jonat941 - Tumblr blog

[jonat941]

Polymerization and New Materials Synthesis through AI Deep Learning

[jonat941]

Polymerization and New Materials Synthesis through AI Deep Learning

Source: news@northwestern.edu New Polymerization Material >< AI Intersect What if we want to have a new polymer that can be used to accept certain proteins and reject the growth of harmful bacteria? This can prove useful in the medical industry that uses cellular-level innovations. In general, these research efforts are exploring the intersection of materials science and AI, using machine…

[jonat941]

Polymerization and New Materials Synthesis through AI Deep Learning

Source: news@northwestern.edu

New Polymerization Material >< AI Intersect

What if we want to have a new polymer that can be used to accept certain proteins and reject the growth of harmful bacteria? This can prove useful in the medical industry that uses cellular-level innovations. In general, these research efforts are exploring the intersection of materials science and AI, using machine learning and other AI techniques to accelerate the discovery and optimization of new materials with specific properties for a wide range of applications. The development of new polymers is a key area of focus, given the critical role that polymers play in many areas of modern technology, from electronics to energy storage to medicine.

Moreover, it is possible to train an AI model to predict the properties and structures of polymers based on a set of input compounds. This approach is known as "inverse design," where the goal is to predict the desired properties of a polymer and then work backward to identify the monomers and reaction conditions needed to synthesize it.

To train such a model, it would be necessary to provide it with a large dataset of known polymers and their corresponding monomers, reaction conditions, and properties. The model could then use this data to learn patterns and relationships between the input compounds and the resulting polymer structures and properties.

Once the model is trained, it could be used to predict the properties of a polymer based on a set of input compounds and guide the selection of monomers and reaction conditions to synthesize the desired polymer.

AI Predictive Models Enhance Accurate Discovery 

Predictive learning models are being used by researchers to expedite the design of new polymers customized to the required functionality or specification. The possibilities are now limited only by the imagination of the AI Model designer. The near future will usher in and be filled with a vast variety of new and more effective but inexpensive polymers and materials all synthesized from accurate predictions by these tried and tested trained AI models.

Making new Polymer Brush Films a Breeze

Source: © Tokyo Institute of Technology

Polymer brush films as per the above illustration consist of monomer chains grown in close proximity to a substrate. The monomers, which look like "bristles" at the nanoscale, form a highly versatile functionality that the resulting polymer bristle coating can selectively adsorb or desorb a variety of chemicals or biological molecules. These polymers can be used to create environmentally friendly, antifouling marine paints that can prevent mussels and other organisms that attach to floating objects like ships in the ocean called "fouling organisms." This negative term originated as a reference to the way they slow the speed of a ship when they build up on the bottom of a hull.

A recent study by a research group led by Associate Professor Tomohiro Hayashi from Tokyo Institute of Technology (Tokyo Tech), Japan, published in ACS Biomaterials Science & Engineering, has used machine learning to predict these interactions and identify the film characteristics that have a significant impact on protein adsorption. The team fabricated 51 different polymer brush films of different thicknesses and densities with five different monomers to train the machine-learning algorithm. They then tested several of these algorithms to see how well their predictions matched up against the measured protein adsorption. "We tested several supervised regression algorithms, namely gradient boosting regression, support vector regression, linear regression, and random forest regression, to select the most reliable and suitable model in terms of prediction accuracy," says Dr. Hayashi.

In their study, the team fabricated 51 polymer brush films of different thicknesses and densities with five monomers to train the machine learning algorithm. They then tested several of these algorithms to see how well their predictions matched up against the measured protein adsorption. "We tested several supervised regression algorithms, namely gradient boosting regression, support vector regression, linear regression, and random forest regression, to select the most reliable and suitable model in terms of prediction accuracy," says Dr. Hayashi.

Source: HAYASHI LABORATORY

Out of these models, the random forest (RF) regression model showed the best agreement with the measured protein adsorption values. Accordingly, the researchers used the RF model to correlate the physical and chemical properties of the polymer brush with its ability to adsorb serum protein and allow for cell adhesion.

"Our analyses showed that the hydrophobicity index, or the relative hydrophobicity, was the most critical parameter. Next in line were the thickness and density of polymer brush films, the number of C-H bonds, the net charge on the monomer, and the density of the films. Monomer molecular weight and the number of O-H bonds, on the other hand, were ranked low in importance," highlights Dr. Hayashi.

Given the highly varied nature of polymer brush films and the multiple factors that affect the monomer-protein interactions, adopting machine learning as a way to optimize polymer brush film properties can provide a good starting point for the efficient design of anti-biofouling materials and functional biomaterials. Source: Materials provided by Tokyo Institute of Technology.

[jonat941]

How the Elephant Man Defied ALL Medical Knowledge

[jonat941]

Meet the Richest Man Who Ever Lived

[jonat941]

How a Japanese Man 'Lived' For 550 Years

[jonat941]

Why We Have No Way to Fight Against North Korean Hackers

[jonat941]

A Real Faster than Light Time and Space Warp Drive Model

A Real Faster than Light Time and Space Warp Drive Model

A pair of researchers at Applied Physics has created what they describe as the first general model for a warp drive, a model for a space craft that could travel faster than the speed of light, without actually breaking the laws of physics. Alexey Bobrick, and Gianni Martire have written a paper describing their ideas for a warp drive and have published it in IOP’s Classical and Quantum…

[jonat941]

Highly Advanced Civilization Types by Kardashev Scale

Highly Advanced Civilization Types by Kardashev Scale

The idea of Technology Levels has some actual reference in the real world in the form of the Kardashev Scale, which indicates how much power a civilization uses. This was originally used in the context of astronomy, speculating about what advanced alien civilizations might look like from afar, particularly the implications of enormous energy demands. It has since been used to compare the Power…

[jonat941]

Intensify Luminosity a Thousand Times

Intensify Luminosity a Thousand Times

Quantum technologies such as quantum computers require sources of entangled pairs of photons. To make these photon pairs, researchers commonly use silicon-based devices, where the silicon sits on an insulator. Galan Moody and his colleagues at the University of California, Santa Barbara, wondered if they could switch the silicon with aluminum gallium arsenide (AlGaAs), a material that has…

[jonat941]

Alpha Centauri 3.4 Light Years = 40 Trillion Km from Earth in 14 Days Onboard NASA'S Starship IXS Enterprise

Alpha Centauri 3.4 Light Years = 40 Trillion Km from Earth in 14 Days Onboard NASA’S Starship IXS Enterprise

NASA announced in 2012 that it was working to build a “warp drive” that could enable “faster-than-light” travel. Two years later and the space agency hasn’t built a spaceship capable of such speeds yet — but thanks to artist Mark Rademaker, we now know what one could look like. The result is the IXS Enterprise, a ship that shares similarities with both its science fiction Star Trek namesake, and…

[jonat941]

The Universe Fundamental Dimensionless Constants

The Universe Fundamental Dimensionless Constants

At a fundamental level, our Universe is made of particles, forces, interactions, and the fabric of space and time. Spacetime forms the ever-evolving stage on which the play of the cosmos unfolds, while the particles are the players. They can bind together, collide, annihilate, repel, attract, or otherwise interact according to the rules that govern the laws of nature. These pieces of information,…

[jonat941]

NASA’s Breakthrough Starshot Microsatellite @20% speed of light reach Alpha Centauri in just 2 Decades

NASA’s Breakthrough Starshot Microsatellite @20% speed of light reach Alpha Centauri in just 2 Decades

The word far is an understatement when it comes to the vast distances between celestial bodies. The distance between the sun and our farthest planet Neptune is 2.7 billion miles—it would take astronauts roughly a dozen years to get there using current technology. The farther out into space you go, miles start to lose their meaning and light-years come into play. To put that into perspective,…

[jonat941]

Scientists create new recipe for single-atom transistors for quantum computing

Scientists create new recipe for single-atom transistors for quantum computing

Now, researchers at the National Institute of Standards and Technology (NIST) and their colleagues at the University of Maryland have developed a step-by-step recipe to produce the atomic-scale devices. Using these instructions, the NIST-led team has become only the second in the world to construct a single-atom transistor and the first to fabricate a series of single electron transistors with…

[jonat941]

The world’s most advanced nanotube computer may keep Moore’s Law alive

The world’s most advanced nanotube computer may keep Moore’s Law alive

A team of academics at MIT has unveiled the world’s most advanced chip yet that’s made from carbon nanotubes—cylinders with walls the width of a single carbon atom. The new microprocessor, which is capable of running a conventional software program, could be an important milestone on the road to finding silicon alternatives. The electronics industry is struggling with a slowdown in Moore’s Law,…

[jonat941]

7 Types of Artificial Intelligence 2021

7 Types of Artificial Intelligence 2021

The rapid development and outstanding capabilities of AI have increased its necessity. AI is transforming every business vertical and giving tremendous benefits. This trend made AI technology as the most sought-after technology in the market. Also, a strong belief in the public that AI is near to reach its peak levels is expanding. Latest types of artificial intelligence will depict the…

[jonat941]

These five AI developments will shape 2021 and beyond

These five AI developments will shape 2021 and beyond

The year 2020 was profoundly challenging for citizens, companies, and governments around the world. As covid-19 spread, requiring far-reaching health and safety restrictions, artificial intelligence (AI) applications played a crucial role in saving lives and fostering economic resilience. Research and development (R&D) to enhance core AI capabilities, from autonomous driving and natural language…