CS702(A) Unit 4 study material for RGPV CSE 7th Semester. Learn Rough Set Theory, fundamental concepts, set approximation, rough membership, attributes, optimization, Hidden Markov Models and Decision Tree Model.
Unit 4 explains important Computational Intelligence models used for uncertainty handling, classification, sequence modeling and decision-making. It covers Rough Set Theory, Hidden Markov Models and Decision Tree models.
Understand uncertainty, approximation, rough membership and attribute reduction.
Learn sequence modeling, hidden states, observations and probabilistic transitions.
Study tree-based classification using decision nodes, branches and leaf nodes.
Complete syllabus-based topics of Computational Intelligence Unit 4.
Rough Set Theory is a mathematical approach used to handle uncertainty and incomplete information.
Rough sets classify objects using available attributes when exact classification is difficult.
Important rough set concepts include universe, attributes, equivalence relation, indiscernibility relation and approximations.
Set approximation represents uncertain data using lower approximation and upper approximation.
Lower approximation contains objects that definitely belong to a target set.
Upper approximation contains objects that possibly belong to a target set.
Rough membership measures the degree to which an object belongs to a rough set.
Attributes describe objects and are used to classify, compare and reduce data.
Rough set optimization reduces unnecessary attributes and improves decision-making accuracy.
Hidden Markov Model is a probabilistic model used for sequence data where states are hidden.
HMM includes hidden states, observations, transition probability, emission probability and initial probability.
Decision Tree is a tree-based model used for classification and decision-making.
Decision nodes represent tests on attributes, branches represent outcomes and leaf nodes represent final decisions.
Rough Set Theory: Handles uncertainty using lower and upper approximations.
Lower Approximation: Definitely belongs to the set.
Upper Approximation: Possibly belongs to the set.
HMM: Probabilistic model where actual states are hidden and observations are visible.
Decision Tree: Tree-like model for classification and decision-making.
| Topic | Expected Frequency | Importance |
|---|---|---|
| Rough Set Theory | Very High | ⭐⭐⭐⭐⭐ |
| Fundamental Concepts | High | ⭐⭐⭐⭐ |
| Set Approximation | Very High | ⭐⭐⭐⭐⭐ |
| Rough Membership | High | ⭐⭐⭐⭐ |
| Attributes | Medium | ⭐⭐⭐ |
| Optimization | High | ⭐⭐⭐⭐ |
| Hidden Markov Models | Very High | ⭐⭐⭐⭐⭐ |
| Decision Tree Model | Very High | ⭐⭐⭐⭐⭐ |
Rough Set Theory is a mathematical method used to handle uncertainty and incomplete information.
Lower approximation contains objects that definitely belong to the target set.
Upper approximation contains objects that possibly belong to the target set.
HMM is a probabilistic model where the actual states are hidden and observations are visible.
Decision Tree is a tree-based model used for classification and decision-making.