BIG DATA COURSE
Applications of techniques and analyzes "Big Data" for railway maintenance.
Technological advances allow for ever greater data collection. The technical challenge is how best to take advantage of the benefits and capitalize on the opportunities presented by Big Data. The application of emerging data techniques in railway maintenance, a two-day professional development course, is focused on data analysis techniques and practical case studies that are directly applicable to professionals working in Railway Engineering.
Instructor: Nii Attoh-Okine
Investment per person: R $ 1,800.00
Way of payment: Via Credit Card online (link to be made available on August 10th).
If you prefer to pay by bank transfer, please send an email to email@example.com
Discounts applicable to students.
Date: October 17 and 18
Duration: 15 hours
Topics covered include:
BASIC CONCEPTS OF DATA ANALYSIS:
Introduction to data
Univariate and multivariate analysis
Correlation and Covariance
TECHNIQUES OF DATA ANALYSIS "BIG DATA" (I):
Supervised / Unsupervised Learning
Support Vector Machines (SVM)
"BIG DATA" (II) DATA ANALYSIS TECHNIQUES:
Multivariate Adaptive Regression Splines (MARS)
"BIG DATA" (IV) DATA ANALYSIS TECHNIQUES:
Metropolis Hastings Algorithm
Markov Chain Monte Carlo Application (MCMC)
CASE STUDIES APPLIED TO RAILWAY
Information and monitoring of geometry and ballast conditions
Condition information for sleepers
Software Implementations - Examples Using R-Software and Ipython
Defects vs. Geometry defect relationships
Geometry Degradation Forecast
Stress failure analysis
Nii Attoh-Okine is a full professor in the Department of Environment and Civil Engineering at the University of Delaware. He received his Master's Degree in Applied Mechanics from the Institute of Civil Engineering in Rostov-on-Don, Russia. He also received a PhD in Civil Engineering and Minor in Statistics from the University of Kansas, United States in 1992. His research line is in computational intelligence and Big Data in systems infrastructure. It has applications of various computational intelligence techniques to the worldwide Rail industry including Bayesian Networks, Belief Functions and Rough Sets. Dr. Okine has publications on uncertainty management, neural networks and tensorial analysis. He has publications in journals such as: Institute of Electrical and Electronics Engineers (IEEE), American Society of Civil Engineers (ASCE), American Railway Engineering and Maintenance of Way Association, and Canadian Journal of Civil Engineering. He has conducted research with the Federal Highway Administration (FHWA), Federal Railway Administration (FRA), National Science Foundation (NSF) and ASCE. He is a member of the ASCE / American Society of Mechanical Engineers (ASME) Journal of Risk and Uncertainty, ASCE Journal of Computing in Civil Engineering and Journal of Civil Engineering and Building Materials. Currently teaches undergraduate and graduate classes in probability and statistics, advanced data analysis and forecasting. He has participated in several assessment boards and guides several students.