Subscribe to our Newsletter | To Post On IoT Central, Click here


Featured Posts (652)

Arm DevSummit 2020 debuted this week (October 6 – 8) as an online virtual conference focused on engineers and providing them with insights into the Arm ecosystem. The summit lasted three days over which Arm painted an interesting technology story about the current and future state of computing and where developers fit within that story. I’ve been attending Arm Techcon for more than half a decade now (which has become Arm DevSummit) and as I perused content, there were several take-a-ways I noticed for developers working on microcontroller based embedded systems. In this post, we will examine these key take-a-ways and I’ll point you to some of the sessions that I also think may pique your interest.

(For those of you that aren’t yet aware, you can register up until October 21st (for free) and still watch the conferences materials up until November 28th . Click here to register)

Take-A-Way #1 – Expect Big Things from NVIDIAs Acquisition of Arm

As many readers probably already know, NVIDIA is in the process of acquiring Arm. This acquisition has the potential to be one of the focal points that I think will lead to a technological revolution in computing technologies, particularly around artificial intelligence but that will also impact nearly every embedded system at the edge and beyond. While many of us have probably wondered what plans NVIDIA CEO Jensen Huang may have for Arm, the Keynotes for October 6th include a fireside chat between Jensen Huang and Arm CEO Simon Segars. Listening to this conversation is well worth the time and will help give developers some insights into the future but also assurances that the Arm business model will not be dramatically upended.

Take-A-Way #2 – Machine Learning for MCU’s is Accelerating

It is sometimes difficult at a conference to get a feel for what is real and what is a little more smoke and mirrors. Sometimes, announcements are real, but they just take several years to filter their way into the market and affect how developers build systems. Machine learning is one of those technologies that I find there is a lot of interest around but that developers also aren’t quite sure what to do with yet, at least in the microcontroller space. When we hear machine learning, we think artificial intelligence, big datasets and more processing power than will fit on an MCU.

There were several interesting talks at DevSummit around machine learning such as:

Some of these were foundational, providing embedded developers with the fundamentals to get started while others provided hands-on explorations of machine learning with development boards. The take-a-way that I gather here is that the effort to bring machine learning capabilities to microcontrollers so that they can be leveraged in industry use cases is accelerating. Lots of effort is being placed in ML algorithms, tools, frameworks and even the hardware. There were several talks that mentioned Arm’s Cortex-M55 architecture that will include Helium technology to help accelerate machine learning and DSP processing capabilities.

Take-A-Way #3 – The Constant Need for Reinvention

In my last take-a-way, I eluded to the fact that things are accelerating. Acceleration is not just happening though in the technologies that we use to build systems. The very application domain that we can apply these technology domains to is dramatically expanding. Not only can we start to deploy security and ML technologies at the edge but in domains such as space and medical systems. There were several interesting talks about how technologies are being used around the world to solve interesting and unique problems such as protecting vulnerable ecosystems, mapping the sea floor, fighting against diseases and so much more.

By carefully watching and listening, you’ll notice that many speakers have been involved in many different types of products over their careers and that they are constantly having to reinvent their skill sets, capabilities and even their interests! This is what makes working in embedded systems so interesting! It is constantly changing and evolving and as engineers we don’t get to sit idly behind a desk. Just as Arm, NVIDIA and many of the other ecosystem partners and speakers show us, technology is rapidly changing but so are the problem domains that we can apply these technologies to.

Take-A-Way #4 – Mbed and Keil are Evolving

There are also interesting changes coming to the Arm toolchains and tools like Mbed and Keil MDK. In Reinhard Keil’s talk, “Introduction to an Open Approach for Low-Power IoT Development“, developers got an insight into the changes that are coming to Mbed and Keil with the core focus being on IoT development. The talk focused on the endpoint and discussed how Mbed and Keil MDK are being moved to an online platform designed to help developers move through the product development faster from prototyping to production. The Keil Studio Online is currently in early access and will be released early next year.

(If you are interested in endpoints and AI, you might also want to check-out this article on “How Do We Accelerate Endpoint AI Innovation? Put Developers First“)

Conclusions

Arm DevSummit had a lot to offer developers this year and without the need to travel to California to participate. (Although I greatly missed catching up with friends and colleagues in person). If you haven’t already, I would recommend checking out the DevSummit and watching a few of the talks I mentioned. There certainly were a lot more talks and I’m still in the process of sifting through everything. Hopefully there will be a few sessions that will inspire you and give you a feel for where the industry is headed and how you will need to pivot your own skills in the coming years.

Originaly posted here

Read more…

Will We Ever Get Quantum Computers?

In a recent issue of IEEE Spectrum, Mikhail Dyakonov makes a pretty compelling argument that quantum computing (QC) isn't going to fly anytime soon. Now, I'm no expert on QC, and there sure is a lot of money being thrown at the problem by some very smart people, but having watched from the sidelines QC seems a lot like fusion research. Every year more claims are made, more venture capital gets burned, but we don't seem to get closer to useful systems.

Consider D-Wave Systems. They've been trying to build a QC for twenty years, and indeed do have products more or less on the market, including, it's claimed, one of 1024 q-bits. But there's a lot of controversy about whether their machines are either quantum computers at all, or if they offer any speedup over classical machines. One would think that if a 1K q-bit machine really did work the press would be all abuzz, and we'd be hearing constantly of new incredible results. Instead, the machines seem to disappear into research labs.

Mr. Duakonov notes that optimistic people expect useful QCs in the next 5-10 years; those less sanguine expect 20-30 years, a prediction that hasn't changed in two decades. He thinks a window of many decades to never is more realistic. Experts think that a useful machine, one that can do the sort of calculations your laptop is capable of, will require between 1000 and 100,000 q-bits. To me, this level of uncertainty suggests that there is a profound lack of knowledge about how these machines will work and what they will be able to do.

According to the author, a 1000 q-bit machine can be in 21000 states (a classical machine with N transistors can be in only 2N states), which is about 10300, or more than the number of sub-atomic particles in the universe. At 100,000 q-bits we're talking 1030,000, a mind-boggling number.

Because of noise, expect errors. Some theorize that those errors can be eliminated by adding q-bits, on the order of 1000 to 100,000 additional per q-bit. So a useful machine will need at least millions, or perhaps many orders of magnitude more, of these squirrelly microdots that are tamed only by keeping them at 10 millikelvin.

A related article in Spectrum mentions a committee formed of prestigious researchers tasked with assessing the probability of success with QC concluded that:

"[I]t is highly unexpected" that anyone will be able to build a quantum computer that could compromise public-key cryptosystems (a task that quantum computers are, in theory, especially suitable for tackling) in the coming decade. And while less-capable "noisy intermediate-scale quantum computers" will be built within that time frame, "there are at present no known algorithms/applications that could make effective use of this class of machine," the committee says."

I don't have a dog in this fight, but am relieved that useful QC seems to be no closer than The Distant Shore (to quote Jan de Hartog, one of my favorite writers). If it were feasible to easily break encryption schemes banking and other systems could collapse. I imagine Blockchain would fail as hash algorithms became reversable. The resulting disruption would not be healthy for our society.

On the other hand, Bruce Schneier's article in the March issue of IEEE Computing Edge suggests that QC won't break all forms of encryption, though he does think a lot of our current infrastructure will be vulnerable. The moral: if and when QC becomes practical, expect chaos.

I was once afraid of quantum computing, as it involves mechanisms that I'll never understand. But then I realized those machines will have an API. Just as one doesn't need to know how a computer works to program in Python, we'll be insulated from the quantum horrors by layers of abstraction.

Originaly posted here

Read more…

SSE Airtricity employees Derek Conty, left, Francie Byrne, middle, and Ryan Doran, right, install solar panels on the roof of Kinsale Community School in Kinsale, Ireland. The installation is part of a project with Microsoft to demonstrate the feasibility of distributed power purchase agreements. Credit: Naoise Culhane

by John Roach

Solar panels being installed on the roofs of dozens of schools throughout Dublin, Ireland, reflect a novel front in the fight against global climate change, according to a senior software engineer and a sustainability lead at Microsoft.

The technology copmpany partnered with SSE Airtricity, Ireland's largest provider of 100% green energy and a part of FTSE listed SSE Group, to install and manage the internet-connected solar panels, which are connected via Azure IoT to Microsoft Azure, a cloud computing platform.

The software tools aggregate and analyze real-time data on energy generated by the solar panels, demonstrating a mechanism for Microsoft and other corporations to achieve sustainability goals and reduce the carbon footprint of the electric power grid.

"We need to decarbonize the global economy to avoid catastrophic climate change," said Conor Kelly, the software engineer who is leading the distributed solar energy project for Microsoft Azure IoT. "The first thing we can do, and the easiest thing we can do, is focus on electricity."

Microsoft's $1.1 million contribution to the project builds on the company's ongoing investment in renewable energy technologies to offset carbon emissions from the operation of its datacenters.

A typical approach to power datacenters with renewable energy is for companies such as Microsoft to sign so-called power purchase agreements with energy companies.The agreements provide financial guarantees needed to build industrial-scale wind and solar farms and connections to the power grid.

The new project demonstrates the feasibility of agreements to install solar panels on rooftops distributed across towns with existing grid connections and use internet of things, or IoT, technologies to aggregate the accumulated energy production for carbon offset accounting.

"It utilizes existing assets that are sitting there unmonetized, which are roofs of buildings that absorb sunlight all day," Kelly said.

New Business Model

The project is also a proof-of-concept, or blueprint, for how energy providers can adapt as the falling price of solar panels enables distributed electric power generation throughout the existing electric power grid.

Traditionally, suppliers purchase power from central power plants and industrial-scale wind and solar farms and sell it to consumers on the distribution grid. Now, energy providers like SSE Airtricity provide renewable energy solutions that allow end consumers to generate power, from sustainable sources, using the existing grid connection on their premises.

"The more forward-thinking energy providers that we are working with, like SSE Airtricity, identify this as an opportunity and industry changing shift in how energy will be generated and consumed," Kelly noted.

The opportunity comes in the ability to finance the installation of solar panels and batteries at homes, schools, businesses and other buildings throughout a community and leverage IoT technology to efficiently perform a range of services from energy trading to carbon offset accounting.

Kelly and his team with Azure IoT are working with SSE Airtricity to develop the tools and machine learning models necessary to unlock this opportunity.

"Instead of having utility scale solar farms located outside of cities, you could have a solar farm at the distribution level, spread across a number of locations," said Fergal Ahern, a business energy solutions manager and renewable energy expert with SSE Airtricity.

For the distributed power purchase agreement, SSE Airtricity uses Azure IoT to aggregate the generation of all the solar panels installed across 27 schools around the provinces of Leinster, Munster and Connacht and run it through a machine learning model to determine the carbon emissions that the solar panels avoid.

The schools use the electricity generated by the solar panels, which reduces their utility bills; Microsoft receives the renewable energy credits for the generated electricity, which the company applies to its carbon neutrality commitments.

The panels are expected to produce enough energy annually to power the equivalent of 68 Irish homes for a year and abate more than 2.1 million kilograms, which is equivalent to 4.6 million pounds, of carbon dioxide emissions over the 15 years of the agreement, according to Kelly.

"This is additional renewable energy that wouldn't have otherwise happened," he said. "Every little bit counts when it comes to meeting our sustainability targets and combatting climate change."

Every little bit counts

Victory Luke, a 16 year old student at Collinstown Park Community College in Dublin, has lived by the "every little bit counts" mantra since she participated in a "Generation Green" sustainability workshop in 2019 organized by the Sustainable Energy Authority of Ireland, SSE Airtricity and Microsoft.

The workshop was part of an education program surrounding the installation of solar panels and batteries at her school along with a retrofit of the lighting system with LEDs. Digital screens show the school's energy use in real time, allowing students to see the impact of the energy efficiency upgrades.

Luke said the workshop captured her interest on climate change issues. She started reading more about sustainability and environmental conservation and agreed to share her newfound knowledge with the younger students at her school.

"I was going around and talking to them about energy efficiency, sharing tips and tricks like if you are going to boil a kettle, only boil as much water as you need, not too much," she explained.

That June, the Sustainable Energy Authority of Ireland invited her to give a speech at the Global Conference on Energy Efficiency in Dublin, which was organized by the International Energy Agency, an organization that works with governments and industry to shape sustainable energy policy.

"It kind of felt surreal because I honestly felt like I wasn't adequate enough to be speaking about these things," she said, noting that the conference attendees included government ministers, CEOs and energy experts from around the world.

At the time, she added, the global climate strike movement and its youth leaders were making international headlines, which made her advocacy at school feel even smaller. "Then I kind of realized that it is those smaller things that make the big difference," she said.

SSE Airtricity and Microsoft plan to replicate the educational program that inspired Luke and her classmates at dozens of the schools around Ireland that are participating in the project.

"When you've got solar at a school and you can physically point at the installation and a screen that monitors the power being generated, it brings sustainability into daily school life," Ahern said.

Proof of concept for policymakers

The project's education campaign extends to renewable energy policymakers, Kelly noted. He explained that renewable energy credits—a market incentive for corporations to support renewable energy projects—are currently unavailable for distributed power purchase agreements.

For this project, Microsoft will receive genuine renewable energy credits from a wind farm that SSE Airtricity also operates, he added.

"And," he said, "we are hoping to use this project as an example of what regulation should look like, to say, 'You need to award renewable energy credits to distributed generation because they would allow corporates to scale-up this type of project.'"

For her part, Luke supports steps by multinational corporations such as Microsoft to invest in renewable energy projects that address global climate change.

"It is a good thing to see," she said. "Once one person does something, other people are going to follow.

Originaly posted HERE

Read more…

An edge device is the network component that is responsible for connecting a local area network to an external or wide area network, which can be accessed from anywhere. Edge devices offer several new services and improved outcomes for IoT deployments across all markets. Smart services that rely on high volumes of data and local analysis can be deployed in a wide range of environments.

Edge device provides the local data to an external network. If protocols are different in local and external networks, it also translates this information, and make the connection between both network boundaries. Edge devices analyze diagnostics and automatic data populating; however, it is necessary to make a secure connection between the field network and cloud computing. In the event of loss of internet connection or cloud crash edge device will store data until the connection is established, so it won’t lose any process information. The local data storage is optional and not all edge devices offer local storage, it depends on the application and service required to implement on the plant.

How does an edge device work?

An edge device has a very straightforward working principle, it communicates between two different networks and translates one protocol into another. Furthermore, it creates a secure connection with the cloud.

An edge device can be configured via local access and internet or cloud. In general, we can say an edge device is a plug-and-play, its setup is simple and does not require much time to configure.

Why should I use an edge device?

Depending on the service required in the plant, the edge devices will be a crucial point to collect the information and create an automatic digital twin of your device in the cloud. 

Edge devices are an essential part of IoT solutions since they connect the information from a network to a cloud solution. They do not affect the network but only collect the data from it, and never cause a problem with the communication between the control system and the field devices. by using an edge device to collect information, the user won’t need to touch the control system. Edge is one-way communication, nothing is written into the network, and data are acquired with the highest possible security.

Edge device requirements

Edge devices are required to meet certain requirements that are to meet at all conditions to perform in different secretions. This may include storage, network, and latency, etc.

Low latency

Sensor data is collected in near real-time by an edge server. For services like image recognition and visual monitoring, edge servers are located in very close proximity to the device, meeting low latency requirements. Edge deployment needs to ensure that these services are not lost through poor development practice or inadequate processing resources at the edge. Maintaining data quality and security at the edge whilst enabling low latency is a challenge that need to address.

Network independence

IoT services do not care for data communication topology.  The user requires the data through the most effective means possible which in many cases will be mobile networks, but in some scenarios, Wi-Fi or local mesh networking may be the most effective mechanism of collecting data to ensure latency requirements can be met.

Good-Edge-IOT-Device-1024x576.jpg

Data security

Users require data at the edge to be kept secure as when it is stored and used elsewhere. These challenges need to meet due to the larger vector and scope for attacks at the edge. Data authentication and user access are as important at the edge as it is on the device or at the core.  Additionally, the physical security of edge infrastructure needs to be considered, as it is likely to hold in less secure environments than dedicated data centers.

Data Quality

Data quality at the edge is a key requirement to guarantee to operate in demanding environments. To maintain data quality at the edge, applications must ensure that data is authenticated, replicated as and assigned into the correct classes and types of data category.

Flexibility in future enhancements

Additional sensors can be added and managed at the edge as requirements change. Sensors such as accelerometers, cameras, and GPS, can be added to equipment, with seamless integration and control at the edge.

Local storage

Local storage is essential in the event of loss of internet connection or cloud crash edge device will store data until the connection is established, so it won’t lose any process information. The local data storage is optional and not all edge devices offer local storage, it depends on the application and service required to implement on the plant

Originaly Posted here

Read more…

by Singapore University of Technology and Design

Internet-of-Things (IoT) such as smart home locks and medical devices, depend largely on Bluetooth low energy (BLE) technology to function and connect across other devices with reduced energy consumption. As these devices get more prevalent with increasing levels of connectivity, the need for strengthened security in IoT has also become vital.

A research team, led by Assistant Professor Sudipta Chattopadhyay from the Singapore University of Technology and Design (SUTD), wit team members from SUTD and the Institute for Infocomm Research (I2R), designed and implemented the Greyhound framework, a tool used to discover SweynTooth—a critical set of 11 cyber vulnerabilities.

Their study was presented at the USENIX Annual Technical Conference (USENIX ATC) on 15 to 17 July 2020 and they have been invited to present at the upcoming Singapore International Cyber Week (SICW) in October 2020.

These security lapses were found to affect devices by causing them to crash, reboot or bypass security features. At least 12 BLE based devices from eight vendors were affected, including a few hundred types of IoT products including pacemakers, wearable fitness trackers and home security locks.

The SweynTooth code has since been made available to the public and several IoT product manufacturers have used it to find security issues in their products. In Singapore alone, 32 medical devices reported to be affected by SweynTooth and 90% of these device manufacturers have since implemented preventive measures against this set of cyber vulnerabilities.

Regulatory agencies including the Cyber Security Agency and the Health Sciences Authority in Singapore as well as the Department of Homeland Security and the Food and Drug Administration in the United States have reached out to the research team to further understand the impact of these vulnerabilities.

These agencies have also raised public alerts to inform medical device manufacturers, healthcare institutions and end users on the potential security breach and disruptions. The research team continues to keep them updated on their research findings and assessments.

Beyond Bluetooth technology, the research team designed the Greyhound framework using a modular approach so that it could easily be adapted for new wireless protocols. This allowed the team to test it across the diverse set of protocols that IoTs frequently employ. This automated framework also paves new avenues in the testing security of more complex protocols and IoTs in next-generation wireless protocol implementations such as 5G and NarrowBand-IoT which require rigorous and systematic security testing.

"As we are transitioning towards a smart nation, more of such vulnerabilities could appear in the future. We need to start rethinking the device manufacturing design process so that there is limited reliance on communication modules such as Bluetooth to ensure a better and more secure smart nation by design," explained principal investigator Assistant Professor Sudipta from SUTD.

Originally posted HERE.

Read more…

When you’re in technology, you have to expect change. Yet, there’s something to the phrase “the more things change, the more they stay the same.” For instance, I see in the industrial internet of things (IIoT) a realm that’ll dramatically shape the future - how we manufacture, the way we run our factories, workforce needs – but the underlying business goals are the same as always.

Simply put, while industrial enterprise initiatives may change, financial objectives don’t – and they’re still what matter most. That’s why IIoT is so appealing. While the possibilities of smart and connected operations, sites and products certainly appeal to the dreamer and innovator, the clear payoff ensures that it’s a road even the most pragmatic decision-maker will eagerly follow.

The big three
When it comes to industrial enterprises, IIoT addresses the “big three” financial objectives head on. The technology maximizes revenue growth, reduces operating expense and increases asset efficiency.

IIoT does this in numerous ways. It yields invaluable operational intelligence, like real-time performance management data, to reduce manufacturing costs, increase flexibility and enable agility. When it comes to productivity, connected digital assets can empower a workforce with actionable insights to improve productivity and quality, even prevent safety and compliance issues.

For example, recognizing defects in a product early on can save time, materials, staff hours and possibly even a company’s reputation.

Whether on or off the factory floor, IIoT can be used to optimize asset efficiency. With real-time monitoring, diagnostics and analytics, downtime can be reduced or avoided. Asset utilization can also be evaluated and maximized. Think applications like equipment health monitoring, predictive maintenance, the ability to provide augmented 3D instructions for complex repairs. And, you can also scale production more precisely via better control over processes and inventory.

All of this accelerates time to market; another key benefit of IIoT and long held business goal.

Why is 5G important for IIoT and augmented reality (AR)?
As we look at the growing need to connect more devices, more sensors and install things like real-time cameras for doing analytics, there is growing stress and strain that is brought into industrial settings. We have seen the need to increase connectivity while having greater scalability, performance, accessibility, reliability, and broader reach with a lower cost of ownership become much more important. This is where 5G can make a real difference.

Many of our customers have seen what we are doing with augmented reality and the way that PTC can help operators service equipment. But in the not so distant future, the way that people interact with robotics, for example, will change. There will be real-time video to do spatial analytics on the way that people are working with man and machines and we’ll be able to unlock a new level of intelligence with a new layer of connectivity that helps drive better business outcomes.

Partner up
It sounds nice but the truth is, a lot of heavy lifting is required to do IIoT right. The last thing you want to do is venture into a pilot, run into problems, and leave the C-suite less than enthused with the outcome. And make no mistake, there’s a lot potential pitfalls to be aware of.

For instance, lengthy proof of concept periods, cumbersome processes and integrations can slow time to market. Multiple, local integrations can be required when connectivity and device management gets siloed. If not done right, you may only gain limited visibility into devices and the experience will fall short. And, naturally, global initiatives can be hindered by high roaming costs and deployment obstacles.

That said, you want to harness best of breed providers, not only to realize the full benefits of Industry 4.0, but to set yourself up with a foundation that’ll be able to harness 5G developments. You need a trusted IoT partner, and because of the sophistication and complexity, it takes an ecosystem of proven innovators working collaboratively.

That’s why PTC and Ericsson are partners.

Doing what’s best
Ericsson unlocks the full value of global cellular IoT connectivity and provides on-premise solutions. PTC offers an industrial IoT platform that’s ready to configure and deploy, with flexible connectivity and capabilities to build solutions without manual coding.

Drilling down a bit further, Ericsson’s IoT Accelerator can connect and manage billions of devices and millions of applications easily, seamlessly and globally. PTC’s IoT solutions digitalize processes and products, combining the physical and digital worlds seamlessly.

And with wireless connectivity, we can deploy a lot of new technology – from augmented reality to artificial intelligence applications – without having to think about the time and cost of creating fixed infrastructures, running wires, adding network capacity and more.

According ABI Research, organizations that embrace Industry 4.0 and private cellular have the potential to improve gross margins by 5-13% in factory and warehouse operations. Manufacturers can expect a 10x return on their investment. And with 4.3 billion wireless connections in smart factories anticipated by 2030, it’s clear where things are headed.

By focusing on what we each do best, PTC and Ericsson is able to do what’s best for our customers. We can help them build and scale global cellular IoT deployments faster and gain a competitive advantage. They can reap the advantages of Industry 4.0 and create that path to 5G, future-proofing their operations and enjoying such differentiators as network slicing, edge computing and high-reliability, low latency communications.

Further, with our histories of innovation, customers are assured they’ll be supported in the future, remaining out front with the ability to adapt to change, grow and deliver on financial objections.

Editor's Note: This post was originally published by Steve Dertien, Chief Technology Officer for PTC, on Ericsson's website, and is part of a joint content effort with Kiva Allgood, head of IoT for Ericsson. To view Steve's original, please click here. To read Kiva's complementary post, please click here.

Read more…

A scientist from Russia has developed a new neural network architecture and tested its learning ability on the recognition of handwritten digits. The intelligence of the network was amplified by chaos, and the classification accuracy reached 96.3%. The network can be used in microcontrollers with a small amount of RAM and embedded in such household items as shoes or refrigerators, making them 'smart.' The study was published in Electronics.

Today, the search for new neural networks that can operate on microcontrollers with a small amount of random access memory (RAM) is of particular importance. For comparison, in ordinary modern computers, random access memory is calculated in gigabytes. Although microcontrollers possess significantly less processing power than laptops and smartphones, they are smaller and can be interfaced with household items. Smart doors, refrigerators, shoes, glasses, kettles and coffee makers create the foundation for so-called ambient intelligece. The term denotes an environment of interconnected smart devices. 

An example of ambient intelligence is a smart home. The devices with limited memory are not able to store a large number of keys for secure data transfer and arrays of neural network settings. It prevents the introduction of artificial intelligence into Internet of Things devices, as they lack the required computing power. However, artificial intelligence would allow smart devices to spend less time on analysis and decision-making, better understand a user and assist them in a friendly manner. Therefore, many new opportunities can arise in the creation of environmental intelligence, for example, in the field of health care.

Andrei Velichko from Petrozavodsk State University, Russia, has created a new neural network architecture that allows efficient use of small volumes of RAM and opens the opportunities for the introduction of low-power devices to the Internet of Things. The network, called LogNNet, is a feed-forward neural network in which the signals are directed exclusively from input to output. Its uses deterministic chaotic filters for the incoming signals. The system randomly mixes the input information, but at the same time extracts valuable data from the information that are invisible initially. A similar mechanism is used by reservoir neural networks. To generate chaos, a simple logistic mapping equation is applied, where the next value is calculated based on the previous one. The equation is commonly used in population biology and as an example of a simple equation for calculating a sequence of chaotic values. In this way, the simple equation stores an infinite set of random numbers calculated by the processor, and the network architecture uses them and consumes less RAM.

7978216495?profile=RESIZE_584x

The scientist tested his neural network on handwritten digit recognition from the MNIST database, which is considered the standard for training neural networks to recognize images. The database contains more than 70,000 handwritten digits. Sixty-thousand of these digits are intended for training the neural network, and another 10,000 for network testing. The more neurons and chaos in the network, the better it recognized images. The maximum accuracy achieved by the network is 96.3%, while the developed architecture uses no more than 29 KB of RAM. In addition, LogNNet demonstrated promising results using very small RAM sizes, in the range of 1-2kB. A miniature controller, Atmega328, can be embedded into a smart door or even a smart insole, has approximately the same amount of memory.

"Thanks to this development, new opportunities for the Internet of Things are opening up, as any device equipped with a low-power miniature controller can be powered with artificial intelligence. In this way, a path is opened for intelligent processing of information on peripheral devices without sending data to cloud services, and it improves the operation of, for example, a smart home. This is an important contribution to the development of IoT technologies, which are actively researched by the scientists of Petrozavodsk State University. In addition, the research outlines an alternative way to investigate the influence of chaos on artificial intelligence," said Andrei Velichko.

Originally posted HERE.

by Russian Science Foundation

Image Credit: Andrei Velichko

 

 

 

 

Read more…

Impact of IoT in Inventory

Internet of Things (IoT) has revolutionized many industries including inventory management. IoT is a concept where devices are interconnected via the internet. It is expected that by 2020, there will be 26 billion devices connected worldwide. These connections are important because it allows data sharing which then can perform actions to make life and business more efficient. Since inventory is a significant portion of a company’s assets, inventory data is vital for an accounting department for the company’s asset management and annual report.

Inventory solutions based on IoT and RFID, individual inventory item receives an RFID tag. Each tag has a unique identification number (ID) that contains information about an inventory item, e.g. a model, a batch number, etc. these tags are scanned by RF reader. Upon scanning, a reader extracts its IDs and transmits them to the cloud for processing. Along with the tag’s ID, the cloud receives location and the time of reading. This data is used for updates about inventory items’, allowing users to monitor the inventory from anywhere, in real-time.

Industrial IoT

The role of IoT in inventory management is to receive data and turn it into meaningful insights about inventory items’ location, status, and giving users a corresponding output. For example, based on the data, and inventory management solution architecture, we can forecast the number of raw materials needed for the upcoming production cycle. The output of the system can also send an alert if any individual inventory item is lost.

Moreover, IoT based inventory management solutions can be integrated with other systems, i.e. ERP and share data with other departments.

RFID in Industrial IoT

RFID consist of three main components tag, antenna, and a reader

Tags: An RFID tag carries information about a specific object. It can be attached to any surface, including raw materials, finished goods, packages, etc.

RFID antennas: An RFID antenna receives signals to supply power and data for tags’ operation

RFID readers: An RFID reader, uses radio signals to read and write to the tags. The reader receives data stored in the tag and transmits it to the cloud.

Benefits of IoT in inventory management

The benefits of IoT on the supply chain are the most exciting physical manifestations we can observe. IoT in the supply chain creates unparalleled transparency that increases efficiencies.

Inventory tracking

The major benefit of inventory management is asset tracking, instead of using barcodes to scan and record data, items have RFID tags which can be registered wirelessly. It is possible to accurately obtain data and track items from any point in the supply chain.

With RFID and IoT, managers don’t have to spend time on manual tracking and reporting on spreadsheets. Each item is tracked and the data about it is recorded automatically. Automated asset tracking and reporting save time and reduce the probability of human error.

Inventory optimization

Real-time data about the quantity and the location of the inventory, manufacturers can reduce the amount of inventory on hand while meeting the needs of the customers at the end of the supply chain.

The data about the amount of available inventory and machine learning can forecast the required inventory which allows manufacturers to reduce the lead time.

Remote tracking

Remote product tracking makes it easy to have an eye on production and business. Knowing production and transit times, allows you to better tweak orders to suit lead times and in response to fluctuating demand. It shows which suppliers are meeting production and shipping criteria and which needs monitoring for the required outcome.

It gives visibility into the flow of raw materials, work-in-progress and finished goods by providing updates about the status and location of the items so that inventory managers see when an individual item enters or leaves a specific location.

Bottlenecks in the operations

With the real-time data about the location and the quantity, manufacturers can reveal bottlenecks in the process and pinpoint the machine with lower utilization rates. For instance, if part of the inventory tends to pile up in front of a machine, a manufacturer assumes that the machine is underutilized and needs to be seen to.

The Outcomes

The data collected by inventory management is more accurate and up-to-date. By reducing these time delays, the manufacturing process can enhance accuracy and reduce wastage. An IoT-based inventory management solution offers complete visibility on inventory by providing real-time information fetched by RFID tags. It helps to track the exact location of raw materials, work-in-progress and finished goods. As a result, manufacturers can balance the amount of on-hand inventory, increase the utilization of machines, reduce lead time, and thus, avoid costs bound to the less effective methods. This is all about optimizing inventory and ensuring anything ordered can be sold through whatever channel necessary.

Originally posted here

Read more…

After so many years evangelizing the Internet of Things (IoT) or developing IoT products or selling IoT services or using IoT technologies, it is hard to believe that today there are as many defenders as detractors of these technologies. Why does the doubt still assail us: "Believe or Not Believe in the IoT"? What's the reason we keep saying every year that the time for IoT is finally now?

It does not seem strange to you that if we have already experienced the power of change that involves having connected devices in ourselves (wearables), in our homes, in cities, in transportation, in business, we continue with so many non-believers. Maybe, because the expectations in 2013 were so great that now in 2020 we need more tangible and realistic data and facts to continue believing.

In recent months I have had more time to review my articles and some white papers and I think I have found some reasons to continue believing, but also reasons not to believe.

Here below there are some of these reasons for you to decide where to position yourself.

Top reasons to believe

  • Mackinsey continue presenting us new opportunities with IoT
    • If in 2015 “Internet of Things: Mapping the value beyond the hype” the company estimated a potential economic impact as much as 11,1 US trillions per year in 2025 for IoT applications in 9 settings.
    • In 2019 “Growing opportunities in the Internet of Things” they said that “The number of businesses that use the IoT technologies has increased from 13 percent in 2014 to about 25 percent today. And the worldwide number of IoT connected devices is projected to increase to 43 billion by 2023, an almost threefold increase from 2018.”
  • Gartner in 2019 predicted that by 2021, there will be over 25 Billion live IoT endpoints that will allow unlimited number of IoT use cases.
  • Harbor Research considers that the market opportunity for industrial internet of things (IIoT) and industry 4.0 is still emergent.
    • Solutions are not completely new but are evolving from the convergence of existing technologies; creative combinations of these technologies will drive many new growth opportunities;
    • As integration and interoperability across the industrial technology “stack” relies on classic IT principles like open architectures, many leading IT players are entering the industrial arena;
  • IoT regulation is coming - The lack of regulation is one of the biggest issues associated with IoT devices, but things are starting to change in that regard as well. The U.S. government was among the first to take the threat posed by unsecured IoT devices seriously, introducing several IoT-related bills in Congress over the last couple of years. It all began with the IoT Cybersecurity Improvement Act of 2017, which set minimum security standards for connected devices obtained by the government. This legislation was followed by the SMART IoT Act, which tasked the Department of Commerce with conducting a study of the current IoT industry in the United States.
  • Synergy of IoT and AI - IoT supported by artificial intelligence enhances considerably the success in a large repertory of every-day applications with dominant one’s enterprise, transportation, robotics, industrial, and automation systems applications.
  • Believe in superpowers again, thanks to IoT - Today, IoT sensors are everywhere – in your car, in electronic appliances, in traffic lights, even probably on the pigeon outside your window (it’s true, it happened in London!). IoT sensors will help cities map air quality, identify high-pollution pockets, trigger alerts if pollution levels rise dangerously, while tracking changes over time and taking preventive measures to correct the situation. thanks to IoT, connected cars will now communicate seamlessly with IoT sensors and find empty parking spots easily. Sensors in your car will also communicate with your GPS and the manufacturer’s system, making maintenance and driving a breeze!. City sensors will identify high-traffic areas and regulate traffic flows by updating your GPS with alternate routes. These IoT sensors can also identify and repair broken street lamps. IoT will be our knight in shining, super-strong metallic armor and prevent accidents like floods, fires and even road accidents, by simply monitoring fatigue levels of truck drivers!. Washing machines, refrigerators, air-conditioners will now self-monitor their usage, performance, servicing requirements, while triggering alerts before potential breakdowns and optimizing performance with automatic software updates. IoT sensors will now help medical professional monitor pulse rates, blood pressure and other vitals more efficiently, while triggering alerts in case of emergencies. Soon, Nano sensors in smart pills will make healthcare super-personalized and 10x more efficient!

Top reasons not to believe

  1. Three fourths of IoT projects failing globally. Government and enterprises across the globe are rolling out Internet of Things (IoT) projects but almost three-fourths of them fail, impacted by factors like culture and leadership, according to US tech giant Cisco (2017). Businesses are spending $745 billion worldwide on IoT hardware and software in 2019 alone. Yet, three out of every four IoT implementations are failing.
  2. Few IoT projects survive proof-of-concept stage - About 60% of IoT initiatives get stalled at the Proof of Concept (PoC) stage. If the right steps aren’t taken in the beginning, say you don’t think far enough beyond the IT infrastructure, you end up in limbo: caught between the dream of what IoT could do for your business and the reality of today’s ROI. That spot is called proof-of-concept (POC) purgatory.
  3. IoT Security still a big concern - The 2019 annual report of SonicWall Caoture Labs threat researchers analyzing data from over 200,000 malicious events indicated that 217.5 percent increase in IoT attacks in 2018.
  4. There are several obstacles companies face both in calculating and realizing ROI from IoT. Very few companies can quantify the current, pre-IoT costs. The instinct is often to stop after calculating the cost impact on the layer of operations immediately adjacent to the potential IoT project.  For example, when quantifying the baseline cost of reactive (versus predictive or prescriptive) maintenance, too many companies would only include down time for unexpected outages, but may not consider reduced life of the machine, maintenance overtime, lost sales due to long lead times, supply chain volatility risk for spare parts, and the list goes on.
  5. Privacy, And No, That’s Not the Same as Security. The Big Corporations don’t expect to make a big profit on the devices themselves. the Big Money in IoT is in Big Data. And enterprises and consumers do not want to expose everything sensors are learning about your company or you.
  6. No Killer Application – I suggest to read my article “Worth it waste your time searching the Killer IoT Application?"
  7. No Interoperable Technology ecosystems - We have a plethora of IoT vendors, both large and small, jumping into the fray and trying to establish a foothold, in hopes of either creating their own ecosystem (for the startups) or extending their existing one (for the behemoths).
  8. Digital Fatigue – It is not enough for us to try to explain IoT, that now more technologies such as Artificial Intelligence, Blockchain, 5G, AR / VR are joining the party and of course companies say enough.

You have the last word

We can go on forever looking for reasons to believe or not believe in IoT but we cannot continue to deny the evidence that the millions of connected devices already out there and the millions that will soon be waiting for us to exploit their full potential.

I still believe. But you have the last word.

Thanks in advance for your Likes and Shares

Read more…

A fingerprint for the Internet of Things

By: Tom Jeltes, Eindhoven University of Technology

The Internet of Things (IoT) consists of billions of sensors and other devices connected to each other via internet, all of which need to be protected against hackers with malicious purposes. A low-cost and energy efficient solution for the security of IoT devices uses the unique characteristics of the built-in memory chips. Ph.D. candidate Lieneke Kusters investigated how to make optimal use of the chip's digital fingerprint to generate a security key.

The higher the number of devices connected to each other via the Internet of Things, the greater the risk that malicious hackers might gain access to important information, or even take over entire systems. Quite apart from all kinds of privacy issues, it's not hard to imagine that that someone who, for example, has control over temperature sensors in a chemical or nuclear plant, could cause serious damage.

 To prevent problems like these from occurring, each IoT device needs to be able, as it were, to show an identity document—"authentication," in professional terms. Normally, speaking, this is done with a kind of password, which is sent in encrypted form to the person who is communicating with the device. The security key needed for that has to be stored in the IoT device one way or another, Lieneke Kusters explains. "But these are often small and cheap devices that aren't supposed to use much energy. To safely store a key in these devices, you need extra hardware with constant power supply. That's not very practical."

Digital fingerprint

There is a different way: namely by deducing the security key from a unique physical characteristic of the memory chip (Static Random-Access Memory, or SRAM) that can be found in practically every IoT device. Depending on the random circumstances during the chip's manufacturing process, the memory locations have a random default value of 0 or 1.

"That binary code which you can read out when activating the chip, constitutes a kind of digital fingerprint of the device," says Kusters, who gained her doctorate at the Information and Communication Theory Laboratory at the TU/e department of Electrical Engineering. This fingerprint is known as a Physical Unclonable Function (PUF). "The Eindhoven-based company Intrinsic ID sells digital security based on SRAM-PUFs. I collaborated with them for my doctoral research, during which I focused on how to generate, in a reliable way, a key from that digital fingerprint that is as long as possible. The longer, the safer."

The major advantage of security keys based on SRAM-PUFs is that the key exists only at the moment when authentication is required. "The device restarts itself to read out the SRAM-PUF and in doing so creates the key, which subsequently gets erased immediately after use. That makes it all but impossible for an attacker to steal the key."

Noise and reliability

But that's not the entire story, because some bits of the SRAM do not always have the same value during activation, Kusters explains. Ten to fifteen percent of the bits turn out not to be determined, which makes the digital fingerprint a bit fuzzy. How do you use that fuzzy fingerprint to make a key of the highest possible complexity that nevertheless still fits into the receiving lock—practically—each time?

"What you want to prevent is that the generated key won't be recognized by the receiving party as a consequence of the 'noise' in the SRAM-PUF," Kusters explains. "It's alright if that happens one in a million times perhaps, preferably less often." The probability of error is smaller with a shorter key, but such a key is also easier to guess for people with bad intentions. "I've searched for the longest reliable key, given a certain amount of noise in the measurement. It helps if you store extra information about the SRAM-PUF, but that must not be of use to a potential attacker. My thesis is an analysis of how you can reach the optimal result in different situations with that extra information."

Originaly posted here.


 
Read more…

Can AI Replace Firmware?

Scott Rosenthal and I go back about a thousand years; we've worked together, helped midwife the embedded field into being, had some amazing sailing adventures, and recently took a jaunt to the Azores just for the heck of it. Our sons are both big data people; their physics PhDs were perfect entrees into that field, and both now work in the field of artificial intelligence.

At lunch recently we were talking about embedded systems and AI, and Scott posed a thought that has been rattling around in my head since. Could AI replace firmware?

Firmware is a huge problem for our industry. It's hideously expensive. Only highly-skilled people can create it, and there are too few of us.

What if an AI engine of some sort could be dumped into a microcontroller and the "software" then created by training that AI? If that were possible - and that's a big "if" - then it might be possible to achieve what was hoped for when COBOL was invented: programmers would no longer be needed as domain experts could do the work. That didn't pan out for COBOL; the industry learned that accountants couldn't code. Though the language was much more friendly than the assembly it replaced, it still required serious development skills.

But with AI, could a domain expert train an inference engine?

Consider a robot: a "home economics" major could create scenarios of stacking dishes from a dishwasher. Maybe these would be in the form of videos, which were then fed to the AI engine as it tuned the weighting coefficients to achieve what the home ec expert deems worthy goals.

My first objection to this idea was that these sorts of systems have physical constraints. With firmware I'd write code to sample limit switches so the motors would turn off if at an end-of-motion extreme. During training an AI-based system would try and drive the motors into all kinds of crazy positions, banging destructively into stops. But think how a child learns: a parent encourages experimentation but prevents the youngster from self-harm. Maybe that's the role of the future developer training an AI. Or perhaps the training will be done on a simulator of some sort where nothing can go horribly wrong.

Taking this further, a domain expert could define the desired inputs and outputs, and then a poorly-paid person do the actual training. CEOs will love that. With that model a strange parallel emerges to computation a century ago: before the computer age "computers" were people doing simple math to create tables of logs, trig, ballistics, etc. A room full all labored at a problem. They weren't particularly skilled, didn't make much, but did the rote work under the direction of one master. Maybe AI trainers will be somewhat like that.

Like we outsource clothing manufacturing to Bangladesh, I could see training, basically grunt work, being sent overseas as well.

I'm not wild about this idea as it means we'd have an IoT of idiots: billions of AI-powered machines where no one really knows how they work. They've been well-trained but what happens when there's a corner case?

And most of the AI literature I read suggests that inference successes of 97% or so are the norm. That might be fine for classifying faces, but a 3% failure rate of a safety-critical system is a disaster. And the same rate for less-critical systems like factory controllers would also be completely unacceptable.

But the idea is intriguing.

Original post can be viewed here

Feel free to email me with comments.

Back to Jack's blog index page.

Read more…

Theoratical Embedded Linux requirements

Hardware

SoC

A System on Chip (SoC), is essentially an integrated circuit that takes a single platform and integrates an entire computer system onto it. It combines the power of the CPU with other components that it needs to perform and execute its functions. It is in charge of using the other hardware and running your software. The main advantage of SoC includes lower latency and power saving.

It is made of various building blocks:

  • Core + Caches + MMU – An SoC has a processor at its core which will define its functions. Normally, an SoC has multiple processor cores. For a “real” processor, e.g. ARM Cortex-A9. It’s the main thing kept in mind while choosing an SoC. Maybe co-adjuvanted by e.g. a SIMD co-processor like NEON.
  • Internal RAM – IRAM is composed of very high-speed SRAM located alongside the CPU. It acts similar to a CPU cache, and generally very small. It is used in the first phase of the boot sequence.
  • Peripherals – These can be a simple ADC, DSP, or a Graphical Processing Unit which is connected via some bus to the Core. A low power/real-time co-processor helps the main Core with real-time tasks or handle low power states. Examples of such IP cores are USB, PCI-E, SGX, etc.

External RAM

An SoC uses RAM to store temporary data during and after bootstrap. It is the memory an embedded system uses during regular operation.

Non-Volatile Memory

In an Embedded system or single-board computer, it is the SD card. In other cases, it can be a NAND, NOR, or SPI Data flash memory. It is the source of data the SoC reads and stores all the software components needed for the system to work.

External Peripherals

An SoC must have external interfaces for standard communication protocols such as USB, Ethernet, and HDMI. It also includes wireless technology protocols of Wi-Fi and Bluetooth.

Software

Second-Article-01-1024x576.jpghttps://www.tirichlabs.com/storage/2020/09/Second-Article-01-300x169.jpg 300w, https://www.tirichlabs.com/storage/2020/09/Second-Article-01-768x432.jpg 768w, https://www.tirichlabs.com/storage/2020/09/Second-Article-01-1200x675.jpg 1200w" alt="" />

First of all, we introduce the boot chain which is the series of actions that happens when an SoC is powered up.

Boot ROM: It is a piece of code stored in the ROM which is executed by the booting core when it is powered-on. This code contains instructions for the configuration of SoC to allow it to execute applications. The configurations performed by Boot ROM include initialization of the core’s register and stack pointer, enablement of caches and line buffers, programming of interrupt service routine, clock configuration.

Boot ROM also implements a Boot Assist Module (BAM) for downloading an application image from external memories using interfaces like Ethernet, SD/MMC, USB, CAN, UART, etc.

1st stage bootloader

In the first-stage bootloader performs the following

  • Setup the memory segments and stack used by the bootloader code
  • Reset the disk system
  • Display a string “Loading OS…”
  • Find the 2nd stage boot loader in the FAT directory
  • Read the 2nd stage boot loader image into memory at 1000:0000
  • Transfer control to the second-stage bootloader

It copies the Boot ROM into the SoC’s internal RAM. Must be tiny enough to fit that memory usually well under 100kB. It initializes the External RAM and the SoC’s external memory interface, as well as other peripherals that may be of interest (e.g. disable watchdog timers). Once done, it executes the next stage, depending on the context, which could be called MLO, SPL, or else.

2nd stage bootloader

This is the main bootloader and can be 10 times bigger than the 1st stage, it completes the initialization of the relevant peripherals.

  • Copy the boot sector to a local memory area
  • Find kernel image in the FAT directory
  • Read kernel image in memory at 2000:0000
  • Reset the disk system
  • Enable the A20 line
  • Setup interrupt descriptor table at 0000:0000
  • Setup the global descriptor table at 0000:0800
  • Load the descriptor tables into the CPU
  • Switch to protected mode
  • Clear the prefetch queue
  • Setup protected mode memory segments and stack for use by the kernel code
  • Transfer control to the kernel code using a long jump

Linux Kernel

The Linux kernel is the main component of a Linux OS and is the core interface between hardware and processes. It communicates between the hardware and processes, managing resources as efficiently as possible. The kernel performs following jobs

  • Memory management: Keep track of memory, how much is used to store what, and where
  • Process management: Determine which processes can use the processor, when, and for how long
  • Device drivers: Act as an interpreter between the hardware and the processes
  • System calls and security: Receive requests for the service from processes

To put the kernel in context, they can be interpreted as a Linux machine as having 3 layers:

  • The hardware: The physical machine—the base of the system, made up of memory (RAM) and the processor (CPU), as well as input/output (I/O) devices such as storage, networking, and graphics.
  • The Linux kernel: The core of the OS. It is a software residing in memory that tells the CPU what to do.
  • User processes: These are the running programs that the kernel manages. User processes are what collectively makeup user space. The kernel allows processes and servers to communicate with each other.

Init and rootfs – init is the first non-Kernel task to be run, and has PID 1. It initializes everything needed to use the system. In production embedded systems, it also starts the main application. In such systems, it is either BusyBox or a custom-crafted application.

View original post here

Read more…

7811924256?profile=RESIZE_400x

 

CLICK HERE TO DOWNLOAD

This complete guide is a 212-page eBook and is a must read for business leaders, product managers and engineers who want to implement, scale and optimize their business with IoT communications.

Whether you want to attempt initial entry into the IoT-sphere, or expand existing deployments, this book can help with your goals, providing deep understanding into all aspects of IoT.

CLICK HERE TO DOWNLOAD

Read more…

Edge Products Are Now Managed At The Cloud

Now more than ever, there are billions of edge products in the world. But without proper cloud computing, making the most of electronic devices that run on Linux or any other OS would not be possible.

And so, a question most people keep asking is which is the best Software-as-a-service platform that can effectively manage edge devices through cloud computing. Well, while edge device management may not be something, the fact that cloud computing space is not fully exploited means there is a lot to do in the cloud space.

Product remote management is especially necessary for the 21st century and beyond. Because of the increasing number of devices connected to the internet of things (IoT), a reliable SaaS platform should, therefore, help with maintaining software glitches from anywhere in the world. From smart homes, stereo speakers, cars, to personal computers, any product that is connected to the internet needs real-time protection from hacking threats such as unlawful access to business or personal data.

Data being the most vital asset is constantly at risk, especially if individuals using edge products do not connect to trusted, reliable, and secure edge device management platforms.

Bridges the Gap Between Complicated Software And End Users

Cloud computing is the new frontier through which SaaS platforms help manage edge devices in real-time. But something even more noteworthy is the increasing number of complicated software that now run edge devices at homes and in workplaces.

Edge device management, therefore, ensures everything runs smoothly. From fixing bugs, running debugging commands to real-time software patch deployment, cloud management of edge products bridges a gap between end-users and complicated software that is becoming the norm these days.

Even more importantly, going beyond physical firewall barriers is a major necessity in remote management of edge devices. A reliable Software-as-a-Service, therefore, ensures data encryption for edge devices is not only hackproof by also accessed by the right people. Moreover, deployment of secure routers and access tools are especially critical in cloud computing when managing edge devices. And so, developers behind successful SaaS platforms do conduct regular security checks over the cloud, design and implement solutions for edge products.

Reliable IT Infrastructure Is Necessary

Software-as-a-service platforms that manage edge devices focus on having a reliable IT infrastructure and centralized systems through which they can conduct cloud computing. It is all about remotely managing edge devices with the help of an IT infrastructure that eliminates challenges such as connectivity latency.

Originally posted here

Read more…

Introducing Profiler, by Auptimizer: Select the best AI model for your target device — no deployment required.

Profiler is a simulator for profiling the performance of Machine Learning (ML) model scripts. Profiler can be used during both the training and inference stages of the development pipeline. It is particularly useful for evaluating script performance and resource requirements for models and scripts being deployed to edge devices. Profiler is part of Auptimizer. You can get Profiler from the Auptimizer GitHub page or via pip install auptimizer.

The cost of training machine learning models in the cloud has dropped dramatically over the past few years. While this drop has pushed model development to the cloud, there are still important reasons for training, adapting, and deploying models to devices. Performance and security are the big two but cost-savings is also an important consideration as the cost of transferring and storing data, and building models for millions of devices tends to add up. Unsurprisingly, machine learning for edge devices or Edge AI as it is more commonly known continues to become mainstream even as cloud compute becomes cheaper.

Developing models for the edge opens up interesting problems for practitioners.

  1. Model selection now involves taking into consideration the resource requirements of these models.
  2. The training-testing cycle becomes longer due to having a device in the loop because the model now needs to be deployed on the device to test its performance. This problem is only magnified when there are multiple target devices.

Currently, there are three ways to shorten the model selection/deployment cycle:

  • The use of device-specific simulators that run on the development machine and preclude the need for deployment to the device. Caveat: Simulators are usually not generalizable across devices.
  • The use of profilers that are native to the target device. Caveat: They need the model to be deployed to the target device for measurement.
  • The use of measures like FLOPS or Multiply-Add (MAC) operations to give approximate measures of resource usage. Caveat: The model itself is only one (sometimes insignificant) part of the entire pipeline (which also includes data loading, augmentation, feature engineering, etc.)

In practice, if you want to pick a model that will run efficiently on your target devices but do not have access to a dedicated simulator, you have to test each model by deploying on all of the target devices.

Profiler helps alleviate these issues. Profiler allows you to simulate, on your development machine, how your training or inference script will perform on a target device. With Profiler, you can understand CPU- and memory-usage as well as run-time for your model script on the target device.

How Profiler works

Profiler encapsulates the model script, its requirements, and corresponding data into a Docker container. It uses user-inputs on compute-, memory-, and framework-constraints to build a corresponding Docker image so the script can run independently and without external dependencies. This image can then easily be scaled and ported to ease future development and deployment. As the model script is executed within the container, Profiler tracks and records various resource utilization statistics including Average CPU UtilizationMemory UsageNetwork I/O, and Block I/O. The logger also supports setting the Sample Time to control how frequently Profiler samples utilization statistics from the Docker container.

Get Profiler: Click here

How Profiler helps

Our results show that Profiler can help users build a good estimate of model runtime and memory usage for many popular image/video recognition models. We conducted over 300 experiments across a variety of models (InceptionV3, SqueezeNet, Resnet18, MobileNetV2–0.25x, -0.5x, -0.75x, -1.0x, 3D-SqueezeNet, 3D-ShuffleNetV2–0.25x, -0.5x, -1.0x, -1.5x, -2.0x, 3D-MobileNetV2–0.25x, -0.5x, -0.75x, -1.0x, -2.0x) on three different devices — LG G6 and Samsung S8 phones, and NVIDIA Jetson Nano. You can find the full set of experimental results and more information on how to conduct similar experiments on your devices here.

The addition of Profiler brings Auptimizer closer to the vision of a tool that helps machine learning scientists and engineers build models for edge devices. The hyperparameter optimization (HPO) capabilities of Auptimizer help speed up model discovery. Profiler helps with choosing the right model for deployment. It is particularly useful in the following two scenarios:

  1. Deciding between models — The ranking of the run-times and memory usages of the model scripts measured using Profiler on the development machine is indicative of their ranking on the target device. For instance, if Model1 is faster than Model2 when measured using Profiler on the development machine, Model1 will be faster than Model2 on the device. This ranking is valid only when the CPU’s are running at full utilization.
  2. Predicting model script performance on the device — A simple linear relationship relates the run-times and memory usage measured using Profiler on the development machine with the usage measured using a native profiling tool on the target device. In other words, if a model runs in time x when measured using Profiler, it will run approximately in time (a*x+b) on the target device (where a and b can be discovered by profiling a few models on the device with a native profiling tool). The strength of this relationship depends on the architectural similarity between the models but, in general, the models designed for the same task are architecturally similar as they are composed of the same set of layers. This makes Profiler a useful tool for selecting the best suited model.

Looking forward

Profiler continues to evolve. So far, we have tested its efficacy on select mobile- and edge-platforms for running popular image and video recognition models for inference, but there is much more to explore. Profiler might have limitations for certain models or devices and can potentially result in inconsistencies between Profiler outputs and on-device measurements. Our experiment page provides more information on how to best set up your experiment using Profiler and how to interpret potential inconsistencies in results. The exact use case varies from user to user but we believe that Profiler is relevant to anyone deploying models on devices. We hope that Profiler’s estimation capability can enable leaner and faster model development for resource-constrained devices. We’d love to hear (via github) if you use Profiler during deployment.

Originaly posted here


Authors: Samarth Tripathi, Junyao Guo, Vera Serdiukova, Unmesh Kurup, and Mohak Shah — Advanced AI, LG Electronics USA

Read more…

Industrial IoT Revolution

Why the Nvidia Jetson Nano is responsible for the biggest industrial IoT revolution these days

 
c1f0a2_ecaa338269684f82b2661b550075f528~mv2.webp
 
 

It feels like yesterday when the Raspberry Pi foundation released the first-in-line Single Board Computer (SBC) to the market. Back in 2012, Raspberry Pi wasn't alone in the SBC growing market, however, it was the first to make a community-based product that brings the hardware and the software eco-system to a beautiful harmony on the internet. Before those days, embedded Linux based SBC's and SOM's were a place for Linux kernel and embedded hardware experts, no easy-to-use tools, ready Linux based distros, or most importantly without the enormous amount of questions and answers across the internet on anything related.

Today, 8 years later, the "2012 revolution" happens again

This time, it took a year to understand the impact of the new 'kid' in the market, but now, there are a few indications that defiantly build the route to a revolution.

The Raspberry Pi was the first to make embedded Linux easy while keeping the advantages of reliability and flexibility in terms of fitting to different kinds of industries applications. It's almost impossible to ignore the variety of industries where Raspberry Pi is in its hurt of products to save time-to-market and costs. The power of this magical board leans on the software side: The Raspberry Pi foundation and their community, worked hard across the years to improve and share their knowledge, but, at the same time, without notice or targeting, they brought the Pi development to an extremely "serverless" level.

The Nvidia Jetson Nano

Let's stop talking about the Raspberry Pi and focus on today's industry needs to understand better why the new kid in the town is here to change the market of IoT and smart products forever.

 
c1f0a2_2ca55bc3cd744a10a05bc244c4e092c1~mv2.webp
 
 Why do we need to thanks Nvidia and the Jetson Nano?
 

The market is going forward. AI, Robotics, amazing-looking screen app Gui's, image processing, and long data calculations are all become the new standard of smart edge products.

If a few years ago, you would only want to connect your product to the cloud and receive anything valuable, today, product managers and developers compete in a much tougher industry era. This time, the Raspberry Pi can't be the technology hero again, its resources are limited and the eco-system starts to squint to a better-fit solution.

 
c1f0a2_b46f958fa9b543af88a6ad38b2afce82~mv2.webp
 
 

NVIDIA Jetson devices in Upswift.io device management platform

The Jetson Nano is the first SBC to understood the necessary combination that will drive new products to use it. It's the first SBC designed in the mind of industrial powerful use cases, while not forgetting the prototyping stage and the harmony that gave the Raspberry Pi their success. It's the first solution to bring the whole package for developers and for hardware engineers with a "SaaS" feel: The OS is already perfect thanks to Ubuntu, there is plenty of software instructions by Nvidia and open-source ready-to-use tools custom made for the Jetson family, and for the hardware engineers: they are free to go with the System On Module (SOM) that is connected to a carrier board which includes all the necessary outputs and inputs to make the development stage even faster.

The Jetson Nano combination is basically providing the first world infrastructure for producing a "2020" product with complex software while working in a minimal budget and time-to-market. The Jetson Nano enables developers and product managers to imagine further without compromises, bringing tough software missions to the edge easily.

Originally posted here

Read more…

by Dan Carroll, Carnegie Mellon University, Department of Civil and Environmental Engineering

7451650263?profile=RESIZE_400x
Credit: Pixabay/CC0 Public Domain
 
Across the U.S., there has been some criticism of the cost and efficacy of emissions inspection and maintenance (I/M) programs administered at the state and county level. In response, Engineering and Public Policy (EPP) Ph.D. student Prithvi Acharya and his advisor, Civil and Environmental Engineering's Scott Matthews, teamed up with EPP's Paul Fischbeck. They have created a new method for identifying over-emitting vehicles using remote data transmission and machine learning that would be both less expensive and more effective than current I/M programs.
 

Most states in America require passenger vehicles to undergo periodic emissions inspections to preserve air quality by ensuring that a vehicle's exhaust emissions do not exceed standards set at the time the vehicle was manufactured. What some may not know is that the metrics through which emissions are gauged nowadays are usually measured by the car itself through on-board diagnostics (OBD) systems that process all of the vehicle's data. Effectively, these emissions tests are checking whether a vehicle's "check engine light" is on. While over-emitting identified by this system is 87 percent likely to be true, it also has a 50 percent false pass rate of over-emitters when compared to tailpipe testing of actual emissions.

With cars as smart devices increasingly becoming integrated into the Internet of Things (IoT), there's no longer any reason for state and county administrations to force drivers to come in for regular I/M checkups when all the necessary data is stored on their vehicle's OBD. In an attempt to eliminate these unnecessary costs and improve the effectiveness of I/M programs, Acharya, Matthews, and Fischbeck published their recent study in IEEE Transactions on Intelligent Transportation Systems.

Their new method entails sending data directly from the vehicle to a cloud server managed by the state or county within which the driver lives, eliminating the need for them to come in for regular inspections. Instead, the data would be run through machine learning algorithms that identify trends in the data and codes prevalent among over-emitting vehicles. This means that most drivers would never need to report to an inspection site unless their vehicle's data indicates that it's likely over-emitting, at which point they could be contacted to come in for further inspection and maintenance.

Not only has the team's work shown that a significant amount of time and cost could be saved through smarter emissions inspecting programs, but their study has also shown how these methods are more effective. Their model for identifying vehicles likely to be over-emitting was 24 percent more accurate than current OBD systems. This makes it cheaper, less demanding, and more efficient at reducing vehicle emissions.

This study could have major implications for leaders and residents within the 31 states and countless counties across the U.S. where I/M programs are currently in place. As these initiatives face criticism from proponents of both environmental deregulation and fiscal austerity, this team has presented a novel system that promises both significant reductions to cost and demonstrably improved effectiveness in reducing vehicle emissions. Their study may well redefine the testing paradigm for how vehicle emissions are regulated and reduced in America.

 
Originally posted here on Tech Xplore
 
Read more…

Upcoming IoT Events

More IoT News

Arcadia makes supporting clean energy easier

Nowadays, it’s easier than ever to power your home with clean energy, and yet, many Americans don’t know how to make the switch. Luckily, you don’t have to install expensive solar panels or switch utility companies…

Continue

Answering your Huawei ban questions

A lot has happened since we uploaded our most recent video about the Huawei ban last month. Another reprieve has been issued, licenses have been granted and the FCC has officially barred Huawei equipment from U.S. networks. Our viewers had some… Continue

IoT Career Opportunities