Course Course Course L T P C

21AIE535T ARTIFICIAL INTELLIGENCE AND INTERNET OF THINGS E PROFESSIONAL ELECTIVE

Code Name Category 3 0 0 3

Pre-requisite Co- requisite Progressive

Nil Nil Nil
Courses Courses Courses
Course Offering Department Computational Intelligence Data Book / Codes / Standards Nil

Course Learning Rationale (CLR): The purpose of learning this course is to: Program Outcomes (PO) Program
Specific
CLR-1: understand the fundamentals and Foundation of Artificial Intelligence and IOT 1 2 3 4 5 6 7 8 9 10 11 12 Outcomes

Individual & Team Work

Engineering Knowledge
CLR-2: learn basics of Machine Learning in IOT and Deep Learning,

Design/development of

Project Mgt. & Finance

Conduct investigations
of complex problems
Modern Tool Usage
CLR-3: remembering knowledge on the Internet of Things for the implementation in Detection, Computer Vision

Life Long Learning

The engineer and
Problem Analysis

Communication
CLR-4: acquire knowledge on IOT for the implementation of NLP and Q- Learning

Environment &
Sustainability
CLR-5: understand the impact of Artificial Intelligence Design for different IoT Applications

solutions

society

PSO-1

PSO-2

PSO-3
Ethics
Course Outcomes (CO): At the end of this course, learners will be able to:
CO-1: illustrate the knowledge on the fundamentals of Artificial intelligence and IOT - - - 2 - - 2 - - - - - - - -
CO-2: make use of the knowledge of fundamentals in Machine learning and Deep Learning - - - 2 - - - - - - - - - - -
CO-3: understand the basic ideas of Implementation on the detection and computer vision - - - 2 - - 2 - - - - - - - 3
CO-4: analysing the implementation of IoT in Q-Learning and NLP - - 3 - - - - - - - - - - - 3
CO-5: organize the concept to use Machine Learning based AI algorithms in IoT applications - - - 2 - - 2 - - - - - - - -

Unit-1 - Principles, Foundations and Data Handling in IoT 9 Hour

Principles and Foundations of IoT and AI, IoT reference model, Platforms, Verticals, Infusion of AI, Data Science in IOT, Setting Up the IoT and AI Environment, Dev kits, Setting up Databricks, IoT Hub and an IoT
Edge device, Deploying ML modules to Edge devices, Setting up Kafka, Installing ML libraries on Databricks, PyTorch, GraphX and Graph Frames, Importing TensorFlow. Data Access for IOT –TXT, CSV, XLSX,
Working with JSON,HDF5 format, NoSQL data, HDFS, Using hdfs3 with HDFS, Using PyArrow's filesystem interface for HDFS, Handling Data- Storing data for analysis using Delta Lake, Data collection design,
Windowing, Exploratory factor analysis, Visual exploration, Implementing analytic queries in Mongo/hot path storage, Ingesting IoT data into Spark
Unit-2 - Machine Learning, Deep Learning for IoT 9 Hour
Analyzing chemical sensors with anomaly detection, Logistic regression with the IoMT, Classifying chemical sensors with decision trees, Simple predictive maintenance with XGBoost, Detecting unsafe drivers, Face
detection on constrained devices, Deep learning, Deep learning—why now? Deep Learning for Predictive Maintenance, enhancing data using feature engineering, using keras for fall detection, Energy output
prediction using MLPs in TensorFlow Wine quality classification using MLPs in TensorFlow, Implementing LSTM to predict device failure, Deploying models to web services, Convolutional neural networks -LeNet
to recognize handwritten digits Autoencoders
Unit-3 - IOT Implementation - I 9 Hour
Anomaly Detection -Using Z-Spikes on a Raspberry Pi and Sense HAT, Using auto encoders to detect anomalies in labeled data, Using isolated forest for unlabeled datasets, Detecting time series anomalies with
Luminol, Detecting seasonality-adjusted anomalies Detecting spikes with streaming analytics, Detecting anomalies on the edge. Computer Vision - Connecting cameras through OpenCV- Using Microsoft's custom
vision to train and label your images - Detecting faces with deep neural nets and Caffe -Detecting objects using YOLO on Raspberry Pi 4 -Detecting objects using GPUs on NVIDIA Jetson Nano-Training vision with
PyTorch on GPUs

111
B.Tech / M.Tech (Integrated) Programmes-Regulations 2021-Volume-5-AI – Higher Semester Syllabi-Control Copy
Unit-4 - IOT Implementation - II 9 Hour
Reinforcement Learning for IoT -Introduction -RL terminology -Deep reinforcement learning -Some successful applications- Simulated environments, OpenAI gym-Q-learning -Taxi drop-off using Q-tables -Q-Network
-Taxi drop-off using Q-Network -DQN to play an Atari game -Policy gradients, Pong using policy gradients-The actor-critic algorithm, NLP and Bots for Self-Ordering Kiosks-Wake word detection-Speech-to-text
using the Microsoft Speech API-Implementing smart bots-Creating a custom voice-Enhancing bots with QnA Maker
Unit-5 - IoT Applications 9 Hour
Personal and Home IoT, Personal IoT - SuperShoes by MIT-Continuous glucose monitoring-Hypoglycemia prediction using CGM data-Heart Monitor-Digital assistants. AI for the Industrial IoT, -Predictive
maintenance using AI -Predictive maintenance using Long Short-Term Memory -Predictive maintenance advantages and disadvantages -Electrical load forecasting in industry, AI for Smart Cities IoT, -, Smart traffic
management, Smart parking, Smart waste management, Smart policing, Smart lighting and Smart governance, Computing in the cloud, AWS ,Google Cloud Platform and Microsoft Azure

1. Michael Roshak “Artificial Intelligence for IoT”, Packt publishing, March 2021 4. Farid Meziane, Sunil Vadera, Khiary Kobbacy and Nathan Proudlove, "Intelligent Systems in
2. Amita Kapoor “Hands-On Artificial Intelligence for IoT”,Mapt Publishing, January Manufacturing: Current Developments and Future Prospects", (unit 1),2000
2019 5. Digital Signal Processing: A Practical Guide for Engineers and Scientists, Steven Smith (unti 2) ,2002
Learning
3. Catherine Elsen, Jean Noël Demaret, Maria C. Yang and Pierre Leclercq,” Artificial 6. ArshdeepBahga, Vijay Madisetti, ―Internet of Things, A Hands -on Approach‖, 1st Edition 2015,
Resources
ntelligence for Engineering Design, Analysis and Manufacturing “/ Volume 26 / University Press, ISBN: 978-81-7371-954-7 6) InternetofThings: Legal Perspectives by RolfH.Weber,
Special Issue 03 / August 2012, pp 281 - 01 DOI: 10.1017/S08900630412000157, RomanaWeber, Springer,2010
Published online: 14 August 2012.

Learning Assessment
Continuous Learning Assessment (CLA)
Summative
Formative Life-Long Learning
Bloom’s Final Examination
CLA-1 Average of unit test CLA-2
Level of Thinking (40% weightage)
(50%) (10%)
Theory Practice Theory Practice Theory Practice
Level 1 Remember 25% - 15% - 15% -
Level 2 Understand 25% - 25% - 20% -
Level 3 Apply 20% - 20% - 15% -
Level 4 Analyze 15% - 20% - 25% -
Level 5 Evaluate 15% - 20% - 25% -
Level 6 Create - - - - - -
Total 100 % 100 % 100 %

Course Designers
Experts from Industry Experts from Higher Technical Institutions Internal Experts
1. Dr. Paventhan Arumugum, Director (R&D), ERNET India 1. Dr. S. Srinivasan, Professor and Head, Dept. of Computer Science & 1. Dr.J.Jeyasudha, SRMIST
Engineering, Anna University, Madurai
2. Mr. Vinay Solanki, Head IoT, Lenovo (APAC & MEA) 2. Dr. R. Krishnamurthy, Professor, Department of CSE and IT, BIT
Campus, Anna University, Trichy
3. Mr.Hariharan Ramalingam, Vertical Delivery Head, Wipro ltd 3. Dr.S.Chithra Selvaraj, Associate Professor, Department of IT, SSN
College of Engineering

112
B.Tech / M.Tech (Integrated) Programmes-Regulations 2021-Volume-5-AI – Higher Semester Syllabi-Control Copy