such as human activity recognition and clothing classification. Also, two problems are described that are solved using CNN and RNN: clothing classification and human activity recognition. Furthermore, a case study about thermal comfort is analyzed through the mentioned AI networks. © 2024 selection and editorial matter, Manuel Cebral-Loureda, Elvira G. Rincón-Flores and Gildardo Sanchez-Ante.