Welcome to the IoTics AIoT Workshop repository! This repository contains all the resources, including circuit diagrams, code, and project files, used in our comprehensive AIoT (Artificial Intelligence of Things) workshop. Each session introduces participants to essential hardware components, cloud services, and machine learning concepts, guiding them to create IoT applications with embedded AI features.

• Resources: Session-0.pptx
• Overview: This session introduces the workshop objectives, schedule, required tools, and IoTics Club team members. Participants will also get an introduction to IoT concepts and build a simple project using Wokwi, an online simulator.
• Objective: Familiarize participants with the workshop framework, introduce the IoTics Club team, and provide a hands-on introduction to IoT with a practical project in Wokwi.

• Resources:
  • basic_part
  • blynk_adafruit
• Content:
  • Setting up and programming an Arduino with an HCSR04 ultrasonic sensor and a buzzer.
  • Integrating the Arduino setup with IoT cloud services like Blynk and Adafruit IO.
• Objective: Learn to create a basic IoT device, understand sensor-cloud connectivity, and visualize sensor data on cloud platforms.

• Resources:
  • obstacle_bot
  • cam_integration
• Content:
  • Programming an Arduino-based obstacle-avoiding robot using the HCSR04 sensor.
  • Enhancing the robot with ESP32-CAM for remote viewing capabilities.
• Objective: Develop a simple autonomous robot and learn to integrate a camera module for video streaming.

• Resources:
  • Energy Meter.csv
  • EvaluatingVariousMLModelforEnergyMeter.ipynb
  • Training&TestingMLAlgorithmForEnergyMeter.ipynb
  • finalized_model.pkl
• Content:
  • Introductory session on machine learning (ML) concepts: types of ML, IoT use cases, and training a simple model.
  • Fitting and evaluating a model on sensor data from an energy meter.
• Objective: Understand basic ML concepts and train a predictive model on sensor data.

• Resources:
  • PTI-mediapipe
  • SurveillanceBotMk2
• Content:
  • Exploring deeper concepts in ML, including Artificial Neural Networks (ANN) and Convolutional Neural Networks (CNN).
  • Using MediaPipe for hand tracking and building a surveillance bot with object detection capabilities.
• Objective: Develop practical AI applications with ML for computer vision, focusing on surveillance and gesture recognition.

• Resources:
  • byte2
  • test
  • WifiCam
  • ckt.png
  • app.py
  • task.txt
• Content:
  • Implementing object detection with Haar Cascade classifiers.
  • Building CamVisioTech Mk1, a Wi-Fi-enabled camera with object recognition capabilities.
• Objective: Learn to implement real-time object detection and build a camera application for smart surveillance.

• Resources: README.md
• Content: Wrap-up session with assignments that consolidate skills from previous sessions.
• Objective: Encourage hands-on practice and independent project development to solidify workshop learnings.

This project is licensed under the terms of the MIT license.

We hope you find this workshop resourceful and engaging as you explore the world of IoT and AI. If you find this information helpful, don't forget to star our repo!