TRAINING.

Overview

After participating in the course, you will be able to:

• have an understanding of primary AI techniques,
• have a basic understanding of evaluation methodologies for Civil/Environmental Engineering problems
• have a working knowledge of how to apply AI technologies to real-world datasets,
• have gained experience designing and using AI techniques in Civil/Environmental engineering problems

Description:
Artificial intelligence (AI) techniques and machine learning approaches will revolutionize many aspects of the future Civil/Environmental Engineering field. AI can be a promising tool to tackle different problems, but related aspects of civil/environmental practical cases are a significant concern worldwide. The main focus of this course is to understand and discuss the recent developments in AI applications relating to practical engineering applications.

This course introduces various topics in AI approaches and learning methods in modelling and predicting complex environmental systems. The practical examples are illustrated and will show you how to apply this technique.

Course Outline:

• Data acquisition/Preprocessing
• Classification methods
• Artificial Intelligence (AI) Modeling tools
• Post-processing

Who Should Attend:
Civil and Environmental Engineers • Project Engineers and Managers • Consultants • Designers • Operation and Maintenance personnel • Developers • Planners

All codes are user-friendly and trainees will be able to use them for their cases after this course. No knowledge of programming is required.

Please note: You can check other time zones here.

Syllabus

Data acquisition and preprocessing

• Gathering the data,
• Outliers detection,
• Transferring raw information into usable data,
• Splitting the data into training & testing sets.

Classification methods

• Decision tree, (DT),
• M5 prime (M5’),
• K-nearest neighbour algorithm (KNN).

Post-processing

• Analysis of statistical indices,
• Scatter plot,
• Box plot,

Artificial Intelligence (AI) Modeling tools

• Multilinear regression (MLR)
• Multivariate adaptive regression splines (MARS)
• Multi-layer perceptrons (MLP)
• Adaptive network-based fuzzy inference system (ANFIS),
• Extreme learning machines (ELM)
• Firefly Algorithm and Genetic Algorithm (MLP-FFA & MLP-GA)

Questions and Answers and Feedback to Participants on Achievement of Learning Outcomes

Instructor

Hossein Bonakdari, Ph.D., P.Eng.

Hossein Bonakdari, Department of Soils and Agri‐Food Engineering, Université Laval.

Hossein Bonakdari has worked for several organizations, most recently as a faculty member of the Department of Soil and Agri-Food Engineering Department at Laval University, Quebec. He has supervised several Ph.D. and MSc students with teaching experience of more than 16 years in the field of Artificial Intelligence application in Civil and Environmental Engineering.

His fields of specialization and interest include the practical application of soft computing techniques in engineering problems. Results obtained from his research have been published in more than 180 papers in international journals (h-index=26). He has also had more than 150 presentations at national and international conferences. He published two books.

Dr. Bonakdari is currently leading several research projects in collaboration with industrial partners.