Course

Unit 1

Overview of Data Science: Definition, Importance, and Applications. Introduction to Automotive Industry: Trends, Challenges, and Opportunities. Role of Data Science in Automotive Applications. Data Sources in Automotive Industry: Sensors, Telematics, IoT. Data Collection Techniques: Real-time vs. Batch Processing. Data Preprocessing: Cleaning, Transformation, and Feature Engineering. Introduction to types of data analytics – descriptive, diagnostic, predictive, prescriptive. Probability Distributions and Hypothesis Testing. Introduction to Machine Learning Algorithms: Supervised vs. Unsupervised Learning.

Unit 2

Regression Techniques: Linear, Polynomial, and Ridge Regression. Classification Methods: Logistic Regression, Decision Trees, Random Forests. Model Evaluation and Validation Techniques. Time Series Data in Automotive Applications – Predictive Maintenance

Unit 3

Principles of Data Visualization. Tools for Data Visualization. Dashboard Design for Automotive Analytics. Introduction to Deep Learning: Neural Networks, CNNs, RNNs. LSTM Networks for Time Series Prediction – Deep Learning Applications in Autonomous Vehicles and Image Recognition. Transfer Learning for Automotive Data. Case Studies – Predictive Maintenance in Automotive Industry- Autonomous Driving Algorithms and Challenges – Working with Real-world Data Sets. Introduction to Digital Twin

Text Books / References

1. Brunton, S. L., & Kutz, J. N, Data-driven science and engineering: Machine learning, dynamical systems, and control, Cambridge University Press, 2022.
2. Cady F, The data science handbook, John Wiley & Sons, 2017.
3. Grus J, Data science from scratch: first principles with python, O’Reilly Media, 2019.
4. Kroese, D. P., Botev, Z., & Taimre, T, Data science and machine learning: mathematical and statistical methods, Chapman and Hall/CRC, 2019.
5. Provost, F., & Fawcett, T, Data Science for Business: What you need to know about data mining and data-analytic thinking, O’Reilly Media, Incm, 2013.
6. Sarang P, Thinking Data Science: A Data Science Practitioner’s Guide, Springer Nature, 2023.
7. Winner H., Prokop G, & Maurer, M. (Eds.), Automotive Systems Engineering II (Vol. 1). Switzerland: Springer, 2018.

Course Objectives

• To provide a comprehensive understanding of data science principles, methodologies, and techniques relevant to automotive applications.
• To equip students with practical skills to collect, preprocess, analyze, and interpret data specific to the automotive industry.
• To familiarize students with supervised and unsupervised learning algorithms essential for predictive modeling in automotive systems.
• To develop students’ ability to critically analyze automotive data, identify challenges, and propose data-driven solutions

Course Outcomes

• CO01: Understand and preprocess diverse automotive data sources, including sensor data and telemetry. CO02: Apply regression, classification, and time series analysis to predict outcomes relevant to automotive systems.
• CO03: Implement and evaluate supervised and unsupervised machine learning algorithms for automotive data analysis.
• CO04: Evaluate and propose solutions to complex problems in automotive data science.

CO-PO Mapping

Skills Acquired: Data Preprocessing, Visualization, Classification & Regression