Atrocity Detection in the Ukraine

How accurately? Always suspicious of social media accounts. 

Researchers Create System to Quickly Identify Ukraine Atrocities Using Social Media

University of Manchester (U.K.), Joe Stafford, April 11, 2022

A system developed by British and American scientists rapidly identifies atrocities occurring in Ukraine based on social media accounts. The U.K.'s Ukrainian-focused MOBILISE project partnered with the University of Maryland, Duke University, and the University of North Carolina to document and trace displacements, human rights abuses, humanitarian needs, and civil resistance in real time through the Data for Ukraine project, which analyzes Twitter data via machine learning algorithms. The system can flag developments several hours ahead of media outlets by demonstrating spikes of credible tweets about certain monitored topics, then mapping where these events transpired. Olga Onuch at the U.K.'s University of Manchester identified which accounts to track and generated over 600 keywords to check.

Novel Inventory Tagging System using Molecular Bits

 Interesting use of molecular tagging.   Could this be used beyond retail inventory? What is the speed and accuracy of reading the tags?  Note use of machine learning integration.

Porcupine Molecular Tagging Scheme Offers Sharp Contrast to Conventional Inventory Control Systems

University of Washington Paul G. Allen School of Computer Science & Engineering Allen School News

An end-to-end molecular tagging system created by researchers at the University of Washington (UW) and Microsoft can be programmed and read within seconds using a portable nanopore device. The Porcupine system can substitute dehydrated strands of synthetic DNA called molbits (molecular bits) for bulky plastic or printed barcodes, eliminating the need for specialized laboratories and equipment. Porcupine enables the binary 0s and 1s of a digital tag to signal the presence or absence of each of 96 molbits; users read a tag's data by rehydrating and running it through Oxford Nanopore Technologies' MinION device. UW's Luis Seze said, “Porcupine is one more exciting example of a hybrid molecular-electronic system, combining molecular engineering, new sensing technology, and machine learning to enable new applications.”

Update on RFID Tags

Related updates for specific RFID applications.    See also continuous updates on this technology.

Vizenex RFID, manufacturing RFID Tags:

Vizinex RFID, which manufactures RFID tags for specific applications, has launched its Sentry Midrange II, the second generation of the company's tag for tracking large metal assets. With a read range of 25 feet when mounted on metal, the Sentry Midrange II allows for the tagging of a variety of assets, the company reports, including reusable containers, oil-field assets and construction equipment.

The Sentry Midrange II is 30 percent smaller than its predecessor, according to the company, but provides a broader frequency response. The tag's optional cover provides extra protection for the RF device and the flexibility to use bolts, rivets or zip-ties for attachment. Industries that use this type of RFID tag include government, military, manufacturing, waste management, rental equipment, and oil and gas. Applications include special transport items, reusable containers, logistics and yard management, and tool and die tracking.  ... "

China Gives Citizens a Danger Code

Via ACM.   Is this a 'troubling precedent', or a reasonable approach for imminent danger?

In Coronavirus Fight, China Gives Citizens a Color Code, with Red Flags
The New York Times
Paul Mozur; Raymond Zhong; Aaron Krolik
March 1, 2020

To manage the coronavirus epidemic, China is requiring citizens to use software on their smartphones to determine whether they should be quarantined or allowed into public spaces—but an analysis in The New York Times found that the underlying code seems to share information with the police. Citizens sign up via the Alipay digital wallet app, then receive a color code denoting their health status. An accompanying quick-response code allows or disallows users to travel freely, according to the color code. Once a user grants the software access to personal data, a program component transmits their location, city name, and an identifying code number to a server. The developers of the Alipay Health Code said the software uses big data to rate an individual's contagion risk, while critics warn the system establishes a troubling precedent for automated social control through mass surveillance. ... " 

AI Birdwatching

Seeing and  imaging continue to be the place where AI/Machine learning make the most progress. Here another tagging example.   Currently working on a horticultural example with plants.

This AI birdwatcher lets you 'see' through the eyes of a machine
by Robin A. Smith, Duke University

It can take years of birdwatching experience to tell one species from the next. But using an artificial intelligence technique called deep learning, Duke University researchers have trained a computer to identify up to 200 species of birds from just a photo.

The real innovation, however, is that the A.I. tool also shows its thinking, in a way that even someone who doesn't know a penguin from a puffin can understand.

The team trained their deep neural network—algorithms based on the way the brain works—by feeding it 11,788 photos of 200 bird species to learn from, ranging from swimming ducks to hovering hummingbirds.

The researchers never told the network "this is a beak" or "these are wing feathers." Given a photo of a mystery bird, the network is able to pick out important patterns in the image and hazard a guess by comparing those patterns to typical species traits it has seen before.

Along the way it spits out a series of heat maps that essentially say: "This isn't just any warbler. It's a hooded warbler, and here are the features—like its masked head and yellow belly—that give it away."

Duke computer science Ph.D. student Chaofan Chen and undergraduate Oscar Li led the research, along with other team members of the Prediction Analysis Lab directed by Duke professor Cynthia Rudin.

They found their neural network is able to identify the correct species up to 84% of the time—on par with some of its best-performing counterparts, which don't reveal how they are able to tell, say, one sparrow from the next.

Rudin says their project is about more than naming birds. It's about visualizing what deep neural networks are really seeing when they look at an image.  .... " 

RFID Paper Embeds several Types of Tags

Interesting, flexible application of RFID embedded paper.

In RFID Journal

RFID Paper Turns the Page on Label and Card Printing
ISBC's new standard paper, with embedded NFC, HF or UHF tags, can be designed, ordered and printed according to customer demand, so that the tags can be cut directly from the paper as needed, and at a low cost.
By Claire Swedberg

Jul 09, 2019—Russian RFID technology company ISBC Group has released a solution known as RFID Paper, which is intended to enable companies to inexpensively print customized RFID labels in-house and on demand, as an alternative to label-conversion machines or third-party service bureaus and the long rolls of tags typically purchased from such businesses. Since its release earlier this year, ISBC's HF- or UHF-enabled paper has been used predominantly to print RFID-based cards and badges. RFID Paper can be printed via HP Indigo printers to produce several rows of ready-to-use RFID tags. .... " 

Google Lens Can Detect a Billion Objects

I noted that the IOS version of Google Lens has been updated to a more stable condition..  Impressive capabilities.  Been experimenting with it to construct reference images for machine learning experiments.   Images will be captured from sources like broadcasts and other advertising resources. 

The claim is that Google Lens 'can now detect over 1 Billion objects': Quote and more from Techspot.

New Kinds of Brain Maps

Unique tagging and looking for patterns to determine interaction among the brain cells. Other ways to use this method?

New Brain Maps With Unmatched Detail May Change Neuroscience
in Quanta Magazine by Monique Brouillette 

A technique based on genetic bar codes can easily map the connections of individual brain cells in unprecedented numbers. Unexpected complexity in the visual system is only the first secret it has revealed....."

Tags in this Blog

This blog contains tags at the end of each post which lead to related posts.   I do go back selectively and update these tags, especially as they relate to my current research, interests or work. The tags can't be complete,  in some cases the tag topic may not exist until much later.     For example a company that is later formed to address some new technology.  This blog is for my own and client reference,  but if you have any suggestions pass then along in a comment or email.  I am on Linkedin and will respond there too.   - FAD

Google Improves, Automates Pet Tagging

We were involved in work that sought to autotag pictures of people and pets in still images and video.  So this is quite a step forward.  Not too long ago this was not achievable.   Some details at the link below. 

Meow it’s even easier to find your furry friends in Google Photos
By Lily Kharevych,  Software Engineer, Google Photos

If you have a bunch of photos of your furry friends, you now have the oppawtunity to see them all in one place in Google Photos.

When you want to look back on old photos of Oliver as a puppy or Mr. Whiskers as a kitten, you no longer need to type “dog” or “cat” into search in Google Photos. Rolling out in most countries today, you’ll be able to see photos of the cats and dogs now grouped alongside people, and you can label them by name, search to quickly find photos of them, or even better, photos of you and them. This makes it even easier to create albums, movies, or even a photo book of your pet.   .... " 

Extracting Tagging Data from Imagery

An example of how advanced deep learning methods can be used to extract information from image data.   The image data is already captured and stored.  And its dynamic.   Could also be used with other imagery, like from store shelf images.   Note the common existence of noise in such recordings.  Also the integrated normalization included in the tagging.  Thinking other possibilities.  

Enhancing Google Maps with Deep Learning and Street View  by Srini Penchikala
" ... The deep learning model also automatically labels new Street View imagery, normalizes the text to be consistent with the naming conventions and ignores extraneous text that's not relevant for the data analytics. This allows the team to create new addresses directly from images without even knowing the name of the street or the location of the addresses. For example, when a Street View car drives on a newly built road, the model can analyze the captured images, extract the street names and numbers, and properly create and locate the new addresses automatically on Google Maps. .... " 

Tracking Ships, Containers with Blockchain

Another example of the used of blockchain as a database, a secure open distributed ledger.

The blockchain heads out to sea as IBM and Maersk develop ship tracking platform By Duncan Riley   In SiliconAngle:

The blockchain is heading out to sea with IBM Corp. and shipping operator A.P. Moller–Maersk Group (most commonly known as Maersk) teaming up to track shipping transactions using the technology that powers bitcoin.

The tracking system is being built on top of The Linux Foundation’s Hyperledger platform and will link shippers, freight forwarders, ocean carriers, ports and customs authorities with a goal to track 10 million shipping containers by the end of this year, some 14 percent of the 70 million containers shipped globally each year.

IBM estimates that the digitization of the supply chain process from end to end could save shipping carriers a whopping $38b billion a year.  .... " 

Blink Security and Amazon Echo

Have thought about how you could compare snippets of a video to infer security status.  Digital Video Analysis.   Blink appears to be doing this.  Though Google has the tagging smarts to be put in Home.  Now to be connected to Alexa.

Blink security system integrates with Amazon Alexa by  Chris Burns
Asking Alexa about the security of one’s home can bring on system status as well as both the time and location of the system’s last recorded motion clip. This can be especially helpful for the times when we’ve lost the cat inside the house and the cat will only come out to visit when we’ve gone away for the day.

Asking Alexa where the cat is might not work quite yet, but asking Alexa to consult Blink to tell us the last time the cat was spotted could very well be a situation we’re in in the near future.

According to the CEO of Blink, Peter Besen, “We live in a world where convenience is king and simplicity wins.”

“link’s seamless setup and easy-to-use interface provided a catalyst for our product’s explosive growth and the addition of voice control through the Amazon Alexa platform marks the next, bold step in Blink’s progression as an industry-leading home security and monitoring system. Whether it is a parent with a handful of kids to keep track of, or someone coming home with two arms full of groceries, it is vital that our consumers receive a hassle-free home security experience.”

Blink systems are available starting at $99 USD – that including one single camera. Two-camera systems are $169, while three and five camera systems are also available. Users that purchase a set of cameras and need just one more, (at the time at which they’re purchasing the first set), will be able to purchase additional cameras for $75 apiece.  ... " 

Blackberry Radar for Goods Security

Worked on related ideas for the supply chain enterprise a decade ago that used tagging and communicating capabilities to track trucks.  There are suppliers that do this already.  Huge amounts of money and security involved. A fundamental part of the IOT. Tracking things.  To me an unexpected participant in this space:

In the Blackberry Blog: " .... Efficiency and loss-prevention are keys to profitability for trucking companies, which are gaining a new way to boost productivity with the introduction of BlackBerry Radar today at the Mid-America Trucking Show. BlackBerry Radar is an end-to-end, Internet of Things (IoT)-based system that monitors the location of trailers and containers and delivers timely, actionable data to transportation managers via a secure, online portal. The portal is accessible from practically any location on any smartphone, tablet or computer. The system optimizes usage of trailers and shipping containers, improves on-time delivery and lets operators generate more revenue per trailer. .... " 

Fintech Evolves, and this Blog Does too.

I just noticed that the term Fintech had never been used in this blog before this year.  So is it that a new term?  I have just updated the text tags for Fintech to point to related articles.   Which points to another way to explore this blog.  You can search for words or phrases in quotes, at the upper left of the blog.  Or you can search by tag at the bottom of each post.  Most posts have been tagged.

I frequently update tags. Such as the newly discovered Fintech. without indicating the update.   If I update the body of a blog I will usually indicate the update with an edit.  Links may go out of date, and I will update them when discovered.

Meanwhile I see that Fintech has been used since at least the 90's, at first as the name of a group, and continues to evolve.

Google Cloud Vision for Image Tagging

Spent quite a bit of time looking at at the problem of recognizing and tagging images for marketing applications.  It turned out to be a  key requirement for systems that deal with asset and engagement management.  So this announcement of advanced image tagging beta capability was fascinating.  A Beta for developers.  If I embed this in a system I have to rely on Google continuing to improve and support it. Looking forward to a deeper examination.

 In CWorld. 
" ... In addition to making the service publicly available, Google also revealed the pricing. Developers will be able to run up to 1,000 images through Google services for free, and then pay a flat fee for each group of 1,000 images they upload after that. Developers will get discounts for sending large volumes of pictures through the service. 

However, users will be able to send a maximum of 20 million images a month through Google Cloud Vision during the open beta period, so companies with large-scale production workloads will likely want to reserve its use for low-volume applications.  ... " 

If Everything had a Chip?

In the early days of working with the MIT lab on the 'Penny Tag' project, a thought experiment often posed was:  What if everything manufactured were tagged, or more radically,  intelligently chipped?   What could be done with that idea using modern analytics?   Marc Andreessen says it is coming.

Tagging Images

In NYTimes:  Worked with a startup that sought to do this automatically.  Good to see the continuation of related work.

" ... A little-known German start-up may have just made it a lot easier to search for photos online.

EyeEm, a photo-sharing service started in 2011 that has drawn parallels to Instagram, announced new technology in Brooklyn on Friday that uses a sophisticated algorithm and machine learning to analyze the details of online photos.

The technology, called EyeVision, automatically scans images and tags them with certain keywords, from “landscape” and “New York” to the perceived emotions of people in each photo, which makes them easier to find through web searches. ..... "\

Target Item Level RFID Tags on Fast Track

In Retailwire:  Experimented with the idea as early as 2000.  Note to be used in some categories only. As we did in areas like Shaving.   But those experiments could spread.  To what degree will this replace the barcode, which were also closely involved with.   Also to address shelf level out of stock issues.

Target puts RFID rollout on the fast track 
Target plans to complete one of the largest rollouts of item-level radio frequency identification (RFID) technology in retailing by next year. What will implementation of item-level RFID tracking in categories such as clothing and home decor mean for Target's ability to reduce out-of-stocks in stores?   ... " 

Tagging Forward

This blog started in 2003, replacing an older internal blog. Starting last year I started to tag items in this blog.  All new items are now tagged.  I have also been able to back tag old items using a search script.   Several thousand posts have now been tagged.  I also started to add a number of new, more descriptive tags on areas of current interest.  When I do research on my own work I have found this to be very useful, rediscovering work I have done before.  Give it a try on some of the popular tags below. You can still search for words or phrases in the blog with the search box on the home page, at the upper left.  Substantive comments on process welcome.