MR-21 B.

Tech CSE MGIT (A), Hyderabad

(IT Operations-II Lab)

MAHATMA GANDHI INSTITUTE OF TECHNOLOGY (Autonomous)

B.Tech. in Computer Science & Engineering
Scheme of Instruction and Examination
(Choice Based Credit System)
Applicable from the Academic Year 2021-22

VIII-Semester
S.No Instruction Examination
Course Hours Per Week Max. Marks
Course Title Duration of SEE in Credits
Code
L T P/D CIE SEE Hours
1 CS801PC Soft Computing 2 0 0 30 70 3 2
2 Professional Elective-V 3 0 0 30 70 3 3
3 Professional Elective-VI 3 0 0 30 70 3 3
4 CS851PC Project Stage-II 0 0 16 30 70 - 8
Total Hours/Marks/Credits 8 0 16 120 280 - 16

L: Lecture T: Tutorial D: Drawing P : Practical

CIE - Continuous Internal Evaluation SEE - Semester End Examination
MR-21 B.Tech CSE MGIT (A), Hyderabad
L T P C
2 0 0 2
VIII Semester Syllabus
CS801PC: SOFT COMPUTING
Course Objectives:
 Familiarize with soft computing concepts
 Introduce and use the idea of fuzzy logic and use of heuristics based
on humanexperience
 Familiarize the Neuro-Fuzzy modeling using Classification and
Clusteringtechniques
 Learn the concepts of Genetic algorithm and its applications
 Acquire the knowledge of Rough Sets.
Course Outcomes:
On completion of this course, the students will be able to:
 Identify the difference between Conventional Artificial
Intelligence toComputational Intelligence.
 Understand fuzzy logic and reasoning to handle and solve engineering problems
 Apply the Classification and clustering techniques on various applications.
 Understand the advanced neural networks and its applications
 Perform various operations of genetic algorithms, Rough Sets.
 Comprehend various techniques to build model for various applications

Unt-I

Introduction to Soft Computing: Evolutionary Computing, "Soft" computing versus "Hard"

computing, Soft Computing Methods, Recent Trends in Soft Computing, Characteristics of
Soft computing, Applications of Soft Computing Techniques.
Pattern Recognition, Fuzzy Pattern Recognition, Image Processing, Fuzzy Image Processing,
Image Processing Through Clustering, Application of Soft Computing in Real Estate, Soft
Computing in Mobile Ad hoc Network, Biogeography-Based Optimization, Soft Computing in
Information Retrieval and Semantic Web, Soft Computing in Software Engineering

Unit- II
Fuzzy Sets Classical Sets and Fuzzy Sets, Crisp Sets, Fuzzy Sets: History and Origin, Fuzzy
Sets: Basic Concepts, Paradigm Shift, Representations of Fuzzy Sets, Alpha-cuts, Basic
Operations on Fuzzy Sets, Fuzzy Complements, Intersections, and Unions
Fuzzy Relations: Crisp Relations and Fuzzy Relations, Crisp Relations, Fuzzy Relations,
Binary Fuzzy Relations, Intuitionistic Fuzzy Relations
Fuzzy Logic: Classical Logic and Fuzzy Logic, Interval Analysis, Fuzzy Numbers, Fuzzy
Logic.
Fuzzy Rule-Based Systems: Fuzzy Rule-Based Systems, Linguistic Variables and Linguistic,
Hedges, Rule-Based Systems, Conventional Programs Versus Rule-Based Systems, Fuzzy
Proposition suzzification and Defuzzification, Approximate Reasoning

Unit-III
Fuzzy Decision Making: Problem Solving Versus Decision Making, Individual Fuzzy Decision
Making, Multiperson Decision Making, Multicriteria Decision Making, Multistage Decision
Making
MR-21 B.Tech CSE MGIT (A), Hyderabad

Particle Swarm Optimization: PSO Algorithm Variants of PSO, Discrete Binary PSO, Adaptive
PSO, Multi-objective PSO Hybrid Model of PSO, Classification Model: ANN PSO,
Clustering Model

Unit-IV
Genetic Algorithms: Basic Concepts, Basic Operators for Genetic Algorithms, Crossover and
Mutation Properties, Genetic Algorithm Cycle, Fitness Function, Applications of Genetic
Algorithm.
History of Evolutionary Computing, Genetic Algorithms: History, Basic Concepts, Basic
Operators for Genetic Algorithms Crossover and Mutation Properties, Single-site Crossover,
Two-point Crossover, Multipoint Crossover

Unit-V
Rough Sets, Rough Sets, Rule Induction, and Discernibility Matrix, Integration of Soft
Computing Techniques.
Fundamentals of Rough Set Theory ,Rough Approximations, Knowledge Base, Properties of
Approximations, Proofs of Properties of Approximation, Measures of Accuracy, Topological
Characterization of Imprecision, Intuitive Meanings of Kinds of Rough Sets, Kinds of
Complement, Union, and Intersection of Rough Sets, Rough Membership Function, Difference
Between Fuzzy Sets and Rough Sets, Attribute Reduction, Reduct and Core, Rough Sets, Rule
Induction, and Discemibility Matrix, Knowledge Representation, Knowledge Representation
Systems, Significance of Attributes, Decision Tables, Rule Induction, Discernibility Matrix
Integration of Soft Computing Techniques, Fuzzy Neural Networks, Fuzzy Rough Sets, Rough
Fuzzy Sets, Rough Fuzzy C-Means Algorithm, Intuitionistic Fuzzy Rough Sets, Rough
Intuitionistic Fuzzy Sets, Rough Intuitionistic Fuzzy C-Means Algorithm, Steps of the RIFCM
Algorithm, Flowchart of the RIFCM Algorithm, Experimental Comparison, Neuro Fuzzy
Systems, Some Neuro Fuzzy Systems, Fuzzy Genetic Algorithms

TEXT BOOK:
1. Soft Computing – Advances and Applications - Jan 2015 by B.K. Tripathy
and J. Anuradha –Cengage Learning

REFERENCE BOOKS:
1. S. N. Sivanandam & S. N. Deepa, “Principles of Soft Computing”, 2nd edition, Wiley
India, 2008.
2. David E. Goldberg, “Genetic Algorithms-In Search, optimization and Machine
learning”,Pearson Education.
3. J. S. R. Jang, C.T. Sun and E.Mizutani, “Neuro-Fuzzy and Soft Computing”,
PearsonEducation, 2004.
4. G.J. Klir & B. Yuan, “Fuzzy Sets & Fuzzy Logic”, PHI, 1995.
5. Melanie Mitchell, “An Introduction to Genetic Algorithm”, PHI, 1998.
6. Timothy J. Ross, “Fuzzy Logic with Engineering Applications”, McGraw- Hill
Internationaleditions, 1995
MR-21 B.Tech CSE MGIT (A), Hyderabad

L T P C
3 0 0 3

VIII Semester Syllabus

CS812PE: WEB SERVICES & SERVICE ORIENTED ARCHITECTURE
(Professional Elective-V)
Course Objectives:
 To Understand Web Services and implementation model for SOA
 To Understand the SOA, its Principles and Benefits
 To Understand XML concepts
 To Understand paradigms needed for testing Web Services
 To explore different Test Strategies for SOA-based applications
 To implement functional testing, compliance testing and load testing of Web Services
 To Identify bug-finding ideas in testing Web Services

UNIT - I
Evolution and Emergence of Web Services - Evolution of distributed computing, Core
distributed computing technologies – client/server, CORBA, JAVA RMI, Microsoft DCOM,
MOM, Challenges in Distributed Computing, role of J2EE and XML in distributed
computing, emergence of Web Services and Service Oriented Architecture (SOA).
Introduction to Web Services – The definition of web services, basic operational model of
web services, tools and technologies enabling web services, benefits and challenges of using
web services.

UNIT - II
Web Services Architecture – Web services Architecture and its characteristics, core
building blocks of web services, standards and technologies available for implementing web
services, web services communication, basic steps of implementing web services. Describing
Web Services – WSDL introduction, nonfunctional service description, WSDL1.1 Vs WSDL
2.0, WSDL document, WSDL elements, WSDL binding, WSDL tools, WSDL port type,
limitations of WSDL.

UNIT – III
Brief Over View of XML – XML Document structure, XML namespaces, Defining structure
in XML documents, Reuse of XML schemes, Document navigation and transformation.
SOAP: Simple Object Access Protocol, Inter-application communication and wire protocols,
SOAP as a messaging protocol, Structure of a SOAP message, SOAP envelope, Encoding,
Service Oriented Architectures, SOA revisited, Service roles in a SOA, Reliable messaging,
The enterprise Service Bus, SOA Development Lifecycle, SOAP HTTP binding, SOAP
communication model, Error handling in SOAP.
MR-21 B.Tech CSE MGIT (A), Hyderabad

UNIT – IV
Registering and Discovering Services: The role of service registries, Service discovery,
Universal Description, Discovery, and Integration, UDDI Architecture, UDDI Data Model,
Interfaces, UDDI Implementation, UDDI with WSDL, UDDI specification, Service
Addressing and Notification, Referencing and addressing Web Services, Web Services
Notification.

UNIT – V
SOA and web services security considerations, Network-level security mechanisms,
Application-level security topologies, XML security standards, Semantics and Web Services,
The semantic interoperability problem, The role of metadata, Service metadata, Overview of
.NET and J2EE, SOA and Web Service Management, Managing Distributed System,
Enterprise management Framework, Standard distributed management frameworks, Web
service management, Richer schema languages, WS-Metadata Exchange.

TEXT BOOKS:
1. Web Services & SOA Principles and Technology, Second Edition, Michael P.
Papazoglou.
2. Developing Java Web Services, R. Nagappan, R. Skoczylas, R.P. Sriganesh,
WileyIndia.
3. Developing Enterprise Web Services, S. Chatterjee, J. Webber, Pearson Education.

REFERENCE BOOKS:
1. XML, Web Services, and the Data Revolution, F.P. Coyle, Pearson Education.
2. Building web Services with Java, 2nd Edition, S. Graham and others, Pearson
Education.
3. Java Web Services, D.A. Chappell & T. Jewell, O’Reilly, SPD.
4. McGovern, et al., “Java web Services Architecture”, Morgan Kaufmann Publishers,
2005.
5. J2EE Web Services, Richard Monson-Haefel, Pearson Education.
 L T P C
3 0 0 3

VIII Semester Syllabus

CS818PE: NEURAL NETWORKS and DEEP LEARNING
(Professional Elective-VI)
(Common to CSE, IT)
Course Objectives:
 To introduce the foundations of Artificial neural Networks
 To learn various types of Artificial neural Networks
 To acquire knowledge on Deep Learning concepts
Course Outcomes:
 Ability to understand the concepts of Neural Networks
 Ability to use an efficient algorithm for Deep Models
 Ability to select the Learning networks in modelling real world systems

Unit-I
Basics of artificial neural networks (ANN): Artificial neurons, Computational models of neurons,
Structure of neural networks, Feedforward neural networks: Pattern classification using
perceprton, Multilayer feedforward neural networks (MLFFNNs), Backpropagation learning.

Unit-II
Introduction to Deep Learning, Historical Trends in Deep learning, Deep Feed - forward networks,
Gradient-Based learning, Hidden Units, Architecture Design, Back-Propagation and Other
Differentiation Algorithms.
Optimization for Train Deep Models:Optimization for training DNNs, Newer optimization
methods for neural networks (AdaGrad, RMSProp, Adam), Second order methods for training,
Regularization methods (dropout, drop connect, batch normalization)

Unit-III

Convolution neural networks (CNNs): Introduction to CNNs – convolution, pooling, Deep

CNNs, Different deep CNN architectures – LeNet, AlexNet, VGG, PlacesNet, Training a CNNs:
weights initialization, batch normalization, hyperparameter optimization, Understanding and
visualizing CNNs.

Unit-IV
Recurrent Neural Networks: LSTM, GRU, Encoder Decoder architectures. Deep Unsupervised
Learning: Autoencoders, Variational Auto-encoders, Adversarial Generative Networks, Auto-
encoder and DBM Attention and memory models, Dynamic Memory Models
MR-21 B.Tech. CSE MGIT (A), Hyderabad

Unit-V
Applications: Large-Scale Deep Learning, Computer Vision, Speech Recognition,
Natural Language Processing

TEXT BOOKS:
1. S. Haykin, Neural Networks and Learning Machines, Prentice Hall of India, 2010.
2. Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville, MIT Press.

REFERENCES:
1. Michael Nielsen, Neural Networks and Deep Learning, Determination Press, 2015
2. Satish Kumar, Neural Networks - A Class Room Approach, Second
Edition, TataMcGraw-Hill, 2013
3. B. Yegnanarayana, Artificial Neural Networks, Prentice- Hall of India, 199.