Course Plan

Duration of Session: 1 No. of Sessions : 45

Faculty Name: Deepa.T.P. Course Name : Pattern Recognition Course Code:17CSDE711 Hr

Nature of Pedagogy/Prior Program Outcomes Course Outcomes

Sessions Session Reading/Links Achieved Achieved
Module Description No. of Sessions Learning Outcomes
No /Resources
1 Basics of Probability Problem Solving (1
.5 Hrs) & Lecture
with PPT(30 Mins)
Bridge 2 with prior formative
Introduction to Linear Algebra assessment
2

What is Pattern recognition? Data sets for 1 Case Discussion (30

3 pattern recognition,paradigms for pattern Mins) Lecture with POs: 1,2
recognition. PPT(30 Mins) Explain and define concepts
PSO:2 1
Data structures for pattern representation 2 Case Discussion (30 of pattern recognition
4 Mins) Lecture with
Pattern PPT(1 .5Hrs)
1 5
Representation-1
6 Representation of clusters 2 Case Discussion (30
Mins) Lecture with
7
PPT(1 .5Hrs)
8 proximity measures, size of pattern 1 Problem Solving (30
Mins)
PPT (20 Mins)
9 Abstractions of the data set PPT (40 mins),
1
Examples(10 Mins)
10 Feature selection and extraction PPT (1 hour), case
2 studies,
11
programming
Evaluation of Classifiers PPT(20 Mins), Perform feature extraction and POs: 1,2,3,4,5,6
Pattern
2 12 1 Problem solving (35 selection through various PSO:2 3
Representation-2
mins) algorithms
Evaluation of clustering PPT(20 Mins),
Problem solving (35
13 1 mins)

16 Nearest neighbor algorithm Lecture (1 hr), case

2 study (1 hr)
17
variants of NN Algorithm Lecture (1 hr), case POs: 1,2
18 Understand the Bayesian
Nearest Neighbor 3 2 study (1 hr) PSO:2 2
19 approach to pattern recognition

20 Efficient algorithms 1 Lecture (1 hr)

21 data reduction Lecture (1 hr)

Class discussion: Based on student
Assessment 14 performance in quiz, MCQs and Assignment 1
using Google Classroom
Group Activity Team activity to practise classification
15 using Feature selection and extraction, 1 Group Activity
Nearest Neighbour
Lecture(30 min),
22 Bayes theorem 1 Case study (20 min)

Lecture (20 min),

23 Minimum error rate classifier 1 Problem solving (30
min) To apply Markov’s approach and POs: 1,2,3,4,5,6
Bayes Classifier 4 problem clustering for pattern PSO:2 5
24 estimation of probabilities 1 solving(40min), recognition
Lecture(10mins)
25 PPT(1hr), case
Naïve Bayes classifier 2 studies(1hr)
26
PPT (30mins),
27 Bayesian belief network 1
Example(20)mins
PPT(1hr), case
28 Markov models for classification 2 studies(1hr)
POs: 1,2,3,4,5,6
Hidden Markov To combine various classifiers
5 PPT (1hr), case PSO:2 4
Models 29 Hidden markov models 2 and boost their performance
studies(1hr)

30 classification using HMM 1 PPT (!hr)

PPT(30min),
31 Why is clustering important? 1
examples(30mins)
PPT(1hr), case
32 Hierarchical algorithm 2 studies(1hr) To apply Markov’s approach and POs: 1,2,3,4,5,6
Clustering 6 clustering for pattern PSO:2 5
PPT(1hr), case
33 Partitional clustering 2 recognition
studies(1hr)

PPT(30mins), case
34 clustering large data sets. 1
studies(20mins)
Group Activity Students present different scenario which Survey &
35 can be solved using Naïve Bayes theorem 1 presentation
and clustering
Class discussion: Based on student
Assessment 36 performance in quiz, MCQs and Assignment 1
using Google Classroom
37 Introduction 1 PPT(1hr)

38 Methods for constructing ensembles of PPT(1.5hrs), case POs: 1,2,3,4,5,6

Combination of 2 To combine various classifiers
7 classifiers study(30mins) PSO:2 4
Classifiers 39 and boost their performance

40 PPT(1.5hrs), case
methods for combining classifiers. 2
41 study(30mins)

42
PPT(1hr),
43 Case Study: Handwritten Digit Recognition 3
Demonstration(2hrs)
Perform feature extraction POs: 1,2,3,4,5,6
44
Case Studies 8 and selection through PSO:2 3
45 Use of the nearest
Case Study:
various algorithms
PPT(1hr),
46 neighbor algorithm for 3
Demonstration(2hrs)
transaction databases
 Perform feature extraction POs: 1,2,3,4,5,6
Case Studies 8 and selection through PSO:2 3
Use of the nearest
Case Study:
various algorithms
PPT(1hr),
neighbor algorithm for 3
Demonstration(2hrs)
47 transaction databases
Class Discussion: Based on student
Assessment 48 performance in quiz, MCQs and case 1
analysis using Google Classroom
Discussion of Previous year sample Question
Revision 49 1
papers
Nature of Sessions Pedagogy/Prior Program Outcomes Course Outcomes
Session Reading/Links Achieved Achieved
Module Description No. of Sessions Learning Outcomes
No /Resources
Course Name : Pattern Recognition Course Code:17CSDE711 No. of Sessions : 45
Faculty Name:
48 1
Deepa.T.P.
Group Activity Students Groups present their analysis of Analysis & Program Outcomes
49-50 financial statements of select companies 2 Presentation Achieved

Basics of Probability Problem Solving (1

.5 Hrs) & Lecture
Concept Essentials 6 51-52 2 with PPT(30 Mins)
with prior formative
assessment

Engaged Learning Introduction to Linear Algebra

53-57 5

What is Pattern recognition? Data sets for 1 Case Discussion (30

58 pattern recognition,paradigms for pattern Mins) Lecture with
recognition. PPT(30 Mins) POs: 1,2
Data structures for pattern representation 2 Case Discussion (30
Explain and define concepts
4 PSO:2 1
Mins) Lecture with of pattern recognition
PPT(1 .5Hrs)
5
Pattern
6 Representation of clusters 2 Case Discussion (30
Representation-1
Mins) Lecture with
PPT(1 .5Hrs)
7

8 proximity measures, size of pattern Problem Solving (30

Mins)
PPT (20 Mins)
2 9 Abstractions of the data set 1 PPT (40 mins), Perform feature POs: 1,2,3,4,5,6 3
Examples(10 Mins) PSO:2
Feature selection and extraction PPT (1 hour), case extraction and selection
##### 2
studies, through various
##### programming
Pattern algorithms
12 Evaluation of Classifiers PPT(20 Mins),
Representation-2
Problem solving (35
mins)
13 Evaluation of clustering 1 PPT(20 Mins),
Problem solving (35
mins)
3 16 Nearest neighbor algorithm 2 Lecture (1 hr), case Understand the Bayesian POs: 1,2 2
study (1 hr) PSO:2
17 approach to pattern
18 variants of NN Algorithm 2 Lecture (1 hr), case recognition
Nearest Neighbor study (1 hr)
19
20 Efficient algorithms Lecture (1 hr)

21 data reduction Lecture (1 hr)

 14 Class discussion: Based on student performance in quiz, MCQs and Assignment using Google Classroom

15 Team activity to practise classification using Feature selection and extraction,

Group Activity
Nearest Neighbour

4 22 Lecture(30 min), To apply Markov’s POs: 1,2,3,4,5,6 5

Bayes theorem 1
Case study (20 min) PSO:2
Lecture (20 min), approach and clustering
23
Minimum error rate classifier 1 Problem solving (30 for pattern recognition
min)
24 problem
Bayes Classifier estimation of probabilities 1 solving(40min),
Lecture(10mins)
25 PPT(1hr), case
Naïve Bayes classifier 2 studies(1hr)
26
27 PPT (30mins),
Bayesian belief network 1
Example(20)mins
5 28 PPT(1hr), case To combine various POs: 1,2,3,4,5,6 4
Markov models for classification 2 studies(1hr) PSO:2
classifiers and boost
Hidden Markov Models 29 PPT (1hr), case their performance
Hidden markov models 2 studies(1hr)

30 classification using HMM 1 PPT (!hr)

6 31 PPT(30min), To apply Markov’s POs: 1,2,3,4,5,6 5

Why is clustering important? 1
examples(30mins) PSO:2
PPT(1hr), case approach and clustering
32 Hierarchical algorithm 2 studies(1hr) for pattern recognition
Clustering
33 PPT(1hr), case
Partitional clustering 2 studies(1hr)

34 PPT(30mins), case
clustering large data sets. 1
studies(20mins)
35 Students present different scenario which can be solved using Naïve Bayes theorem and clustering

36 Class discussion: Based on student performance in quiz, MCQs and Assignment using Google Classroom

7 37 Introduction 1 PPT(1hr) To combine various POs: 1,2,3,4,5,6 4

PSO:2
38 Methods for constructing ensembles of classifiers
2 PPT(1.5hrs), classifiers and boost
Combination of Classifiers
case their performance
39 study(30mins)
40 methods for combining classifiers. 2 PPT(1.5hrs),
41 case
8 42 Case Study: Handwritten Digit Recognition 3 PPT(1hr), Perform feature extraction and POs: 1,2,3,4,5,6 3
selection through various PSO:2
43 Demonstration(
algorithms
Case Studies
44 2hrs)
45 Case Study: Use of the nearest neighbor algorithm
3 for transaction databases
PPT(1hr),
46 Demonstration(
47 2hrs)
48
Revision 49 Discussion of Previous year sample Question papers
1