AI for IoT using Edge Devices
Course provided by Model Institute of Engineering & Technology
4 modules
Master Drone Technology for Environmental Science
5 Level NCrF
National Credit Framework
60 Hours
Flexible Learning
Beginner Level
No prior experience required
Micro Course
02 Credit
Course Overview
This course aims to introduce the fundamentals and application of Artificial Intelligence for Internet of Things (IoT) systems, with a strong focus on deploying AI at the edge. Learners will gain hands-on experience in AI algorithms, learn to differentiate between cloud-based and edge-based computation, and develop and test sample AI models on real-world edge architectures.
Key Learning Highlights
Understanding Industrial IoT systems, data accumulation, and the role of AI in predictive analytics.
Edge vs Cloud AI architectures, hardware platforms (Jetson, Coral, Raspberry Pi), and software frameworks (TensorFlow Lite, ONNX, Edge Impulse).
Data collection, preprocessing, and model training using Python (TensorFlow/Keras, scikit-learn).
Model optimization (quantization, pruning) and deployment on real devices with sensor/camera input.
Case studies in smart agriculture and automation, security and privacy, emerging trends like federated learning and low-power AI chips.
Tools & Platforms Used
Learning Outcome
By the end of this course, students will be able to:
Understand the role of AI in Digital Transformation and Industrial IoT systems.
Apply machine learning and deep learning models in an IoT context.
Design and implement AI algorithms suitable for Edge Computing environments.
Distinguish between edge and cloud computing for AI workload placement.
Develop sample AI models and deploy them on edge devices.
Analyze hardware and software architectures for Edge AI deployment.
Master the course with just 4 Modules
This course explores AI for Industrial IoT and Edge Computing, covering AI algorithms, predictive analytics, and real-world applications such as smart factories and predictive maintenance. Students learn to train, optimize, and deploy AI models on edge devices using platforms like Jetson, Raspberry Pi, and software frameworks like TensorFlow Lite and ONNX. Hands-on labs, case studies, and a capstone project provide practical experience in real-time inference, low-power AI, and AI-enabled edge systems.
Introduction to AI for IoT Systems
Overview of Industrial IoT and data accumulation
Role of AI in predictive analytics and decision support
Introduction to AI algorithms (classification, regression, clustering)
Real-world use cases: smart factories, predictive maintenance, optimization
Machine Learning at the Edge
Understanding Edge vs Cloud architectures
Edge AI hardware platforms: NVIDIA Jetson, Coral, Raspberry Pi
Edge AI software frameworks: TensorFlow Lite, ONNX, Edge Impulse
Metrics for evaluating edge AI systems (latency, power, accuracy)
Implementing AI Models for Edge Devices
Data collection and preprocessing for edge deployment
Model training using Python (scikit-learn, TensorFlow/Keras)
Conversion and optimization for edge deployment (quantization, pruning)
Deployment on real devices with camera/sensor input
Case Studies and Emerging Trends
Case studies in Edge AI for smart agriculture, surveillance, and automation
Security and privacy in edge deployments
Overview of market-ready Edge AI solutions and products
Emerging trends: federated learning, real-time inference, low-power AI chips
