The following code bases and data sets have produced either fully or in part with funding from The ISTC for Pervasive Computing. All have been released under an open source license and each release below should contain the specifics of their license.
The Graphical Models Toolkit 1.0 (GMTK) – The Graphical Models Toolkit (GMTK) is an open source, publicly available toolkit for rapidly prototyping statistical models using dynamic graphical models (DGMs) and dynamic Bayesian networks (DBNs). GMTK can be used for applications and research in speech and language processing, bioinformatics, activity recognition, and any time series application.
Ohmage – Ohmage is an open-source participatory sensing platform. It supports project authoring; mobile phone-based data capture through inquiry-based surveys and automated data capture as well as temporally and spatially triggered reminders, data visualization and real-time feedback. (Supports IOS and Android)
Multipath Hierarchical Matching Pursuit (HMP) software package The HMP toolkit achieves state-of-the-art results on many types of machine-learning recognition tasks via flexible feature learning. This package contains Matlab code with key components coded in C++ for speed. It also contains demo data sets.
Sparse code based contour detection (zip file) – This code archive contains training code for computing sparse-code contour gradients in natural images. Tested on Ubuntu 12.04 64-bit and released under the BSD license.
The RGB-D Object Dataset – The RGB-D Object Dataset is a large dataset of 300 common household objects. The objects are organized into 51 categories arranged using WordNet hypernym-hyponym relationships. Each object was recorded using a Kinect style 3D camera that records synchronized and aligned 640×480 RGB and depth images at 30 Hz.
SensorSift – SensorSift works to find a balance between user privacy and functionality in sensor-driven applications. SensorSift is a principled framework for computing transformations (called sifts) of raw [sensor] data to enable a simultaneous balance between user’s privacy choices and applications data requests. The mathematical algorithm for generating sifts is described in a ACSAC ’12 paper. Sample data and the source code are available under the BSD license.