A Machine Learning Approach to Modeling Small Vessel Performance
This research introduces an LSTM based method for predicting fuel usage aboard small fishing vessels.
Research Publications.
Maplet: Integrating Distributed Data Signal Mappings for Performative Interactions Within the Eurorack Modular Synthesizer Ecosystem
This research introduces a prototype Eurorack module that brings the libmapper ecosystem to modular synthesizers.
Extending Networked Mapping Research Middleware into the Browser Sandbox
This research introduces how to integrate the Libmapper system into the browser while getting around sandbox restrictions via websockets.
Creating Latent Representations of Synthesizer Patches using Variational Autoencoders
This research introduces two ways of representing synthesizer patches using the latent space of a Variational Autoencoder.
FAUSTMapper: Facilitating Complex Mappings for Smart Musical Instruments
FAUSTMapper is a lightweight binding between arbitrary FAUST-based audio projects and the mapping middleware, libmapper.
Supporting Spatial Thinking in Augmented Reality Narrative: A Field Study
This work is an evaluation of the StoryCreatAR tool kit with real authors, real narratives, and results from deploying that narrative as a public installation.
MoveBox: Democratizing MoCap for the Microsoft Rocketbox Avatar Library
MoveBox looks at using Azure Kinect / Kinect 2 to handle Motion Capture for the RocketBox library of virtual avatars. This project was led by Microsoft Research and I was pleased to collaborate with the EPIC group.
Story CreatAR: a Toolkit for Spatially-Adaptive Augmented Reality Storytelling
Story CreatAR is a tool that helps authors write immersive narratives for virtual reality.
Using Space Syntax to Enable Walkable AR Experiences
This research demonstrates how Space Syntax can be used to create walkable AR experiences in any building or location.
Capture and Recognition of Bead Weaving Activities using Hand Skeletal Data and an LSTM Deep Neural Network
This project, lead by Rowland Goddy-Worlu, focused on using recurrent ML architectures (LSTM based) for classifying hand-gestures associated with bead-weaving.