Module 4: AI Application in Water Resources Engineering (7 hours) Rainfall Forecasting– Storm water and ground water management –Water quality- Waste managementRecharge ground water Module 5: AI Application in Construction Management (7 hours) AI in Decision-Making - Resources Optimization - Construction cost- Construction budget - Maintenance - Construction Demand- Labour Productivity. Module 6: AI Application in Geotechnical Engineering (7 hours) Bearing capacity-settlement-stability of slopes-different soil properties-Earth retaining structures Text Books: 1. Krishnamoorthy C.S., Rajeev S, “Artificial Intelligence and Expert Systems for Engineers”, CRC Press, 2018 2. Pijush Samui, “Artificial Intelligence in Civil Engineering”, LAP LAMBERT Academic Publishing , 2012 References: 1. Rajesaekaran S, Vijayalakshmi Pai G.A, “Neural Networks, Fuzzy Logic and Genetic Algorithm Synthesis and Applications”, Prentice Hall of India New Delhi 2003 2. Rich E, K Knight, “Artificial Intelligence”, Tata McGraw Hil, 2009. 3. Saroj Kaushik, “Artificial Intelligence”, Cengage Learning. 2011 4. Paresh Chandra Deka, “A Primer on Machine Learning Applications in Civil Engineering”, CRC Press Book, Taylor and Francis Group, 2019 5. Russell, Norvig, “Artificial intelligence, A Modern Approach”, Pearson Education, 2nd edition, 2004 APPLICATIONS OF MACHINE LEARNING AND DEEP L T P C 3 0 0 3 LEARNING IN CIVIL ENGINEERING Course Objectives: 1. To introduce The Students to state-of-the-art methods and modern programming tools for data analysis. 2. To introduce the computer applications in civil engineering 3. To explore various paradigms for knowledge encoding in computer systems. Course Outcome: The Student will be able to 1. illustrate the concepts of machine learning and deep learning 2. understand complexity of machine and deep learning algorithms and their limitations 3. comprehend modern notions in data analysis oriented computing 4. apply common algorithms in practice and implement it 5. perform distributed computations 6. execute experiments in Machine Learning using real-world data. Module 1: Introduction to Machine Learning and Deep Learning (7 hours) Unsupervised and Supervised – Reinforcement – Hybrid models, Crisp and non-crisp – Optimization problems – Examples of unsupervised and supervised learning – Design of construction – Analysis in monitoring construction health. Module 2: Neural Networks (8 hours) Introduction to Neural Networks – Multi-Layer Perceptron; Conventions, restricted non-linearity – Basic Perceptron – Optimisation – Estimating network parameters for a regression problem – flow prediction – Pipeline and discrete optimization – Damage detection in structure – Environmental modelling. Module 3: SVMS (Support Vector MachinE) (7 hours) Introduction –Basic optimization problem: margin maximization – Basic SVM optimization – Kernel trick – Lagrange multipliers - Soft-Margin SVM – SVM in road projects and liquefaction. 19CE2014
CIVIL ENGINEERING (2020)