PURR Registry

The manuscript presents a non-parametric Bayesian algorithm called ASPIRE (Anomalous Sample Phenotype Identification with Random Effects) able to identify phenotypic differences across batches of cytometry samples in the presence of random effects

AML Bayesian Biomedical Engineering BMC Bioinformatics Computer Science cytometry Dirichlet process Gaussian mixture model Interdisciplinary Research Life Sciences random effects

RP1D (Clustering Method Using 1D Random Projections)

10.4231/R74F1NN4

Mireille Boutin , Sangchun Han

11/12/2014

The source code of RP1D (Clustering Method Using 1D Random Projections).

Clustering Computer Science Electrical and Computer Engineering Random Projection Source Code

Task analysis cases and results for Ex Libris Primo at Purdue University Libraries

10.4231/R7CZ3538

Marlen Promann , Tao Zhang

11/06/2014

These figures represent the task analysis results of different use cases of Ex Libris Primo implemented at Purdue University Libraries, depending on the availability and format of the resource being searched by the user.

Computer Science Library Science Library Website Primo Task Analysis

Link Pivot Algorithm for Offset Optimization

10.4231/R7GQ6VPT

Christopher Day , Darcy M. Bullock

11/20/2014

This animation illustrates the use of the Link Pivot algorithm for optimizing offsets on a signalized arterial.

Civil Engineering Computer Science optimization traffic engineering traffic signal timing traffic signals

Graph of Flickr Photo-Sharing Social Network Crawled in May 2006

10.4231/D39P2W550

David F Gleich

02/22/2012

Crawl of the Flickr photo-sharing social network from May 2006 returning a graph with 820,878 nodes and 9,837,214 edges. Dataset is distributed as a SMAT file with README file with code to read file in Python and MATLAB.

Communication Computer Science

Controlling the cost and increasing the utility of network measurement infrastructures

10.4231/D3TH8BM5D

Ethan L Blanton

09/13/2012

Dissertation on the cost and utility of network measurement infrastructures, including mechanisms for admission control, identifying measurement patterns that will benefit from inference, and selecting vantage points for wide-scale measurement.

Computer Science Inference Internet

Simplicity of K-means versus deepness of Deep Learning. A Case of Unsupervised Feature Learning with Limited Data

10.4231/R7N58J9Z

Baichuan Zhang , Bartlomiej P. Rajwa , Murat Dundar , Qiang Kou , Yicheng He

10/01/2015

A study contrasting K-means-based unsupervised feature learning and deep learning techniques for small data sets with limited intra- as well as inter-class diversity

bacterial colonies BARDOT Biomedical Engineering Computer Science deep learning Elastic light scattering Interdisciplinary Research K-Means Clustering Life Sciences Machine Learning representation learning