List of Symposium ADPRL CIASG CIBD CICA CICARE CIComms CICS CIDM CIDUE CIEG CIEL CIES CIFEr CIHLI CIMSIVP CIPLS CIR2AT CISDA CISND CIVTS DL EALS FASLIP FOCI IA ICES IntECS ISIC MBEA MCDM RiiSS SDE SIS SNCI Special Sessions

Call for Tutorial Sessions

Instructions for Tutorial Proposals

Proposals for SSCI’16 tutorials should contain the following information:

All tutorials will be 2 hours. Tutorial proposals should be submitted by July 30, 2016 to Nikhil R. Pal (Email: nrpal59@gmail.com, nikhil@isical.ac.in).

Accepted Tutorial Sessions


Medical Applications of Evolutionary Computation

Stephen L. Smith

The University of York, Uk


Abstract: The use of evolutionary computation in medical application is becoming widespread but the nature of the application area does present special challenges, not least of all regarding the acquisition and reliability of data.  The aim of this tutorial is to give a practical guide to applying evolutionary computation to medicine and healthcare, for those new to evolutionary computation and the seasoned practitioner.  Subjects will range from preprocessing of data to how to establish good collaborations with world leading medical centers.  This will be illustrated through consideration of three case examples in detail: the diagnosis of Parkinson's disease, detection of breast cancer from mammograms and using Raman spectroscopy to predict cancer.


Astronomy Data Analysis using Deep Learning and Information Theoretical Learning

Pablo A. Estevez

Department of Electrical Engineering, University of Chile, and Millennium Institute of Astrophysics, Chile


Abstract: Astronomy is facing a paradigm shift caused by the exponential growth of the sample size, data complexity and data generation rates of new sky surveys. To cope with a change of paradigm to data-driven astronomy new computational intelligence, machine learning and statistical approaches are needed. In this tutorial I will present two main applications. The first is to discriminate periodic versus non-periodic light curves, and then estimate the period of the periodic ones. Light curves are one-dimensional time series of the brightness of a star versus time. We have developed several methods based on the correntropy function (generalized correlation using information theoretical learning concepts), which outperforms conventional approaches. Results using 32.8 million light curves will be presented. The second application is the automated real-time transient detection in astronomical images. The aim is to achieve real-time detection of supernovae and other transients with the Dark Energy Camera. A novel transient detection pipeline was developed. We have been applying convolutional neural nets to discriminate between true transients and bogus transients, among other techniques, e.g non-negative matrix factorization combined with random forest. Results using 1.5 million images will be presented. The new pipeline was successfully tested online in February 2015 finding more than 60 supernovae in a few days of telescope observation. We are also developing an extended Kalman filter based on correntropy to preprocess the images discarding unwanted objects such as cosmic rays and asteroids.