IT5601 EMBEDDED SYSTEMS AND INTERNET OF THINGS L T PC

3 0 0 3

OBJECTIVES:
• To learn the internal architecture and programming of an embedded processor.
• To introduce interfacing I/O devices to the processor.
• To introduce the evolution of Internet of Things(IoT).
• To build a small low-cost embedded and IoT system using Arduino/Raspberry Pi/ open
platform.
• To apply the concept of Internet of Things in real world scenario.

UNIT I 8-BIT EMBEDDED PROCESSOR 9

8-Bit Microcontroller – Architecture – Instruction Set and Programming – Programming
Parallel Ports – Timers and Serial Port – Interrupt Handling.
Suggested Activities:
• Flipped classroom activity on different types of microcontrollers.
• Assignment on writing simple assembly codes.
• Practical - Developing simple application using assembly code.

Suggested Evaluation Methods:

• Tutorials on instruction set and programming.
• Assignments on programming using machine code.
• Quizzes on instruction set and programming.

UNIT II EMBEDDED C PROGRAMMING 9

Memory And I/O Devices Interfacing – Programming Embedded Systems in C – Need For
RTOS – Multiple Tasks and Processes – Context Switching – Priority Based Scheduling
Policies.

Suggested Activities:
• Flipped classroom on different types of RTOS.
• Practical - Writing simple embedded C codes.
• Practical - Developing simple application using embedded C code.

Suggested Evaluation Methods:

• Tutorials on embedded C programming.
• Assignment on scheduling policies.
• Practical - Developing applications using embedded C.
• Quizzes on Embedded C and RTOS.

UNIT III IOT AND ARDUINO PROGRAMMING 9

ARM Processor – Introduction to the Concept of IoT Devices – IoT Devices Versus Computers
– IoT Configurations – Basic Components – Introduction to Arduino – Types of
Arduino – Arduino Toolchain – Arduino Programming Structure – Sketches – Pins –
Input/Output From Pins Using Sketches – Introduction to Arduino Shields – Integration of
Sensors and Actuators with Arduino.

Suggested Activities:
• Flipped classroom on ARM processors and its applications.
• Practical - Developing simple application using Arduino.

1
 • Case study of different sensors used in IoTs.
Suggested Evaluation Methods:
• Tutorials on Arduino programming.
• Assignment problems on interfacing I/O based applications with Arduino board.
• Quizzes on IoT devices.

UNIT IV IOT COMMUNICATION AND OPEN PLATFORMS 9

IoT Communication Models and APIs – IoT Communication Protocols – Bluetooth – WiFi –
ZigBee – GPS – GSM modules – Open Platform (like Raspberry Pi) – Architecture –
Programming – Interfacing – Accessing GPIO Pins – Sending and Receiving Signals Using
GPIO Pins – Connecting to the Cloud.

Suggested Activities:
• Flipped classroom on Bluetooth, WiFi, ZigBee, GPS, GSM etc. standards.
• Practical - Developing simple application using open platform (like Raspberry Pi).
• Case study of different existing IoT related standards.

Suggested Evaluation Methods:

• Tutorials on programming with open platforms for IoT.
• Assignment on interfacing different sensors/actuators with open platform.
Quizzes on IoT communications.

UNIT V APPLICATIONS DEVELOPMENT 9

Complete Design of Embedded Systems – Development of IoT Applications – Home
Automation – Smart Agriculture – Smart Cities – Smart Healthcare.

Suggested Activities:
• Flipped classroom activity on different existing IoT applications.
• Designing simple applications.
• Case study on IoT based home automation solutions.

Suggested Evaluation Methods:

• Tutorials on design and development of IoT applications.
• Assignment on different IoT based smart solutions.
• Demonstrating real-time applications using embedded and IOT processors.
Quizzes on Design of embedded systems and IoT applications.

TOTAL: 45 PERIODS
OUTCOMES:
On completion of the course, the student will be able to:
CO1: Understand and compare various embedded processors.
CO2: Design and deploy timers and interrupts.
CO3: Write embedded C programs.
CO4: Design simple embedded applications.
Co5: Design portable IoT using Arduino/Raspberry Pi /open platform. Co6:
Analyze applications of IoT in real time scenario.

2
 TEXT BOOKS:
1. Muhammed Ali Mazidi, Janice Gillispie Mazidi, Rolin D. McKinlay, “The 8051
Microcontroller and Embedded Systems”, Pearson Education, Second Edition, 2014.
2. Adrian McEwen, Hakim Cassimally “Designing the Internet of Things”, John Wiley &
Sons, 2014.

REFERENCES:
1. Michael J. Pont, “Embedded C”, Pearson Education, 2007.
2. Robert Barton, Patrick Grossetete, David Hanes, Jerome Henry, Gonzalo Salgueiro,
“IoT Fundamentals: Networking Technologies, Protocols, and Use Cases for the
Internet of Things”, CISCO Press, 2017.
3. Wayne Wolf, “Computers as Components: Principles of Embedded Computer System
Design”, Elsevier, 2006.
4. IOT (Internet of Things) Programming: A Simple and Fast Way of Learning, IOT Kindle
Edition.
5. Andrew N Sloss, D. Symes, C. Wright, “Arm System Developers Guide”, Morgan
Kauffman/ Elsevier, 2006.
6. Arshdeep Bahga, Vijay Madisetti, “Internet of Things: A Hands-on Approach”, VPT,
2014.

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12
CO1 ✓ ✓ ✓ ✓ ✓ ✓

CO2 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO3 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO4 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO5 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO6 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

IT5602 DATA SCIENCE AND ANALYTICS LT PC

3 0 03

OBJECTIVES:
• To learn the fundamentals of data science and big data.
• To gain in-depth knowledge on descriptive data analytical techniques.
• To gain knowledge to implement simple to complex analytical. Algorithms in big data
frameworks.
• To develop programming skills using required libraries and packages to perform data
analysis in Python.
• To understand and perform data visualization, web scraping, machine learning and
natural language processing using various Data Science tools.

3
UNIT I INTRODUCTION TO DATA SCIENCE AND BIG DATA 9
Data Science – Fundamentals and Components – Data Scientist – Terminologies Used in Big
Data Environments – Types of Digital Data – Classification of Digital Data – Introduction to
Big Data – Characteristics of Data – Evolution of Big Data – Big Data Analytics – Classification
of Analytics – Top Challenges Facing Big Data – Importance of Big Data Analytics – Data
Analytics Tools.

Suggested Activities:
• Case studies on big data application domain.
• Real world domain specific problems involving big data and listing out the challenges.
• Demonstration on data analytics tools.

Suggested Evaluation Methods:

• Student assignment on case studies related to healthcare, climate change,
ecommerce, retail business, manufacturing etc.
• Group presentation on big data applications with societal need.
• Quizzes on topics like big data terminologies, big data applications, etc.

UNIT II DESCRIPTIVE ANALYTICS USING STATISTICS 9

Types of Data – Mean, Median and Mode – Standard Deviation and Variance – Probability –
Probability Density Function – Types of Data Distribution – Percentiles and Moments –
Correlation and Covariance – Conditional Probability – Bayes’ Theorem – Introduction to
Univariate, Bivariate and Multivariate Analysis – Dimensionality Reduction using Principal
Component Analysis and LDA – Dimensionality Reduction using Principal Component
Analysis and Linear Discriminant Analysis (LDA) – Principal Component Analysis (PCA)
example with Iris Data Set from UCI repository.

Suggested Activities:
• Solving numerical problems based on statistics and probability.
• Demonstration of descriptive analysis using Python.
• Demonstrate PCA using Iris data set in Python.

Suggested Evaluation Methods:

• Assignment on data understanding using open source tools.
• Student Presentation of real world applications and the required descriptive analysis.
• Quiz on all topics in descriptive analytics using statistics.

UNIT III PREDICTIVE MODELING AND MACHINE LEARNING 9

Linear Regression – Polynomial Regression – Multivariate Regression – Multi Level Models –
Data Warehousing Overview – Bias/Variance Trade Off – K Fold Cross Validation – Data
Cleaning and Normalization – Cleaning Web Log Data – Normalizing Numerical Data –
Detecting Outliers – Introduction to Supervised And Unsupervised Learning – Reinforcement
Learning – Dealing with Real World Data – Machine Learning Algorithms –Clustering – Python
Based Application.

Suggested Activities:
• Solve numerical problem solving using linear regression models.
• Demonstrate data cleaning using WEKA tool.
• Demonstration of data preprocessing and machine learning features in Python.

4
Suggested Evaluation Methods:
• Simple lab based activities for machine learning in Python using small benchmark
datasets.
• Tool based assignments on linear, polynomial and multivariate regression using real
world case studies.
• Assignment on comparative analysis of two or more data sets using their features.

UNIT IV DATA ANALYTICAL FRAMEWORKS 9

Introducing Hadoop –Hadoop Overview – RDBMS versus Hadoop – HDFS (Hadoop
Distributed File System): Components and Block Replication – Processing Data with Hadoop
– Introduction to MapReduce – Features of MapReduce – Introduction to NoSQL: CAP
theorem – MongoDB: RDBMS Vs MongoDB – Mongo DB Database Model – Data Types and
Sharding – Introduction to Hive – Hive Architecture – Hive Query Language (HQL).

Suggested Activities:
• Case studies on applications involving usage of data analytical frameworks.
• Demonstration of Installation and configuring Hadoop and MapReduce.
• Design and develop algorithms to be executed in Map Reduce involving numerical
methods for analytics.
• Installation of MongoDB and simple data management.

Suggested Evaluation Methods:

• Mini Project (Group) – Real time data collection, saving in Hive, implement analytical
techniques using Map-Reduce Tasks and Result Projection.
• Practical – Programming assignments in MongoDB.
• Quiz on Hive query language.

UNIT V DATA SCIENCE USING PYTHON 9

Introduction to Essential Data Science Packages: Numpy, Scipy, Jupyter, Statsmodels and
Pandas Package – Data Munging: Introduction to Data Munging, Data Pipeline and Machine
Learning in Python – Data Visualization Using Matplotlib – Interactive Visualization with
Advanced Data Learning Representation in Python.

Suggested Activities:
• Demonstration of simple Python scripts using NumPy and SciPy Package.
• Demonstration on NumPy arrays and matrix operations.
• Simple lab activities on dimensionality reduction and feature selection using Python.
• Demonstration of experiments on data visualization using matplotlib functions.

Suggested Evaluation Methods:

• Mini Project using Python for data analytics with benchmark datasets.
• Quiz on data visualization functions.

TOTAL: 45 PERIODS
OUTCOMES:
On completion of the course, the student will be able to:
CO1: Identify the real world business problems and model with analytical solutions.
CO2: Solve analytical problem with relevant mathematics background knowledge.
CO3:Convert any real world decision making problem to hypothesis and apply suitable
statistical testing.
CO4:Write and demonstrate simple applications involving analytics using Hadoop and
MapReduce.

5
CO5: Use open source frameworks for modeling and storing data. CO6:
Perform data analytics and visualization using Python.

TEXT BOOKS:
1. Frank Pane, “Hands On Data Science and Python Machine Learning”, Packt
Publishers, 2017.
2. Seema Acharya, Subhashini Chellapan, “Big Data and Analytics”, Wiley, 2015.

REFERENCES:
1. Alberto Boschetti, Luca Massaron, “Python Data Science Essentials”, Packt
Publications, 2nd Edition, 2016.
2. DT Editorial Services, Big Data, Black Book, Dream Tech Press, 2015.
3. Yuxi (Hayden) Liu, “Python Machine Learning”, Packt Publication, 2017.

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12

CO1 ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO2 ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO3 ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO4 ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO5 ✓ ✓ ✓ ✓ ✓

CO6 ✓ ✓ ✓ ✓ ✓ ✓ ✓

IT5603 DISTRIBUTED AND CLOUD COMPUTING L T PC

3 0 0 3

OBJECTIVES:
• To learn about the concepts of distributed systems.
• To understand distributed resource management.
• To study the basics of cloud computing.
• To study about virtualization and cloud resource management. To be aware of
different cloud platforms.

UNIT I INTRODUCTION TO DISTRIBUTED SYSTEM CONCEPTS 11

Introduction to Distributed Systems – Characteristics – Issues in Distributed Systems –
Distributed System Model – Request/Reply Protocols – RPC – RMI – Logical Clocks and
Casual Ordering of Events – Election Algorithm – Distributed Mutual Exclusion –Distributed
Deadlock Detection Algorithms.

Suggested Activities:
• Implement RPC and Bankers algorithm.
• Create and Distribute a Torrent file to share a file in LAN Environment.

6
Suggested Evaluation Methods:
• Demonstration and assessment of the working of the implemented algorithm.

UNIT II INTRODUCTION TO CLOUD COMPUTING 10

Introduction to Cloud Computing – Evolution of Cloud Computing – Cloud Characteristics –
Elasticity in Cloud – On-demand Provisioning – NIST Cloud Computing Reference
Architecture– Architectural Design Challenges – Deployment Models: Public, Private and
Hybrid Clouds – Service Models: IaaS – PaaS – SaaS – Benefits of Cloud Computing.

Suggested Activities:
• Use Google Collaboration Tools: Create Google Docs, Sheets, and Slides and share
it with others.
• Explore public cloud services like Amazon, Google, Sales force, and Digital Ocean etc.

Suggested Evaluation Methods:

• Quiz on different architectural styles of cloud.
• Report Submission - Comparison of various services provided by different Cloud
Service Providers (Configuration of VM, Cost, Network Bandwidth etc.).

UNIT III CLOUD ENABLING TECHNOLOGIES 9

Introduction to Web Service and Service Oriented Architecture – SOAP – REST – Basics of
Virtualization – Full and Para Virtualization– Implementation Levels of Virtualization – Tools
and Mechanisms – Virtualization of CPU – Memory – I/O Devices – Desktop Virtualization –
Server Virtualization.

Suggested Activities:
• Create a simple web service using Python Flask /Java /any language [Web service:
Client-server model should be implemented using socket/http].
• Install Oracle Virtual Box/VMware Workstation and Create a chat application [Note:
Launch two Virtual Machines for chat application].

Suggested Evaluation Methods:

• Review the web service implementation - Proper Connection should be established
between the client and server to make use of the service offered by the Server.
• Review the working of Application in virtual environment.

UNIT IV CLOUD MANAGEMENT, STORAGE AND SECURITY 8

Resource Provisioning and Methods – Cloud Management Products – Cloud Storage –
Provisioning Cloud Storage – Managed and Unmanaged Cloud Storage – Cloud Security
Overview – Cloud Security Challenges –Security Architecture design – Virtual Machine
Security – Application Security –Data Security.

Suggested Activities:
• Use security tools like ACUNETIX, ETTERCAP to scan web applications on the cloud,
cloud networks for finding vulnerabilities, verifying leakage of information to an
unauthorized third party.
Suggested Evaluation Methods:
• Report Submission - Generate a detailed report describing vulnerabilities along with
the suitable action that can be taken to remedy the loopholes.

7
UNIT V CLOUD SOFTWARE AND COMPUTING PLATFORMS 7
HDFS – Map Reduce – Google App Engine (GAE) – Programming Environment for GAE –
Architecture of GFS – Case Studies: Openstack, Heroku, and Docker Containers –Amazon
EC2, AWS, Microsoft Azure, Google Compute Engine.

Suggested Activities:
• Install and configure OpenStack all-in-one using Devstack/Packstack and Launch VMs
in OpenStack through dashboard.

Suggested Evaluation Methods:

• OpenStack Dashboard should be accessed though web browser. Verify the working of
instance by logging into it / pinging the instance.

TOTAL: 45 PERIODS
OUTCOMES:
On completion of the course, the students will be able to:
CO1: Appreciate distributed computing, distributed resource management.
CO2: Articulate the main concepts, key technologies, strengths and limitations of cloud
computing.
CO3: Develop the ability to understand and use the architecture of compute and storage
cloud, service and delivery models.
CO4: Explain the core issues of cloud computing such as resource management and
security.
CO5: Choose the appropriate technologies, algorithms and approaches for implementation
and use of cloud.
CO6: Establish own cloud environment using Openstack and work on it.

TEXTBOOKS:
1. Andrew S. Tanenbaum, Maarten Van Steen, “Distributed Systems - Principles and
Paradigms”, Second Edition, Pearson, 2006.
2. Kai Hwang, Geoffrey C Fox, Jack G Dongarra, “Distributed and Cloud Computing,
From Parallel Processing to the Internet of Things”, Morgan Kaufmann Publishers,
2012.

REFERENCES:
1. Mukesh Singhal, “Advanced Concepts In Operating Systems”, McGraw Hill Series in
Computer Science, 1994.
2. Buyya R., Broberg J., Goscinski A., “Cloud Computing: Principles and Paradigm”, John
Wiley, 2011.
3. John W. Rittinghouse, James F. Ransome, “Cloud Computing: Implementation
“Management and Security”, CRC Press, 2010.

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12

CO1 ✓ ✓

CO2 ✓ ✓ ✓

CO3 ✓ ✓ ✓ ✓ ✓ ✓

8
 CO4 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO5 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO6 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

IT5611 EMBEDDED SYSTEMS AND INTERNET OF THINGS LABORATORY L T P C

0042

OBJECTIVES:
• To learn tools relevant to Embedded System and IoT development.
• To write simple assembly programs that use various features of the processor.
• To explore Embedded C Programs for different embedded processors.
• To develop simple applications using Arduino/Raspberry Pi/open platform.
• To design and develop IOT application for real world scenario.

LIST OF EXERCISES:
1. Write 8051 Assembly Language experiments using simulator.
2. Test data transfer between registers and memory.
3. Perform ALU operations.
4. Using interrupts generate waveforms and test Timers.
5. Write assembly language experiments using Kit to test interfaces and interrupts using
Traffic Generator, DAC, ADC, Stepper Motor (2).
6. Write Basic and arithmetic Programs Using Embedded C.
7. Write Embedded C program to test interrupt and timers.
8. Develop Real time applications – clock generation, wave form generation, counter –
using embedded C.
9. Explore ARM/PIC based controllers using Embedded C.
10. Explore different communication methods with IoT devices.
11. Develop simple application – testing infrared sensor – IoT Applications – using Aurdino.
12. Develop simple application – testing temperature, light sensor – IOT Application –
using open platform/Raspberry Pi.
13. Deploy IOT applications using platforms such as Bluemix.

TOTAL: 60 PERIODS
OUTCOMES:
On completion of the course, the students will be able to:
CO1: Write and implement simple assembly programs that use various features of the
processor.
CO2: Write an Embedded C Program, debug and interpret the results.
CO3: Develop micro controller based application.
CO4: Test and experiment different sensors for application development.
CO5: Develop IoT applications using Arduino/Raspberry Pi/open platform. CO6:
Explore deployment platforms for IoT applications.

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12

CO1 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO2 ✓ ✓ ✓ ✓ ✓ ✓ ✓ - ✓ ✓ ✓

9
 CO3 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO4 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO5 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO6 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

IT5612 DATA ANALYTICS AND CLOUD COMPUTING LABORATORY LTPC

0 04 2

OBJECTIVES:
• To provide hands-on experience to cloud and data analytics frameworks and tools.
• To use the Python packages for performing analytics.
• To learn using analytical tools for real world problems.
• To familiarize the usage of distributed frameworks for handling voluminous data.
• To write and deploy analytical algorithms as MapReduce tasks.

LIST OF EXERCISES:
Analytics Using Python:
1. Download, install and explore the features of NumPy, SciPy, Jupyter, Statsmodels and
Pandas packages.
(i) Reading data from text file, Excel and the web.
(ii) Exploring various commands for doing descriptive analytics on Iris data set.
2. Use the diabetes data set from UCI and Pima Indians Diabetes data set for performing
the following:
(i) Univariate analysis: Frequency, Mean, Median, Mode, Variance, Standard
Deviation, Skewness and Kurtosis.
(ii) Bivariate analysis: Linear and logistic regression modeling
(iii) Multiple Regression analysis
Also compare the results of the above analysis for the two data sets.
3. Apply Bayesian and SVM techniques on Iris and Diabetes data set.
4. Apply and explore various plotting functions on UCI data sets.

Cloud Computing:
5. Installation of OpenStack.
6. Creation of VMs and installing applications and executing simple programs in
OpenStack.
7. Simple applications for communication across VMs.

Hadoop, MapReduce, HDFS, Hive:

8. Install and configure Hadoop in its two operating modes: Pseudo distributed and fully
distributed.
9. Implement the following file management tasks in Hadoop: Adding files and
directories, retrieving files and deleting files.
10. Create a retail data base with the following tables: Product, Customer, Manufacturer,
Shipping and Time using MongoDB and perform data replication using sharding
techniques.
11. Install HIVE and implement the above retail schema definition and perform CRUD
operations.
TOTAL:45 PERIODS

10
OUTCOME:
On completion of the course, the students will be able to:
CO1: Install analytical tools and configure distributed file system.
CO2: Have skills in developing and executing analytical procedures in various distributed
frameworks and databases.
CO3: Develop, implement and deploy simple applications on very large datasets.
CO4: Implement simple to complex data modeling in NoSQL databases.
CO5: Develop and deploy simple applications in OpenStack cloud.
CO6: Implement real world applications by using suitable analytical framework and tools.

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12

CO1 ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO2 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO3 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO4 ✓ ✓ ✓ ✓ ✓

CO5 ✓ ✓ ✓ ✓ ✓

CO6 ✓ ✓ ✓ ✓ ✓ ✓ ✓

IT5613 SOCIALLY RELEVANT PROJECT LABORATORY LTPC

0 0 21
OBJECTIVES:
• To identify socially relevant problems.
• To design solutions for socially relevant problems.
• To develop projects based on software design process.
• To implement solutions for societal valued projects using relevant state of the art
technologies.
• To test the implemented project based on user needs and usefulness.

Students are expected to take up problems that would directly benefit the society and design
and implement an IT based solution for the problem, based on the courses undertaken up to
that semester. The domains of the problems may reach out to sectors like but not limited to
Energy, Education, Material, Environment, Telecommunications, Defense, Healthcare,
Entertainment and Agriculture. The societal value of the project is to be evaluated based on
the need of the hour and request from stakeholders. The evaluation of the project would be
based on the usefulness of the problem statement, formulation of the problem, stakeholders
need, and the usage statistics of the solution and the technical merit of the solution.

The project design, development and testing phases can be as shown below:

REQUIREMENTS ENGINEERING PHASE:

• Problem identification.
• Feasibility study of domain.
• Requirement elicitation and analysis.

11
DESIGN PHASE:
• Architectural design.
• UI design.
• Component Design.
• Database design.

IMPLEMENTATION PHASE:
• Coding in a suitable language using necessary platforms and tools.

TESTING AND VALIDATION PHASE:

• Component Testing
• System Testing
• Acceptance Testing
TOTAL : 30 PERIODS
OUTCOMES:
On completion of the course, the students will be able to:
CO1: Analyze social problems and provide technical solutions.
CO2: Benefit the society by providing IT based solutions for social problems.
CO3: Design, develop and implement solutions for social problems.
CO4: Develop innovative technical solutions of social relevance.
CO5: Design, develop and implement standard solutions to social problems applying CO6:
Software engineering methodologies.
CO6: Evaluate the solution based on usefulness, effectiveness and user satisfaction.

REFERENCES:
1. https://www.niti.gov.in/.
2. https://www.sih.gov.in/.

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12

CO1 ✓ ✓ ✓ ✓ ✓

CO2 ✓ `✓ ✓ ✓ ✓

CO3 ✓ ✓ ✓ ✓ ✓

CO4 ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO5 ✓ ✓ ✓ ✓

CO6 ✓ ✓ `✓ ✓

12
IT5019 SOFT COMPUTING L T P C
3 0 0 3

OBJECTIVES:
• To give students knowledge of soft computing theories and fundamentals.
• To design a soft computing system required to address a computational task and use
heuristics based on human experience.
• To understand fuzzy sets and fuzzy logic for problem solving.
• To become familiar with neural networks that can learn from available examples and
generalize to form appropriate rules for inferencing systems.
• To familiarize with genetic algorithms and other random search procedures useful while
seeking global optimum in self-learning situations.

UNIT I FUZZY COMPUTING 9

Basic Concepts of Fuzzy Logic – Fuzzy Sets and Crisp Sets – Fuzzy Set Theory and
Operations – Properties of Fuzzy Sets – Fuzzy and Crisp Relations – Fuzzy to Crisp
Conversion – Membership Functions – Interference in Fuzzy Logic – Fuzzy If-Then Rules,
Fuzzy-Implications and Fuzzy Algorithms – Fuzzifications and Defuzzificataions – Fuzzy
Controller – Industrial Applications.

Suggested Activities:
• Install MatLab Fuzzy Logic Toolbox and ANN toolbox to design and simulate systems.
Suggested Evaluation Methods:
• Quizzes on basic concepts of fuzzy logic and operations.

UNIT II FUNDAMENTALS OF NEURAL NETWORKS 9

Neuron, Nerve Structure and Synapse – Artificial Neuron and its Model – Activation Functions
– Neural Network Architecture: Single Layer and Multilayer Feed Forward Networks,
Recurrent Networks – Various Learning Techniques: Perception and Convergence Rule,
Auto-Associative and Hetero-Associative Memory.

Suggested Activities:
• Practical – Develop a supervised model to train neural net that uses the AND/OR/XOR
two input binary/bipolar input and output data and learn linear models to understand
the importance of initialization parameters.

Suggested Evaluation Methods:

• Implementation evaluation with appropriate input set.

UNIT III BACK PROPAGATION NETWORKS 9

Back Propagation Networks Architecture: Perceptron Model, Solution, Single Layer Artificial
Neural Network, Multilayer Perception Model – Back Propagation Learning Methods – Effect
of Learning Rule Co-Efficient – Factors Affecting Back Propagation Training – Applications.

Suggested Activities:
• Train neural net that uses the XOR three input binary/bipolar input and output data and
learn linear models to understand the importance of learning parameters.
• Train a linear / non linear model with one hidden layer, two hidden layers.
• Observe the performance with different learning rates and draw the graph depicting
the error rate with iterations.

13
Suggested Evaluation Methods:
• Implementation evaluation with new input set.

UNIT IV COMPETETIVE NEURAL NETWORKS 9

Kohenen’s Self Organizing Map – SOM Architecture, learning procedure – Application;
Learning Vector Quantization, Learning by LVQ – Adaptive Resonance Theory – Learning
procedure – Applications.

Suggested Activities:
• Train a neural net that uses any dataset and plot the cluster of patterns.

Suggested Evaluation Methods:

• Implementation evaluation with new input set.

UNIT V GENETIC ALGORITHM 9

Basic Concepts – Working Principle – Procedures of GA – Flow Chart of GA – Genetic
Representation: (Encoding) Initialization and Selection – Genetic Operators: Mutation,
Generational Cycle – Applications.

Suggested Activities:
• Implement GA for the Travelling Salesman problem to find the shortest path that visits
all cities in a set exactly once.

Suggested Evaluation Methods:

• Implementation evaluations by testing the code on different route maps and checking
the optimal solution.
TOTAL: 45 PERIODS
OUTCOMES:
On completion of the course, the student will be able to:
1. Identify and describe soft computing techniques and their roles in building intelligent
machines.
2. Recognize the feasibility of applying a soft computing methodology for a particular
problem.
3. Apply fuzzy logic and reasoning to handle uncertainty and solve engineering problems.
4. Apply genetic algorithms to optimization problems.
5. Design neural networks for pattern classification and regression problems.
6. Compare different neural network approaches.

TEXTBOOKS:
1. S. Rajasekaran, G.A. Vijayalakshmi Pai, “Neural Networks, Fuzzy Logic and Genetic
Algorithm: Synthesis and Applications”, Prentice Hall of India, 2010.
2. J.S.R. Jang, C.T. Sun, E. Mizutani, “Neuro-Fuzzy and Soft Computing”, Pearson
Education, 2004.

REFERENCES:
1. S.N. Sivanandam, S.N. Deepa, “Principles of Soft Computing”, Second Edition, Wiley-
India, 2007.
2. Siman Haykin, “Neural Networks”, Prentice Hall of India, 1999.
3. Timothy Ross, “Fuzzy Logic with Engineering Applications”, Wiley Publications, 2016.

14
 4. David E. Goldberg, “Genetic Algorithms in Search, Optimization and Machine
Learning”, Pearson Education, 2008.

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12

CO1
✓ ✓

CO2
✓ ✓ ✓ ✓ ✓ ✓

CO3
✓ ✓ ✓ ✓ ✓

CO4
✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

IT5022 INFORMATION RETRIEVAL LT PC

3 0 0 3

OBJECTIVES:
• To learn the fundamentals of Information Retrieval and its various models.
• To learn about the preprocessing techniques and query languages used in IR system.
• To understand the performance metrics of IR System.
• To learn the usage and design of Web Search Engines.
• To study the basics of recommender systems and information extraction system.

UNIT I INTRODUCTION 9
Introduction – Goals and History of IR – The Impact of the Web on IR – The Role of Artificial
Intelligence (AI) in IR – Basic IR Models – Boolean and Vector Space Retrieval Models –
Ranked Retrieval – Text similarity metrics – TF-IDF (term frequency/inverse document
frequency) Weighting – Cosine Similarity.

Suggested Activities:
• Understanding the basics of IR.
• Study of other retrieval models.
• Practical – Implementation of the retrieval model with Lemur Tool kit and test the
performance of different retrieval algorithms.

Suggested Evaluation Methods:

• Quizzes on IR and other retrieval models.
• Assignments on retrieval models.

UNIT II PREPROCESSING 9
Basic Tokenizing – Indexing and Implementation of Vector Space Retrieval – Simple
Tokenizing – Stop Word Removal and Stemming – Inverted Indices –Efficient Processing with
Sparse Vectors – Query Operations and Languages – Relevance Feedback – Query
Expansion – Query Languages.

15
Suggested Activities:
• Study of indexing techniques.
• Practical – Implementation of vector space model.
• Flipped classroom on query expansion with thesaurus.

Suggested Evaluation Methods:

• Case studies on tokenization, stop word removal and stemming.
• Tutorials on query operations and languages.

UNIT III METRICS 9

Experimental Evaluation of IR – Performance metrics Recall, Precision and F measure –
Evaluations on Benchmark Text Collections – Text Representation – Word Statistics – Zipf’s
Law – Porter Stemmer – Morphology – Index Term Selection using Thesauri –Metadata and
Markup Languages – Web Search Engines – Spidering – Metacrawlers – Directed Spidering
– Link Analysis Shopping Agents.

Suggested Activities:
• Practical – Implementation of evaluation metrics.
• Study and implementation of PageRank algorithm.
• Study of web page duplicate detection technique.

Suggested Evaluation Methods:

• Tutorials on web search and crawling.
• Quizzes on precision, recall and f-measure.
• Assignments on web search engines.

UNIT IV CATEGORIZATION AND CLUSTERING 9

Text Categorization and Clustering – Categorization Algorithms – Naive Bayes – Decision
Trees and Nearest Neighbor – Clustering Algorithms – Agglomerative Clustering – k Means –
Expectation Maximization (EM) – Applications to Information Filtering – Organization and
Relevance Feedback.

Suggested Activities:
• Study of different classification techniques and its uses in different applications.
• Practical – Implementation of classification and clustering techniques with WEKA tool.
• Assignments on clustering algorithms.

Suggested Evaluation Methods:

• Quizzes on different categorization and clustering methods.
• Exercise on categorization and clustering algorithms for real time applications.

UNIT V EXTRACTION AND INTEGRATION 9

Recommender Systems – Collaborative Filtering – Content Based Recommendation of
Documents and Products – Information Extraction and Integration – Extracting Data from Text
– XML – Semantic Web – Collecting and Integrating Specialized Information on the Web.

Suggested Activities:
• Study of types of collaborative filtering techniques.
• Flipped classroom on semantic web.

16
Suggested Evaluation Methods:
• Assignments on item based and user based collaborative filtering techniques.
• Quizzes on semantic web.
TOTAL: 45 PERIODS
OUTCOMES:
On completion of the course, the student will be able to:
1. Build an Information Retrieval system using the available tools.
2. Apply indexing and query expansion techniques for efficient retrieval.
3. Apply performance metrics to validate any information retrieval system.
4. Apply machine learning techniques for text classification and clustering for efficient
Information Retrieval.
5. Design and analyze the Web content structures.
6. Design and implement recommender and information extraction system.

TEXT BOOKS:
1. Christopher D. Manning, Prabhakar Raghavan, Hinrich Schütze,” Introduction to
Information Retrieval”, Cambridge University Press, 2008.
2. Ricci, F. Rokach, L. Shapira, B. Kantor, P.B. “Recommender Systems Handbook”,
Springer, 2011.

REFERENCES:
1. Brusilovsky, Peter, “The Adaptive Web Methods and Strategies of Web
Personalization”, Springer, 2007.
2. Jure Leskovec, Anand Rajaraman, Jeffrey David Ullman, “Mining of Massive
Datasets”, Second Edition, Cambridge University Press, 2014.
3. Ricardo Baeza-Yates, Berthier Ribeiro-Neto, “Modern Information Retrieval: The
Concepts and Technology behind Search”, Second Edition, ACM Press books, 2011.

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12

CO1 ✓ ✓ ✓ ✓ ✓ ✓ ✓

CO2 ✓ ✓ ✓ ✓ ✓ ✓

CO3 ✓ ✓ ✓ ✓ ✓ ✓

CO4 ✓ ✓ ✓ ✓ ✓

CO5 ✓ ✓ ✓ ✓ ✓ ✓

CO6 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

17