Scribd
Upload
2 views

Edge_AI_Presentation

Edge AI involves deploying AI algorithms on edge devices for real-time data processing and decision-making. Key components include edge devices, lightweight AI models, and low-latency communication, with applications in smart surveillance, autonomous vehicles, and healthcare. Future research will address challenges like computational limitations and privacy concerns while focusing on model optimization and the integration of advanced networks.

Uploaded by

shilparp1234
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
2 views

Edge_AI_Presentation

Edge AI involves deploying AI algorithms on edge devices for real-time data processing and decision-making. Key components include edge devices, lightweight AI models, and low-latency communication, with applications in smart surveillance, autonomous vehicles, and healthcare. Future research will address challenges like computational limitations and privacy concerns while focusing on model optimization and the integration of advanced networks.

Uploaded by

shilparp1234
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 14

Edge AI: Intelligence at the Edge

Technical Seminar Presentation


Shilpa R P
8th Sem CSE - VTU
Introduction to Edge AI
• Edge AI refers to the deployment of artificial
intelligence algorithms on edge devices.
• It enables real-time data processing and
decision-making closer to the data source.
What is Edge AI?
• Edge AI is the integration of AI algorithms with
edge computing devices, such as IoT devices,
sensors, or gateways.
• Unlike cloud computing, Edge AI processes
data locally at the point of collection.
Key Components of Edge AI
• 1. Edge Devices: Raspberry Pi, NVIDIA Jetson,
Google Coral
• 2. AI Models: Lightweight models like
MobileNet, TinyML
• 3. Edge Infrastructure: Distributed computing,
low-latency communication
Applications of Edge AI
• 1. Smart Surveillance Systems
• 2. Autonomous Vehicles
• 3. Healthcare and Remote Monitoring
• 4. Industrial IoT (IIoT)
Gill et al. (2024): Edge AI Taxonomy
• This paper presents a systematic taxonomy of
Edge AI and highlights future research
directions in this field.
• It emphasizes real-time decision-making, AI
model compression, and privacy-enhancing
techniques.
Tu et al. (2023): DeepEn2023
• Introduces DeepEn2023, an energy-efficient
dataset for benchmarking Edge AI systems.
• Focuses on optimizing energy consumption
and sustainability of AI models deployed at
the edge.
Wingarz et al. (2024): Security and
Safety
• Reviews the security challenges in Edge AI,
such as data breaches and system
vulnerabilities.
• Proposes safety measures to ensure reliable
and secure edge device operations.
Ye et al. (2024): Galaxy for Efficient
Inference
• Galaxy is an efficient system for running
Transformer models on edge devices.
• It uses model parallelism and hardware
optimization to ensure faster inference with
low resource usage.
Himeur et al. (2023): Edge AI for
Internet of Energy
• This paper explores the application of Edge AI
in the Internet of Energy (IoE), providing real-
time energy analytics and optimization.
Wang et al. (2024): Federated
Continual Learning
• Examines how federated continual learning
can improve Edge AI by enabling models to
learn and adapt from decentralized data
sources.
Challenges in Edge AI
• 1. Limited computational resources on edge
devices
• 2. Energy efficiency and battery life
• 3. Privacy and data security concerns
Future of Edge AI
• 1. AI model optimization and compression
• 2. Growth of 5G/6G networks enabling faster
data transfer
• 3. Integration of federated learning and AI at
the edge
Conclusion
• Edge AI is a transformative technology that
brings intelligence closer to data sources,
enabling faster and more secure real-time
decision-making.
• Future research will focus on optimization,
privacy, and security improvements.

You might also like