Curiosity and AI

Curiosity is often key to solution.

MIT News | Massachusetts Institute of Technology

 SUBSCRIBE TO MIT NEWS NEWSLETTER

Ensuring AI works with the right dose of curiosity

Researchers make headway in solving a longstanding problem of balancing curious “exploration” versus “exploitation” of known pathways in reinforcement learning.

Rachel Gordon | MIT CSAIL, Publication Date:November 10, 2022

It’s a dilemma as old as time. Friday night has rolled around, and you’re trying to pick a restaurant for dinner. Should you visit your most beloved watering hole or try a new establishment, in the hopes of discovering something superior? Potentially, but that curiosity comes with a risk: If you explore the new option, the food could be worse. On the flip side, if you stick with what you know works well, you won't grow out of your narrow pathway. 

Curiosity drives artificial intelligence to explore the world, now in boundless use cases — autonomous navigation, robotic decision-making, optimizing health outcomes, and more. Machines, in some cases, use “reinforcement learning” to accomplish a goal, where an AI agent iteratively learns from being rewarded for good behavior and punished for bad. Just like the dilemma faced by humans in selecting a restaurant, these agents also struggle with balancing the time spent discovering better actions (exploration) and the time spent taking actions that led to high rewards in the past (exploitation). Too much curiosity can distract the agent from making good decisions, while too little means the agent will never discover good decisions.

In the pursuit of making AI agents with just the right dose of curiosity, researchers from MIT’s Improbable AI Laboratory and Computer Science and Artificial Intelligence Laboratory (CSAIL) created an algorithm that overcomes the problem of AI being too “curious” and getting distracted by a given task. Their algorithm automatically increases curiosity when it's needed, and suppresses it if the agent gets enough supervision from the environment to know what to do.  ... ' 

Privd AI for Differential Privacy

 Surveillance privacy from Cameras

Researchers from MIT CSAIL Introduce ‘Privid’: an AI Tool, Build on Differential Privacy, to Guarantee Privacy in Video Footage from Surveillance Cameras

By Annu Kumari -March 30, 2022  This research summary article is based on the paper 'Privid: Practical, Privacy-Preserving Video Analytics Queries' and MIT article 'Security tool guarantees privacy in surveillance footage'

Surveillance cameras have an identity crisis exacerbated by a conflict between function and privacy. Machine learning techniques have automated video content analysis on a vast scale as these sophisticated small sensors have shown up seemingly everywhere. Still, with increased mass monitoring, there are currently no legally enforceable standards to curb privacy invasions.

Security cameras have evolved into wiser and more capable tools than the grainy images of the past, which were frequently used as the “hero tool” in crime dramas. Video surveillance can now assist health regulators in determining the percentage of persons using masks, transportation departments in monitoring the density and flow of automobiles, cyclists and walkers, and businesses in gaining a better understanding of buying habits. But why has privacy remained a second-class citizen?

Privid

Currently, the footage is retrofitted with blurred faces or black boxes. This prevents analysts from asking some legitimate questions (for example, are people wearing masks? ). Dissatisfied with the present status quo, MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) developed a system with other institutions to better guarantee privacy in surveillance video footage. The system, dubbed “Privid,” allows analysts to input video data searches and then adds a tiny amount of noise (additional data) to the result to ensure that no one can be identified. The method is based on a formal notion of privacy known as “differential privacy,” which permits without having access to aggregate statistics about private data disclosing individually identifying information. ... ' 

Quantifying Computing Power and Innovation

Powerful computers,  better innovation? 

Quantifying Computing Power and Innovation    By MIT News., June 29, 2022

Futuristic image of a microprocessor in a circuit.

"By looking directly at capabilities, we are able to get more precise measurements and thus get better estimates of how computing power influences performance." -Neil Thompson

Neil Thompson is an MIT research scientist at the Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Sloan School of Management.

Neil Thompson and his research team set out to quantify the importance of more powerful computers for improving outcomes across society. They analyzed five areas where computation is critical, including weather forecasting, oil exploration, and protein folding. The team found that between 49 and 94 percent of improvements in these areas can be explained by computing power. But computer progress is slowing, which could have far-reaching impacts across the economy and society.

In an interview, Thompson discusses this research and the implications of the end of Moore's Law.

From MIT News

View Full Article    

New form of Machine Learning Vision

Machine Learning Vision

MIT Advances Unsupervised Computer Vision with ‘STEGO’

By Oliver Peckham

Training machine learning models often means working with labeled data. For computer vision tasks, this might look, for instance, like an hour of camera footage from a car, meticulously sectioned by humans to designate roads, road signs, vehicles, pedestrians and so forth. But labeling even this small amount of data could take hundreds of hours for a human, bottlenecking the training process. Now, researchers from MIT’s Computer Science & Artificial Intelligence Laboratory (CSAIL) are introducing a new, state-of-the-art algorithm for unsupervised computer vision tasks that operates without any human labels.

The model is called STEGO, short for “Self-supervised Transformer with Energy-based Graph Optimization.” STEGO is a semantic segmentation algorithm, the process of labeling the pixels in an image. Historically, semantic segmentation has been easiest for discrete objects like people or vehicles and harder for more amorphous, blended elements of the environment like clouds or bushes—or cancers.

“If you’re looking at oncological scans, the surface of planets, or high-resolution biological images, it’s hard to know what objects to look for without expert knowledge. In emerging domains, sometimes even human experts don’t know what the right objects should be,” explained Mark Hamilton, a research affiliate of MIT CSAIL, software engineer at Microsoft, and lead author of the paper describing STEGO, in an interview with MIT’s Rachel Gordon. “In these types of situations where you want to design a method to operate at the boundaries of science, you can’t rely on humans to figure it out before machines do.”

STEGO is built on top of the DINO algorithm, itself trained on 14 million images. The researchers tested STEGO on a variety of test cases, including the incredibly diverse COCO-Stuff image dataset. The researchers reported that STEGO doubled the performance of prior unsupervised computer vision models on the COCO-Stuff benchmark, and performed similarly well on tasks like driverless car datasets and space imagery datasets.  ... ' 

Self Configuring Robotic Cubes

Quite interesting application for space, and perhaps other complex environments for sensors?

 Robotic cubes: Self-reconfiguring ElectroVoxels use embedded electromagnets to test applications for space exploration

by Rachel Gordon, Massachusetts Institute of Technology

If faced with the choice of sending a swarm of full-sized, distinct robots to space, or a large crew of smaller robotic modules, you might want to enlist the latter. Modular robots, like those depicted in films such as "Big Hero 6," hold a special type of promise for their self-assembling and reconfiguring abilities. But for all of the ambitious desire for fast, reliable deployment in domains extending to space exploration, search and rescue, and shape-shifting, modular robots built to date are still a little clunky. They're typically built from a menagerie of large, expensive motors to facilitate movement, calling for a much-needed focus on more scalable architectures—both up in quantity and down in size.

Scientists from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) called on electromagnetism—electromagnetic fields generated by the movement of electric current—to avoid the usual stuffing of bulky and expensive actuators into individual blocks. Instead, they embedded small, easily manufactured, inexpensive electromagnets into the edges of the cubes that repel and attract, allowing the robots to spin and move around each other and rapidly change shape.

The "ElectroVoxels" have a side length of about 60 millimeters, and the magnets consist of ferrite core (they look like little black tubes) wrapped with copper wire, totaling a whopping cost of just 60 cents. Inside each cube are tiny printed circuit boards and electronics that send current through the right electromagnet in the right direction  .... ' 

Consider the AI Outlook

Good piece, the rest at the continuation link. 

An AI Outlook, By Karen Emslie, Commissioned by CACM Staff, February 1, 2022

Five global AI experts weigh in on the challenges they anticipate the technology will face, and potentially overcome, this year.

Advances in artificial intelligence (AI) continue to happen at an extraordinary pace. News of breakthroughs in machine learning, computer vision, data science, and machine-human interaction come almost daily. Growth is massive, and it is impacting all sectors.

According to a new forecast from the technology research company Gartner, worldwide artificial intelligence (AI) software revenue is forecast to total $62.5 billion in 2022, an increase of 21.3% from 2021.

The AI boom has been fueled by incredible technological leaps, yet with progress comes challenges. We asked five global AI experts to weigh in with their thoughts on trends, breakthroughs, and challenges in the year ahead.

Societal concerns will increasingly drive AI breakthroughs

Adji Bousso Dieng is a computer science professor at Princeton University and a research scientist at Google AI; her work spans probabilistic graphical modelling, statistics, and deep learning.

Dieng flagged up the growing trend of applying AI to "critical domains" that impact everyone in society, such as climate and biology. "I am expecting AI to continue to break ground in more scientific domains in 2022 and beyond, and I am very excited to live in this era where we are able to tackle important problems leveraging data, computation, and human insights," she said.

According to Dieng, AI research has tended to focus on building increasingly large models, supported by investment from both industry and academia. She expects this trend continue, but adds, "I personally hope we will shift energy and focus away from chasing bigger and bigger models and focus on tackling the important problems facing humanity."

Daniela Rus is a professor of electrical engineering and computer science at Massachusetts Institute of Technology (MIT), where she also serves as director of the university's Computer Science and Artificial Intelligence Laboratory (CSAIL). As an expert in AI, robotics, and data science, Rus said she has noticed a "heightened awareness about the challenges with today's AI solutions" and expects this to inform future trends.

Among Rus' predictions for 2022 are developments in data availability, interpretability, and privacy. She pointed out that the massive datasets that deep neural networks depend upon need to be manually labeled, and are not easily obtained in every field. "The quality of that data needs to be very high, and if the data is biased or bad, the performance of the systems trained on this data will be equally bad."

Rus said AI currently faces significant challenges around privacy and trust. "As we gather more data to feed into AI systems, the risks to privacy will grow. So will the opportunities for authoritarian governments to leverage these tools to curtail freedom and democracy in countries around the world." ..... ' 

MIT Reveals new Quantum Computing Language: Twist

 A Language for Quantum Computing

ACM NEWS

A New Language for Quantum Computing, By MIT News

January 25, 2022

Time crystals. Microwaves. Diamonds. What do these three disparate things have in common? 

Quantum computing. Unlike traditional computers that use bits, quantum computers use qubits to encode information as zeros or ones, or both at the same time. Coupled with a cocktail of forces from quantum physics, these refrigerator-sized machines can process a whole lot of information — but they're far from flawless. Just like our regular computers, we need to have the right programming languages to properly compute on quantum computers. 

Programming quantum computers requires awareness of something called "entanglement," a computational multiplier for qubits of sorts, which translates to a lot of power. When two qubits are entangled, actions on one qubit can change the value of the other, even when they are physically separated, giving rise to Einstein's characterization of "spooky action at a distance." But that potency is equal parts a source of weakness. When programming, discarding one qubit without being mindful of its entanglement with another qubit can destroy the data stored in the other, jeopardizing the correctness of the program. 

Scientists from MIT's Computer Science and Artificial Intelligence (CSAIL) aimed to do some unraveling by creating their own programming language for quantum computing called Twist. Twist can describe and verify which pieces of data are entangled in a quantum program, through a language a classical programmer can understand. The language uses a concept called purity, which enforces the absence of entanglement and results in more intuitive programs, with ideally fewer bugs. For example, a programmer can use Twist to say that the temporary data generated as garbage by a program is not entangled with the program's answer, making it safe to throw away.

From MIT News

View Full Article  

Bending Light for a Cheaper Internet

Who Can Bend Light for a Cheaper Internet?

By MIT Computer Science and Artificial Intelligence Laboratory  in CACM

Massachusetts Institute of Technology (MIT) researchers have developed a system that can maintain network connections when optical fibers break by reconfiguring optical transmissions from damaged fibers to healthy ones.

The ARROW system plans for potential fiber cuts in advance using an online algorithm that accounts for real-time Internet traffic demands.

Simulations revealed that ARROW could carry up to 2.4 times more traffic without deploying new fibers, and while maintaining high network reliability.

MIT's Zhizhen Zhong said, "With ARROW, some failures can be eliminated or partially restored, and this changes the way we think about network management and traffic engineering, opening up opportunities for rethinking traffic engineering systems, risk assessment systems, and emerging applications, too."

The researchers are working with Facebook to deploy ARROW in real-world wide-area networks.

From MIT Computer Science and Artificial Intelligence Laboratory

View Full Article 

Robot Hair Untangling

This got some rare general press, since it deals with a real concern/chore in the home.  And I do have a general 'hair care' link below from my Consumer package company goods days.    Perhaps they want to pick this up, but I am assuming the robot required is expensive. 

Untangle Your Hair With Help From Robots

MIT Computer Science and Artificial Intelligence Laboratory

Rachel Gordon, May 3, 2021

Researchers at the Massachusetts Institute of Technology's Computer Science and Artificial Intelligence Laboratory (CSAIL) and Harvard University's Soft Math Lab teamed up to develop a robotic arm setup that can comb tangled hair. "RoboWig" features a sensorized soft brush equipped with a camera to assess curliness, so the system can adapt to the degree of hair tangling it encounters. CSAIL's Josie Hughes said, "By developing a model of tangled fibers, we understand from a model-based perspective how hairs must be entangled: starting from the bottom and slowly working the way up to prevent 'jamming' of the fibers." Tests on wigs of various hair styles and hair types helped determine appropriate brushing lengths, taking into consideration the number of entanglements and pain levels.

Navigating Complex Computer Instructions

Technical look at improvements in acceleration by better understanding computer instructions.

A Tool for Navigating Complex Computer Instructions

MIT Computer Science and Artificial Intelligence Laboratory, Rachel Gordon, April 16, 2021

A new tool developed by researchers at the Massachusetts Institute of Technology's Computer Science and Artificial Intelligence Laboratory (CSAIL) and the University of Illinois at Urbana-Champaign automatically generates compiler plugins that can handle more complex instructions. The tool, VeGen, could help eliminate the need for software developers to manually write assembly code for new Intel computer chips. The compiler plugins generated by VeGen allow for the exploitation of non-Single Instruction Multiple Data (SIMD), which allows multiple operations, like addition and subtraction, to be performed simultaneously. CSAIL's Yishen Chen said, "The long-term goal is that, whenever you add new features on your hardware, we can automatically figure out a way—without having to rewrite your code—to use those hardware accelerators."... ' 

Automatically Updating Facts

 When we sought to construct a company Wiki, we found one of the most important issues, after validating it, was updating knowledge.  Here MIT CSAIL is looking at that problem.

Auto-Updating Websites When Facts Change

MIT Computer Science and Artificial Intelligence Laboratory

March 29, 2021

Massachusetts Institute of Technology (MIT) researchers have developed models to reduce the amount of incorrect or outdated information online and dynamically adjust to recent changes. The researchers used deep learning models to rank an initial set of about 200 million revisions to popular English-language Wikipedia pages. Annotators found about a third of the top 300,000 revisions included a factual difference. The researchers created a model to mimic the filtering performed by human annotators, which can detect nearly 85% of revisions that include a factual change. They also created a model to automatically revise texts and suggest edits to other articles, as well as a robust fact verification model. MIT's Tal Schuster said, "Instead of teaching the model that the population of a certain city is this and this, we teach it to read the current sentence from Wikipedia and find the answer that it needs." ... '

Fabricating Functional Devices and Drones

3D Printing and more.  Impressive too for spacecraft?  

Fabricating Fully Functional Drones  From MIT CSAIL

Researchers at the Massachusetts Institute of Technology's Computer Science and Artificial Intelligence Laboratory (CSAIL) developed a three-dimensional (3D) printing system to manufacture functional, custom-made devices and robots like drones, without human intervention. CSAIL's Martin Nisser said, "By leveraging widely available manufacturing platforms like 3D printers and laser cutters, LaserFactory is the first system that integrates these capabilities and automates the full pipeline for making functional devices in one system." LaserFactory combines a software toolkit for custom design with a hardware platform, enabling users to fabricate structural geometry, print traces, and build electronic components like sensors and actuators. Said Nisser, "Beyond engineering, we're also thinking about how this kind of one-stop shop for fabrication devices could be optimally integrated into today's existing supply chains for manufacturing, and what challenges we may need to solve to allow for that to happen."

(Updated): Is Blockchain e-Voting a Solution to Elections?

 Blockchain Voting.    In Coindesk. 

New MIT Paper Roundly Rejects Blockchain Voting as Solution to Election Woes  By Benjamin Powers

As media outlets waited to announce a winner until the Saturday following the election day, calls for how blockchains would have made this process easier emerged, most prominently perhaps by  Changpeng Zhao, CEO of Binance, as well as Vitalik Buterin, who added that, though there are technical challenges, the call for a blockchain-based, mobile voting app “is directionally 100% correct.”

A new report from MIT, however, strongly argues against the idea of blockchain-based e-voting, largely on the basis that it will increase cybersecurity vulnerabilities that already exist, it fails meet the unique needs of voting in political elections and it adds more issues than it fixes. 

 (Update:  Here is draft of paper:  https://people.csail.mit.edu/rivest/pubs/PSNR20.pdf ) 

The report’s authors are Ron Rivest, MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) professor and one of the creators of RSA encryption; Michael Specter; Sunoo Park; and Director of MIT’s Digital Currency Initiative (DCI) Neha Narula. The paper will be published in the Journal of Cybersecurity later this month.    ... "     (Impressive group) 

Choosing Antibiotics

Narrow example of applicaation of recommendation in healthcare

MIT CSAIL researchers claim their algorithm helps doctors pick the right antibiotics

Kyle Wiggers@Kyle_L_Wiggers in Venturebeat

Researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) say they’ve developed a recommendation algorithm that predicts the probability a patient’s urinary tract infection (UTI) can be treated by first- or second-line antibiotics. With this information, the model makes a recommendation for a specific treatment that selects a first-line agent as frequently as possible, without leading to an excess of treatment failures.

UTIs, which affect half of all women, add almost $4 billion a year in health care costs. Doctors often treat UTIs using antibiotics called fluoroquinolones, but they’ve been found to put women at risk of contracting other infections. They’re also associated with a higher risk of tendon injuries and life-threatening conditions like aortic tears, leading medical associations to issue guidelines recommending fluoroquinolones as “second-line treatments.” (A second-line treatment is a treatment for a disease employed after the initial treatment has failed, stopped working, or caused intolerable side effects.) Despite this, doctors with limited time and resources continue to prescribe fluoroquinolones at high rates. ... " 

Optimization Assisting the User of Large Databases

Using tools like machine learning to adapt how we do complex operations, like analyzing increasingly large databases for complex uses.  Here work at MIT in this space.  I can see this being used further, to analyze and leverage the context in which the data will be used. 

MIT Is Developing a Tool for Machine Learning-Powered Data Retrieval   Oliver Peckham in DataNami

With the global deluge of data, the opportunities are endless – but so are the challenges. Within five years, the world’s data is estimated to reach 175 zettabytes: enough to fill over 23,000 one-terabyte hard drives for every single person alive. In the context of such a data-driven world, managing and sorting through that data is a task that gets harder by the day, with database and query managers struggling to keep up. Now, researchers from MIT are developing a tool to intelligently assist users of large databases.

“It’s like building a database system for every application from scratch, which is not economically feasible with traditional system designs,” explained MIT Professor Tim Kraska in an interview with MIT’s Adam Conner-Simons. Kraska and his colleagues – from the institute’s Computer Science and Artificial Intelligence Laboratory (CSAIL) – are debuting a design for what they call “instance-optimized systems”: database systems that are able to optimize and reorganize themselves in response to the data types and workloads at hand. 

MIT’s instance-optimized system will be the child of two parents: the “Tsunami” and “Bao” tools. Using machine learning, Tsunami (a successor to “Flood”) interprets user queries to reorganize the layouts of databases. Bao, meanwhile, uses machine learning to intelligently pick the appropriate plan for completing a given query. On their own, Tsunami improved query speed up to tenfold, while Bao-created query plans ran up to 50% faster. When combined: the instance-optimized system.

“Query optimizers have been around for years, but they often make mistakes, and usually they don’t learn from them. That’s where we feel that our system can make key breakthroughs, as it can quickly learn for the given data and workload what query plans to use and which ones to avoid,” Kraska said. “Our hope is that a system like this will enable much faster query times, and that people will be able to answer questions they hadn’t been able to answer before.”   ... "

Meshing and Simulation

Design meshes are  a means for determining the design of simulation, especially for design problems.  Good discussion.

Better simulation meshes well for design software (and more)
New work on 2D and 3D meshing aims to address challenges with some of today’s state-of-the-art methods.   By Adam Conner-Simons | MIT CSAIL

The digital age has spurred the rise of entire industries aimed at simulating our world and the objects in it. Simulation is what helps movies have realistic effects, automakers test cars virtually, and scientists analyze geophysical data.

To simulate physical systems in 3D, researchers often program computers to divide objects into sets of smaller elements, a procedure known as “meshing.” Most meshing approaches tile 2D objects with patterns of triangles or quadrilaterals (quads), and tile 3D objects with patterns of triangular pyramids (tetrahedra) or bent cubes (hexahedra, or “hexes”).

While much progress has been made in the fields of computational geometry and geometry processing, scientists surprisingly still don’t fully understand the math of stacking together cubes when they are allowed to bend or stretch a bit. Many questions remain about the patterns that can be formed by gluing cube-shaped elements together, which relates to an area of math called topology.

New work out of MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) aims to explore several of these questions. Researchers have published a series of papers that address shortcomings of existing meshing tools by seeking out mathematical structure in the problem. In collaboration with scientists at the University of Bern and the University of Texas at Austin, their work shows how areas of math like algebraic geometry, topology, and differential geometry could improve physical simulations used in computer-aided design (CAD), architecture, gaming, and other sectors.

“Simulation tools that are being deployed ‘in the wild’ don’t always fail gracefully,” says MIT Associate Professor Justin Solomon, senior author on the three new meshing-related papers. “If one thing is wrong with the mesh, the simulation might not agree with real-world physics, and you might have to throw the whole thing out.”  .... ' 

In one paper,  https://diglib.eg.org/handle/10.1111/c 4074a gf14074a team led by MIT undergraduate Zoë Marschner developed an algorithm to repair issues that can often trip up existing approaches for hex meshing, specifically.  ..." 

Robots Manipulating Cables

Been at times responsible for cable rooms, and know of the messiness in manipulating cable.  Never thought of this being solved by robotics. In fact thought of it as a particularly difficult thing to do that way.   This particular example will be interesting to see, and what part of the problem it can address.

Letting robots manipulate cables
Robotic gripper with soft sensitive fingers developed at MIT CSAIL can handle cables with unprecedented dexterity.
Rachel Gordon | MIT CSAIL

For humans, it can be challenging to manipulate thin flexible objects like ropes, wires, or cables. But if these problems are hard for humans, they are nearly impossible for robots. As a cable slides between the fingers, its shape is constantly changing, and the robot’s fingers must be constantly sensing and adjusting the cable’s position and motion.
Standard approaches have used a series of slow and incremental deformations, as well as mechanical fixtures, to get the job done. Recently, a group of researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) pursued the task from a different angle, in a manner that more closely mimics us humans. The team’s new system uses a pair of soft robotic grippers with high-resolution tactile sensors (and no added mechanical constraints) to successfully manipulate freely moving cables.  ... " 

Robot Disinfecting a Food Bank

Would seem to be a very efficient use of robotics.  Considerable detail and video about the process at the link.

CSAIL robot disinfects Greater Boston Food Bank
Using UV-C light, the system can disinfect a warehouse floor in half an hour — and could one day be employed in grocery stores, schools, and other spaces.
Watch Video

By Rachel Gordon | MIT CSAIL

Searching Websites the Way You Want

Interesting for non-programmers, to use API's.  At the link some technical examples.

Searching Websites the Way You Want
MIT CSAIL
Adam Conner-Simons
May 18, 2020

Researchers at the Massachusetts Institute of Technology's Computer Science & Artificial Intelligence Laboratory (CSAIL) have developed ScrAPIr, a tool that enables non-programmers to access, query, save, and share Web data application programming interfaces (APIs). Traditionally, APIs could only be accessed by users with strong coding skills, leaving non-coders to laboriously copy-paste data or use Web scrapers that download a site's webpages and search the content for desired data. To integrate a new API into ScrAPIr, a non-programmer only needs to fill out a form telling the tool about certain aspects of the API. Said MIT’s David Carger, “APIs deliver more information than what website designers choose to expose it, but this imposes limits on users who may want to look at the data in a different way. With this tool, all of the data exposed by the API is available for viewing, filtering, and sorting.” ... ' 

Microwaves Sensing Your Health?

This struck me at first as being even more interesting than it actually seems to be:  Detect what machines you are using. And derive some health measures from behavior.   It turns out I had just placed a large long russet potato in the microwave, and hit the 'potato' button, and for the first ten minutes the display said 'sensing', then it changed to 'cooking' as it proceeded to create a soft potato.  Was this something like that?   Well, no it seems, but it made me think more along those lines.   Can more derived from the sensing?  No plans to crawl into the microwave. 

" ... Sapple, a system developed at the MIT Computer Science and Artificial Intelligence Laboratory, analyzes in-home appliance usage to better understand health patterns, using just radio signals and a smart electricity meter.

What can your microwave tell you about your health?
An MIT system uses wireless signals to measure in-home appliance usage to better understand health tendencies.   Rachel Gordon | MIT CSAIL

For many of us, our microwaves and dishwashers aren’t the first thing that come to mind when trying to glean health information, beyond that we should (maybe) lay off the Hot Pockets and empty the dishes in a timely way.

But we may soon be rethinking that, thanks to new research from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL). The system, called “Sapple,” analyzes in-home appliance usage to better understand our health patterns, using just radio signals and a smart electricity meter.

Taking information from two in-home sensors, the new machine learning model examines use of everyday items like microwaves, stoves, and even hair dryers, and can detect where and when a particular appliance is being used.

For example, for an elderly person living alone, learning appliance usage patterns could help their health-care professionals understand their ability to perform various activities of daily living, with the goal of eventually helping advise on healthy patterns. These can include personal hygiene, dressing, eating, maintaining continence, and mobility.

“This system uses passive sensing data, and does not require people to change the way they live,” says MIT PhD student Chen-Yu Hsu, the lead author on a new paper about Sapple. “It has potential to improve things like energy saving and efficiency, give us a better understanding of the daily activities of seniors living alone, and provide insight into the behavioral analytics for smart environments.” ... ."   ... '