Mihail Mateev
Senior Solution Architect at EPAM Systems, Soft Project, Owner
Sofia, Bulgaria
Mihail Mateev is an owner, Solution Architect, Senior Technical Evangelist at SoftProject, responsible for .Net, IoT and cloud solutions. Mihail currently works as a Senior Solution Architect at EPAM Systems. He also worked many years like a Technical evangelist in the Infragistics. Last years Mihail was focused on various areas related to technology Microsoft: Visual Studio , ASP.Net, Windows client apps, MS SQL Server and Microsoft Azure.
Awards
Area of Expertise
Topics
Software Update for IoT Devices - Best Practices
Software update is one of the major parts of the modern big IoT Solutions. This is probably also one of the most critical and sensitive parts in IoT Solutions. For the big IoT Systems we need to solve different cases firmware and business applications update. We need to have scalable and HA repository, but also need to have a device pooling based on campaign concept. It is needed to update software packages, but also often to provision containerized business applications. This talk is about the real-life cases and best practices when need to design and implement device software like general concepts and specific implementations using Microsoft Azure.
Prompt Engineering with OpenAI for Construction Industry
This session gives an overview of the application of Generative AI, particularly ChatGPT.
This talk covers different areas of implementation of ChatGPT in the building industry with a focus on construction:
- 3D modelling
- Labor Safety
- Automation of Business Processes
- Post-Construction Management
- Smart Digital Replicas like Cognitive Digital Twins (CDT) etc.
PREDICTIVE ANALYTICS BASED ON DIGITAL TWINS, GENERATIVE AI AND CHATGPT
This session gives an overview of the application of Generative AI, particularly ChatGPT, for predictive analytics in different areas focusing on the construction and building industry.
The paper analyzes options to use Generative AI together with another essential for modern analysis technology – Digital Twins
in two different aspects:
1) To design and build systems for Predictive Analytics
2) To implement Cognitive Digital Twins,
The research used prototypes based on Microsoft Power Platform (Power Virtual Agents, Power Automate), OpenAI, and Azure Digital Twins, which can offer predictive analytics in the construction industry.
Offload AI and analytics workloads to the edge
Edge Computing is a pattern in which part of the computation is done on decentralized edge devices and is a great way to extend cloud computing. Using this pattern, Artificial Intelligence (AI) models are trained in the cloud and deployed on the edge which has the advantages like speed, availability and reduced need of bandwidth.
Azure IoT Edge is a fully managed service built on Azure IoT Hub.
Via Azure IoT Edge it is possible to deploy cloud workloads—artificial intelligence, Azure and third-party services, or own logic—to run on IoT devices.
Using Azure IoT Edge is possible to deploy models built and trained in the cloud and run them on-premises.
This presentation demonstrates how you can run data processing and AI related workloads on devices, including real life use-cases and useful demos.
IoT Duel - Cloud vs. on Premises Solutions
This talk is a parallel, between IoT solutions, based on premise and systems, build with Microsoft Azure components. The presentation will cover the architecture, technology stack, implementation and best practices. We will consider plusses and deltas in different cases, using both approaches. You will see also many demos, which will help you to build own cloud based or on premises Internet of Things systems.
Integrating Azure Stream Analytics with Azure Machine Learning in a Nutshell
This talk is on implementing machine learning models as a user-defined function (UDF) in Azure Stream Analytics jobs to do real-time scoring and predictions on streaming input data. Azure Machine Learning allows to use any popular open-source tool to prep, train, and deploy models.
This presentation is on how to use machine learning models as functions into Stream Analytics job. Session includes real life use cases and demos.
Implement predictive analytics for IoT solutions using AI in Azure
Technology allows modern IoT solutions to generate more data than traditional systems and users can digest. Predictive analytics, enabled by big data and cloud technologies, can take advantage of this data and provide new and unique insights into the health of manufacturing equipment and processes.
This talk is about business cases and concepts to use predictive analysis in IoT solutions with Azure AI Platform.
Get Deep Insights from Dynamics 365 and Power Apps linking your Dataverse Environment to Microsoft F
The integration of Microsoft Dataverse with Microsoft Fabric allows businesses to enhance their Dynamics 365 and Power Apps enterprise solutions and workflows by incorporating them into Fabric. This integration is facilitated through the "Link to Microsoft Fabric" functionality embedded in Power Apps, which ensures that Dynamics 365 and Power Apps data is accessible in Microsoft OneLake, Microsoft Fabric's integrated data lake.
Integration between Microsoft Dataverse and Microsoft Fabric has many benefits:
- No need to export data, build extract, transform, load (ETL) pipelines, or use our partner integration tools.
- With shortcuts from Dataverse directly into OneLake, your data stays in Dataverse while authorized users work with data in Fabric.
- Link data from all Dynamics 365 apps, including Dynamics 365 Finance and Operations apps.
- Build Power Apps and automation to drive action from insights in OneLake.
This session represents use cases, main concepts, technical implementation, and demos.
Explore the OpenAI GPT Models
This session is a workshop of interaction with the OpenAI model ChatGPT.
The goal of this 60-minute workhsop is to:
Understand the implementation and capabilities of ChatGPT
Learn how to use and customize natural language generative AI models using prompt engineering techniques
Empower Your business with Power Automate’ RPA Solutions
Power Automate broadens the existing robotic process automation (RPA) capabilities. it is possible to automate all repetitive desktop and cloud processes, use prebuilt drag-and-drop actions or record flows to run later.
Power Automate enables coders and non-coders alike to automate processes and tasks across different applications.
Users can automate most of workloads - from simple data transfers between modern and legacy systems, to more complex business workflows, Power Automate also has the capabilities to get the job done with artificial intelligence, using AI builder or integration with other Azure AI services
This training is about good practices how to use Power Automate. The workshop demonstrates real-life cases and useful demos.
Data processing with Azure Data Factory and Cosmos DB
In the world of data, raw, unorganized data is often stored in relational, nonrelational, and other storage systems. Data requires a service that can orchestrate and operationalize processes to refine these enormous stores of raw data into actionable business insights. It is important to have platforms where with minimal number of components to be possible to persist, manage and process big data. Cosmos DB and Azure Data Factory offer such solution.
Azure Cosmos database is multi-model, globally distributed database from Microsoft. Currently Cosmos DB supports five database models. This is like having for different database servers in one. Cosmos DB provides robust infrastructure for building data structures within enterprises and helps to get real value and insights from existing data.
Azure Data Factory is a cloud-based data integration service that allows you to create data-driven workflows in the cloud for orchestrating and automating data movement and data transformation. Using Azure Data Factory, you can create and schedule data-driven workflows (called pipelines) that can ingest data from disparate data stores.
In this presentation will be demonstrated how to orchestrate and operate with data using Cosmos Db and Azure Data Factory
Cosmos DB Server-Side Programming with TypeScript
Cosmos DB allows for stored procedures, triggers, and user-defined functions to run within its database engine. These components are written using JavaScript/TypeScript and uploaded to the Cosmos DB collection in which they will run. Server-side programming gives a lot of extra power to a Cosmos DB-based application.
This session is focused on server-side programming in Cosmos DB, using TypeScript to write the server-side code. Presentation focus is on how to build real-world applications, including adding unit tests to ensure the code behaves as expected, and incorporating the build and deployment of Cosmos DB server-side code
Clash of Technologies: AWS vs Google Cloud vs Microsoft Azure
This presentation is a short overview and comparison between AWS, Google Cloud and Microsoft Azure.
The session covers mojor components and use cases which have in cloud platforms.
Utilizing Microsoft Fabric and OpenAI Technologies for Advanced Dataset Search Operations
Integrating OpenAI into Microsoft Fabric for dataset search involves leveraging OpenAI's advanced natural language processing (NLP) capabilities within the Microsoft Fabric environment, which is designed for enterprise-grade data management and analysis. This integration can significantly enhance the efficiency and effectiveness of searching through large datasets.
This session covers the methodologies for optimizing the employment of OpenAI's artificial intelligence capabilities within the Microsoft Fabric ecosystem to simplify and improve the procedures involved in identifying and acquiring information from large and complex datasets.
The presentation demonstrates how users can utilize Microsoft Fabric to establish a connection with the OpenAI service. Through this connection, they generated embeddings, which serve as numerical representations of words, phrases, or documents within a continuous vector space. These embeddings are specifically crafted to capture semantic relationships between words, enhancing the capability of algorithms to comprehend and process textual data more efficiently. Furthermore, the user searched within a dataset using this concept, leveraging the embeddings to enhance the accuracy and relevance of the search results.
Using Digital Twins, IoT, and Open AI for predictive analytics
Nowadays, automation is one of the most critical trends worldwide. One of the most critical questions in modern technology is how to build cost-effective, modern, intelligent solutions fast and at a lower cost.
One possible option is to empower analysis using the Digital Twins concept and analyze possible anomalies regarding the expected parameters using the multivariate anomaly detector. These systems are also real Internet of Things (IoT) solutions because such solutions gather data from different sensors.
The modern industry allows the use of cloud-based components such as Azure IoT Suite, Azure Digital Twins, and Azure OpenAI service, offered by Microsoft, to simplify the implementation of complex analytics systems related to predictive analytics.
There are different options for implementing predictive analytics and maintenance, but OpenAI brings a unique general approach to building intelligent, self-improving solutions, able to get insight even beyond the expected business cases.
This presentation covers best practices for building intelligent solutions for modern industry, including architecture, practical use cases, and demos.
Using Azure AI Vision and Open AI to analyze images for predictive analysis
One of the primary applications of predictive analytics involves extracting necessary metadata from images and videos to evaluate the condition of real-world systems and recommend measures to sustain these systems.
Microsoft's Azure AI Vision service offers access to sophisticated algorithms that analyze images and generate insights based on the visual aspects of interest to the user. Additionally, Azure OpenAI Service has introduced an image analysis feature that leverages large language models (LLMs) to comprehend the content of images.
GPT-4 Turbo with Vision, developed by OpenAI, is a significant multimodal model (LMM) capable of interpreting images and providing text-based answers to queries regarding those images, combining capabilities in both natural language processing and visual comprehension.
This session aims to compare Azure AI Vision and GPT-4 Turbo with Vision, exploring how these two technologies can be utilized together for enhanced predictive analysis.
Using AI Builder Capabilities with Power Automate Robotic Process Automation
AI Builder is a new Microsoft Power Platform capability that enables you to add intelligence to your automated processes, predict outcomes, and help improve business performance.
Power Automate is a service that helps you create automated workflows between your favorite apps and services to synchronize files, get notifications, collect data, and more.
Expanding the capabilities of Power Automate, Microsoft has come up with a new feature called UI Flow which helps to create a Robotic process Automation (RPA). With this new addition, Power Automate now also helps these organizations to automate their legacy apps and manual processes though UI- based automation resulting in minimal effort.
This presentation is how to use AI Builder with Power Automat. Session demonstrates real-life cases and useful demos.
Provisioning the IoT Devices - Best Practices
Initial configuration of many devices is one of the biggest challenges in modern IoT solutions, managing many client devices. It is very difficult to configure indivisually so many devices and industry is looking for modern approaches to have a zero-touch automated initial provisioning in the modern Internet of Things system.
This talk is about the real-life cases and best practices when need to design and implement zero-touch provisioning like general concepts and specific implementations using Microsoft Azure.
Microsoft Fabric Real-Time Analytics for IoT : Activating and Alalyzing IoT Device Reflex Data
Microsoft Fabric is an all-in-one analytics solution for enterprises that covers everything from data movement to data science, Real-Time Analytics, and business intelligence.
For IoT Developers, this is an excellent addition to our Azure IoT resource toolkit because streaming IoT data via IoT Hub and IoT Operations solutions is also supported.
Microsoft Fabric offers a solution to react to specific incoming data supporting event-driven scenarios.
This session covers designing and implementing real-time analytics scenarios for IoT solutions using Data Activator and Real-Time analytics components like KQL Querysets and Power BI.
Indexing in Azure Cosmos DB
In this presentation, you will modify the indexing policy of an Azure Cosmos DB container. You will explore how you can optimize the indexing policy for writing or reading heavy workloads and understand the indexing requirements for different SQL API query features.
In this session, you can learn the following:
- Customizing the indexing policy
- Crating composite indexes
- Creating spacial indexes
- Cosmos DB Query specifics
Implementing Modern Automation using Power Automate and Microsoft Fabric
Microsoft Fabric is an all-in-one analytics solution for enterprises that covers everything from data movement to data science, Real-Time Analytics, and business intelligence.
There are different options to integrate Power Platform and Microsoft Fabric. This talk is about how to use the Data Activator Early Access connector in Power Automate flows.
This connector is for use with Data Activator in Microsoft Fabric. This connector can start a flow when a Data Activator triggers fires.
The presentation will demonstrate real-life use cases in which Microsoft Fabric and Power Automate could be used and practical demos.
How to Build my Copilot for MS Teams - Using Copilot Studio or Calling OpenAI with Power Automate
Building your Copilot for Microsoft Teams can be approached through different methods, including using Copilot Studio or integrating OpenAI with Power Automate. Each approach offers a unique way to leverage AI within the Teams environment. Below, I've outlined the general steps for both methods:
1. Using Copilot Studio, if available as part of your Microsoft ecosystem, provides a user-friendly interface to create, train, and manage your AI models without extensive coding knowledge.
2. Integrating OpenAI with Power Automate allows for a more custom and potentially powerful implementation, leveraging the OpenAI API to handle complex queries and tasks.
Both approaches require careful planning and testing to ensure the AI interacts effectively with users. The choice between Copilot Studio and Power Automate with OpenAI largely depends on your specific needs, the complexity of the tasks, and the available resources.
This session compares both options, providing use cases, technical samples, and demos.
How to Build Modern IoT Solutions with CosmosDB and PowerBI
Sometimes design and implementation of modern IoT solutions can be easy. This talk is how to implement modern IoT server-less solutions in Azure, based on event driven design, and powered by Cosmos DB and Power BI.
During the presentation, you will see how you can have a very good integration between Azure IoT components using Azure Functions, a fast scalable multi-model database as Cosmos DB and how to create nice dashboards for monitoring using Power BI.
Expecting the Future Internet of Things
The future IoT solutions are horizontally placed on vertical IoT elements such as device, edge and cloud. Data is produced by sources through the observation of the real-world such as physical phenomena measurements. The capabilities are then fulfilled by functions that are executed either in the cloud or in the edge depending on the hardware resource requirements, real-time constraints, and/or optimization of network bandwidth .
Moreover, due to the geographically distributed nature of the IoT services, edge computing has become very significant.
Nowadays, business requires strong AI capabilities like predictive analysis from modern IoT systems.
This talk is about IoT: trends, challenges and near future vision.
Empower OpenAI with Vector Search for Optimal Performance and Cost Reduction
OpenAI is a powerful platform for the generation of different content, empowered by Generative AI,
However, using the latest models also brings additional costs to AI solutions.
One good option when you have reputable or similar requests is to keep your information in
a database with an optimized indexing approach to have the similarity between requests and reuse
in the most optimal way, the information that has already been generated.
In this session, you will learn how to use vector search in Azure SQL and Cosmos DB to empower the productivity of OpenAI-based solutions.
Device management system - the hearth of IoT Solutions
Device Management System is used for configuration (provisioning), software update, management and tracking of IoT devices in the modern IoT Solutions. This talk is about the challenges when design and implement IoT device management systems. We will discuss the best practices and often seen issues focused more on Azure IoT Solutions.
Deep Dive into Power BI Paginated Reports
Paginated reports are focused on optimized formatting to fit well on a printed page.
Power BI paginated reports are best for scenarios that require a highly formatted, pixel-perfect output optimized for printing or PDF generation.
This session is about specifics and good practices creating and disttributting Power Bi Paginated Reports, including:
- How to create paginated reports
- How do paginated reports work behind the stage
- Finding and solving some possible issues, offten seen in paginated reports
- Creating parameters for paginated reports in the Power BI service
- How to deiver Business Intelligence content to users using Power BI Paginated Reports:
-- Exporting PBI reports to OneDrive or SharePoint Online
-- Distribution via email using PBI service subsciption or Power Automate flows
-- Embedding a Paginated Report Visual in Power BI
Presentation includes tips and trick, real life use cases and useful demos.
Dealing with Cosmos DB in 2021
The is in updated session on best practices using Cosmos DB. Cosmos DB is delivered as a fully managed service with an enterprise grade SLA. It supports querying of documents using a familiar SQL over hierarchical JSON documents. Azure Cosmos DB is a superset of the DocumentDB service. It allows you to store and query noSQL data, regardless of schema. In this presentation, you will learn:
• How to get started with DocumentDB you provision a new database account.
• How to index documents
• How to create applications using Cosmos Db (using REST API or programming libraries for several popular language)
• Best practices designing applications with Cosmos DB
• Best practices creating queries.
Creating O365 Office Scripts with TypeScript in a Nutshell
Office Scripts in Excel on the web allows organization to automate workloads on Excel-related tasks. It is possible to record Excel actions with the Action Recorder, which creates a TypeScript language script. Server-side automation is possible also with creating and editing scripts with the Code Editor. Office Scripts can then be shared across the organization so coworkers can also automate their workflows.
Office Scripts allow organizations to automate tasks and workflows easily and eliminate the need for repetitive steps as you create and manage workbooks.
This talk is about Office Scripts concept, real life use cases and best practices how to create Office Scripts using TypeScript. Presentation includes covers with demos some of the most popular real-life scenarios.
Creating Custom BI Solutions with Power BI Embedded
Microsoft Power BI Embedded is a Microsoft Azure that enables developers to integrate Power BI reports into their web or mobile applications so they don’t need to build custom solutions to visualize data for the users.
Microsoft Power BI Embedded helps Independent Software Vendors to use Power BI data experiences within their applications. Customers, who use applications with Power BI Embedded don’t need to have a Power BI account or to know anything about this Azure service.
This talk is a practical session on Microsoft Power BI Embedded concept with many examples how to create custom BI solutions using this technology.
Creating Custom Visuals in Power BI with TypeScript and D3.js
This presentation is about how to create custom visuals (components) for your PowerBI reports. Power BI reporting features could be extended with custom components, that developers can implement and BI specialist can include in their dashboards. Many visuals are also availabe in the Power BI Visuals Gallery.
Power BI is flexible with which graphical API you prefer to use, but their open source project is all D3.
D3.js is a JavaScript library of objects to produce sophisticated, interactive, dynamic data visualizations using modern web-based technologies
In this talk you will learn how to:
- Set up the dev environment (using PowerBI visuals CLI tool)
- Build your visuals
- Debug your Power BI components
- Use custom visuals in your dashboards
- Publish visuals to Power BI Visuals Gallery
- Roadmap of Power BI Visuals API
Creating Applications that can See, Hear, Speak and Understand Using Azure Cognitive Services
Workshop for beginners using Azure Cognitive Services
Building Modern IoT Solutions with Azure Cosmos DB and Power Platform in a Nutshell
Using vector embeddings, Azure Cosmos DB's vector search capability enables you to run similarity searches on data kept in your Cosmos DB container. This feature is very helpful in situations requiring computer vision, natural language processing, machine learning, and other applications where you need to locate objects that are comparable to a specified query item.
Your AI-powered apps can advance significantly with the help of the Large Language Models (LLMs) in Azure OpenAI. When LLMs have timely access to the appropriate data from your application's data store, their usefulness can rise considerably.
Building Modern Azure IoT Edge Solutions – Vision, Challenges and Best Practices
IoT Edge Solutions are critical for many industries. Many data analyses and transformations can be done
at the edge, and in this way, businesses can have highly optimized solutions for many use cases.
Microsoft Azure has a mature IoT Edge platform optimized for embedded device management. Azure IoT Edge is a device-focused runtime that enables you to deploy, run, and monitor containerized Linux workloads. It helps you bring the analytical power of the cloud closer to your devices to drive better business insights and enable offline decision-making.
Recently, Microsoft announced Azure IoT Operations, which strongly focused on a variety of use cases in various industries, such as predictive/prescriptive maintenance, factory automation, asset health, sustainable operations, modernizing store operations, edge vision AI, and real-time analytics and monitoring.
Azure IoT Operations is an industrial cloud-to-edge data and messaging plane enabled by Azure Arc. With its modular services, organizations can build interoperable digital solutions that transform physical operations at scale.
This session provides a comparable analysis between Azure IoT Edge and Azure IoT Operations, as the presentation shows specific use cases for each platform, good practices for where to use them, and considerations about the future of these solutions. This talk also includes demos that demonstrate specific features for each of these platforms,
Building IOT solutions with Microsoft Azure and PowerApps
In this presentation is about how to use Azure to process, analyze and store IOT data then visualize it in a Power App. We will learn how to seamlessly combine Azure IoT and Power Apps to create powerful IoT solutions.
Building IOT Solutions with Cosmos DB and Power Platform
This session covers different options for using Cosmos DB in IoT solutions with Power Platform.
The focus is primarily on how to use Cosmos DB from Power Automate and Power Apps.
The presentation will demonstrate the implementation of Power Automate flows using Cosmos DB as data storage with specific details related to Cosmos DB connectors for Power Automate.
We will discuss different options to use Cosmos DB indirectly with Power Automate Canvas Apps (non-structured and semi-structured data are not directly supported in Power Apps). Options cover the usage of Power Apps with Power Automate Flows as well as using Azure Functions, Cosmos DB and Power Apps solutions or creating custom connectors.
There will also be a short overview of the new Power Apss connector for NoSQL (in preview)
Ultimately, we will demonstrate complex IoT scenarios for data ingestion and device monitoring using Azure IoT Hub, Power Automate, Power Apps, and Power BI for data visualization and analytics.
Building flows with Power Automate, Office Scripts and Azure Data Lake
Power Automate is an online service that automates events across the most common apps and services.
This talk demonstrates how to build Power Automate flows, using ADL and Office Scripts to integrate, process and visualize live Azure Data Lake data, and more.
Building Automated Flows using Power Automate and Office Scripts
Power Automate is the latest generation of Microsoft automation tools on Microsoft Azure cloud. It allows to integrate and synchronize all our data analysis and applications in an automated way, with the aim of increasing productivity and business efficiency.
This online service automates processes and tasks in a simple and intuitive way. Power Automate allows to have a functional flow as low-code / no-code-platform
Office Scripts are TypeScript based server-side technology that allow organizations to automate tasks and workflows easily and eliminate the need for repetitive steps.
Build Natural Language Queries using Microsoft Copilot for Azure in CosmosDB
Copilot eliminates the concern for syntax or structure of NoSQL queries. You can Enter your question in English regarding your data and items within your Azure Cosmos DB collection, and Copilot will provide a suggested query. Furthermore, each suggestion comes with an explanation in natural language, aiding your understanding and verification of the Copilot-generated query. This enables swift and straightforward access to your Azure Cosmos DB data while enhancing your proficiency in crafting NoSQL queries.
This presentation is about how to make queries from simple to complex, powered by CosmosDB Copilot. The sessions include the concept, use cases, and valuable demos.
Bringing cloud to a vehicle
Automotive companies are increasingly reliant on software, and cars are a perfect example of this trend. The automotive manufacturers are transforming to be software-driven in the same way we have recently witnessed in mobile, consumer electronics, fintech, e-commerce, hospitality and others.
However, the unique challenges for the automotive industry are significant. The major difference between transforming the car to be software-centric and sectors like mobile, fintech and e-commerce is that car software development is more complex and requires very strict control over the entire development and quality control process. This is because of the basic fact that even minor software bugs could lead to injuries and death of people, even in much simpler cases than a self-driving vehicle.
Therefore, it would be a mistake to assume that mobile, fintech, e-commerce experienced software engineers, using Agile approaches, Java, .NET or Python can instantly transform the car to be the part of the digital world. Car manufactures will not accept this, not because they do not want to, but because they are dedicated to manufacturing safe, secure and reliable products.
I will describe the concept – how to bring cloud to a vehicle.
Boosting Power Platform with OpenAI Capabilities.
Power Platform features enable enterprises to use OpenAI’s GPT technology to create AI-powered bots or summarize and create content.
This session is on how to use ChatGPT with Power Platform solutions, including real-life cases and demos.
This talk demonstrates different options to integrate OpenAI into Power Platform services:
- using OpenAI and Azure OpenAI APIs
- using Power Automate actions calling OpenAI
- integrating AI Builder & Copilot Studio
- using Copilot for Power Automate flows.
Attendees can see several cases and various demos.
Best Practices of Implementing Intelligent Edge Solutions with Azure IoT & AI
Azure IoT Edge to build IoT solutions that require having cloud intelligence deployed locally on IoT Edge devices. Azure IoT Edge is a fully-managed service built on Azure IoT Hub.
Via Azure IoT Edge it is possible to deploy cloud workloads—artificial intelligence, Azure and third-party services, or own business logic—to run on Internet of Things (IoT) edge devices via standard containers.
In this talk you will lear:
- What is the common between Azure Edge and Azure IoT Edge
- Azure IoT Edge architecture
- Best practices to design, implement and deploy Intelligent Edge Solutions
- Using Azure IoT Edge in the Real World
Azure IoT Solution Architecture Best Practices
The Internet of Things is becoming reality at a rapid pace. Many objects in the real world can be connected to the Internet. Cloud computing is the best option for the IoT backend. Microsoft Azure offers the offers a wide range of services, used in the Internet of Things solutions
This presentation provides a deeper architecture implementation overview of the Microsoft Azure services and Microsoft Data Platform components for IoT that you can use for solution development. In this session we will cover architectural considerations , best practices (common concepts and the context of Microsoft Azure) and implementation guidance for your IoT solution.
Azure IoT Edge, Powered by Azure Sphere
Azure IoT Edge is a fully managed service built on Azure IoT Hub.
It is a software platform to build edge iot devices.
Azure IoT Edge runs on any device that is able to run the IoT Edge runtime, either x86/x64 or ARM MCU based.
Azure Sphere is a device architecture, based on ARM, which is composed by:
- an special ARM MCU design with a specific security module
- a Linux-based OS tailored specifically for this MCU
- a cloud infrastructure to manage this device.
This talk is about how to run analytics workloads on Azure Sphere using Azure IoT Edge frameworks. We will discuss the best practices to use Azure IoT Edge on Azure Sphere.
Azure Digital Twins in a Nutshell
Digital twins make it possible to simulate, analyze and test scenarios digitally, before implementing changes in the real world.
There are already huge advantages in being able to digitally monitor and control physical objects near or far and at any time. It also possible to explore and experiment further on these objects by building virtual models of them.
Digital twins allow engineers to work with objects in ways that would be impossible in the real world. Nowadays, Microsoft Azure offers this capability on its Internet of Things (IoT) platform with Azure Digital Twins. This technology enable spaces and individual devices to be modelled and let users develop scalable, reusable structures that can combine digital and physical data.
This presentation is about Azure Digital Twins: the main business benefits and technical advantages. Presentation demonstrate the key features of technology the context of Microsoft Azure with real use cases and live demos. This talk will cover also the major functionalities where can see the benefits of Digital Twins for Azure IoT Solutions:
- Device configuration management
- Device provisioning
- Software update
- Triggering of alarms
Azure Custom Vision - Find the Right Tool
Session Abstract: In this session you will be introduced to the Microsoft Azure Cognitive Services, a range of offerings you can use to infuse intelligence and machine learning into your applications without needing to build the code from scratch. We will cover pre-trained AI APIs, such as computer vision, that are accessed by REST protocol. Next we will dive into Custom AI that uses transfer learning - Microsoft Azure Custom Vision. This enables you to provide a small amount of your own data to train an image classification model.
Azure Cosmos DB Serverless Unleashed
Azure Cosmos DB serverless allows to use Azure Cosmos account in a consumption-based way only charged for the Request Units consumed by database operations and the storage consumed by data.
This talks is about when and how to choose between provisioned throughput and serverless, best practices in solution design and cost estimation when need to use Cosmos DB serverless
Presentation also demonstrates real life use-cases and demos
Anomaly Detection, Powered by Azure AI and Digital Twins
Detecting the Onset of System Failure using Anomaly Detection Techniques is one of the key demands in Industry 4.0. Nowadays implementation of this functionality is often related to two concepts: Digital Twins and Anomaly Detection with AI
Anomaly detection is the identification of rare items, events or observations which raise suspicions by differing significantly from the majority of the data. Typically, anomalous data can be connected to some kind of problem or rare event such as e.g. bank fraud, medical problems, structural defects, malfunctioning equipment etc.
Digital twins have been around for several decades, the rapid rise of the internet of things (IoT) is that they have become more widely considered as a tool of the future. Digital twins are getting attention because they also integrate things like artificial intelligence (AI) and machine learning (ML) to bring data, algorithms, and context together
In this presentation will be discussed various techniques that can be used to detect the onset of failure occurring in systems in the context of Microsoft Azure, using Azure Digital Twins Service and Azure Cognitive Service Anomaly Detector API.
Azure Digital Twins is a game-changer in the modern IoT and AI solutions. This a SaaS offering easy to build digital models of complex systems.
The Anomaly Detector API enables you to monitor and detect abnormalities in your time series data with machine learning. This feature adapts by automatically identifying and applying the best-fitting models to your data, regardless of industry, scenario, or data volume.
This talk is covering the whole content from Digital Twins and Anomaly Detection concepts via Azure based implementation demonstrating real use cases and demos.
Data Saturday Croatia 2024 Sessionize Event Upcoming
Global Azure Bulgaria 2024 Sessionize Event
Global AI BootCamp Bulgaria 2024 Sessionize Event
JS Experts 2024 Sessionize Event
Global Power Platform Bootcamp Bulgaria 2024 Sessionize Event
XmasDev 2023 Sessionize Event
Prompt Engineering Bulgaria Sessionize Event
JSTalks Bulgaria 2023 Sessionize Event
#DataWeekender 6.5 Sessionize Event
Data Saturday Sofia 2023 Sessionize Event
Data Saturday Lublin Sessionize Event
AI Industrial Summit 2023 Sessionize Event
Beer.JS Summit 2023 Sessionize Event
Data Saturday Croatia 2023 Sessionize Event
Global Azure Bulgaria 2023 Sessionize Event
SQLDay 2023 Sessionize Event
SQLBits 2023 - General Sessions Sessionize Event
Global AI BootCamp Bulgaria 2023 Sessionize Event
Global Power Platform Bootcamp Bulgaria 2023 Sessionize Event
Virtual Azure Community Day Sessionize Event
Difinity Conference 2022 Sessionize Event
JSTalks Bulgaria 2022 Sessionize Event
Global AI Developer Days Bulgaria 2022 Sessionize Event
Global AI Developers Days Sessionize Event
Global AI Developer Days 2022 Lisboa Sessionize Event
Data Saturday Sofia 2022 Sessionize Event
AI and IoT Bulgaria Summit 2022 Sessionize Event
Data Insight Summit Sessionize Event
Data Saturday Gothenburg 2022 Sessionize Event
Data Saturday Plovdiv 2022 Sessionize Event
DataSaturday Croatia 2022 Sessionize Event
Data Saturday Stockholm 2022 Sessionize Event
Global Azure Bulgaria 2022 Sessionize Event
SQLDay 2022 Sessionize Event
Global Azure 2022 Sessionize Event
Azure Cosmos DB Conf 2022 Sessionize Event
Power BI Summit 2022 Sessionize Event
Global Power Platform Bootcamp Bulgaria 2022 Sessionize Event
Global Power Platform Bootcamp 2022 Lisboa Sessionize Event
Global AI Bootcamp 2022 Lisboa Sessionize Event
Global AI BootCamp Bulgaria 2022 Sessionize Event
Collabdays Lisbon 2021 Sessionize Event
#DataWeekender v4.2 Sessionize Event
DataSaturdays #13 - Minnesota - Oct 16 2021 Sessionize Event
Data Saturday Sofia Sessionize Event
Azure Serverless Conf Sessionize Event
DataSaturday Croatia 2021 Sessionize Event
KulenDayz 2021 Sessionize Event
Data Saturday Plovdiv Sessionize Event
Azure AI Summit Sessionize Event
AI and IoT Bulgaria Summit 2021 Sessionize Event
#DataWeekender v3.1 Sessionize Event
Global AI Night Bulgaria 2021 Sessionize Event
Power BI Summit Sessionize Event
Global Azure Bulgaria 2021 Sessionize Event
Global Azure Virtual 2021 Sessionize Event
Global Power Platform Bootcamp Bulgaria 2021 Sessionize Event
Global Power Platform Bootcamp - New York Sessionize Event
Azure BootCamp Bulgaria 2020 Sessionize Event
Data Community Weekender Europe Sessionize Event
Global Azure Virtual Sessionize Event
Virtual Azure Community Day Sessionize Event
Global Power Platform Bootcamp Bulgaria 2020 Sessionize Event
Global AI BootCamp Bulgaria 2019 Sessionize Event
JSTalks Bulgaria 2019 Sessionize Event
IoT Bulgaria Summit 2019 Sessionize Event
KulenDayz 2019 Sessionize Event
Global AI Night Bulgaria September 2019 Sessionize Event
Global Azure BootCamp Bulgaria 2019 Sessionize Event
Azure Day 2019 Saint-Petersburg Sessionize Event
Global AI Night Bulgaria 2019 Sessionize Event
IoT Bulgaria Summit 2018 Sessionize Event
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top