Abstract
This chapter presents the first stage of the procedural modelling methodology addressed in this book, which is capable of generating domus—ancient roman houses—considering rectangular constraint shapes, through the combination of an ontological schema—extended to support some elements of the roman architecture—and a treemap-based procedural modelling process, that is responsible for creating the geometry according to the rules that define the buildings. © The Author(s) 2016.

Abstract
Most of the existing procedural modelling solutions still lacks from support to the generation of virtual buildings with both exteriors and interiors composed by arbitrary shapes. To address this issue, a new procedural modelling methodology is presented in this book, one that produces virtual models of buildings, including exteriors outlined by arbitrary shapes and interiors formed by convex polygons. Regarding this specific chapter, some relevant subjects that define the boundaries of this book are introduced along with the motivation and goals that lie at the basis of the new methodology. Afterwards, a list of main contributions and assumptions are presented, shortly before book organization section. © The Author(s) 2016.

Abstract
This chapter consists of a literature review regarding the use of ontologies on virtual environments and the procedural modelling solutions that have been proposed with focus in two approaches: (1) the production of virtual hollow buildings, uniquely composed by outer facades; and (2) the production of virtual traversable buildings, with interior divisions included. The integration of ontologies and semantics in procedural modelling is also addressed in each one of the referred approaches. © The Author(s) 2016.

Abstract
The evaluation of the presented procedural modelling methodology will be addressed in this chapter. Thus, a set of tests made to demonstrate the capabilities of this methodology in producing buildings compliant with a real subset of architectural rules (RGEU [1]) and others with distinct formats and different architectonic structures will be presented. Moreover, the effectiveness of the treemap approach in subdividing random layouts is shown, along with a generic stochastic process for automatic building generation and also some computational performance measurements that point out to the methodology expeditiousness. © The Author(s) 2016.

Abstract
This chapter provides an overview of the procedural modelling methodology that is addressed in this book. With the purpose of pointing out its need, the current issues in Procedural Modelling will be highlighted. In addition, the justification of some strategic decisions made during the development activities will be presented along with a brief enlightenment of the aforementioned methodology. © The Author(s) 2016.

Abstract
In agricultural applications hyperspectral imaging is used in cases where differences in spectral reflectance of the examined objects are small. However, the large amount of data generated by hyperspectral sensors requires advance processing methods. Machine learning approaches may play an important role in this task. They are known for decades, but they need high volume of data to compute accurate results. Until recently, the availability of hyperspectral data was a big drawback. It was first used in satellites, later in manned aircrafts and data availability from those platforms was limited because of logistics complexity and high price. Nowadays, hyperspectral sensors are available for unmanned aerial vehicles, which enabled to reach a high volume of data, thus overcoming these issues. This way, the aim of this paper is to present the status of the usage of machine learning approaches in the hyperspectral data processing, with a focus on agriculture applications. Nevertheless, there are not many studies available applying machine learning approach to hyperspectral data for agricultural applications. This apparent limitation was in fact the inspiration for making this survey. Preliminary results using UAV-based data are presented, showing the suitability of machine learning techniques in remote sensed data. © 2018 Association for Computing Machinery.