UNIQUE SERIES AKTU Syllabus
BCE071

Artificial Intelligence and Machine Learning in Civil Engineering

L-T-P3-0-0 Credits3 Session2025-26 TypeTheory
Appears in 1 semester

B.Tech Civil Engineering · Sem 7 (Departmental Elective-IV)

Download PDF

Syllabus

5 units · 40 lecture hours
Unit1

Unit 1: Foundations of Al and ML in Civil Engineering

8 hrs
  • Introduction to Artificial Intelligence and Machine Learning
  • Differences and relationships: Al, ML, Deep Learning
  • Supervised, Unsupervised, and Reinforcement Learning
  • Applications of Al/ML in Civil Engineering: planning, risk prediction, BIM
  • Tools Overview: Python, Jupyter, Pandas, Scikit-learn
Unit2

Unit 2: Regression and Classification Models

8 hrs
  • Regression: Linear, Polynomial, Ridge, Lasso
  • Classification: Decision Tree, Random Forest, SVM
  • Evaluation Metrics: MAE, RMSE, R?, Accuracy, Precision, Recall
  • Overfitting, Cross-validation, Regularization
Unit3

Unit 3: Al-Based Optimization Tools in Civil Engineering

8 hrs
  • Optimization in design: problem formulation and motivation
  • Basics of Neural Networks (NN): input-output structure, practical use
  • Basics of Genetic Algorithms (GA): natural selection and evolution in design
  • Case studies: concrete strength prediction, foundation cost optimization
  • Visual tools: Teachable Machine, Excel GA demos, Python examples
Unit4

Unit 4: Construction and Infrastructure Applications

8 hrs
  • ML for project delay and cost prediction
  • Al for construction planning and resource optimization
  • Sensor-based infrastructure health monitoring
  • Case Studies: traffic flow forecasting, bridge safety prediction
Unit5

Unit 5: Interpretation, Deployment & Ethics

8 hrs
  • ~=SHAP, LIME, and PDP: Model interpretation and visualization
  • Simple deployment with Streamlit/Flask (conceptual overview only)
  • Ethics in Al/ML: bias, transparency, fairness, and privacy
  • Emerging trends: Al + FEM integration, Digital Twins in infrastructure
Course Objectives2 points
  • To introduce Al and ML concepts and tools for analysing and solving civil engineering problems.
  • To apply ML techniques on real-world data in areas like construction, SHM, and traffic.
Course Outcomes (COs)5 outcomes

After completion of the course student will be able to:

  1. CO1_ Define basic Al and ML concepts in civil engineering.K1, K2
  2. CO2Understand ML models and learn to apply on civil engineering datasets.K2, K3
  3. CO3Analyze model performance using standard evaluation metrics.K3, K4
  4. CO4Interpret results for engineering decision-making in real world scenario.K3, K4
  5. CO5Use Al/ML tools to solve simple civil engineering problems.K3

Suggested Reading

  1. & Resources:
  2. Machine Learning Applications in Civil Engineering — R. Mohan & V. Ravi, Notion Press
  3. Internet of Things and Machine Learning — Dr. A, Suganthi, Charulatha Publications
  4. Neural Networks, Fuzzy Logic, and Genetic Algorithms — S. Rajasekaran & G.A. Vijayalakshmi Pai, PHI
  5. Big Data and Al in Smart Construction — John Soldatos, Edward Curry & Manfred Hauswirth, River Publishers
  6. Alin Construction Management — Jay Yang & Simaan AbouRizk, Springer
  7. Artificial Intelligence in Structural Engineering — Feng Chen & Baoming Sun, Springer
  8. \IT Bombay — FOSSEE Project (Free Python ML tutorials and case studies); https://fossee.in

Official AKTU syllabus

This subject is on page 6 of the original AKTU PDF.

Official AKTU syllabus PDF ↗