Spatial Datasets 

 

UCLA IDEAS Technology Studio Seminar Winter 2019

Research Lead: Guvenc Ozel 

Instructors: Benjamin Ennemoser, Gabby Shawcross

Technologies: gaming engines, XR, digital fabrication, projection mapping

Students: Christina Charalampaki, Pratina Chadha, Bohan Cheng, Ruiyang Cheng, Kevin Clark, Haocheng Dai, Yutong Dai, Yue Di, Rui Ding, Lu Geng, Jorge Gutierrez, Vigil Escalera, Hoodeen Hakimian, Ying Huang, So Hyun Kim, Zhou Le, Luo Lei, Yunqi Lei, Zhengtao Liu, Qingyun Lu, Sanjeet Sanjay Mukadam, Narisu Narisu, Nidhi Parsana, Kshama Swamy, Hanshuang Tong, Yiliang Wang, Kan Yen Wu, Xuanyi Xu, Ce Yan, Yixuan Ye, Yicheng Zhao, Yiran Zhou\

This Technical Seminar explores the tools, techniques and technologies associated with the design and experience of tangible and immersive interactive visualizations of large sets of data. Architectural design thinking is combined with interaction design, gaming and machine learning processes to classify, organize, navigate and access large data sets in compelling spatial visualizations experienced through augmented, virtual and mixed reality environments. Through machine learning, we investigate how to embed highdimensional data sets and reorganize them in 3-dimensional space. Students use machine learning algorithms such as T-distributed Stochastic Neighbor Embedding (t-SNE) and Principal component analysis (PCA) to visualize and spatialize big data sets, embed multidimensional information such as images, labels and numerical sets into x,y,z coordinates. The t-SNE machine learning vectorizes discrete elements and establishes spatial relationships with relative adjacencies. Connections between data points and clusters of information create new spatial configurations and a skeletal frame work for modeling tangible objects, surfaces and spaces. Different formal and aesthetic strategies for the representation of these data constructs are explored through three- imensional and four-dimensional modeling techniques, and then tested through working interactive VR and AR environments. Intuitive interactive representations will allow a user to browse and navigate information in the data set as a spatial sculpture at both object scale and room scale.