Unit 1

Artificial Intelligence (AI) and its Next Wave – Edge Computing, Programming Fundamentals – A backbone for AI and Edge Computing – AI & Edge Computing – Course Description, Relational Model of AI and Edge Computing – Artificial Intelligence(Ai) Principles And Products – Machine Learning(ML) Fundamentals and Principles – Quick Tour on Edge Devices in IoT – Edge AI and Cloud AI – An Overview – ‘TinyML’ – A Cutting Edge Field – Introduction to Python – Python Internals – Programming Essentials in python – Machine Learning Libraries and Functions in Python – House Pricing Prediction with Sklearn Framework – Working with Data for ML – Demo with Kaggle Data set – Titanic accident analysis – Working with Micropython – An Overview – Case Study: (1) Application of ML in Manufacturing and Production Industries – (2) Diesel Generators with IoT Framework – A Model IoT Architecture – (3) Case Study on ‘ Edge AI Practices in Industrial Applications – (4) DEMO PROGRAMS IN PYTHON – Beginners Perspective – Bot detection – (5) Python in Electronic Health Records (EHR) – Case Study Approach – (6) Python in ” Deep Learning for Self Driving Cars ” – A case study approach.

Unit 2

Python Demos and Case-Studies on Machine Learning (ML) Algorithm Fundamentals, Demonstrating Unsupervised & Reinforcement Machine Learning Algorithms with Python demos – Machine Learning Algorithms Architecture – Big Data in the context of Machine Learning – Machine Learning Types & Algorithm Selection Strategy – Machine Learning Strategies for Business Improvement, An Overview – Preparing Data for Optimization in Production Man hours – Supervised Machine Learning Algorithm – Principle and types – Regression Algorithm – Classification Algorithms – Principle, Implementation framework of ML algorithms – Future of COBOT, Principles of Unsupervised Machine Learning Algorithm – Clustering Algorithm – Dimensionality Reduction Algorithm – Principle & Implementation of PCA – Autonomous vehicle embedded with Dimensionality Reduction Algorithm – Reinforcement Machine Learning Algorithm – Model Based Algorithms – Model Free Reinforcement learning – exploring policy based methods – Deployment Of Deep Q-Learning In Pick And Place Cobot – An Industrial application of ML – Case Study: (1) Preparing Data for Optimization in Production Manhours – (2)Demo with EDA procedures – (3)Supervised Machine Learning Algorithm- Principle and types- species classification of flowers – (4) Regression Algorithm – Principle & Practicing exercise on Salary Prediction – (5) Implementation framework of ML algorithms – Lung Cancer Prediction – (6) Future of COBOT – An application of ML in Oil & Gas industry – (7) Principles of Unsupervised Machine Learning Algorithm – face prediction – (8) Clustering Algorithm – K-Means as a Hands-on approach – (9) Clustering Algorithm – DBSCAN as a Hands-on approach – (10) Reinforcement Machine Learning Algorithm – With a Practice Approch In Hvac System – (11) Model Based Algorithms – Principle And Example With Dyna Q Algorithm – (12) Paradigm shift in health care diagnosis with reinforcement learning – a review exercise.

Unit 3

Principles and successful demonstrations of Neural Networks (Text Analytics), Advanced Applications with Deep Learning Networks – Fundamentals Of Neural Network, Digit Recognition Using Mlp Model – Gradient Descent Algorithm- Working Principle – Backpropagation Algorithm – Working Principle, Cross-Entropy cost function and its implementation using MLP – Overfitting and Regularization principle – Digit Recognition System For Visually Impared – Cnn Based Ml Algorithm – Stochastic Gradient Descent Algorithm Principle and Analysis Using Iris Dataset – Issues and challenge in neural network training – Vanishing Gradient Principles and Its Measurements In Sigmoid Activation Function, Unstable Gradient in Complex networks, Motivation for Deep Learning – A case study on application of DL – Introduction to convolutional neural networks – Image Recognition principles – Applications of CNN – Generative Network Principles – Introduction to RNN – Properties and Construction of RNN – Implementation of RNN – Case Study: (1) Strategic deployment of shallow neural network for enhancing agriculture – a review exercise – (2) Motivation for Deep Learning – A case study on application of DL for banana leaf disease prediction – (3) Image Recognition principles with a Case study approach in Retail Industry.

Unit 4

IoT Architecture and Development model of Edge Computing – Software platforms and tools for Edge Computing – Hardware tools and resources for Edge Computing – IoT General Architecture – IoT Architecture with AI – Issues and Challenges in IOT with Cloud AI – Revised IOT Architecture with Fog AI and Edge AI – Tiny ML working principle – Tiny ML as SaaS model – High Computing Machine based Edge Architecture – Distributed Training – Compression technique – Software tools and their scope for AI and ML – Additional software requirements for Tiny ML, Example IDE for ML – Colab, Libraries required for ML, Tensor Flow Library – Principles – Keras Library – Principles – Arduino IDE for Edge Computing – Tensor Flow Lite – Principles – Quick survey on the hardware resources – Basics of Arduino Nano BLE Board – Programming with Arduino Nano BLE(ANB) – Programming with built-in Sensors in ANB – Design framework for Edge computing in ANB – Sinewave prediction model using ANB – Word Detection model using ANB – Person Detection Model using ANB – Magic Wand model using ANB – Case Study: (1) Programming with built-in Sensors in Arduino Nano BLE – (2) Design framework for Edge computing in Arduino Nano BLE – (3) Sinewave prediction model using Arduino Nano BLE – (4) Word Detection model using Arduino Nano BLE – (5) Person Detection Model using Arduino Nano BLE – Magic Wand model using Arduino Nano BLE.

Unit 5

Real-Time Applications of ML – A Structured Approach and Demos – ML algorithms and scope for Edge Computing in Electrical, Civil & Mechanical Engineering, ML algorithms and scope for Edge Computing in Future – Case Study: (1) Automated Vehicle support using ML – (2) Fraud System Diagnosis using ML – (3) Deep learning-based shop floor management – (4) Neural networks-based ground water quality distribution analysis – (5) Potential applications of AI in Healthcare – Discussion – (6) Image Classification in IoT Devices – (7) Remotely Piloted Aircraft – (8) AI Products – A survey – (9) Education Quality updates in Design, Development and Delivery using ML – (10) ANN Architecture for Substations – (11) Load Prediction in Substations – (12) Geo-spatial database for power infrastructure – (13) Feature Extraction of substation using Deep Learning – (14) Secondary Substation Load profiling – (15) Estimation of unknown secondary substation profile – (16) Multichannel characterization of substation features – (17)CNN based preliminary citing of substation – (18) Substation Device Diagnosis using Infrared Images- Principle – (19) CNN based Infrared Fault Image Diagnosis – (20) Impact of ML in O&G Industry – (21) Seismic Data Processing Techniques – (22) Geomodelling Process – (23) ML in Reservoir Engineering – (24) Optimal Production Engineering in O&G Industry – (25) AI in upstream sector of O&G Industry – (26) Advances in AI Technology for O&G Industry – (27) Fundamentals of Data handling in O&G Industry – (28) SOA of big data for O&G Industry – (29) ML for Civil Engineering – (30) Contextualized ML Techniques for Civil Engineering Applications – (31) Deep Learning Techniques in Construction Industry – (32) ML approach for Construction Management – (33) CNN based Planetary Lego Brick – (34) AI in Transport Engineering – A Survey – (35) Road Traffic Prediction – Bayesian Approach – (36) ML for Naval Architecture – (37) AI based Wave Height Forecasting – (38) AI impacts in Education – (39) AI open-source software libraries – (40) Computer Vision – (41) Language and Language Reasoning – (42) Speech Recognition – (43) Healthcare and Biology – (44) Ethical Challenges in AI – (45) Economy Implications due to AI – (46) Policies and Strategies for AI.

Pre-requisite

Fundamentals of Engineering Mathematics, Some basic programming knowledge

Course Objective

1. Introduce composite relational model of edge computing along with AI, Machine Learning and IoT
2. Impart the ML and IoT frameworks suitable for Edge Computing
3. Elevate the learners with a knowledge and practice on tools supporting for Edge Computing solutions
4. Offer pilot training on modular development boards of Tiny ML

Course Outcomes

• CO1: Understand the AI, ML and Python programming in the context of Edge Computing
• CO2: Model Python based ML solutions for simple applications
• CO3: Develop ML and IoT frameworks for EC architecture
• CO4: Defend for various ML algorithms and CNNs for their compatibility with EC
• CO5: Estimate hardware and software tools appropriate for Tiny ML
• CO6: Adapt EC based architecture for various applications of:
  • Civil engineering like construction management, transport engineering, naval architecture etc.
  • Electrical engineering like load prediction, multi-channel characterization etc., for substations
  • Mechanical engineering domains like reservoir engineering, upstream sector of O&G Industry etc.,

CO-PO Mapping

1. Understanding Machine Learning: From Theory to Algorithms- Shai Shalev-Shwartz and Shai Ben-David
2. Machine Learning Algorithms and Applications- Mohsen Mohammed Muhammad Badruddin Khan Eihab Bashier Mohammed Bashier
3. TinyML Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers- OREILLY, By Pete Warden & Daniel Situnayake
4. E-resources – Machine Learning- by Judith Hurwitz and Daniel Kirsch