lOMoARcPSD|17790867

MU 7th Semester Question Papers December-22

Computer Engineering (University of Mumbai)

Studocu is not sponsored or endorsed by any college or university

Downloaded by Movies Duniya (jharoshan457@gmail.com)
 lOMoARcPSD|17790867

42171/MACHINE LEARNING
Paper Subject Code:
CoR-19
Duration: 3hrs Max Marks:80

N.B.: (1) Question No l is Compulsory.

(2) Attempt any three questions out of the remaining five.
(3) All questions carry equal marks.
(4) Assume suitable data, if required and state it clearly.

Q1. Solve any four from following. [20]

a. What are the issues in Machine learning?
b. Explain Regression line, Scatter plot, Error in prediction and Best fitting line.
C. Explain the concept of margin and support vector.
d. Explain the distance metries used in clustering.
e. Explain Logistic Regression

Q2. a. Explain the steps of developing Machine Learning applications. [10

b. Explain Linear regression along with an example. [10]

Q3. a. Create a decision tree using GiniIndex to classify following dataset. [10
Sr. No. Income Age Own Car
Very High Young Yes
Yes
High Medium
Low Young No
High Medium Yes

Very High Medium Yes

Medium Young Yes
High Old Yes
Medium Medium No
Low Medium No

10 Low Old No
High Young Yes
12 Medium Old No

b. Describe Multiclass classification. [10

Q4. a. Explain the Random Forest algorithm in detail. [10

b. Explain the different ways to combine the
classifiers. [10]

for the following two-dimensional [10]

Q5. a. Compute the Linear Discriminant projection
and
dataset. X1=(xl, x2) {(4,1), (2,4). (2,3), (3,6), (4,4)}
=

X2- (x1, x2) = {(9,10), (6.8). (9,5). (8,7). (10,8)

b. Explain EM algorithm. [10

Q6. Write detailed note on following. (Any two) [20

a. Performance Metrics for Classification
for Dimension Reduction
b. Principal Component Analysis
c. DBSCAN

15549

Downloaded by Movies Duniya (jharoshan457@gmail.com)

 lOMoARcPSD|17790867

raper/ Subject Code: 42172/ BIG DATA ANALYTICS

Co -R-1i
Time: 03 Hours Marks: 80

Note: 1. Question 1 is compulsoryy

2. Answer any three out of the
remaining five questions:
3. Assume any suitable data wherever
required and justify the sae.
Q1 a) What is function of Map Tasks in the Map Reduce framework? Explain with the 5]
help of an example.
b) Demonstrate how business problems have been su cessfully solved faster, cheaper [5]
and more effectively considering No$QL Google's MapReduce case study. Also
illustrate the business drivers and the findings in it.
c)Why isHDFSmore suited for applications havinglargedatasets and not when there S)
are small files? Elaborate.
d) Explain the concept of bloom filter with an example

Q2 a) Name the threë ways that resources can be shared between'c or systems. Name [101
the architecture used in big data,solutions and describe it in detail
b) Write a map reduce pseudo. code for word cout problem-Apply map reduce T10]
working on the föllowing document:

"This is an apple. Apple îs red in color".

3 a) Suppose the stream,is 1, 3, 2, 1,2,3, 4, 3,1, 2, 3, 1. Let h(x) =6x +1 mod3. [10]
Show how the Flajolet- Martin algorithm will estimate the number of distinct
elements in this stream.
b) Considerthe following dataframe given below [10]
subject class marks
6
75
48
69
84
53

i. Create a subsct of subject less than 4 by using subsct ) function and demonstrate
the output.
1. Create a subset where the subject column is less than 3 and the class equals to 2
by using [ ] brackets and demonstrate the output.

Q4 a) What are the Core Hadoop components? Explain in detail.

[10)
b) With a neat sketch, explain the architecture of the data-stream management system. [10
Q5 a) Determin communities for the given social network graph using Girvan- Newman [10]
algorithm.

15786 Page I of 2

RADRA65CRC75RCA AA°3A 0N77KAC 9RI 7

Downloaded by Movies Duniya (jharoshan457@gmail.com)
 15CB
9,7R4
14 09R74Cs B
CAA+:A09B74 ?DR4 5
lOMoARcPSD|17790867

i4 A,4C?,AAC
A097

Downloaded by Movies Duniya (jharoshan457@gmail.com)

i 34650H 4CACPK7498:3
977:4
 lOMoARcPSD|17790867

uugeui vue: 421 / /

NAIURAL LANGUAGE PROCESSING
(DLOC - II)
Co (R-19)
Time: 3 Hours
Max. Marks: 80
N.B. (1) Question No. I is
compulsory
(2) Assume suitable data if
necessary
(3)Attempt any three questions froni remaining questions

Q.1 Any Four

Differentiate between Syntactic 20[M
ambiguity and Lexical Ambiguity. 5M
b Define affixes. Explain the types of affixes.
Describe open clas_ words and closed class words 5M
in English with examples.
d What is rule base machine translation? 5M
Explain with suitable example following relationships between word 5M]
meanings. 5M]
Homonymy, Polysemy, Synonymy, Antonymy
f Explain perplexity of any language model.
5M]
Q.2 a) Explain the role of FSA in
morphological analysis?
Q.2 b) Explain Different stage involved in NLP process with suitable
example. I10M
Q.3 a) Consider the following corpus
I tell you to
sleep and rest </s> 5M
<S> I would like to
sleep
for an hour </s>
s> Sleep helps one to relax <is>
List all possible bigrams.
Compute conditional probabilities and predict
the next ord for the word "to".

Q.3 b) Explain Yarowsky bootstrapping approach of semi

Q.3 c) What is POS tagging? Discuss various
supervised learning 5M
challenges faced by POS tagging.
10M
Q.4 a) What the limitations of Hidden Markov Model?
are

Q.4 b) Explain different steps in text processing for Information Retrieval

the (5M]
Q.4 c) Compare top-down and bottom-up approach of parsing with SM
example. 10M
Q.5 a) What do you mean by word sense
disambiguation (WSD)? Discuss dictionary based [10M|
approach for WSD.
Q.5 b) Explain Hobbs algorithm for pronoun resolution.
[10M]
Q.6 a) Explain Text summarization in detail
Q.6 b) Explain Porter Stemming algorithm in detail 1OM
10M
**********4******

16298.

Downloaded by Movies Duniya (jharoshan457@gmail.com)

 lOMoARcPSD|17790867

Paper / Subject Code: 42178 /INFORMATION RETRIEVAL (DL0C- IV)

Co (R-
Duration:3 Hours Marks: 80 Marks

N.B.:(1) Question No l is Compulsory.

(2) Attempt any three questions out of the remaining five.
(3) All questions carry equal marks.
(4) Assume suitable data, if fequired andstate it clearly.

Q.1 Solve any four.

a. Compare and contrast Boolean Model vs Vector Space Model.
b. Specify the significance of User Rclevancefeedback in an IR system.
c. Explain inverted fileindexing withsuitable examples
d. Explain the process of Structured Text retrieval model.
e. Illustrate different types ofkeyword-based queries.
Q.2 a Draw the taxonomy ofIR models. nd expláin any one-IR modeling 10
techniqu
What is the significance of tfand idf ? How can you calculate tf and idfin a 10
vector-imodel?C
a. Explain the various systém relatedissues faced in Information retrieval 10,
Q.3 .
systems and how theý can be refined for adeployed_ystem.
b. State the different types of queries. Explain the pattern matching query 10

concept with an example .

suffix tree in information retrieval 10

Q.4 a. What is the role of suffix array and
system with example
What is Látent Semantic Indexing model? Write the advantages of Latent 10

Semantic Indexing Model?

L
Q.5 a. Define Multimedia information retricval. Discüss indexing and searching 10
Q.5 a.
and Ranked
b What is thie difference betweenUnranked Retrieval models
Retrievalmodels."
Write short ngtes on any two. 20
Q.6
a. Informmation Retrievalin digital libraries.
b. Sequential Searching
c. Flat browsing vs Hypertext Browsing model.
d. Distributed Information Retrieval.

Page 1 of 1
16035

134RRORSR432FAF7I FRRO5ns6549a I80

Downloaded by Movies Duniya (jharoshan457@gmail.com)
 lOMoARcPSD|17790867

Paper/ Subject Code: 42181/Management Information Systegms

Duration: 3hrs [MaxMarks: 80]

N.B. (1) Question No l is Compulsory.

(2) Attempt any three questions outof the remaining five.
3) All questions cary equal marks.
(4) Assume suitable data, if required and state it clearly. O8
(20].
Attempt any FOUR
a What are the different types of MIS? (051
How is data governance achieved in case of MIS? J05]
Web 2.0 and 3.0? Web 105]
c Analyse briefly to highlight the difference between [05)
d Evaluate the MIS Hierarchy to comment on Decision Support System.
e List the main difference between Wireless and Wired Technologies? [05]

2 a Give an understanding on types of Control to achieve Security. [10]

b What is Mobile Commerce? What are the new challenges that it has introduced 10]

inbusiness?
3 a What do you mean by CRM? Give its types and relate the role of SC on CRM. [10
What is Data Mart and Data Warehouses? Give two examples which show
generationof Big Data.

4 a Write short notes on (1) TPS (2) ERP

[10]
Evaluate the role of Confidentiality, Integrity and Availability in order to achieve [10]

5
b

a
security.
What is the need of Social Computing for Businesses?
72 . [10]
b Create MIS system for any hospital. [10]
of Big [10]
What is Big Data? What are the various challenges and characteristics
Data? their evolution. [10]
b Describe various Cloud Computing Models and highlight

**************

70

408 Page 1 of1

15529

082F 12BDSDF7FC9F24086ADAE807C17F

Downloaded by Movies Duniya (jharoshan457@gmail.com)