Course Details
Subject {L-T-P / C} : MN3004 : Data Analytics for Mining { 3-0-0 / 3}
Subject Nature : Theory
Coordinator : Tushar Gupta
Syllabus
| Module 1 : |
Data foundation: Introduction to data analytics, Digitisation in mining, Mining data sources (IoT, Sensors, Logs), Data Types, Visualisation, Pre-processing and data cleaning, , Correlation Analysis. |
| Module 2 : |
Basic Statistics: Simple & Multivariate Regression, Curve Fitting, Fitness Parameters, ANOVA, Principal Component Analysis (PCA), Case studies |
| Module 3 : |
Advanced Statistics Soft Computing: ANN Perceptrons, Backpropagation, Architecture Design, Activation Functions, Overfitting (Regularization), Case Studies |
| Module 4 : |
Uncertainty Modelling: Fuzzy Sets, Membership Functions, FIS (Mamdani/Sugeno), ANFIS Architecture and Training, Case Studies |
| Module 5 : |
Advanced Trends and Capstone Project: Intro to Support Vector Machines (SVM), Deep Learning, Capstone Project Presentations. |
Course Objective
| 1 . |
Understand the lifecycle of data in the mining industry, from sensor acquisition to decision-making. |
| 2 . |
Master data pre-processing techniques to handle the inherent noise and uncertainty in mining datasets. |
| 3 . |
Apply classical statistical models and regression analysis to mining productivity problems |
| 4 . |
Develop soft computing skills using Artificial Neural Networks (ANN) and Fuzzy Logic, and others for advanced data analytics |
| 5 . |
Evaluate and validate predictive and prescriptive models for mining applications |
Course Outcome
| 1 . |
CO1: Ability to clean, visualize, and interpret complex multivariate mining datasets. |
| 2 . |
CO2: Perform multivariate curve fitting and classical statistical analysis to validate research findings in mining |
| 3 . |
CO3: Build and train Artificial Neural Networks to predict non-linear phenomena in mining and allied fields |
| 4 . |
CO4: Design and implement Fuzzy Inference Systems (FIS) and ANFIS-based systems for advanced data analysis |
| 5 . |
CO5: Comprehend large-scale mining data and perform advanced multi-stage analysis to derive useful results for operational decision-making and safety management. |
Essential Reading
| 1 . |
Ali Soofastaei, Data Analytics Applied to the Mining Industry, CRC Press , Basics of the course are well covered. |
| 2 . |
Jacek M. Czaplicki, Statistics for Mining Engineering, CRC Press |
Supplementary Reading
| 1 . |
Ali Soofastaei, Advanced Analytics in Mining Engineering, CRC Press , Advanced mining statistical application |
| 2 . |
Theodore T. Allen, Introduction to Engineering Statistics and Six Sigma, Springer |
Journal and Conferences
| 1 . |