B.

Tech Robotics and AI

6th Semester
BTRA 601-22 Advanced Artificial Intelligence 3 0 0
BTRA 603-22 Kinematics and Robotics 3 0 0
Elective-II 3 0 0
Elective-III 3 0 0
Open Elective-I 3 0 3
BTRA 602-22 Advanced Artificial Intelligence Lab 0 0 2
BTRA 604-22 Kinematics and Robotics Lab 0 0 2
Elective-II Lab 0 0 2
Elective-III Lab 0 0 2
Project-I 0 0 6
Elective-II
BTRA 605-22 Embedded System Design
BTRA 606-22 Embedded System Design Lab
BTRA 607-22 Robot Operating System
BTRA 608-22 Robot Operating System Lab
BTRA 609-22 Control System
BTRA 610-22 Control System Lab

Elective-III
BTRA 611-22 Mobile and Micro Robotics
BTRA 612-22 Mobile and Micro Robotics Lab
BTRA 613-22 Data Analytics
BTRA 614-22 Data Analytics Lab
BTRA 615-22 Intelligent Manufacturing
BTRA 616-22 Intelligent Manufacturing Lab
BTRA 601-22 Advanced Artificial Intelligence 3L:0T:0P 3 credits

Unit 1:
Overview of Probability Theory, Bayes Networks, Independence, I-Maps, Undirected Graphical
Models, Bayes Networks and Markov Networks,

Unit 2:
Local Models, Template Based Representations, Exact Inference: Variable Elimination; Clique
Trees, Belief Propagation Tree Construction.

Unit 3:
Introduction to Optimization, Approximate Inference: Sampling, Markov Chains, MAP Inference,
Inference in Temporal Models, Learning Graphical Models: Intro Parameter Estimation, Bayesian
Networks and Shared Parameters.

Unit 4:
Structure Learning, Structure Search Partially Observed Data, Gradient Descent, EM, Hidden
Variables, Undirected Models, Undirected Structure Learning, Causality, Utility Functions,

Unit 5:
Decision Problems, Expected Utility, Value of Information, Decision- Making: basics of utility
theory, decision theory, sequential decision problems, elementary game theory, sample application.

Suggested Text Books:

(i) Russell, Stuart and Norvig, Peter, Artificial Intelligence: A Modern Approach" Prentice Hall,
2003.
(ii) Zhongzhi Shi, “Advanced Artificial Intelligence”, World Scientific Publishing Company,
March 2011.
(iii) Luger " Artificial Intelligence", Edition 5, Pearson, 2008.

Suggested Reference Books:

(i) Daphne Koller and Nir friedman, “Probabilistic Graphical Models”, MIT Press, 2009.
(ii) Russell and P. Norvig, “Artificial Intelligence”, Pearson Publication, 2020.
(iii) Cristopher Bishop: pattern Recognition and machine Learning, Springer, 2006.

Course Outcomes:
After the completion of this course, the students will be able to:
● Explain in detail how the techniques in the perceive-inference-action loop work.
● Choose, compare, and apply suitable basic learning algorithms to simple applications.
● Ability to explain how deep neural networks are constructed and trained, and apply deep
neural networks to work with large scale datasets.
● Understand and develop deep reinforcement learning algorithms for suitable applications.
BTRA 603-22 Kinematics and Robotics 3L:0T:0P 3 credits

Unit 1: Introduction
Vector Representations and Operations, Transformations, Translational and Rotational, Coordinate
Reference Frames, Properties of Transformation Matrices, Matrix Creation and Manipulation
using MATLAB.

Unit 2: Homogeneous Transformations

Pure Translation, Pure Rotation about an Axis, Representation of Combined Transformations,
Transformations Relative to a Moving Frame, Homogeneous Transformations using MATLAB.

Unit 3: Kinematics:
Kinematic Parameters, The Denavit-Harternberg (DH) Representation, Forward & Inverse
Kinematic Equations: Position, Cartesian Coordinates, Cylindrical Coordinates, Spherical
Coordinates, Articulated Coordinates, Kinematics of Industrial Robots, Kinematics using
MATLAB.

Unit 4: Forward & Inverse Kinematic:

Orientation Description, Forward & Inverse Kinematic Equations Orientation, Roll, Pitch and Yaw
(RPY) Angles, Euler Angles, Geometric Approach to Inverse Kinematics, Forward and Inverse
Kinematics of Industrial Robots, Design Project: A 3-DOF Robot.

Unit 5: Velocity & Acceleration Analysis:

Differential Motions and Relationships, Jacobian, Forward and Inverse Velocity Analysis,
Acceleration Analysis, Design Project: A 3-DOF Robot.

Suggested Text Books

(i) S. K. Saha, “Introduction to Robotics”, McGraw Hill Education (India) Pvt. Ltd., 2014.
(ii) John J. Craig, “Introduction to Robotics – Mechanics and Control”, Pearson Education, 2004.
Suggested Text Books
(i) Saeed B. Niku, “Introduction to Robotics – Analysis, Control, Applications”, Wiley India Pvt.
Ltd., 2010.
(ii) Reza N. Jazar, “Theory of Applied Robotics: Kinematics, Dynamics, and Control”, Springer
July 2010.
(iii) Tuna Balkan, “Robot Kinematics: Forward and Inverse Kinematics”, Intech, Dec. 2006.
Course Outcomes:
After the completion of this course, the students will be able to:
● Explain position and orientation parameters for describing the pose of industrial robots.
● Apply mathematical tools for solving robot kinematics problems.
● Assign the coordinate frames to industrial robots and derive their forward and inverse
kinematic equations.
● Use software tools for obtaining solutions to forward and inverse kinematics problems.
BTRA 602-22 Advanced Artificial Intelligence Laboratory 0L:0T:2P 1 credit
Suggested List of Assignments
● Implement A* algorithm.
● Implement AO* algorithm.
● Implementation of other Searching algorithms.
● Implementation of Min/MAX search procedure for game Playing.
● Implementation of variants of Min/ Max search procedure.
● Implementation of a mini Project using the concepts studied in the AI course.
This list is a guideline. The instructor is expected to improve it continuously.
Suggested Text Books:
(i) Luger "Artificial Intelligence", Edition 5, Pearson, 2008.
(ii) Michael Negnevitsky, “Artificial Intelligence: A Guide to Intelligent Systems”, Addison-
Wesley, May 2011.
Suggested Reference Books:
(i) Russell, Stuart and Norvig, Peter, “Artificial Intelligence: A Modern Approach" Prentice Hall,
2003.
(ii) Bench-Capon, T. J. M., “Knowledge Representation: An approach to artificial intelligence”,
Academic Press, 1990.
(iii) Mohamad H. Hassoun, “Fundamentals of Artificial Neural Networks”, The MIT Press, 1995.
Course Outcomes:
Upon successful completion of the course, the students will be able to:
● Develop an Explanation of what is involved in learning models from data.
● Implement a wide variety of learning algorithms.
● Apply principles and algorithms to evaluate models generated from data.
● Apply the algorithms to a real-world problem.
BTRA 604-22 Kinematics and Robotics Lab 0L:0T:2P 1 credits

Course Outcomes: At the end of the course, the student will be able to:

 demonstrate the mechanism of various robots

 determine the end-effector positions and joint variables using forward and inverse
kinematics respectively (L3)
 apply principles of kinematics to generate workspaces of planar and spatial robots
 determine joint velocities and accelerations of a 2R planar robot for the given input torques
 demonstrate trajectory planning, loading unloading, and pick and place operations of an
industrial robot

LIST OF EXERCISES

1. Simulate the robot motion for various inputs of the joint angular value for Move master RM-
501 robotic arm

2. Solve direct kinematics of a PUMA 560 robotic arm for the given joint variables and simulate
the robot remotely to identify the end-effector trajectory

3. Determine the joint variables of a PUMA 560 robotic arm for a given Cartesian trajectory and
compare with simulation

4. Forward kinematic analysis of a 2R planar robot and 6 DoF robots

5. Inverse kinematic analysis of a 2R planar robot and 6 DoF robots

6. Generate workspace of planar robots

7. Generate workspace of spatial robots

8. Generate a 3D model of a robot based on DH parameters

9. Forward dynamic analysis of a 2R planar robot

10. Inverse dynamic analysis of a 2R planar robot

11. Program for loading and unloading operations on 6 DoF Articulated robot

12. Program for palletizing application on 6 DoF Articulated robot

13. Program for conveyor belt application on SCARA robot

14. Program for deburring and assembly application on SCARA robot

Weblinks:

1. http://vlabs.iitkgp.ernet.in/mr/index.html# (IIT Kharagpur)

2. RoboAnalyzer (IIT Delhi)

3. RT Toolbox (Mitsubishi Robots)

BTRA 605-22 Embedded Systems Design 3L:0T:0P 3 credits

Unit 1: ARM-Cortex Series Architecture:

Embedded systems, classification, ARM 32-bit microcontroller Tiva, architecture technology
overview, Architectural Features of ARM Cortex M series: Tiva Block Diagram, CPU modes,
register organization, ROM, RAM, timers, data and address bus, Memory and I/O interfacing
concepts, memory mapped I/O. CISC Vs RISC design philosophy, Von-Neumann Vs Harvard
architecture, instruction set, pipelining, exceptions and its handling, memory, I/O’s and addressing
modes.

Unit 2: Operating system based development:

Operating systems fundamentals, operating system services, memory management, process
management, device management, file management, operating system services- program
execution, I/O operation, file manipulation, communication, operating system properties-
multitasking, parallel programming, interactivity, scheduling and scheduling algorithms. Linux:
An overview of Red Hat Linux, installing Ubuntu, Linux commands, shell scrip programming,
embedded Linux.

Unit 3: Development Tools (Open Source):

GNU tools, text editors-vi, nano, pico, etc. IDE-Eclipse, code lite, compilers-gcc, g++, debuggers,
cross- compilers, gcc- arm specific tool chains and in line assembly, Writing and compiling C/C++
programs, cross-compilation for ARM development board, Basics of make file, static and dynamic
libraries.

Unit 4: Kernel programming:

Kernel, basic functionalities of kernel, kernel module programming, Linux kernel sources, kernel
configuration, booting kernel, kernel booting parameters, root file system, bootloader, U- boot,
porting Linux ARM board, device driver programming, architecture, I/O communication, writing
simple character device driver.

Unit 5: RTOS:
RTOS concepts using Tiva: foreground and background systems, critical section, shared resources,
tasks, multitasking, context switching, kernels, pre-emptive and non- pre-emptive schedulers,
static and dynamic priorities, priority inversion, mutual exclusion, synchronization, inter task
communication mechanisms, Interrupts: latency, response and recovery, clock tick, memory
requirements.

Unit 6: Interfacing and application development

Interfacing of peripherals using Tiva: LED and sensors, ADC, Timer, PWM, UART, SPI,
I2C.Development of web server, wireless module interfacing, camera interfacing, open CV on
Beagle Bone Black. Control application, Java programming on Beagle Bone Black, porting
android for mobile applications like controlling Beagle Bone Black I/O through mobile.

Suggested Text Books:

(i) Sloss Andrew N, Symes Dominic, Wright Chris, “ARM System Developer's Guide: Designing
and Optimizing”, Morgan Kaufman Publication, 2004.
(ii) Michael Beck, “Linux Kernel Programming”, Addison-Wesley Professional, 3rd ed., 2002.
Suggested Reference Books:
(i) Raj Kamal, “Embedded Systems – Architecture: Programming and Design”, Tata McGraw-
Hill Education, 3rd edition, 2003.
(ii) Embedded Systems: Real-Time Interfacing to ARM Cortex-M Microcontrollers, 2014,
Jonathan W Valvano Create space publications ISBN: 978-1463590154.
(iii) Embedded Systems: Introduction to ARM Cortex - M Microcontrollers, 5th edition Jonathan
W Valvano, Create space publications ISBN-13: 978-1477508992.
Course Outcomes:
● Hands on usage of IDE of processors and algorithm development.
● To understand the concept of OS, RTOS and application perspectives.
● Understanding of RISC architecture of processor, its features and application.
● Study, design, analyze and prototype various embedded systems.
BTRA 606-22 Embedded Systems Design Laboratory 0L:0T:2P 1 credit

Laboratory Experiments:

1. Study of ARM evaluation system.

2. Interfacing ADC and DAC.

3. Interfacing LED and PWM.

4. Interfacing real time clock and serial port.

5. Interfacing keyboard and LCD.

6. Interfacing EPROM and interrupt.

7. Mailbox.

8. Interrupt performance characteristics of ARM and FPGA.

9. Flashing of LEDS.

10. Interfacing stepper motor and temperature sensor.

11. Implementing ZigBee protocol with ARM.

Suggested Text Books:

(i) Sloss Andrew N, Symes Dominic, Wright Chris, “ARM System Developer's Guide:

Designing and Optimizing”, Morgan Kaufman Publication, 2004.

(ii) Michael Beck, “Linux Kernel Programming”, Addison-Wesley Professional,3rd edition

2002.

Suggested Reference Books:

(i) Raj Kamal, “Embedded Systems – Architecture: Programming and Design”, Tata McGraw-Hill
Education, 3rd edition,2003.

(ii) Embedded Systems: Real-Time Interfacing to ARM Cortex-M Microcontrollers, 2014,

Jonathan W Valvano Create space publications ISBN: 978-1463590154.

(iii) Embedded Systems: Introduction to ARM Cortex - M Microcontrollers, 5th edition Jonathan
W Valvano, Create space publications ISBN-13: 978-1477508992.

Course Outcomes:
● Write programs in ARM for a specific Application.
● Interface memory and Write programs related to memory operations.
● Interface A/D and D/A convertors with ARM system.
● Analyze the performance of interrupt.
● Write programmes for interfacing keyboard, display, motor and sensor.
● Formulate a mini project using embedded system.
BTRA 607-22 Robot Operating Systems 3L:0T:0P 3 credits

Unit 1: Basic principles, Operating System Structures, System Calls & Types, Processes: Concept
Scheduling, Inter Process Communication, Introduction to distributed Operating System, Types of
network based OS.
Unit 2: Overview of RTOS, RTOS Task and Task State, Pre-emptive Scheduler, Process
Synchronization, Message Queues, Mailboxes, Pipes, critical Section, Semaphores, Classical
Synchronization Problem, Deadlocks.
Unit 3: Inserting BSP in Kernel Build Procedure, Boot loader Interface, Memory Map, Interrupt
Management, PCI Subsystem, Timers - UART- Power Management. Embedded Storage: MTD –
MTD Architecture - MTD driver for NOR Flash – Flash Mapping driver
Unit 4: Embedded kernel & components, Embedded File System: RAM Disk – RAMFS –
CRAMFS, Journaling Flash File Systems: JFFS and JFSS2, NFS: PROC File system, Optimizing
storage Space: Kernel space optimization - Application Space Optimization, Applications for
Embedded Linux - Tuning kernel memory.
Unit 5: Linux Devices Drivers, Embedded Drivers: Linux Serial Driver - Ethernet Driver - I 2C
Subsystem on Linux - USB Gadgets, Watchdog Timer, Kernel Modules.

Text Books:
 Silberschatz, Galvin, Gagne, “Operating System Concepts”, 6th edition, John Wiley, 2003.
 Raj Kamal, “Embedded Systems -Architecture, Programming and Design”, Tata McGraw
Hill, 2006.
 P. Raghavan, Amol Lad, SRIram Neelakandan, “Embedded Linux System Design and
development”, Auerbach Publications 2005.
 Jonathan Corbet, Allesandro Rubini & Greg Kroah-Hartman, “Linux Device DRIvers”,
O’Reilly, 3rdedition, 2005.
Reference Books:
 LENTIN JOSEPH “ Robot operating system (ROS) for absolute beginners”. Released May
2018 Publisher(s): Apress ISBN: 9781484234051.
 Anis Koubaa Robot Operating System (ROS) The Complete Reference (Volume 6)
BTRA 608-22 Robot Operating Systems Lab 0L:0T:2P 1 credits

Laboratory Experiments:

1. Endowing mobile autonomous robots with planning, perception, and decision- making
capabilities.

2. Trajectory optimization.

3. Robot motion planning and perception.

4. Robot, localization, and simultaneous localization and mapping.

5. Robot Operating System (ROS) for demonstrations and hands-on activities.

Suggested Text Books:

(i) Morgan Quigley, “Programming Robots with ROS: A Practical Introduction to the Robot
Operating System” , O'Reilly Media, 2015.

(ii) Carol Fairchild, Dr. Thomas L. Harman, “ROS Robotics by Example”, Packt, 2016.

Suggested Reference Books:

(i) Anis Koubaa, “Robot Operating System”, Springer link, 2016.

(ii) Anil Mahtani, “Effective Robotics Programming with ROS”, Packt Publishing, 2016.

(iii) Ramkumar Gandhinathan , Lentin Joseph , “ ROS Robotics Projects: Build and control robots
powered by the Robot Operating System, machine learning, and virtual reality”, Packt Publishing
Limited, December 2019.

Course Outcomes:

At the end of the course the students will be able to:

● Learn fundamentals, including key ROS concepts, tools, and patterns.

● Program robots that perform an increasingly complex set of behaviors, using the powerful
packages in ROS.

● See how to easily add perception and navigation abilities to your robots.

● Integrate your own sensors, actuators, software libraries, and even a whole robot into the ROS
ecosystem.

● Learn tips and tricks for using ROS tools and community resources, debugging robot behavior
using C++ in ROS.
BTRA 609-22 Control Systems 3L:0T:0P 3 credits

Unit 1: Introduction to Control System: Introduction to control system block diagram.

Importance of Control Systems. Components of control. Explanation with the help of the liquid
level control system. Significance of actuators and sensors. Types of actuators, Types of sensors.
Open loop control and closed loop control. Use of relays, switches and contactors for simple and
sequential control systems.
Module 2: Control system representation:
Mathematical representation of simple mechanical, electrical, thermal, hydraulic systems. Block
diagram representation and reduction. Signal flow graph. Transfer function of these systems. Pole
zero concepts.
Module 3: Time domain analysis:
Time response of first order, second order systems. Analysis of steady state error, Type of system
and steady state error, Time response specifications. Effect of parameter variation on open loop
and closed loop system response, sensitivity. Effect of feedback on system response, stability and
disturbance.
Module 4: Stability:
Concept of stability, Effect of pole zero location on stability, Routh- Hurwitz criterion. Root Locus
method for analysis of gain margin, phase margin and stability.
Module 5: Control system analysis in frequency domain:
Concept of frequency domain behavior, Bode Plot for analyzing systems in frequency domain.
Frequency domain performance specifications. Correlation between time domain and frequency
domain specification. Nyquist Analysis.
Module 6: State Space Approach:
Representation of system in state space, Converting transfer function model into state space model.
Non uniqueness of state space model, Canonical representation, Eigenvalues, Solution of state
equations, Concept of State feedback control, controllability, Observability.
Suggested Text Books:
(i) Nagrath & M. Gopal “Control System Engineering”, Anshan, 2008.
(ii) Norman S. Nice, “Control System Engineering”, Wiley, 2008.
Suggested Reference Books:
(i) Smarajit Ghosh, “Control Systems Theory & Applications”, Pearson Education, 2007.
(ii) Katsuhiko Ogata,” Modern Control Engineering”, Prentice Hall, 2010.
(iii) Norman S. Nise, “Control System Engineering”, Wiley, 2014.
Course Outcomes:
At the end of this course, the students will demonstrate the ability to:
● Appreciate the role of the control system.
● Analyze the mathematical model of the control system.
● Solve to get a time domain response.
● Analyze stability of the system.
● Use bode plot for frequency domain analysis.
● Analyze the control system in state space.
BTRA 610-22 Control Systems Laboratory 0L:0T:2P 1 credit

Experiments:
● To study input out characteristic of various control system components.
● To obtain step response and find time response specification of electrical system, hydraulic
system, pneumatic system and thermal system.
● To obtain transfer function and poles zeros of DC motor experimentally.
● To obtain root locus experimentally.
● Use Matlab to study the effect of feedback gain on system response.
● Use Matlab to study the effect of damping factor zeta on time control performance specifications.
● Use Matlab to obtain root locus for a given system and find performance specifications there
from. Study effect of addition of zero and pole on root locus.
● Use Matlab to get a bode plot and obtain gain margin and phase margin for various systems.
● Use Matlab to obtain state space representation from transfer function, find Eigenvalues,
Analyze controllability, observability and stability.
Suggested Text Books:
(i) Nagrath & M. Gopal “Control System Engineering”, Anshan, 2008.
(ii) Norman S. Nice, “Control System Engineering”, Wiley, 2008.
Suggested Reference Books:
(i) Smarajit Ghosh, “Control Systems Theory & Applications”, Pearson Education 2007.
(ii) Katsuhiko Ogata,” Modern Control Engineering”, Prentice Hall, 2010.
(iii) Norman S. Nise, “Control System Engineering”, Wiley, 2014.
Course Outcomes:
At the end of this course, the students will demonstrate the ability to:
● Develop the mathematical model of different components of linear feedback control system
using simulation and experiments.
● Analyze the transient characteristics of different first order and second order systems using
simulation and experiments.
● Determine the performance of system using root locus.
● Carry out the stability analysis of linear feedback control system using Bode plot and Nyquist
plot.
● Carry out the stability analysis of linear feedback control system using Modern control
techniques.
● Analyze the different types of controllers like PI, PD, PID and tuning of these controllers using
simulation and experiments.
● Describe various applications like temperature controller experimentally.
● Demonstrate an industrial application (like Bottle filling/ Pick and Place control) using PLC
BTRA 611-22 Mobile and Micro-Robotics 3L:0T:0P 3 credits

Unit 1: Introduction to Mobile Robots - Tasks of mobile robots, robots manufacturers, type of
obstacles and challenges, tele-robotics, philosophy of robotics, service robotics, types of
environment representation. Ground Robots: Wheeled and Legged Robots, Aerial Robots,
Underwater Robots and Surface Robots.
Unit 2: Kinematics and Dynamics of Wheeled Mobile Robots (two, three, four - wheeled robots,
omnidirectional and macanum wheeled robots). Sensors for localization: magnetic and optic
position sensor, gyroscope, accelerometer, magnetic compass, inclinometer, GNSS and Sensors
for navigation: tactile and proximity sensors, ultrasound rangefinder, laser scanner, infrared
rangefinder, visual system.
Unit 3:
Localization and Mapping in mobile robotics. Motion Control of Mobile Robots (Model and
Motion based Controllers): Lyapunov-based Motion Control Designs and Case Studies.
Understand the current application and limitations of Mobile Robots. Introduction to Mobile
Manipulators and Cooperative Mobile Robots.
Unit 4:
Micro-robotics: Introduction, Task specific definition of micro-robots - Size and Fabrication
Technology based definition of micro-robots - Mobility and Functional-based definition of
microrobots - Applications for MEMS based micro-robots. Implementation of Micro-robots:
Arrayed actuator principles for micro-robotic applications – Micro-robotic actuators.
Unit 5:
Design of locomotive micro-robot devices based on arrayed actuators. Micro-robotics devices:
Micro- grippers and other micro-tools - Micro-conveyors - Walking MEMS Micro-robots–
Multirobot system: Micro-robot powering, Micro-robot communication. Microfabrication and
Microassembly: Micro-fabrication principles - Design selection criteria for micromachining-
Packaging and Integration aspects – Micro-assembly platforms and manipulators.

Suggested Reference Books:

(i) Roland Siegwart, Illah Reza Nourbakhsh, Davide Sacramuzza, Introduction to
Autonomous Mobile Robots, MIT press, 2nd edition, 2011.
(ii) Howie Choset, Kevin Lynch Seth Hutchinson, George Kantor, Wolfram Burgard, Lydia
Kavraki, and Sebastian Thrun, ―Principles of Robot Motion-Theory, Algorithms, and
Implementation, MIT Press, Cambridge, 2005.
Suggested Text Books:
(i) Atnaik, Srikanta, "Robot Cognition and Navigation: An Experiment with Mobile Robots",
Springer-Verlag Berlin and Heidelberg, 2007.
(ii) Spyros G. Tzafestas, “Introduction to Mobile Robot Control”, Elsevier, 2021.
(iii) Margaret E. Jefferies and Wai-Kiang Yeap, "Robotics and Cognitive Approaches to Spatial
Mapping", Springer-Verlag Berlin Heidelberg, 2008.
Course Outcomes:
At the end of the course students will be able to:
● Identify and design a suitable manufacturing process for micro robots.
● Understand the importance of visual perception and recognition for cybernetic view.
● Program a robot for wandering and teleoperation.
BTRA 612-22 Mobile and Micro-Robotics Lab 0L:0T:2P 1 credits

Experiment based upon the theory subject.

BTRA 613-22 Data Analytics 3L:0T:0P 3 credits

Unit 1: Fundamentals of Data Analytics, Descriptive, Predictive, and Prescriptive Analytics, Data
Types, Analytics Types, Data Analytics Steps: Data Pre-Processing, Data Cleaning, Data
Transformation, and Data Visualization.

Unit 2: Data Analytics Tools

Data Analytics using Python, Statistical Procedures, NumPy, Pandas, SciPy, Matplotlib.

Unit 3: Data Pre-Processing

Understanding the Data, Dealing with Missing Values, Data Formatting, Data Normalization, Data
Binning, Importing and Exporting Data in Python, Turning categorical variables into quantitative
variables in Python, Accessing Databases with Python.

Unit 4: Data Visualization

Graphic representation of data, Characteristics and charts for effective graphical displays, Chart
types- Single variable: Dot plot, Jitter plot, Error bar plot, Box-and whisker plot, Histogram,
Twovariable: Bar chart, Scatter plot, Line plot, Log-log plot, More than two variables: Stacked
plots, Parallel coordinate plot.

Unit 5: Descriptive and Inferential Statistics

Probability distributions, Hypothesis testing, ANOVA, Regression.

Unit 6: Machine Learning Concepts

Classification and Clustering, Bayes‟ classifier, Decision Tree, Apriori algorithm, K-Means
Algorithm, Logistics regression, Support Vector Machines, Introduction to recommendation
system.

Suggested Text books:

(i) Anil Maheshwari, “Data Analytics made accessible,” Amazon Digital Publication, 2014.
(ii) James R. Evans, “Business Analytics: Methods, Models, and Decisions”, Pearson 2012.
(iii) Song, Peter X. K, “Correlated Data Analysis: Modeling, Analytics, and Applications”,
Springer-Verlag New York 2007.

Suggested Reference Books:

(i) Glenn J. Myatt, Wayne P. Johnson, “Making Sense of Data I: A Practical Guide to Exploratory
Data Analysis and Data Mining”, Wiley 2009.
(ii) Thomas H. Davenport, Jeanne G. Harris and Robert Morison, “Analytics at Work: Smarter
Decisions, Better Results”, Harvard Business Press, 2010.
(iii) Rachel Schutt, Cathy O’Neil, “Doing Data Science”, O’REILLY, 2006. Shamanth Kumar Fred
Morstatter Huan Liu “Twitter Data Analytics”, Springer-Verlag, 2014.
Course Outcomes:
At the end of the course the students will be able to:
● Examine and compare various datasets and features.
● Analyze the business issues that analytics can address and resolve.
● Apply the basic concepts and algorithms of data analytics.
● Interpret, implement, analyze and validate data using popular data analytics tools.
BTRA 614-22 Data Analytics Lab 0L:0T:2P 1 credits

List of Experiments:

1. Setting up Hadoop on standalone machine.

2. Wordcount Map Reduce program using standalone Hadoop.

3. Adding the combiner step to the Wordcount Map Reduce program.

4. Setting up HDFS.

5. Using HDFS monitoring UI

6. HDFS basic command-line file operations.

7. Setting Hadoop in a distributed cluster environment.

8. Running the Word Count program in a distributed cluster environment.

9. Using Map Reduce monitoring UI

Text Books:

Hadoop Map Reduce Cookbook, Srinath Perera & Thilina Gunarathne, 2013, PACKT
PUBLISHING.
BTRA 615-22 Intelligent Manufacturing 3L:0T:0P 3 credits

Unit 1:
Computer Integrated Manufacturing Systems Structure and functional areas of CIM system, CAD,
CAPP, CAM, CAQC, ASRS. Advantages of CIM.

Unit 2:
Manufacturing Communication Systems - MAP/TOP, OSI Model, Data Redundancy, Top- down
and Bottom-up Approach, Volume of Information. Intelligent Manufacturing System Components,
System Architecture and Data Flow, System Operation.

Unit 3:
Basic Components of Knowledge Based Systems, Knowledge Representation, Comparison of
Knowledge Representation Schemes, Interference Engine, Knowledge Acquisition. Automated
Process Planning - Variant Approach, Generative Approach, Expert Systems for Process Planning,
Feature Recognition, Phases of Process planning. Knowledge Based System for Equipment
Selection (KBSES) - Manufacturing system design. Equipment Selection Problem, Modeling the
Manufacturing Equipment Selection Problem, Problem Solving approach in KBSES, Structure of
the KRSES.

Unit 4:
Group Technology: Models and Algorithms Visual Method, Coding Method, Cluster Analysis
Method, Matrix Formation - Similarity Coefficient Method, Sorting-based Algorithms, Bond
Energy Algorithm, Cost Based method, Cluster Identification Method, Extended CI Method.
Knowledge Based Group Technology - Group Technology in Automated Manufacturing System.
Structure of Knowledge based system for group technology (KBSC IT) — Data Base, Knowledge
Base, Clustering Algorithm.

Suggested Text Books:

(i) Andrew Kusiak, “Intelligent Manufacturing Systems”, Prentice Hall, 1990.
(ii) Pat Langley, “Computational Intelligence and Intelligent Systems”, 2006.

Suggested Reference Books:

(i) Mohammad Jamshidi, “Design and Implementation of Intelligent Manufacturing Systems:
From Expert Systems, Neural Networks to Fuzzy Logic”, 1st Edition, 1995.
(ii) Lucia Knapčíková, Michal Balog, “Industry 4.0: Trends in Management of Intelligent
Manufacturing Systems”, Springer, 2019.

Course Outcomes:
After completion of the course, the students will be able to:
● Summarize the concepts of computer integrated manufacturing systems and manufacturing
communication systems.
● Identify various components of knowledge based systems.
● Demonstrate the concepts of artificial intelligence and automated process planning.
● Select the manufacturing equipment using knowledge based system for equipment selection.
● Apply various methods to solve group technology problems and demonstrate the structure for
knowledge based system for group technology.
BTRA 616-22 Intelligent Manufacturing Lab 0L:0T:2P 1 credits

Experiment based upon the theory subject.