Contests in Signal Processing and Machine Learning

During the last couple of months a few new Signal Processing and Machine Learning contests were initiated. Some of the ongoing ones with a strong relation to Signal Processing include:

From the domain of public health, there is a Kaggle contest asking to predict whether or not West Nile virus is present, for a given time and location in the area of Chigago. The predictor variables include aspects of weather, geography, and maps of areas that were sprayed to kill mosquitos. A more accurate method of predicting outbreaks of West Nile virus in mosquitos will help the City of Chicago and CPHD more efficiently and effectively allocate resources towards preventing transmission of this potentially deadly virus.

Again from the health domain, a different Kaggle contest focuses on creating an automated detection system for Diabetic Retinopathy – ideally resulting in models with realistic clinical potential. The input to the contest is color photographs, in some of which lesions associated with the vascular abnormalities caused by the disease are present (these lesions are what trained clinicians are also searching in standard manual examination). Diabetic retinopathy is the leading cause of blindness in the working-age population of the developed world. It is estimated to affect over 93 million people and an automated early detection system can help providing timely treatment, thus slowing or averting the disease.