Paper-Like, Battery-Free, AI-Enabled Sensor for Holistic Wound Monitoring

 Paper-Like, Battery-Free, AI-Enabled Sensor for Holistic Wound Monitoring

ACM TECHNEWS

By National University of Singapore, June 29, 2023

The sensor patch, resembling a five-petaled Pinwheel Flower (Tabernaemontana divaricata), and the sensing materials/principles for each colorimetric sensor.

Credit: Xin Ting Zheng et al

A battery-free holistic wound monitoring sensor patch developed by researchers at the National University of Singapore (NUS) and the Agency for Science, Technology and Research's Institute of Materials Research and Engineering uses artificial intelligence (AI) to identify the wearer's wounding healing status within 15 minutes.

The PETAL (Paper-like Battery-free In situ AI-enabled Multiplexed) sensor patch features five colorimetric sensors that measure the wound's temperature, pH, trimethylamine, uric acid, and moisture.

A mobile phone is used to capture the sensor images, which are then analyzed by an AI algorithm.

NUS's Benjamin Tee said, "Our AI algorithm is capable of rapidly processing data from a digital image of the sensor patch for very accurate classification of healing status. This can be done without removing the sensor from the wound. In this way, doctors and patients can monitor wounds more regularly with little interruption to wound healing."

From National University of Singapore

View Full Article   

Light-Field Sensor for 3D Scene Construction with Unprecedented Angular Resolution

Light-Field Sensor for 3D Scene Construction with Unprecedented Angular Resolution

By NUS News (Singapore),   May 18, 2023

A large scale angle-sensing structure comprising nanocrystal phospors, a key component of the sensor, illuminated under ultraviolet light.

At the core of the novel light-field sensor are inorganic perovskite nanocrystals—compounds that have excellent optoelectronic properties.

National University of Singapore scientists created a three-dimensional (3D) light-field sensor that can reconstruct scenes with ultra-high angular resolution using a novel angle-to-color conversion framework.

The device features an angular measurement range exceeding 80 degrees, high angular resolution which can potentially be less than 0.015 degrees for smaller sensors, and a 0.002-nanometer-to-550-nanometer spectral response range.

Inorganic perovskite nanocrystals form the heart of the sensor, which can detect 3D light fields across the X-ray to visible light spectrum due to the crystals' controllable nanostructures.

The researchers patterned the crystals onto a transparent thin-film substrate mated to a color charge-coupled device, which transforms incoming optical signals into color-coded output for use in 3D image reconstruction.

Proof-of-concept experiments showed the sensor could accurately reconstruct images of objects 1.5 meters (4.9 feet) away.

From NUS News (Singapore)

View Full Article  

Singapore, Germany to Mutually Recognize IoT Cybersecurity Labels

IOT security direction particularly important.     Why 

Singapore, Germany to Mutually Recognize IoT Cybersecurity Labels

By ZDNet,  October 27, 2022

Singapore and Germany have agreed to mutually recognize their respective smart computer product cybersecurity rating labels, with Germany the second European company to do so after Finland.

The pact stipulates that products issued with Germany's Federal Office for Information Security (BSI) label would be designated as satisfying Level 2 of the Cyber Security Agency of Singapore (CSA)'s cybersecurity labeling system.

CSA's system rates smart devices into four asterisk-demarcated levels, with each asterisk indicating an additional tier of completed testing and assessment; products rated Levels 2 through 4 must meet "enhanced" cybersecurity mandates, including device and data requirements.

The mutual CSA-BSI recognition would apply to consumer Internet of Things devices like smart TVs, smart toys, health trackers, smart lighting, and smart thermostats.

CSA said it would add more product categories under the bilateral agreement in cooperation with BSI.

The mutual recognition will apply to consumer Internet of Things devices including smart televisions, smart toys, health trackers, smart lighting, and smart thermostats.

Full article:   

This Robot Catches Grandma Before She Falls

I doubt it, but its a good direction.

 Robot Catches Grandma Before She Falls

The Washington Post

Pranshu Verma, September 10, 2022

A mobile robot balance assistant developed by scientists at Singapore's Nanyang Technological University (NTU) can anticipate and catch seniors before they fall. The robot, called Mr. Bah, is equipped with guardrails that come up to hip level, as well as sensors to assess when a person may begin to lose their balance. Wei Teh Ang of the Rehabilitation Research Institute of Singapore said the robot was designed "to help people walk around at home without the fear of falling down." Ang and colleagues at NTU and Singapore's Tan Tock Seng Hospital tested Mr. Bah on patients who had suffered strokes, brain trauma, or spinal cord injuries; during the tests, the researchers said, no falls were recorded.

Full article 

Singapore's Robot Workforce Plugs Labor Gaps

Singapore's Robot Workforce Plugs Labor Gaps

Reuters, Travis Teo, May 31, 2022

Businesses in Singapore increasingly are resorting to robots to help address labor shortages and perform a range of jobs. Singaporean construction firm Gammon uses Boston Dynamics' four-legged "Spot" robot to scan mud and gravel to check on progress at construction sites. Meanwhile, Singapore's National Library Board has deployed at a public library two shelf-reading robots that can scan labels on 100,000 books, or about 30% of its collection, daily. The International Federation of Robotics estimated last year that Singapore has 605 robots installed per 10,000 employees in the manufacturing sector, just behind the 932 per 10,000 workers installed by top placeholder South Korea. Moreover, more than 30 metro stations in Singapore are set to have barista robots from Crown Digital preparing coffee for commuters. ... ' 

Hint at Dystopian Futures

Expected direction?

‘Dystopian world’: Singapore patrol robots stoke fears of surveillance state

Trial of robots to police ‘undesirable’ behaviour such as smoking or breaching social-distancing rules   in The Guardian

Singapore has trialled patrol robots that blast warnings at people engaging in “undesirable social behaviour”, adding to an arsenal of surveillance technology in the tightly controlled city-state that is fuelling privacy concerns.

From vast numbers of CCTV cameras to trials of lampposts kitted out with facial recognition tech, Singapore is seeing an explosion of tools to track its inhabitants.

That includes a three-week trial in September, in which two robots were deployed to patrol a housing estate and a shopping centre. Officials have long pushed a vision of a hyper-efficient, tech-driven “smart nation”, but activists say privacy is being sacrificed and people have little control over what happens to their data.

Singapore is frequently criticised for curbing civil liberties and people are accustomed to tight controls, but there is still growing unease at intrusive tech. The government’s latest surveillance devices are robots on wheels, with seven cameras, that issue warnings to the public and detect “undesirable social behaviour”. .....' 

P&G Launches iLab 2021

Procter continues to work innovation:

PR NEWSWIRE: P&G launches iLab 2021 in partnership with the Singapore EDB to strengthen Singapore's innovation ecosystem

P&G launches iLab 2021 in partnership with the Singapore EDB to strengthen Singapore's innovation ecosystem

SINGAPORE, May 4, 2021 /PRNewswire/ -- Procter & Gamble (NYSE:PG), in partnership with the Singapore Economic Development Board (EDB), today launched iLab 2021, a 3-day virtual innovation festival. The festival will see start-ups from Singapore and across the region come together to collaborate with P&G and develop innovations that can overcome real-world challenges faced in the areas of advertising, retail, and supply chain. Held at P&G's i-Singapore Digital Omni-Channel Center (i-SiDOC)  ,... " 

More Singapore Law Boosting Sensors

Its inevitable that policing will be advanced by cameras, sensors, automation.

Singapore Eyes More Cameras, Technology to Boost Law Enforcement  By ZDNet

Singapore intends to utilize more cameras and technology to support law enforcement and first responders, by harnessing sensors, video analytics, artificial intelligence (AI), automation, and drones.

Singaporean police already have deployed nearly 90,000 cameras in public spaces, and Minister for Home Affairs and Law K. Shanmugam said neighbor police centers and police posts have been repurposed with automated self-help kiosks, so citizens could access police services round the clock.

Efforts also are underway to build smart fire stations that use sensors and automation to enable operational response, decision-making, and manpower management.

An AI-driven system would transmit data in emergencies to officers before their arrival at the location.

Shanmugam also cited the use of drones and robots to effect security at Covid-19 isolation facilities, to reduce exposure risk for frontline officers. ... " 

Soft Robot Swims in the Mariana Trench

An example of extreme exploration, using a soft biomimicking design.  Considerable possibilities here.

Soft robot swims in the Mariana Trench  in Techexplore by Bob Yirka 

A team of researchers affiliated with multiple institutions in China has developed a soft robot that can successfully swim in the Mariana Trench. In their paper published in the journal Nature,, the group describes their soft robot and its capabilities. Cecilia Laschi and Marcello Calisti with the National University of Singapore and the University of Lincoln, respectively, have published a News & Views piece in the same journal issue outlining the work by the team in China. ... " 

Making Smart Plugs Smarter

Considering a broader view of 'smart', more like cooperative towards goals.

Engineers make smart plugs smarter  by National University of Singapore

Singapore is in the midst of its Smart Nation transformation, and researchers from the National University of Singapore (NUS) have a new invention that could take it a big step forward.

It is a network of smart electrical sockets controlled by a central computer, optimizing energy use throughout a building or even across buildings. The team that created this was led by Associate Professor Sanjib Kumar Panda from the NUS Department of Electrical and Computer Engineering.

So far, most people have used smart appliances in a very piecemeal way. For example, an appliance, such as a television or an air conditioner, is connected to the Internet, and then controlled remotely from a mobile app. However, this approach is actually inefficient, so the NUS team set out to improve it.

"The current trend is to put a computing unit in every new appliance, which generates a lot of e-waste and drives up costs, so we are avoiding that," said Dr. Krishnanand Kaippilly Radhakrishnan, who worked with Panda to develop the technology.  ... " 

Smart Electrical Outlet/Socket (SEOS) system

The NUS researchers' Smart Electrical Outlet/Socket (SEOS) system monitors and controls every socket in a building in real-time.

Each socket has a chip that communicates with the central server over WiFi. When an appliance is connected, the socket recognizes it through an electronic sticker on the plug, known in the industry as Near Field Communication. This is a concept similar to tapping a person's staff pass to enter the office. The electrical specifications of the appliance are then called up from a database.

Operators of a SEOS-enabled network can track and quantify how much energy various devices consume—including calculating energy costs—and then configure the system to deliver power only when needed.

The SEOS system can be programmed to completely switch off appliances when not in use, rather than waste electricity by leaving them on idle or standby. Appliances left on when not in use make up 25 percent to 50 percent of a building's electricity consumption. ... " 

Singapore Using Facial Recognition Broadly

  Note the focused use, and the automatic disposal of the data after 30 days.   Is this sufficient to sufficiently suppress misuse?   Once again,  it is inevitable that such methods will be used broadly. 

 In Singapore, Facial Recognition Getting Woven Into Everyday Life  from ACM

Singaporeans will be able to access government and other services through a facial recognition feature in its SingPass national identity program.

SingPass Face Verification lets users securely log in to their government services accounts at public kiosks and on home computers, tablets, and mobile phones just using their faces. Singapore's Government Technology Agency said the data collected via facial recognition is "purpose-driven," solely for a specific transaction, and deleted after 30 days.

The technology allegedly prevents login attempts using photos, masks, and deepfakes, as well as repelling replay attacks, which use a recording of a person's face to attempt authentication.  ... " 

Internal Integration of AI Chips

Continued work on AI oriented computer chips.

Chip Designed by AI   by Agency for Science, Technology and Research (A*STAR), Singapore from TechXplore

A*STAR researchers have developed a machine learning algorithm that can help designers decide where to place components on an integrated circuit. Credit: Agency for Science, Technology and Research (A*STAR), Singapore

In less than a decade, artificial intelligence (AI) has gone from an obsession of a few ivory tower academics to runaway commercial success, potentially adding around US$13 trillion to the global economy by 2030 according to a McKinsey projection. One reason that AI is taking off now rather than when it was first conceptualized in the late 1950s is the availability of affordable computational power, in turn, made possible by steady advances in chip design.

But for all the technological advances ever smaller and more powerful integrated circuits (IC) have ushered in, designing the chips themselves remains a time-consuming and labor-intensive task. Although electronic design automation (EDA) software automating the placement of transistors on a chip has been available since the 1980s, the input of experienced human engineers is still required in what is largely a trial-and-error process, together with EDA tools to find the optimized sweet spot.

"More specifically, a large number of simulations and verifications are manually performed during the conventional design process. If the specification in any design cycle is not met, the designers have to redesign and verify the performance through simulation again," explained Salahuddin Raju, a Scientist at the Institute of Microelectronics (IME), A*STAR. .... " 

Singapore to Pay Citizens for Using Apple Watch

Seem a boon for Apple.   Has it been proven the watch significantly improves health?

Singapore to Pay Citizens for Keeping Healthy with Apple Watch  

Bloomberg,  Vlad Savov    September 15, 2020

Apple and Singapore's government have partnered on the two-year LumiHealth initiative, which will monitor and reward user behavior via the Apple Watch and an iPhone application. Singaporeans will be able to earn as much as S$380 ($280) in financial compensation and vouchers by fulfilling goals and tasks—like exercise—set within the LumiHealth app. The app will offer personalized coaching and reminders for health screenings and inoculations, in addition to wellness challenges to encourage healthier dieting and sleep habits. Apple said all user data will be encrypted, with none to be sold or shared for marketing purposes. ... ' 

Intelligent Sensing

More examples of integrating sensors for learning.  Adapting. 

Intelligent Sensing Abilities for Robots to Carry Out Complex Tasks
National University of Singapore
July 15, 2020

Researchers at the National University of Singapore (NUS) have developed a sensory integrated artificial brain system that mimics biological neural networks in order to make robots smarter and more intuitive. The system features an artificial skin sensor that can identify an object's shape, texture, and hardness 10 times faster than the blink of an eye. Intel's Loihi neuromorphic research chip processes sensory data from the artificial skin. The researchers used a robotic hand equipped with the artificial skin to read Braille; tactile data was passed to the Loihi chip, which was more than 92% accurate in classifying the Braille letters. By combining both vision and touch data in a spiking neural network, the robot was able to classify objects and detect object slippage. Said NUS' Harold Soh, "[A] neuromorphic system is a promising piece of the puzzle for combining multiple sensors to improve robot perception." ... '

Scientists Build Ultra-High-Speed Terahertz Wireless Chip

More chips to support high speed AI applications.

Nanyang Technological University (Singapore)
August 5, 2020

Scientists at Nanyang Technological University, Singapore (NTU Singapore) and Japan's Osaka University have constructed an ultra-high-speed terahertz (THz) wireless chip using photonic topological insulators (PTIs). This enabled an 11 gigabits-per-second (Gbps) data rate, which can support real-time streaming of 4K high-definition video. The PTIs avoid the material defects and transmission error rates of conventional waveguides by directing light waves along the surface and edges of the insulators. Light waves are "topologically protected" via a small silicon chip with rows of triangular holes, with smaller triangles oriented opposite to larger triangles. NTU's Ranjan Singh said, "THz technology ... can potentially boost intra-chip and inter-chip communication to support artificial intelligence and cloud-based technologies, such as interconnected self-driving cars, which will need to transmit data quickly to other nearby cars and infrastructure to navigate better and also to avoid accidents."

Picking Locks from Audio

That is picking locks of the physical, notched metal kind.  Seems a machine learning kind of approach would be possible. Learn from the sounds emitted when opening or manipulating a lock.  The author seems skeptical. Further the NUS team looks at what crimes might be possible with emergent tech, leveraging sensing, networks and machine learning.  A good follow.

Picking Locks with Audio Technology
By Paul Marks  ACM
August 13, 2020

The next time you unlock your front door, it might be worth trying to insert your key as quietly as possible; researchers have discovered that the sound of your key being inserted into the lock gives attackers all they need to make a working copy of your front door key.

It sounds unlikely, but security researchers say they have proven that the series of audible, metallic clicks made as a key penetrates a lock can now be deciphered by signal processing software to reveal the precise shape of the sequence of ridges on the key's shaft. Knowing this (the actual cut of your key), a working copy of it can then be three-dimensionally (3D) printed.

This discovery of a major vulnerability in the physical keys that millions of us use to secure domestic and workplace doors and lockers was made by cyberphysical systems researcher Soundarya Ramesh and her team at the National University of Singapore. At the 21st International Workshop on Mobile Computing Systems and Applications (HotMobile 2020) in Austin, TX, in early March, Ramesh revealed how their technique works.

What's being attacked by the NUS team are the keys to pin-tumbler locks, best known as Yale or Schlage keys, though those are just the market leaders and a whole host of other firms make them, too. Inside such locks, six metal pins, affixed to springs, are pushed up to different heights by the ridged teeth on the key, or kept low by the voids between the ridges. When all six spring-loaded pins are pushed to the correct height by the right key, the tumbler containing them is freed to turn, allowing the lock to be opened. Such a lock typically has something of the order of 330,000 possible key shapes.  ... " 

General approach: " ... The NUS team, which studies sensing and embedded and network security, previously investigated potential future crimes that tech might allow to happen. Last year, for instance, they developed a way of fingerprinting the sound of parcel courier drones, to distinguish them from criminal attack drones that might impersonate the real thing to steal valuable parcels awaiting pickup.  ... "?

Spot the Robot Patrols Singapore Parks

This is scarier than facial recognition.  Using Spot the Robot to remind park goers to stay apart.




 Video: https://youtu.be/viuR7N6E2LA  from Singapore Times

Spot the robot is reminding park goers in Singapore to keep their distance from one another
A different kind of walkies for Spot the robot dog
By James Vincent  in TheVerge

At a time when simply sharing space with a fellow human being can be a dangerous activity, many governments, airports, and hospitals are discovering the non-contagious delights of robots, which can be deployed to clean surfaces and deliver goods without fear.

Their latest deployment comes from Singapore, where municipal authorities are using Boston Dynamics’ four-legged Spot robot to remind park visitors to keep a safe distance from one another. Starting today, a Spot unit will patrol the city’s Bishan-Ang Mo Kio Park as part of a two-week trial, broadcasting prerecorded messages “to remind park visitors to observe safe distancing measures.”  ... "

Speak Math, not Code

Makes sense to understand the math and its implications.  I would add that the logic involved in implementation is often ignored by the mathematicians involved. 

Speak Math, Not Code
By Singapore Management University
March 4, 2020

Leslie Lamport, recipient of the 2013 ACM A.M. Turing Award, told a group at the Singapore Management University recently that "Most programmers just start writing code; they don't even know what the algorithm is. It's like starting to build without a blueprint."

Have you ever followed a recipe to bake some bread? If you have, congratulations; you have executed an algorithm. The algorithms that follow us around the internet to suggest items we might like, and those that control what shows up in our Facebook feeds may seem mysterious and uncanny at times. Yet, an algorithm is simply a set of instructions to be completed in a specified sequence, whether by human bakers or computer programs.

The difference, however, lies in how the algorithm is expressed. Recipes are written in English or other spoken languages while computer programs are written in programming languages or code. According to Leslie Lamport, winner of the 2013 Turing Award, thinking mathematically can be a useful step to specifying the algorithm for computer programs, as it can help programmers clarify their thinking and make programs more efficient.

"Most programmers just start writing code; they don't even know what the algorithm is. It's like starting to build without a blueprint," said Lamport, speaking at an exclusive dialogue at the Singapore Management University (SMU) on 14 January 2020, held in conjunction with the SMU-Global Young Scientists Summit 2020.

"And the result? The program is hard to debug and inefficient because you would be trying to optimise at the code level rather than at the algorithm level. We should do what almost every other field of science and engineering does: initially describe the problem with math instead."

From Singapore Management University.... '

Rules for Crypto Business in Singapore

Interesting as an example of what kind of regulations are being written.  An note the connection to business models. How about process models?  Installation of specific risk and fraud predictions and alarms?

The Monetary Authority of Singapore (MAS) is updating its regulatory framework for digital payments. in Coindesk

Announced Tuesday, Singapore’s Payment Services Act 2019 (PSA) brings so-called Digital Payment Token (DPT) services – effectively covering all crypto businesses and exchanges based in Singapore – under current anti-money laundering (AML) and counterterrorist-financing (CTF) rules.

As such, crypto businesses in Singapore are required to first register and then apply for a license to operate in the jurisdiction. 

Similar to the Fifth European Anti-Money Laundering Directive (AMLD5), which went into effect Jan. 10, Singapore’s new rules are long awaited: the PSA was passed back in January 2019. In the intervening months, Singapore has further cemented itself a forward-thinking jurisdiction in regulating the cryptocurrency industry.

As of Jan. 28, firms will have a month to register with MAS, stating they are based in Singapore and are operating a DPT business. Once firms have registered, there’s a six-month grandfathering period during which they have to apply for a payment institution license. 

“The Payment Services Act provides a forward-looking and flexible regulatory framework for the payments industry,” MAS Assistant Managing Director Loo Siew Yee said in a statement. “The activity-based and risk-focused regulatory structure allows rules to be applied proportionately and to be robust to changing business models. The PS Act will facilitate growth and innovation while mitigating risk and fostering confidence in our payments landscape.”

'FATF-ready'
When it comes to implementing crypto regulations, countries around the world are dancing to the beat of the latest Financial Action Task Force (FATF) recommendations, first made in October 2018 and then updated in June 2019. 

This means preparing for a future when payment data relating to the originator and beneficiary of a crypto transaction travels with the payment, guidance known as FATF’s “travel rule.”  .... " 

Singapore Cashierless Convenience Stores

More experience with cashierless models.

Singapore's Unmanned Convenience Stores Learn from China's Failures
Nikkei Asian Review
By Dylan Loh

Unmanned stores are appealing to retailers in Singapore, where workers are in short supply and labor costs are rising. Governmental support for unmanned stores has helped spur automated retail in Singapore; government agencies such as Enterprise Singapore can contribute up to 70% of the technology costs required to launch an unmanned store. Singapore's unmanned retailers are being careful not to repeat the mistakes that led to the failure of unmanned stores in other markets. For example, a recent boom in unmanned stores in China ended almost as quickly as it started, as stores struggled to move fresh groceries. Full-scale automated retail stores worldwide will grow from fewer than 500 this year to more than 44,000 by 2023, according to ABI Research.  .... "