The MLPMEA 2017 special session provides an excellent international forum for sharing
knowledge and results in theory, methodology and applications of Machine Learning for
developing predictive models for different engineering applications. Machine Learning
models are efficient for handing complex prediction models due to their outstanding
performance in handling large scale datasets with uniform characteristics and noisy data.
Examples of MLPMEA 2017 topics of interest include building predictive models using
Machine Learning to solve specific engineering problems such as regression and
classification problems.
The aim of this work is to obtain a good perspective into the current state of practice of
Machine Learning to address various predictive problems. Some topics relevant to this
session include, but are not limited to:
 Biomedical image analysis/processing
 Clustering
 Decision Support
 Support Vector Machine
 Time Series
 Decision Trees
 Fuzzy Logic & Systems
 Probabilistic Reasoning
 Lazy Learning
 Classification
 Recommender Systems
 Expert Systems
 Artificial Neural Networks
 Evolutionary Algorithms
 Ranking Algorithms
 Cognitive Processes
 Evolutionary Computing
 Swarm Intelligence
 Artificial Immune Systems
 Markov Model
 Chaos Theory
 Multi-Valued Logic
 Ensemble Techniques
 Hybrid Intelligent Models
 Reasoning Models
Applied to
 Nuclear Engineering
 Sustainable and Renewable Energy
 Software Engineering
 Biomedical Engineering
 Mechanical Engineering
 Civil Engineering
 Electrical Engineering
 Computer Engineering
 Chemical Engineering
 Industrial Engineering
 Environmental Engineering
Papers should be submitted for this special session at the regular paper submission website
(http://www.icmla-conference.org/icmla17/). Papers should not exceed a maximum of 6 pages
(including abstract, body, tables, figures, and references), and should be submitted as a pdf in
2-column IEEE format. Detailed instructions for submitting the papers are provided on the
conference at home page.