Course

Unit 1

Introduction of Machine Learning (ML), Historical context, Necessities, ML in modern civil engineering, Real-world application examples. Recapitulation of linear regression, Logistic regression, Model evaluation

Unit 2

Adaline, Backpropagation, Neural Networks Learning, Learning rate, Unsupervised Learning, Clustering, Reinforcement Learning, Overview of DL

Applications: Density-based clustering Rainfall-runoff modelling, Soil strength prediction.

Unit 3

Supervised Learning, Decision Tree, Bayes Classifier, Bayesian Networks, k-Nearest Neighbour, Support Vector Machines and Kernel Machines.

Applications: Soil Classification, Gap acceptance characteristics of traffic, Forecasting.

Pre-Requisite(s): Probability & Statistics, Introduction to Computing, Foundation of Data Science

Course Objectives

1. To understand the basics of machine learning and its need for Civil Engineering.
2. To learn the concept of supervised learning, unsupervised learning with reinforcement learning.
3. To be able to apply the techniques to build models for different applications in Civil Engineering.

Course Outcome

CO1: Understanding the basics of machine learning and its real-world applications.

CO2: Understanding the concept of supervised learning, unsupervised learning with reinforcement learning

CO3: Apply the techniques to build models for different applications in Civil Engineering.

CO-PO Mapping

Text Book(s)

Kevin Murphy, Machine Learning: A probablistic perspective, MIT Press, 2012

Trevorhastie, Robert Tibshirani, Jerome Ffriedman, The Elements of Statistical Learning, Springer 2009 (freely available online)

Reference(s)

Murad, Yasmin, Husam, Abu Hajar and Iftikhar Azim, eds. Machine learning applications in Civil Engineering, Vol 16648714.Frontiers Media SA, 2022