Research and Development

Typhoon · Post by **Typhoon** » 20 Feb 2025 20:23

Photonics Spectra | Hologram Method Boosts Additive Manufacturing

Brilliant.

Doc · Post by **Doc** » 20 Feb 2025 22:03

Typhoon wrote: ↑20 Feb 2025 20:23 Photonics Spectra | Hologram Method Boosts Additive Manufacturing

Brilliant.

Yeah really A tunable detector... I get a hard copy of Photonics but I missed this article.

Doc · Post by **Doc** » 21 Feb 2025 02:51

https://www.rdworldonline.com/ai-based- ... s-to-text/

AI-based brain decoder translates thoughts to text
By Brian Buntz | February 19, 2025
Brain activity measured in an fMRI machine can train a brain decoder to interpret a person's thoughts. UT Austin researchers have developed a faster adaptation method, even for those with language comprehension difficulties. Credit: Jerry Tang/University of Texas at Austin.
Brain activity measured in an fMRI machine can train a brain decoder to interpret a person’s thoughts. UT Austin researchers have developed a faster adaptation method, even for those with language comprehension difficulties. Credit: Jerry Tang/University of Texas at Austin.

Researchers Jerry Tang and Alex Huth at UT Austin have developed an AI tool that decodes brain activity into continuous text, even for those who struggle with language comprehension. Unlike previous methods that needed many hours of training and worked only for specific individuals, the technique can be adapted to new users in about an hour, using fMRI while users watch silent videos, like Pixar shorts.

The research holds particular promise for aphasia, a neurological disorder affecting about one million people in the U.S. The condition impairs the ability to produce and comprehend language, which can result from strokes, brain injuries or neurodegenerative diseases. This condition poses significant challenges to communication, impacting personal, social, and professional interactions.

This novel research at UT Austin occupies a new niche in the BCI landscape by balancing the benefits of high-fidelity decoding with a non-invasive approach. Invasive BCI implants can deliver faster, more precise results but require neurosurgery, extensive calibration, and ongoing clinical management. Conversely, other non-invasive methods like EEG remain more portable but lack the resolution to produce rich, continuous text. By tapping fMRI data and a converter algorithm that adapts the model to new individuals in about one hour—even for those who cannot comprehend spoken language—UT Austin’s system demonstrates that meaningful, free-form semantic decoding is feasible without surgery or months of training.

Jerry Tang (left) and Alex Huth (right) demonstrate an AI tool that converts thoughts into continuous text without requiring spoken word comprehension. Here, they prepare the fMRI scanner for a brain activity recording. Credit: Nolan Zunk/University of Texas at Austin.
Jerry Tang (left) and Alex Huth (right) demonstrate an AI tool that converts thoughts into continuous text without requiring spoken word comprehension. Here, they prepare the fMRI scanner for a brain activity recording. Credit: Nolan Zunk/University of Texas at Austin.

How it works
One of the most notable features of the brain decoder is its reliance on functional magnetic resonance imaging (fMRI) coupled with a transformer-based AI model, akin to GPT-style language architectures. In essence, the system captures a person’s brain activity patterns while they engage with certain stimuli—originally spoken stories, but now more flexibly with silent videos. The AI analyzes these patterns to extract semantic meaning, producing an ongoing stream of text that describes the user’s thoughts, as Physics World noted last year.

Because fMRI records slow blood-oxygen-level-dependent (BOLD) signals, the decoder often paraphrases rather than delivering literal word-for-word transcripts. Despite this, the resulting text captures the “gist” of what a person is mentally processing, as an NIH article noted. Earlier versions required up to 16 hours of fMRI data from a single user, but the latest improvements cut training time to roughly one hour by using visual, language-free stimuli. This shift to non-verbal training helps those who cannot comprehend or produce speech.

Adapting to new users
Another unique aspect of this research is the converter algorithm that speeds adaptation to new individuals. While a reference model might still require longer sessions with several participants (often listening to narratives or stories), a new user only needs around one hour of silent video viewing. During this time, the algorithm aligns the new user’s brain activity with the pre-trained model’s patterns. This approach leverages “cross-modal semantics”—the idea that meaning exists independent of how it’s conveyed (audio, language, or visuals)—so the system can detect and decode that underlying meaning.

Technically, the alignment is achieved through the comparison of fMRI signals from the silent videos in the new user to similar signals in the reference subjects. The converter then “translates” these new signals into a format that the already-trained language model can recognize, thus producing coherent text from a minimal dataset.

Potential applications
Because the decoder can glean meaning from non-verbal, internal brain signals, it holds tremendous promise for therapeutic and assistive technologies. In particular. In addition to aphasia, the technology holds promise for helping individuals with paralysis and ALS. Beyond medical uses, a non-invasive decoder could someday act as a hands-free keyboard for note-taking or device control purely via mental activity.

Other brain-computer interfaces use invasive implants (such as electrocorticography grids) to achieve faster and more precise communication rates, sometimes reaching up to 62 words per minute, as Brown News has noted. Yet the surgical risks, technical complexities\ and long-term maintenance requirements pose barriers to widespread adoption.

A core concern in any “mind-reading” technology is misuse or unauthorized data acquisition. The UT AUstin brain decoder only works with cooperative participants who undergo proper training sessions. If a person is unwilling or actively thinking of something else, the model’s output degrades into incoherence. Furthermore, if the decoder is trained on one individual’s brain signals but used on another, it produces nonsensical text. These safeguards help ensure that unauthorized mind-reading isn’t a near-term concern.

Brain activity from two individuals watching the same silent film. A converter algorithm developed at UT Austin maps one person’s brain activity (left) onto another’s (right), enabling faster adaptation of the brain decoder. Credit: Jerry Tang/University of Texas at Austin.
Brain activity from two individuals watching the same silent film. A converter algorithm developed at UT Austin maps one person’s brain activity (left) onto another’s (right), enabling faster adaptation of the brain decoder. Credit: Jerry Tang/University of Texas at Austin.

The UT Austin neurotech research is something of a microcosm in that it representing a quickly advancing field. For instance, in a recent BrainGate2 clinical trial at Stanford University, a 69-year-old man with C4 AIS C spinal cord injury successfully piloted a virtual quadcopter using only his thoughts. Two 96-channel microelectrode arrays were implanted in the “hand knob” region of his left precentral gyrus, enabling real-time decoding of neural signals as he attempted to move individual fingers. The participant achieved a mean target acquisition time of about two seconds and navigated through 18 virtual rings in under three minutes—over six times faster than a comparable EEG-controlled system. Researchers suggest that this finger-level control could translate to more natural, multi-degree-of-freedom tasks, potentially facilitating improved independence and leisure activities for people living with paralysis.

Typhoon · Post by **Typhoon** » 01 May 2025 17:42

MIT Tech Rev | A long-abandoned US nuclear technology is making a comeback in [PR] China

A thorium-fueled reactor is the latest idea being revived after getting shelved in the mid-20th century.

Doc · Post by **Doc** » 07 Jun 2025 05:53

WV Rare Earth Minerals
West Virginia University (WVU) is actively researching methods to extract rare earth elements (REEs) from coal waste and acid mine drainage, aiming to create a domestic supply chain for these critical materials. WVU's Water Research Institute has developed techniques that could transform acid mine drainage into valuable REEs, which are crucial for high-tech products and clean energy technologies like wind turbines and electric vehicles.

The U.S. currently relies heavily on China for REEs, with China accounting for approximately 60% of global rare earth mining and 90% of refining and magnet-making worldwide.
This dependency poses a strategic concern for the U.S., particularly given the geopolitical tensions between the two countries.

WVU researchers have received significant funding from the U.S. Department of Energy and other agencies to advance this technology. They are working on scaling up their methods to produce larger quantities of REEs, with plans to construct a pilot plant that could extract one ton of REEs per year.
Additionally, WVU is collaborating with various partners, including the West Virginia Department of Environmental Protection and private companies, to develop a national supply chain based on their technology.

This initiative not only seeks to reduce the environmental impact of coal mining but also aims to create economic opportunities and secure a domestic supply of REEs for the U.S..

https://wvutoday.wvu.edu/stories/2021/0 ... production

From pollutant to resource: WVU scientists push rare earth element technologies closer to production
Wednesday, April 21, 2021
Man with grey hair and a lab coat
Paul Ziemkiewicz, director of the West Virginia Water Research Institute, is leading an effort to explore a nationwide supply chain, based on acid mine drainage treatment, that would produce at least 400 tons of rare earth elements and critical materials each year, with support from the National Energy Technology Laboratory. (WVU Photo)

Water researchers at West Virginia University hope to turn a pollutant – acid mine drainage - into a technological resource through the continuation of a $2.1 million contract from the National Energy Technology Laboratory.

The West Virginia Water Research Institute, a program of the Energy Institute at WVU, earned the funding to explore a nationwide supply chain, based on acid mine drainage treatment, that would produce at least 400 tons of rare earth elements and critical materials each year.

The project inches WVU closer to producing rare earth element technologies, which power everything from smartphones to the nation’s missile guidance system.

“We’re partnered with the WV Department of Environmental Protection to build a pilot plant that will treat acid mine drainage while producing about one ton per year of rare earth and critical mineral concentrate,” said Paul Ziemkiewicz, WVWRI director and principal investigator. “NETL wants us to take it to the next step and assess the feasibility of a national supply chain based on our technology. Mine drainage treatment plants like this would be part of that supply chain.”

The process will collect acid mine drainage from the Northern and Central Appalachian Coal Basin, treat it to meet clean water standards and harvest the rare earth elements and the critical minerals cobalt and manganese. Acid mine drainage treatment plants would feed the resulting concentrates into a central facility. The NETL contract will be used to conduct a feasibility study on a potential site for this facility.

Establishing a national supply chain for rare earth elements would help address at least two of the nation’s most pressing challenges -- water pollution and dependence on imports, Ziemkiewicz stated.

About 15,000 tons of rare earth elements are used annually in the U.S., although the country imports nearly all of them. China produces more than 80 percent of the world’s rare earth elements used in modern technologies such as phones, batteries, TVs and medical and defense applications.

Rare earth metals consist of 17 chemically similar elements at the bottom of the periodic table, such as neodymium and dysprosium. Despite their name, they’re not “rare” but they are rarely found in high concentrations and they are hard to extract.

“Acid mine drainage happens when coal waste rock weathers and forms sulfuric acid,” Ziemkiewicz explained. “The acid leaches all manner of metal pollutants out of rock, so why wouldn’t it leach rare earths? Mother Nature does that heavy lifting for free. Fortunately, AMD is, in fact, enriched in rare earth elements and critical materials in an easily recovered form. Best of all, you can’t recover them without treating AMD to environmental standards. Our byproduct is clean water.”

Ziemkiewicz called acid mine drainage the most urgent water pollution problem in the Appalachian Coal Basin and metal mining districts in the western U.S.

His team’s efforts date back to 2016 when the U.S. Department of Energy requested ideas to recover rare earth elements from coal and coal waste. Around that time, his team examined 120 acid mine drainage treatment sites throughout West Virginia, Pennsylvania, Maryland and Ohio. They found that acid mine drainage could produce up to 2,200 tons of rare earth elements per year in those states.

Joining Ziemkiewicz on this project are Aaron Noble, of Virginia Tech, and Tom Larochelle, of Process Engineering Associates.

Partners include Continental Heritage and Montana Resources, a large copper mine in Butte, Montana and operator of its Berkeley Pit AMD facility.

“Throughout the history of this great country, mining of all forms has been critical to the economic development, national security and social prosperity that we enjoy today,” said Mark Thompson, vice president of environmental affairs for Montana Resources, LLP. “However, historic mining has often left behind an impactful legacy. Projects such as this one being undertaken at WVU have the potential to transform negative mining legacies into the raw materials necessary to sustain this nation.”

“Continental Heritage welcomes the opportunity to host WVU’s ingenious technology that turns the challenge of AMD into a solution for something so vital to America’s success, security and advancement of new technology and industry,” said Sean O’Brien, COO of Continental Heritage. “To do so in an environmentally-friendly way while creating much-needed sustainable jobs, Continental Heritage is thrilled to support WVU’s research.”

“This project will solidify WVU’s position as the leader in the recovery and processing of rare earth elements,” said Gary White, former Marshall University president and a consultant on the project. “This project’s contribution to national security and the local economy will be significant.”