Today's case for AI at the edge

Display portlet menu

Today's case for AI at the edge

Display portlet menu

Today's case for AI at the edge for engineers

person touching globe with finger

Artificial intelligence (AI) might feel far away, but many of us experience AI every single day in applications like speech to text virtual assistance or fingerprint recognition on smartphones. AI capabilities in IoT applications help to identify patterns and detect variations in IoT edge devices carrying sensors for environmental parameters like temperature or pressure.

Traditionally, simple embedded edge devices collect this data from sensors in the application environment and stream the data to AI systems built on cloud infrastructures to perform analytics and draw inferences. Yet, as the need for real-time decision making in IoT implementations grows, so do connectivity or processing needs—and it is not always possible to stream all data to the cloud for AI processing. This paper will discuss how deploying AI at the edge can improve the efficiency and cost-effectiveness of IoT implementations.

 

How to deploy AI at the edge

The basic components of a typical edge AI model include both the hardware and software for capturing sensor data, software for training the model for application scenarios as well as the application software that runs the AI model on the IoT device.

A micro-service software that is running on the edge device is responsible for initiating the AI package residing on the edge device upon request by the user. Within the edge device, the feature selections and transformations defined during the training phase are used. The models are customized to the appropriate feature set, which can be extended to include aggregations and engineered features.

Intelligent edge devices are deployed in battery operated applications in areas with low bandwidth and intermittent network connectivity. Edge device manufacturers are building sensors with integrated processing and memory capabilities and widely used low-speed communication protocols like BLE, Lora, and NB-IoT in tiny footprints and low power consumption.

 

The benefits of AI at the edge

While the complexity of such designs may make the edge expensive, the benefits far outweigh the related costs.

Apart from being highly responsive in real time, edge-based AI has significant advantages such as greater security built into the edge devices and lesser data flowing up and down the network. It is highly flexible, as customized solutions are built for each application. Since the inferences are pre-built into the edge devices, it needs fewer skills to operate and maintain.

Edge computing also allows developers to distribute computing across the network by transferring some sophisticated activities to edge processors in the local network like routers, gateways, and servers. They provide very good operational reliability as data is stored and intelligence is derived locally helping deployment in areas of intermittent connectivity or without a network connection.

Ordinarily, building a machine learning model to solve a challenge is complex. Developers have to manage vast amounts of data for model training, choose the best algorithm to implement, and manage the cloud services to train the model. Application developers then deploy the model into a production environment using programming languages like Python. The smart edge device manufacturer will find it extremely difficult to invest in resources to execute an AI implementation on edge from scratch.

Learn more with our AI at the Edge whitepaper for engineers

Today's case for AI at the edge

Display portlet menu

Today's case for AI at the edge

Display portlet menu
Related Articles
Interior of autonomous car
The state of automotive only starts with autonomous driving
April 4, 2020
Learn how the state of automotive spans a variety of applications, from electrication to in-cabin AI.
Woman using VR goggles
Artificial Intelligence: The Future of Fashion
By Jürgen Kalwa   -   February 19, 2020
Designers and manufacturers of men’s and women’s apparel are exploring ways to predict trends faster and more accurately than ever before. They are helped by researchers who are looking for ways to utilize artificial intelligence.
man wearing virtual reality headset with graphic overlays
How LoRaWAN and AI at the Edge Revolutionize the IoT
January 3, 2020
Learn how LoRaWAN and artificial intelligence (AI) at the edge can revolutionize the internet of things by reducing data transmission and improving latency.
A group of colleagues working in a computer security room having a discussion
Avnet and Microsoft Azure Sphere: IoT security in hardware, software and at the edge
March 5, 2019
IoT has transformed various industries by automating them at large, but the security concerns associated are just as large as the market opportunity this technology presents. That’s where Azure Sphere comes in.
shopping cart in grocery store
4 ways AI connects retailers and customers
February 25, 2019
Technologies like machine learning and AI help retailers to process massive amounts of customer data. And with this data in hand, retailers can thoroughly understand their customers’ buying behavior.
depiction of brain surrounded by icons
The rise of machine intelligence in the AI era
February 24, 2019
Whether you know it or not, this technology has a lot of potential to deal with business-specific challenges and the benefits of deep learning outnumber its drawbacks.
man using tablet computer in industrial setting
5 of the best artificial intelligence use cases
January 3, 2019
AI’s upgraded algorithms make predictive analytics, parse data, and help businesses make smarter decisions from the boardroom to the factory floor.

Today's case for AI at the edge

Display portlet menu
Related Events
Seminar situation
NXP eXperience
Date: March 31, 2020
Location: online, on-demand