This document discusses using machine learning for industrial applications with tiny machine learning (TinyML). It notes that 99% of sensor data from industrial sensors is discarded due to constraints. On-device intelligence using TinyML can help find patterns in this data. The document outlines steps for developing TinyML models, including collecting raw sensor data, extracting meaningful features from it, and training and deploying neural network models on edge devices. It provides examples of using TinyML for predictive maintenance, audible monitoring, and lone worker monitoring.
Introduction to AIoT & TinyML - with ArduinoAndri Yadi
On last March 21, 2020, we participated in worldwide Arduino Day 2020 and organized the online event for Bandung, Indonesia. This is the deck I delivered for my talk and demo.
Big Data with KNIME is as easy as 1, 2, 3, ...4!KNIMESlides
This presentation shows how we have re-engineered an old legacy workflow to run partially on Hadoop from within the KNIME Analytics Platform, to speed up dramatically the execution time.
It also shows how easy it has been to move the ETL part of the workflow to Hadoop using the KNIME big data access nodes and in-database processing nodes.
KNIME big data nodes are Cloudera, Hortonworks, and MapR certified, as of today (October 21 2015)
Webinar: Machine Learning para MicrocontroladoresEmbarcados
Neste webinar, serão apresentados conceitos sobre inteligência artificial, assim como ferramentas disponíveis para o desenvolvimento integradas ao MPLAB X e ao Harmony 3 e demonstração de um sistema de detecção de anomalia utilizando um microcontrolador da família ATSAMD21 (ARM Cortex M0+).
ThingsBoard IoT Platform provides device management, telemetry, data processing and visualization. It combines with ThingsBoard IoT Gateway and Trendz Analytics. It is suitable for a wide variety of use cases including smart energy, fleet tracking, smart farming and IIoT.
Introduction to AIoT & TinyML - with ArduinoAndri Yadi
On last March 21, 2020, we participated in worldwide Arduino Day 2020 and organized the online event for Bandung, Indonesia. This is the deck I delivered for my talk and demo.
Big Data with KNIME is as easy as 1, 2, 3, ...4!KNIMESlides
This presentation shows how we have re-engineered an old legacy workflow to run partially on Hadoop from within the KNIME Analytics Platform, to speed up dramatically the execution time.
It also shows how easy it has been to move the ETL part of the workflow to Hadoop using the KNIME big data access nodes and in-database processing nodes.
KNIME big data nodes are Cloudera, Hortonworks, and MapR certified, as of today (October 21 2015)
Webinar: Machine Learning para MicrocontroladoresEmbarcados
Neste webinar, serão apresentados conceitos sobre inteligência artificial, assim como ferramentas disponíveis para o desenvolvimento integradas ao MPLAB X e ao Harmony 3 e demonstração de um sistema de detecção de anomalia utilizando um microcontrolador da família ATSAMD21 (ARM Cortex M0+).
ThingsBoard IoT Platform provides device management, telemetry, data processing and visualization. It combines with ThingsBoard IoT Gateway and Trendz Analytics. It is suitable for a wide variety of use cases including smart energy, fleet tracking, smart farming and IIoT.
TinyML: Machine Learning for MicrocontrollersRobert John
My presentation at TensorFlow User Groups Sub-Saharan Africa Summit discusses machine learning for embedded devices, the importance, and the challenges.
3 Things to Learn About:
*The IoT ecosystem and data management considerations for IoT
*Top IoT use cases and data architecture strategies for managing the sheer volume and variety of IoT data
*Real-life case studies on how our customers are using Cloudera Enterprise to drive insights and analytics from all of their IoT data
Check out the differences between IoT, IIoT & Industry 4.0. Looking to increase your revenue by leveraging IoT or Industry 4.0, click here - https://smacar.com/
To know more about the differences between IoT, IIoT and Industry 4.0, click here - https://smacar.com/iot-iiot-industry-4-0/
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2022/06/tensorflow-lite-for-microcontrollers-tflm-recent-developments-a-presentation-from-bdti-and-google/
David Davis, Senior Embedded Software Engineer, and John Withers, Automation and Systems Engineer, both of BDTI, present the “TensorFlow Lite for Microcontrollers (TFLM): Recent Developments” tutorial at the May 2022 Embedded Vision Summit.
TensorFlow Lite Micro (TFLM) is a generic inference framework designed to run TensorFlow models on digital signal processors (DSPs), microcontrollers and other embedded targets with small memory footprints and very low power usage. TFLM aims to be easily portable to various embedded targets from those running an RTOS to bare-metal code. TFLM leverages the model optimization tools from the TensorFlow ecosystem and has additional embedded-specific optimizations to reduce the memory footprint. TFLM also integrates with a number of community contributed optimized hardware-specific kernel implementations.
In this talk, Davis and Withers review collaboration between BDTI and Google over the last year, including porting nearly two dozen operators from TensorFlow Lite to TFLM, creation of a separate Arduino examples repository, improved testing and documentation of both Arduino and Colab training examples and transitioning TFLM’s open-source CI framework to use GitHub Actions.
An introductory video and presentation looking at Internet of Things (IoT) and differences between IoT and #IIoT. Examples are provided to help clarify the understanding.
AI firsts: Leading from research to proof-of-conceptQualcomm Research
AI has made tremendous progress over the past decade, with many advancements coming from fundamental research from many decades ago. Accelerating the pipeline from research to commercialization has been daunting since scaling technologies in the real world faces many challenges beyond the theoretical work done in the lab. Qualcomm AI Research has taken on the task of not only generating novel AI research but also being first to demonstrate proof-of-concepts on commercial devices, enabling technology to scale in the real world. This presentation covers:
The challenges of deploying cutting-edge research on real-world mobile devices
How Qualcomm AI Research is solving system and feasibility challenges with full-stack optimizations to quickly move from research to commercialization
Examples where Qualcomm AI Research has had industrial or academic firsts
Fast, Scalable Quantized Neural Network Inference on FPGAs with FINN and Logi...KTN
This presentation, delivered by Yaman Umuroğlu, Research Scientist, Xilinx, was the second presentation of the Implementing AI: Vision Systems Webinar.
ARCHITECTURE MICROSERVICE : TOUR D’HORIZON DU CONCEPT ET BONNES PRATIQUESSOAT
Les systèmes distribués ont largement évolués ces 10 dernières années, passant d’énormes applications monolithiques à de petits containers de services, apportant plus de souplesse et d’agilité au sein des systèmes d’information.
Le terme « Architecture microservice » a vu le jour pour décrire cette manière particulière de concevoir des applications logicielles.
Bien qu’il n’y ait pas de définition précise de ce style d’architecture, elles ont un certain nombre de caractéristiques communes basées autour de l’organisation de l’entreprise, du déploiement automatisé et de la décentralisation du contrôle du langage et des données.
Seulement, développer ces systèmes peut tourner au véritable casse-tête. Je vous propose donc un tour des concepts et différentes caractéristiques de ce type d’architecture, des bonnes et mauvaises pratiques, de la création jusqu’au déploiement des applications.
Kevin Huang: AWS San Francisco Startup Day, 9/7/17
Architecture: When, how, and if to adopt microservices - Microservices are not for everyone! If you're a small shop, a monolith provides a great amount of value and reduces the complexities involved. However as your company grows, this monolith becomes more difficult to maintain. We’ll look at how microservices allow you to easily deploy and debug atomic pieces of infrastructure which allows for increased velocity in reliable, tested, and consistent deploys. We’ll look into key metrics you can use to identify the right time to begin the transition from monolith to microservices.
Predictive Maintenance Using Recurrent Neural NetworksJustin Brandenburg
My presentation from AnacondaCON 2018 where I discussed using Recurrent Neural Networks, Python, Tensorflow and the MapR Platform to develop deploy a predictive maintenance model for an IoT device in the manufacturing industry.
Adding intelligence to your LoRaWAN devices - The Things Conference on tourJan Jongboom
Want to get started? Check the tutorial here: https://www.edgeimpulse.com/blog/adding-machine-learning-to-your-lorawan-device/
Talk about machine learning for IoT devices (TinyML), and everything that it entails. From signal processing to neural networks to classic ML algorithms. Presented in Reading, UK and Hyderabad, India during The Things Conference on Tour.
TinyML: Machine Learning for MicrocontrollersRobert John
My presentation at TensorFlow User Groups Sub-Saharan Africa Summit discusses machine learning for embedded devices, the importance, and the challenges.
3 Things to Learn About:
*The IoT ecosystem and data management considerations for IoT
*Top IoT use cases and data architecture strategies for managing the sheer volume and variety of IoT data
*Real-life case studies on how our customers are using Cloudera Enterprise to drive insights and analytics from all of their IoT data
Check out the differences between IoT, IIoT & Industry 4.0. Looking to increase your revenue by leveraging IoT or Industry 4.0, click here - https://smacar.com/
To know more about the differences between IoT, IIoT and Industry 4.0, click here - https://smacar.com/iot-iiot-industry-4-0/
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2022/06/tensorflow-lite-for-microcontrollers-tflm-recent-developments-a-presentation-from-bdti-and-google/
David Davis, Senior Embedded Software Engineer, and John Withers, Automation and Systems Engineer, both of BDTI, present the “TensorFlow Lite for Microcontrollers (TFLM): Recent Developments” tutorial at the May 2022 Embedded Vision Summit.
TensorFlow Lite Micro (TFLM) is a generic inference framework designed to run TensorFlow models on digital signal processors (DSPs), microcontrollers and other embedded targets with small memory footprints and very low power usage. TFLM aims to be easily portable to various embedded targets from those running an RTOS to bare-metal code. TFLM leverages the model optimization tools from the TensorFlow ecosystem and has additional embedded-specific optimizations to reduce the memory footprint. TFLM also integrates with a number of community contributed optimized hardware-specific kernel implementations.
In this talk, Davis and Withers review collaboration between BDTI and Google over the last year, including porting nearly two dozen operators from TensorFlow Lite to TFLM, creation of a separate Arduino examples repository, improved testing and documentation of both Arduino and Colab training examples and transitioning TFLM’s open-source CI framework to use GitHub Actions.
An introductory video and presentation looking at Internet of Things (IoT) and differences between IoT and #IIoT. Examples are provided to help clarify the understanding.
AI firsts: Leading from research to proof-of-conceptQualcomm Research
AI has made tremendous progress over the past decade, with many advancements coming from fundamental research from many decades ago. Accelerating the pipeline from research to commercialization has been daunting since scaling technologies in the real world faces many challenges beyond the theoretical work done in the lab. Qualcomm AI Research has taken on the task of not only generating novel AI research but also being first to demonstrate proof-of-concepts on commercial devices, enabling technology to scale in the real world. This presentation covers:
The challenges of deploying cutting-edge research on real-world mobile devices
How Qualcomm AI Research is solving system and feasibility challenges with full-stack optimizations to quickly move from research to commercialization
Examples where Qualcomm AI Research has had industrial or academic firsts
Fast, Scalable Quantized Neural Network Inference on FPGAs with FINN and Logi...KTN
This presentation, delivered by Yaman Umuroğlu, Research Scientist, Xilinx, was the second presentation of the Implementing AI: Vision Systems Webinar.
ARCHITECTURE MICROSERVICE : TOUR D’HORIZON DU CONCEPT ET BONNES PRATIQUESSOAT
Les systèmes distribués ont largement évolués ces 10 dernières années, passant d’énormes applications monolithiques à de petits containers de services, apportant plus de souplesse et d’agilité au sein des systèmes d’information.
Le terme « Architecture microservice » a vu le jour pour décrire cette manière particulière de concevoir des applications logicielles.
Bien qu’il n’y ait pas de définition précise de ce style d’architecture, elles ont un certain nombre de caractéristiques communes basées autour de l’organisation de l’entreprise, du déploiement automatisé et de la décentralisation du contrôle du langage et des données.
Seulement, développer ces systèmes peut tourner au véritable casse-tête. Je vous propose donc un tour des concepts et différentes caractéristiques de ce type d’architecture, des bonnes et mauvaises pratiques, de la création jusqu’au déploiement des applications.
Kevin Huang: AWS San Francisco Startup Day, 9/7/17
Architecture: When, how, and if to adopt microservices - Microservices are not for everyone! If you're a small shop, a monolith provides a great amount of value and reduces the complexities involved. However as your company grows, this monolith becomes more difficult to maintain. We’ll look at how microservices allow you to easily deploy and debug atomic pieces of infrastructure which allows for increased velocity in reliable, tested, and consistent deploys. We’ll look into key metrics you can use to identify the right time to begin the transition from monolith to microservices.
Predictive Maintenance Using Recurrent Neural NetworksJustin Brandenburg
My presentation from AnacondaCON 2018 where I discussed using Recurrent Neural Networks, Python, Tensorflow and the MapR Platform to develop deploy a predictive maintenance model for an IoT device in the manufacturing industry.
Adding intelligence to your LoRaWAN devices - The Things Conference on tourJan Jongboom
Want to get started? Check the tutorial here: https://www.edgeimpulse.com/blog/adding-machine-learning-to-your-lorawan-device/
Talk about machine learning for IoT devices (TinyML), and everything that it entails. From signal processing to neural networks to classic ML algorithms. Presented in Reading, UK and Hyderabad, India during The Things Conference on Tour.
Teaching your sensors new tricks with Machine Learning - CENSIS Tech Summit 2019Jan Jongboom
We collect more sensor data than ever, but throw most of it away due to cost, bandwidth or power constraints. In this presentation we'll look at embedded machine learning, pushing intelligence directly to the sensor edge. Given during the CENSIS Tech Summit 2019 in Glasgow, Scotland.
Adding intelligence to your LoRaWAN deployment - The Things Virtual ConferenceJan Jongboom
LoRaWAN devices are typically simple, they grab some sensor data and deliver it back to the network. By adding some embedded machine learning we can make them a lot more intelligent!
Agilent Technologies
The premier measurement company -- advancing electronics, communications, life sciences and chemical analysis
Agilent Technologies Inc adalah perusahaan pengukuran utama dunia dan pemimpin teknologi dalam elektronik dan komunikasi. 20.500 karyawan perusahaan melayani pelanggan di lebih dari 100 negara. Sebagai perusahaan pengukuran utama dunia, Agilent menawarkan jangkauan luas solusi pengukuran inovatif di industri. Perusahaan empat bisnis – Analisis Kimia, Biologi, Diagnostik dan Genomics, dan Elektronik Pengukuran – menyediakan pelanggan dengan produk dan layanan yang membuat perbedaan nyata dalam kehidupan orang-orang di mana-mana. Dan di Agilent Laboratorium Penelitian, kita melakukan penelitian yang mengantisipasi kebutuhan pelanggan dan menghasilkan terobosan bahwa pertumbuhan listrik.
Asal Negara : U.S.A
Jenis Industri :
Automotive/Transportation, Communications and Networking Systems or Equipment , Computers and Peripherals , Consumer Electronics & Appliances , Aerospace/Defense/Government , Electronic Instrumentation or Test , Medical Devices & Systems , Semiconductor Design & Manufacturing , Academia , Energy , Application & Technologies: Advanced Technology , Components , Design Tools (EDA) , Manufacturing , Software/Hardware Development , Test & Measurement
Kategori Produk :
Oscilloscopes , Spectrum Analyzers (Signal Analyzers) , Network Analyzer , Handheld Oscilloscopes, Analyzers, Meters , Logic Analyzers , Protocol Analyzers and Exercisers , EMI/EMC, Phase Noise, Physical Layer Test Systems ,Bit Error Ratio Test (BERT) Solutions , Digital Multimeters (DMM) , Power Meters & Power Sensors , Frequency Counter Products , Noise Figure Analyzers & Noise Sources , LCR Meter & Impedance Measurement Products , Digitizers , DC Power Analyzers , Dynamic Signal Analyzers, Materials Measurement , Parameter & Device Analyzers, Curve Tracer
Untuk pemesanan dan informasi hubungi :
Tridinamika - Test and Measurement
www.tridinamika.com
email to : sales@tridinamika.com
Hướng dẫn sử dụng máy đo tốc độ vòng quay Tenmars TM-4100Tenmars Việt Nam
Hướng dẫn sử dụng máy đo tốc độ vòng quay Tenmars TM-4100
https://tenmars.vn/danh-muc/do-toc-do-vong-quay-tenmars/
https://tenmars.vn/san-pham/may-do-toc-do-vong-quay-tenmars-tm-4100/
Technical Data Built-in computer
Simple, fast and easy to operate
Posterior segment OCT. The OCT is an
ophthalmic optical coherence tomography
scanner tailored for rapid screening of
fundus diseases in outpatient clinics. It is
easy to use, clear in image, smooth and
delicate in operation, and equipped with
professional analysis software to meet the
requirements of OCT in the clinical
examination and analysis of
ophthalmology.
Pemesanan produk, hubungi PT Siwali Swantika melalui WhatsApp, Jakarta : 0811-1519-949 (chat only) | Surabaya : 0811-1519-948 (chat only). Kunjungi website kami di www.siwali.com, untuk detail informasi spesifikasi dan model alat.
LUCID Vision Labs - Enhance Your Industrial Application with LUCID’s Factory ...ClearView Imaging
In recent years, there has been a growing demand for short-wave infrared (SWIR) imaging with more products becoming available that enhance the capabilities of machine vision systems beyond the visible wavelength. Industrial applications such as fruit inspection and sorting, packaging, IR microscopy, semiconductor inspection, material sorting can greatly benefit from SWIR imaging. In this presentation, we will cover the advancements of Sony’s
SenSWIR technology paired with our brand new Atlas SWIR Factory Tough™camera, capable
of capturing images across both visible and invisible light spectrums, and boasting a
miniaturized pixel size of 5μm. The IP67-rated Atlas SWIR camera is equipped with integrated
single-stage thermoelectric sensor cooling (TEC1) for superior image quality and extended operating temperature range, making it ideal for challenging industrial environments.
Machine learning on 1 square centimeter - Emerce Next 2019Jan Jongboom
Machine Learning is widely applied, but the models operate on digital data and run in big data centers. But there's more to the world. This is my presentation from Emerce Next 2019 about pushing ML to the smallest of devices.
Fundamentals of IoT - Data Science Africa 2019Jan Jongboom
As data scientists your job is to create order in the data chaos. But where does this data come from? Real-world data does not magically appear cleanly in your Matlab scripts. This is a talk about the fundamentals of IoT, and how to retrieve data from the real world using sensors and devices. Given during Data Science Africa 2019 in Addis Ababa.
Recording: https://www.youtube.com/watch?v=DxTetwYsXvo&index=1&list=PLiVCejcvpsevQ_I9oDIK6eIgau45fWje2
The Mbed Simulator allows you to cross-compile Mbed OS 5 applications and run them on your computer.
LoRaWAN is great, but it requires so much hardware. As I live on a plane I want something better. Presentation about simulating LoRaWAN devices. Here's a video of the simulator: https://www.youtube.com/watch?v=C1S8knMlX7w
Firmware Updates over LoRaWAN - The Things Conference 2019Jan Jongboom
IoT deployments last for ten years, but that's a long time. Requirements change, vulnerabilities are found, and standards evolve. You'll need a firmware update solution.
Talk during The Things Conference 2019.
Faster Device Development - GSMA @ CES 2019Jan Jongboom
Presentation about interesting open source developments that can be used in conjunction with LTE Cat-M1 and NB-IoT. Presentation from the GSMA IoT workshop at CES 2019.
Introduction to Mbed - Etteplan seminar - August 2018Jan Jongboom
What is Arm Mbed, what is Arm Pelion, and how can it help me create IoT devices faster? Introductionary talk during the Etteplan seminars in Oulu and Espoo 21-22 August 2018 about LoRa in Mbed.
Machine Learning on 1 cm2 - Daho.am 2018Jan Jongboom
Putting machine learning on edge nodes adds local control, reduces privacy concerns, and doesn't require a fast internet connection. uTensor and CMSIS-NN bring ML to the cheapest of computers: microcontrollers. $2 cost and 1 cm2 in size they're found everywhere.
What if we can push machine learning to edge nodes? Presentation about uTensor, Mbed OS and ML in general. https://gbgtechweek.com/program/iot-bootcamp/
Embedded Development: meet the web browser - TEQNation 2018Jan Jongboom
Embedded development is stuck in the 90s, building and flashing takes just as long as 20 years ago and development tools are horrendous. Browser development goes way faster, new tools and languages are being launched every other day. What if we can bring these two together? Meet the Mbed Simulator. It allows you to cross-compile embedded code to the browser for a faster development cycle and much better debugging tools.
Machine learning on microcontrollers - Tech Power Summit 2018Jan Jongboom
When we think about machine learning we think about data centers full of GPUs and TPUs, but many interesting usecases lay on the edge: local control, no latency and no privacy issues. Presentation during STX Next's Tech Power Summit in Poznan.
Deep learning on microcontrollers - IETF 101 - T2TRG Jan Jongboom
Machine learning is cool, but requires clusters of GPUs. But what if we can put machine learning on the edge? It would enable new use cases such as sensor fusion, federated learning, or super-advanced compression through auto-encoders. uTensor and CMSIS-NN make it possible for microcontrollers that cost <1$.
Videos in this presentation:
Slide 12: https://www.youtube.com/watch?v=FhbCAd0sO1c
Slide 23: https://twitter.com/janjongboom/status/953014129580748800
Slide 25: https://www.youtube.com/watch?v=PdWi_fvY9Og
Presentation for Thing-to-Thing Research Group during IETF 101 in London.
ER(Entity Relationship) Diagram for online shopping - TAEHimani415946
https://bit.ly/3KACoyV
The ER diagram for the project is the foundation for the building of the database of the project. The properties, datatypes, and attributes are defined by the ER diagram.
This 7-second Brain Wave Ritual Attracts Money To You.!nirahealhty
Discover the power of a simple 7-second brain wave ritual that can attract wealth and abundance into your life. By tapping into specific brain frequencies, this technique helps you manifest financial success effortlessly. Ready to transform your financial future? Try this powerful ritual and start attracting money today!
1.Wireless Communication System_Wireless communication is a broad term that i...JeyaPerumal1
Wireless communication involves the transmission of information over a distance without the help of wires, cables or any other forms of electrical conductors.
Wireless communication is a broad term that incorporates all procedures and forms of connecting and communicating between two or more devices using a wireless signal through wireless communication technologies and devices.
Features of Wireless Communication
The evolution of wireless technology has brought many advancements with its effective features.
The transmitted distance can be anywhere between a few meters (for example, a television's remote control) and thousands of kilometers (for example, radio communication).
Wireless communication can be used for cellular telephony, wireless access to the internet, wireless home networking, and so on.
Multi-cluster Kubernetes Networking- Patterns, Projects and GuidelinesSanjeev Rampal
Talk presented at Kubernetes Community Day, New York, May 2024.
Technical summary of Multi-Cluster Kubernetes Networking architectures with focus on 4 key topics.
1) Key patterns for Multi-cluster architectures
2) Architectural comparison of several OSS/ CNCF projects to address these patterns
3) Evolution trends for the APIs of these projects
4) Some design recommendations & guidelines for adopting/ deploying these solutions.
3. 3
Typical industrial sensor in 2020
Vibration sensor (up to 1,000 times per second)
Temperature sensor
Water & explosion proof
Can send data >10km using 25 mW power
Processor capable of running >20 million
instructions per second
4. 4
But... what does it actually do?
Once an hour:
• Average motion (RMS)
• Peak motion
• Current temperature
5. 5
99% of sensor data is discarded due to
cost, bandwidth or power constraints.
https://www.mckinsey.com/~/media/McKinsey/Business%20Functions/McKinsey%20Digital/Our%20Insights/
The%20Internet%20of%20Things%20The%20value%20of%20digitizing%20the%20physical%20world/The-
Internet-of-things-Mapping-the-value-beyond-the-hype.ashx
8. 8
On-device intelligence is the only solution
Vibra&on pa+ern
heard that lead to fault
state in a weekTemperature
varies in a way that
I've never seen
before
Machine
oscillates different
than all other
machines in the
factory
12. 12
TinyML
Inspired by "OK Google"
Focus on inferencing, not training
Machine learning model is just a mathematical
function with lots of parameters
Accuracy vs. speed, reducing parameters, hardware-
optimized paths
Targeting battery-powered microcontrollers
Pete Warden
Neil Tan
15. Lone worker monitoring
Check new Person Presence Detection example in
FP-AI-VISION1 !
https://www.st.com/en/embedded-software/fp-ai-vision1.html
16. Endpoint
Machine level
Decisions
Distributed AI from Edge to Cloud
Edge
Actions
Data
Gateways
Room or building-level
Decisions
HomeIndustrial
Cloud
Cities or factory-level
decisions
• Fleet monitoring
• Macro Decisions (AI)
• Macro Actuation
Sensor
• Sensing
Smart sensor
• Sensing
• Preprocessing
• Micro classification
Data
MCU
• Real time
• Data privacy
• Micro Decisions (AI)
• Micro Actuation
Actions
Event
detection
Event
detection
Sensor Data
(Option)
Event
MCU / MPU
• Data or Event integration
• Data Privacy
• Meso Decisions (AI)
• Meso Actuation
16
17. GatewaysEndpoint
Edge
Actions
Data
Room or building-level
Decisions
Cloud
Cities or factory-level
decisions
• Fleet monitoring
• Macro Decisions (AI)
• Macro ActuationActions
Event
detection
Connectivity
Security
Sensing
Accelerometer
Gyrometer
Magnetometer
Vibration
PressureAcoustic Temperature
ML Core
Extensive MCU
portfolio
Processing &
Actuating
Machine level
Decisions
STM32MP1
STM32H7
STM32WB
Connectivity
Security
Processing &
Actuating
Event
detection
Sensor Data
(Option)
Event
Distributed AI from Edge to Cloud
17
18. IIS3DWB
Ultra Wide Bandwidth
Accelerometer
ISM330DLC
ISM330DHCX
Wide Bandwidth
Accelerometer + Gyroscope
IIS2DH
Wide Bandwidth, Ultra-low-power
Accelerometer
IIS2MDC
Low-Noise, Low Power
Magnetometer
18
ST portfolio for condition monitoring
Vibration
MP23ABS1TR Analog Differential Microphone
IMP34DT05-A Digital Top Port Microphone
Acoustic
LPS22HH
High Accuracy – Compact Size
Absolute Pressure Sensor
LPS27HHW
LPS33HW
Water Resistant
Absolute Pressure Sensor
STTS22H Digital Temperature Sensor
STLM20 Analog Temperature Sensor
Environmental
High Perf
MCUs
Ultra-low Power
MCUs
Wireless
MCUs
Mainstream
MCUs
MPU MEMS & Sensors
19. Wireless Industrial node
to capture data at industrial grade
19www.st.com/stwin
Industrial-grade sensors
• Industrial scale 9-DoF motion sensors including accelerometer, gyrometer
and an ultra wide-band vibrometer with ultra low noise
• Very high frequency audio and ultrasound microphone
• High precision temperature and environmental monitoring
• Micro SD card for standalone data logging
• BLE connectivity and WiFi expansion board
• USART
STWIN
Process & analyze new
data using trained NNCapture data
9
25. Classification
What's happening right now?
Anomaly detection
Is this behavior out of the ordinary?
Forecasting
What will happen in the future?
25
3. Letting the computers figure it out
26. 26
Picking the right algorithm
Classification
Neural network
Anomaly detection
K-means clustering
Forecasting
Regression
28. Seamless integration to STM32Cube ecosystem
STM32CubeMX, GUI Builders
Configure & generate code
28
Configure clocks, peripherals
and generate low-level code
Add application code and compile for any
STM32 target with the IDE of your choice
Deploy, debug and monitor
Generate model, optimize with STM32Cube.AI and export as CMSIS-PACK
And commercial IDEs
CMSIS-PACK
Import in CubeMX and benefit from STM32 ecosystem
CMSIS-PACK
running in Edge
Impulse’s Cloud
29. STM32CubeL1
Hardware Abstraction Layer
CMSI
S
STM32CubeF0
Hardware Abstraction Layer
CMSI
S
STM32CubeF2
Hardware Abstraction Layer
CMSI
S
STM32CubeF4
Hardware Abstraction Layer
CMSI
S
STM32CubeF1
Hardware Abstraction Layer
CMSI
S
STM32Cube
Hardware abstraction layer
CMSIS
STM32Cube
Middleware
User code
FirmwareHardware
Making it easy to start development, develop Proof of Concept
STM32
Ecosystem foundations
Configuration Development
Programming Monitoring
Tools
macOS®
And more
30. STM32CubeMX expansion
STM32Cube.AI tool
STM32Cube.AI offers interoperability
with state-of-the-art Deep Learning
design frameworks
Any framework that can export models in
ONNX open format can be imported,
including quantized models
Automatic and fast generation of an
STM32-optimized library
Train NN Model
Convert NN into
optimized code
for MCU
Process & analyze new
data using trained NN
30
On-device validation enable fast
comparison of model accuracy vs
different memory / quantization options
And more
35. 35
Get some hardware
ST IoT Discovery Kit
80MHz, 128K RAM, $50
Any smartphone Any other device
With our SDKs
36. 36
Edge Impulse - TinyML as a service
Embedded or edge
compute deployment
options
Test
Edge Device Impulse
Dataset
Acquire valuable
training data securely
Test impulse with
real-time device
data flows
Enrich data and
generate ML process
Real sensors in real time
Open source SDK
Free for developers: edgeimpulse.com