Orchid Project

Orchid Blog

Tracking mosquitoes with sound and statistics

Created on 3 October 2014, 17:00, by Tom Nickson

Malaria and Dengue Fever, spread by mosquitos, are a big public health issue in developing countries. If we could detect mosquitos and classify their species, governments and NGOs would be able to more effectively target eradication and treatment resources. Additionally, the technology could be incorporated into smoke alarm style appliances for the home that released […]

pyIBCC and Friends

Created on 3 October 2014, 17:00, by Edwin Simpson

New Software Packages for Experimenting with IBCC   I would like to highlight some new software packages being developed within ORCHID that will allow you test out various IBCC variants with new datasets. IBCC — or Independent Bayesian Classifier Combination, to use the full name — is a method for aggregating categorical labels from different […]

New Python package for ProvStore

Created on 25 July 2014, 15:08, by T. Dong Huynh

Sam Millar, an Orchid intern, recently released an open-source Python package provstore-api which greatly facilitates storing and retrieving provenance documents on ProvStore. The packaged is registered on PyPi (hence can be quickly installed with easy_install or pip) and comes with full API documentation. If you’re working with provenance in Python, do check out his tutorial.   Notes: ProvStore is […]

Provenance in the Wild: Provenance at The Gazette

Created on 23 July 2014, 07:42, by admin

Today, following my post on Provenance in the 2014 National Climate Assessment, I continue to blog about applications making use of PROV. The Gazette is the UK’s official public record since 1665, The Gazette has a long and established history and has been at the heart of British public life for almost 350 years (see […]

New Concentration Bounds and Their Application in Finite-Time Analysis of Bayesian Online Algorithms

Created on 22 July 2014, 19:28, by Long Tran-Thanh

Bayesian learning is a widely used class of techniques in the online machine learning community, especially in large scale domains, due to its conceptional simplicity and philosophical intuitions. In particular, it expresses the expert knowledge and the current belief of the world through the choice of a prior  distribution, which is then subsequently updated and refined by (future) observations. […]

Azure ML: Machine learning in the cloud

Created on 14 July 2014, 23:18, by Matteo Venanzi

Azure ML is the new cloud-based service that implements a number of state of the art machine learning algorithms available for commercial and research software development. Azure ML is the container of a variety of professionally developed powerful machine learning modules (including Recommender system, Bayes Point Machine Classifier, and Decision Forests/Jungles modules, and many more hopefully soon). This service […]

Provenance in the Wild: the 2014 National Climate Assessment

Created on 11 July 2014, 11:57, by admin

A year after the publication of PROV recommendations by the W3C provenance working group, it is nice to see the deployment of applications making use of PROV. In this blog, I talk about the 2014 National Climate Assessment report. A quick reminder of what I mean by provenance: Provenance is a record that describes the people, institutions, entities, […]

Veri.ly Crowdsourcing Challenge this weekend

Created on 8 July 2014, 11:14, by Victor Naroditskiy

We are developing a platform for gathering evidence during natural disasters. The platform poses questions such as “Has the Brooklyn Bridge been damaged by Hurricane Sandy?” The users are asked to submit evidence to answer the question as well as to evaluate previously submitted evidence. This weekend we are running a challenge to test feasibility of […]

« Previous Page  |  Next Page »

Highlighted Publications

Browse Publications »

Disaster response

We are developing systems that allow first responders, unmanned ground and aerial vehicles, and software agents to work effectively together.

Learn more about Disaster response »

Smart Grid

We are developing novel algorithms and interfaces to optimise energy consumption and coordinate consumers and producers in the smart grid.

Learn more about Smart Grid »

Citizen Science

We are developing approaches that make full use of the skills, preferences and capabilities of citizen scientists.

Learn more about Citizen Science »