Inducing Vascular Grammars for Anomaly Classification in Brain Angiograms

As machine learning is used to make strides in med- ical diagnostics, few methods provide heuristics from which human doctors can learn directly. This work introduces a method for leveraging human observable structures, such as macro scale vascular formations, for producing assessments of medical conditions with rela- tively few training cases, and uncovering patterns that are potential diagnostic aids. The approach draws on shape grammars, a rule-based technique, pioneered in design and architecture, and accelerated through a re- cursive sub-graph mining algorithm. The distribution of rule instances in the data from which they are in- duced is then used as an intermediary representation en- abling common classification and anomaly detection ap- proaches to identify indicative rules with relatively small data sets. The method is applied to 7 Tesla time-of- flight (TOF) angiography MRI (n = 54) of human brain vasculature. The data were segmented and induced to generate representative grammar rules. Ensembles of rules were isolated to implicate vascular conditions reli- ably. This application demonstrates the power of auto- mated structured intermediary representations for as- sessing nuanced biological form relationships, and the strength of shape grammars, in particular for identify- ing indicative patterns in complex vascular networks.

Spatial Thinking as a Path Towards Computational Thinking

Considering what we know about computational thinking, how much of this cognitive domain hangs on one's ability to think spatially? Is spatial thinking a hidden foundational property for developing strong computational thinking skills? If coding is the new literacy for 21st century thinking, educators must diversify their methodology of instruction. Mathematics must not be the only pathway to computational thinking, computer science, and coding. This book chapter opens up new insight into spatial reasoning, showing it as a new viable method to give students the computational thinking skills necessary to thrive in STEM fields. Finally, this chapter presents concepts found in shape grammars as a methodology used to teach students how to approach art and design computationally. With shape, grammars we find computational thinking at the center of creative activities.

Decoding and recoding informal settlements in a design studio: an overview of the world studio project

The world is experiencing a surge in its urban population accompanied by rapidly advancing urbanization processes. Contemporary cities are witnessing the rise of numerous urban and social problems, leading, in turn, to the emergence of informal settlements. In response, computational and parametric resources are increasingly being adopted to create innovative and effective approaches to urban planning and design. These resources can be used in informal settlements to improve urban quality without losing their essential features. This paper describes the World Studio, a teaching experience that began in 2017 and continues in the present day, in which undergraduate architecture and landscape architecture students learn how to use shape grammars and parametric tools to design for informal settlements in international contexts (Rio de Janeiro, Brazil, and Ahmedabad, India, to date).

SHAPE GRAMMAR LIBRARIES OF EUROPEAN CLASSICAL ARCHITECTURAL ELEMENTS FOR HISTORIC BIM

This paper proposes a design for libraries of European Classical architectural elements based on shape grammars. This design is based on a workflow which develops library objects from 3D CAD primitives using architectural rules to construct parametric representations of architectural elements. In the case of Classical architecture, the design and detail for the parametric objects are based on manuscripts ranging from Vitruvius to Palladio to the architectural pattern books of the eighteenth century. The generation of 3D objects for virtual reconstruction necessitates the application of computer algorithms and rules introduced by the user to generate objects, buildings and spaces from a grammar and vocabulary of shapes. Both the use of graphicly constructed and coded parametric libraries in formal and open-source platforms will be considered here.

CAPTURING MATHEMATICAL AND HUMAN PERCEPTIONS OF SHAPE AND FORM THROUGH MACHINE LEARNING

Classifying shape and form is a core feature of Engineering Design and one that we do this instinctively on a daily basis. Matching similar components to then reduce unique component counts, determining whether a competitors design infringes on copyright and receiving market feedback on product styling are all examples where shape and form comes into play. However, shape and form can be perceived in different ways from purely mathematical (e.g. shape grammars) to wholly subjective (e.g. market feedback) and these perceptions may not entirely agree.This paper examines the mathematical and human perceptions of shape and form through a study of classifying shapes that have been interpolated between one another, and in doing so, highlights the disparity in perceptions. Following this, the paper demonstrates how the emergent field of Machine Learning can be applied to capture mathematical and human perceptions of shape and form resulting in a means to twin this feedback into product development.