Abstract:
Big Data gained importance, as many organizations have been collecting massive amounts of domain-specific information, i.e., in cybersecurity, medicine, forecasting, etc.
Analyzing and extracting the high-level complex information contained in the data belonging to these particular domains need more sophisticated algorithms. The new emerging DNN techniques and the evolutionary computing-based approaches, can work also with little knowledge of the domain and also handle massive amounts of data in an incremental way.
In addition, the ensemble paradigm permits handling the problem of unbalanced classes, captures better non-linear correlation in the data, works well with changing data streams and are robust to noise and missing data.
In this talk, we first introduce the paradigm of the ensemble and some relevant strategies for their combining function; then, we explore how ensembles of Deep Learning and evolutionary algorithms can be exploited for addressing some important problems in Big Data Analytics, varying from the detection of attacks in modern intrusion detection systems to the real-time rainfall estimation for the prevention of disasters.
Bio:
Gianluigi Folino holds a Ph.D. in Physics, Mathematics and Computer Science. Since 2001, he works as a senior researcher at ICAR-CNR (the Institute of High Performance Computing and Networking of the Italian National Research Council).
He is also a lecturer at the University of Calabria. His research interests focus on applications of distributed computing in the area of data mining, bio-inspired algorithms, big data, bioinformatics and cybersecurity.
He was visiting researcher at University of Nottingham (United Kingdom), at Radbound University, Nijmegen (Netherlands) and at University of California (UCLA). He is in the Editorial Board of Applied Soft Computing, Elsevier and published more than 100 papers in international conferences and journals among which IEEE Transactions on Evolutionary Computation, IEEE Transactions on Knowledge and Data Engineering, Parallel Computing, Information Sciences and Bioinformatics.