AI Tactical Skills:

IoT Hacking and Defense

Who Should Attend:

Cyber Security engineers / analysts
Network and system administrators
Drone, & Robotic Engineers & Developers
Drone Operators
Digital Forensics Investigators
Penetration Testers
Cloud computing personnel
Cloud project managers
Operations support looking for career advancement

By the end of this course, participants will be able to:

Understand the fundamentals of IoT and AI.
Set up and configure development boards for AI-enabled IoT projects.
Develop and deploy AI models for various IoT applications.
Build and integrate IoT systems for smart homes, industrial applications, and smart cities.
Analyze and visualize data from IoT devices using AI and cloud platforms.
Implement a comprehensive AI-enabled IoT solution as a capstone project.

This course will provide a robust foundation for integrating AI with IoT, enabling learners to create innovative and intelligent projects across various domains.

Course Outline

Module 1: Introduction to AI and IoT

Basics of IOT / Artificial Intelligence
Introduction to AI concepts and its importance in IoT
Overview of Machine Learning (ML) and Deep Learning (DL)
Key AI frameworks and tools for IoT (TensorFlow, PyTorch, OpenCV)

Module 2: Setting Up the Development Environment

Introduction to IoT Development Platforms
Ai for IOT hardware device options
IoT Communication Protocols
Detailed look at MQTT, HTTP, CoAP, and other protocols
Setting up a basic MQTT server
Connecting sensors and actuators to the development board

Module 3: Handling Data

Delta Lake and Databricks
Data collection
Garbage data = no ML
Streaming data into IOT Hub
Z-spike anomaly detection

Module 4: Machine Learning for IOT

IOT sensors with anomaly detection
Regression with IOMT
Classifying sensor with decision trees
Deep learning predictive maintenance
Face detection

Module 5: Deep Learning

Analyzing traffic patterns using AI
Keras fall detection
LSTM to predict device failure
Deploying models

Module 6: AI Anomaly Techniques for IoT

Z-Spikes using sense HAT on Rpi
Use of autoencoders in labeled data
Isolated forest for unlabeled data sets
Anomalies on the edge

Module 7: Cloud Integration and Data Analytics

Integrating IoT with Cloud Platforms
Overview of cloud platforms (AWS IoT, Azure IoT, Google Cloud IoT)
Connecting IoT devices to the cloud

Module 8: Computer Vision

OpenCV camera deployment
Deep neural nets and caffe
Object detection with NVIDIA Jetson nano
PyTorch on GPU's

Module 9: NLP (natural language processing)

Speech to text
Luis (language understanding with Microsoft)
Deploying smart bots
Enhancing bots with QnA

Module 10: Optimization of MCU

ESP32 for IOT in Azure
Streaming machine learning with Kafka and Spark
Enriching data with Kafka

Module 11: Deploying to the edge

OTA updates
Offloading to the web with Tensorflow.js
Mobile model
Distributed machine learning using Fog computing

Overall, AI significantly enhances the functionality, efficiency, and security of IoT systems, making it a critical component for the future of connected technologies.