Streaming analytics is a term that refers to using powerful machine learning on streaming data that is always in motion to derive insights quickly and uncover patterns for faster decision making. Using advanced machine learning for computer vision is a problem made more difficult when you consider the various machine learning frameworks for training models and the challenges of deploying these machine learning models to the powerful accelerated GPU and CPU hardware options now available. It’s a challenge when considering where and how to deploy these models to put them to work.   Increasingly, Open Neural Network Exchange (ONNX) formats are used to help with portability of models across frameworks and is an open standard format to represent machine learning models.  SAS Event Stream Processing natively integrates with ONNX format models and has been enhanced for ONNX Runtime to reduce the complexity and time needed to deploy your models in various hardware settings. SAS Event Stream Processing delivers the following new benefits to solve these challenges: Native ONNX format model support for data scientist using 3 rd -party machine learning frameworks Simplified design to integrate ONNX Models within your streaming projects Streamlined deployment to the edge or cloud reducing the inherent complexities of GPU and CPU hardware using ONNX Runtime In the video below you’ll see how SAS Event Stream Processing supports ONNX Runtime and simplifies use of ONNX format models to deliver powerful computer vision models like OpenPose and TinyYolo to edge and cloud runtime environments.    Also, please check out our ESP using ONNX tutorial on GitHub to get started quickly. You can access the latest GitHub tutorial at GitHub for ESP ONNX Runtime Tutorial.   More use cases, examples, and reference architectures for SAS Event Stream Processing and IoT at: Getting Started with SAS IoT analytics. Contact Steve Sparano for questions and more information. ... View more

Great news to share!! Forrester released its latest Streaming Analytics Wave for 2021 and SAS is ranked as a Leader due to our performance, depth of analytic power, and Edge capabilities. This is recognition for the innovation and hard work that the SAS Event Stream Processing team has delivered. I wanted to share this news here on our community since it's the feedback from our community of customers, partners, and other key stakeholders that provides important enhancements for the SAS Event Stream Processing product. Thank you!    More details can be found here: https://www.sas.com/en_us/news/analyst-viewpoints/forrester-names-sas-leader-in-streaming-analytics.html  ... View more

Watch this Ask the Expert session to learn how to use SAS ® Event Stream Processing on the Azure platform. Q&A, webinar recording, and slides are available at links below.   Watch the webinar   Join Steve Sparano and Steven Allen as they discuss and show a demo on migrating SAS Event Stream Processing workloads to Microsoft Azure. Watch this webinar to learn: How to use SAS Event Stream Processing on the Azure platform. Optimal methods for streaming analytics on the Azure platform. How to benefit from moving streaming analytic workloads to Azure. The questions from the Q&A segment held at the end of the webinar are listed below and the slides from the webinar are attached.   Since we already have a cloud environment, why do we need edge and how it is different from the current cloud environment from a development perspective? If you already have a cloud environment, SAS Event Stream Processing on Azure can enhance your current cloud environment by adding automation, SAS analytics and Python support. This includes not just the analytics on streams of data, but also the support for deployments that are automated and already tied into Azure for scale/reliability/security. You could use edge computing to make decisions closer to where the events originate. That does several things for you: 1. Makes it faster to respond. You don’t have connect back to cloud. The processes run stand-alone on the edge devices. 2. Can create a closed loop analytic system. 3. Eliminate or reduce info to send back to the cloud. For example, only send an anomaly back to the cloud. It gives you a lot of flexibility to push the decisioning and analytics down to the edge.   Can you provide examples of any of your customers who are using ESP in Azure today? Direct customers – Town of Cary in North Carolina is using it for flood prediction and improved emergency personnel response. It’s deployed in Azure. We’re receiving data from the edge sensors and all the analytics and predictions are being done in Azure. Partners – pushing their deployments to the cloud. They must be secure and they have to scale. In the hospital space they are tracking assets. This allows everything to scale as they add new hospitals, sensors, or events. They enjoy the benefits of security, scalability and not having to add new hardware.   You mentioned that this was for Azure but are there other public Cloud providers that SAS is targeting? SAS has a partnership with Microsoft so Azure is the preferred provided. We also work with AWS and Google (GCP). They are compatible with the Dockers and Kubernetes technologies.     Recommended Resources SAS Event Stream Processing Product Page (Free Trial available here) Understanding Streaming Analytics e-book IoT Community Master Class: Streaming Analytics SAS Global Hackathon SAS and Microsoft Partnership Press Release   Want more tips? Be sure to subscribe to the Ask the Expert board to receive follow up Q&A, slides and recordings from other SAS Ask the Expert webinars.   ... View more

Hi SAS IoT Community, I’m presenting a live “Ask the Expert” webinar on December 1, 11 AM – noon ET entitled How Do I Migrate SAS ® Event Stream Processing Workloads to Microsoft Azure? SAS Event Stream Processing continuously assesses streaming data, from near origination to the cloud. It transforms and analyzes in real time, helping you understand what actions to take, what alerts to issue and what portions of your data to retain for deeper investigation. Streaming data insights are immediately understood and connected to the correct action. Join Steven Allan and myself for this webinar to learn more. At the end of the webinar, we’ll answer your questions during the Q&A session. You will learn: How to use SAS Event Stream Processing on the Azure platform. Optimal methods for streaming analytics on the Azure platform. How to benefit from moving streaming analytic workloads to Azure.. Click here to register for the webinar.   Want more tips? Be sure to subscribe to the Ask the Expert board to receive follow up Q&A, slides and recordings from this and other SAS Ask the Expert webinars.   Can't join the live event? You can view this and other Ask the Expert sessions on-demand here.  ... View more

Please note that a new SAS Event Stream Manager 5.2 Product Brief is now available. Operationalizing, monitoring, and updating SAS Event Stream Processing (ESP) streaming models and analytics is an important capability for SAS ESP, and SAS Event Stream Manager delivers on that need for our customers.  See new doc here on the SAS.com site: https://www.sas.com/content/dam/SAS/documents/product-collateral/product-brief/en/sas-event-stream-manager-110313.pdf ... View more