PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Novel machine learning-based cluster analysis method that leverages target material property

New cluster analysis technique for grouping materials based on both basic features and targeted properties

Novel machine learning-based cluster analysis method that leverages target material property
2024-08-06
(Press-News.org)

In materials science, substances are often classified based on defining factors such as their elemental composition or crystalline structure. This classification is crucial for advances in materials discovery, as it allows researchers to identify promising classes of materials and explore new ones with similar functions and properties. A recent Advanced Intelligent Systems study led by Researcher Nobuya Sato and Assistant Professor Akira Takahashi from Tokyo Institute of Technology developed a new machine learning-powered clustering technique. This technique groups similar materials by taking into account both their basic characteristics and target properties.

Advances in machine learning have made the classification process significantly less tedious and also opened up efficient ways of predicting materials with interesting properties based on basic features of chemical compositions and crystal structures. Cluster analysis, a commonly used machine-learning technique uses these basic features to not only categorize materials and summarize similarities between them but also provide information regarding relationships between materials belonging to the same group. While this represents significant progress toward discovering new materials with unique functionalities, conventional clustering techniques often fail to consider target material properties, such as band gaps and dielectric constants, which are related to these basic features.

But why is it important to include target properties for cluster analysis of materials?

Takahashi explains, “If we try to categorize semiconductors as per width of the band gap and investigate the chemical characteristics of respective categories, analyzing only with the target property wouldn’t provide the complete picture. Clustering in terms of the band gap may gather materials into a cluster where some gaps are determined by electronegativity while others are determined by features relevant to covalency. Conversely, using only basic features might not cluster materials that are similar in the property of interest. Hence, we need an approach that considers the relationship between basic features and target properties.”

To ensure the simultaneous inclusion of basic features and target properties, the researchers input the latter information into the clustering model by the random forest (RF) regression—a supervised learning algorithm that learns the relationship between the inputs and outputs to improve itself. The researchers trained the RF regression model to predict a given targeted property. Following this, the basic features were transformed into z-vectors—information based on the paths taken by the RF model. And finally, cluster analysis was performed on the transformed z-vectors.

This allowed the researchers to categorize more than 1,000 oxides into material groups based on their basic features like composition and crystal structure alongside target properties such as the formation energy, band gap, and electronic dielectric constant. While this study focused on only single target property cases, the researchers suggest that this new technique could be extended for grouping material based on multiple target properties. “Our method provides a unique viewpoint for clustering which emphasizes understanding and learning from the relationship between the target property and basic features thus providing unforeseen promising materials group and key factor for desirable material function, and accelerate discovery of new materials with fascinating properties,” concluded Takahashi.

 

###

About Tokyo Institute of Technology

Tokyo Tech stands at the forefront of research and higher education as the leading university for science and technology in Japan. Tokyo Tech researchers excel in fields ranging from materials science to biology, computer science, and physics. Founded in 1881, Tokyo Tech hosts over 10,000 undergraduate and graduate students per year, who develop into scientific leaders and some of the most sought-after engineers in industry. Embodying the Japanese philosophy of “monotsukuri,” meaning “technical ingenuity and innovation,” the Tokyo Tech community strives to contribute to society through high-impact research.

https://www.titech.ac.jp/english/

 

Institute of Science Tokyo (Science Tokyo) will be established on October 1, 2024, following the merger between Tokyo Medical and Dental University (TMDU) and Tokyo Institute of Technology (Tokyo Tech), with the mission of “Advancing science and human wellbeing to create value for and with society.”

https://www.isct.ac.jp/en

 

END


[Attachments] See images for this press release:
Novel machine learning-based cluster analysis method that leverages target material property

ELSE PRESS RELEASES FROM THIS DATE:

CT health screening can identify diabetes risk

2024-08-06
OAK BROOK, Ill. – Analysis of CT scans in people who undergo imaging for health screening can identify individuals at risk of type 2 diabetes, according to a study published today in Radiology, a journal of the Radiological Society of North America (RSNA). Researchers said the findings underscore CT’s value in opportunistic imaging—the use of information from routine imaging examinations to learn more about a patient’s overall health. For the new study, researchers evaluated the ability of automated CT-derived markers ...

AI model effective in detecting prostate cancer

AI model effective in detecting prostate cancer
2024-08-06
OAK BROOK, Ill. – A deep learning model performs at the level of an abdominal radiologist in the detection of clinically significant prostate cancer on MRI, according to a study published today in Radiology, a journal of the Radiological Society of North America (RSNA). The researchers hope the model can be used as an adjunct to radiologists to improve prostate cancer detection. Prostate cancer is the second most common cancer in men worldwide. Radiologists typically use a technique that combines different MRI sequences (called multiparametric MRI) to diagnose clinically significant prostate cancer. ...

Exposure to wildfire smoke may affect patients undergoing surgery

2024-08-06
CHICAGO – Nearly 100 wildfires are currently raging throughout the country, burning more than 2 million acres. The rising frequency of these fires poses a special concern for anesthesiologists – the potential for increased rates of adverse outcomes from anesthesia and surgery among patients exposed to wildfire smoke, according to a special article in the Online First edition of Anesthesiology, the peer-reviewed journal of the American Society of Anesthesiologists (ASA). "Wildfire smoke causes inflammation and is known to worsen heart and lung disease and pregnancy outcomes," said senior author Vijay Krishnamoorthy, M.D., M.P.H., Ph. D., chief of the Critical Care ...

Visiting an art exhibition can make you think more socially and openly. But for how long?

Visiting an art exhibition can make you think more socially and openly. But for how long?
2024-08-06
A new study by an international team of collaborators led by researchers at the University of Vienna, and in collaboration with the Dom Museum Wien, aimed to address the questions of whether art exhibitions can make us more empathic or even change our attitudes and behaviors? The researchers were able to show that, indeed, looking through the exhibition reduced xenophobia and increased acceptance of immigration. Even more, by employing a new cellphone-based experience sampling method, they could track how long ...

Heating for fusion: Why toast plasma when you can microwave it!

Heating for fusion: Why toast plasma when you can microwave it!
2024-08-06
Some believe the future of fusion in the U.S. lies in compact, spherical fusion vessels. A smaller tokamak, it is thought, could offer a more economical fusion option. The trick is squeezing everything into a small space. New research suggests eliminating one major component used to heat the plasma, freeing up much-needed space. Scientists at the U.S. Department of Energy’s (DOE) Princeton Plasma Physics Laboratory (PPPL), the private company Tokamak Energy and Kyushu University in Japan have proposed a design for a compact, spherical fusion pilot plant ...

Nudges fail to motivate vaccination

2024-08-06
One popular strategy to motivate people to get vaccinated is the nudge—a message designed to take advantage of human tendencies to conform to social norms, seek to protect loved ones or community, and to prefer treatments with high efficacy rates. Jiseon Chang and colleagues sought to assess the efficacy of such nudges in real world contexts during the COVID-19 pandemic. The authors paid for ads to appear on Facebook between October 2021 and January 2022, reaching almost 15 million users in Brazil, Russia, South Africa, Taiwan, ...

Caregiving: Poll reveals who’s providing care and who they’re caring for

Caregiving: Poll reveals who’s providing care and who they’re caring for
2024-08-06
More than 1 in 4 people age 50 and older helps take care of at least one family member or friend who has a health problem or disability, a new poll finds. And among those caregivers, the new results from the University of Michigan National Poll on Healthy Aging reveal a lot about who they are and who they’re caring for. In all, 30% of all people in their 50s and early 60s provide care to at least one person with a health issue or disability, compared with 23% of people over 65. And 1 in 10 caregivers in their 50s and early 60s are juggling taking care of three or more people. In ...

To predict tax revenue, look at corporate earnings

2024-08-06
To Predict Tax Revenue, Look at Corporate Earnings States can make more accurate budget forecasts and avoid midyear cuts if they include growth in corporate earnings AUSTIN, Texas -- In the complex task of building a state budget, much rides on the accuracy of its fiscal crystal ball: its forecast of how much tax revenue will come in to fund services during the year ahead. Forecasting errors have increased since 2001 due to revenue volatility, such as wider swings in personal income and consumer spending. New research from Texas ...

New visual technique could advance early detection of neurodegenerative diseases

New visual technique could advance early detection of neurodegenerative diseases
2024-08-06
MINNEAPOLIS / ST. PAUL (08/06/2024) — Researchers at the University of Minnesota, have developed a new visual diagnostic technique that can be used to advance early detection for neurodegenerative diseases like Parkinson's disease and similar diseases that affect animals, including Chronic Wasting Disease in deer.  The research is published in npj Biosensing, a peer-reviewed scientific journal published by Nature.  Named Cap-QuIC (Capillary-enhanced Quaking-Induced Conversion), researchers will now be able to distinguish infected samples with the naked eye, which makes testing ...

ALS diagnosis and survival linked to metals in blood, urine

2024-08-06
People with higher levels of metals found in their blood and urine may be more likely to be diagnosed with — and die from — amyotrophic lateral sclerosis, or ALS, a University of Michigan-led study suggests. Researchers have known that ALS, a rare but fatal neurodegenerative condition, is influenced by genetic and environmental factors, including exposure to pesticides and metals. This latest study examined the levels of metals in the blood and urine of people with and without ALS, finding that exposure to individual and mixtures of metals is associated with a greater risk for ALS and shorter survival. The ...

LAST 30 PRESS RELEASES:

Slow editing of protein blueprints leads to cell death

Industrial air pollution triggers ice formation in clouds, reducing cloud cover and boosting snowfall

Emerging alternatives to reduce animal testing show promise

Presenting Evo – a model for decoding and designing genetic sequences

Global plastic waste set to double by 2050, but new study offers blueprint for significant reductions

Industrial snow: Factories trigger local snowfall by freezing clouds

Backyard birds learn from their new neighbors when moving house

New study in Science finds that just four global policies could eliminate more than 90% of plastic waste and 30% of linked carbon emissions by 2050

Breakthrough in capturing 'hot' CO2 from industrial exhaust

New discovery enables gene therapy for muscular dystrophies, other disorders

Anti-anxiety and hallucination-like effects of psychedelics mediated by distinct neural circuits

How do microbiomes influence the study of life?

Plant roots change their growth pattern during ‘puberty’

Study outlines key role of national and EU policy to control emissions from German hydrogen economy

Beloved Disney classics convey an idealized image of fatherhood

Sensitive ceramics for soft robotics

Trends in hospitalizations and liver transplants associated with alcohol-induced liver disease

Spinal cord stimulation vs medical management for chronic back and leg pain

Engineered receptors help the immune system home in on cancer

How conflicting memories of sex and starvation compete to drive behavior

Scientists discover ‘entirely unanticipated’ role of protein netrin1 in spinal cord development

Novel SOURCE study examining development of early COPD in ages 30 to 55

NRL completes development of robotics capable of servicing satellites, enabling resilience for the U.S. space infrastructure

Clinical trial shows positive results for potential treatment to combat a challenging rare disease

New research shows relationship between heart shape and risk of cardiovascular disease

Increase in crisis coverage, but not the number of crisis news events

New study provides first evidence of African children with severe malaria experiencing partial resistance to world’s most powerful malaria drug

Texting abbreviations makes senders seem insincere, study finds

Living microbes discovered in Earth’s driest desert

Artemisinin partial resistance in Ugandan children with complicated malaria

[Press-News.org] Novel machine learning-based cluster analysis method that leverages target material property
New cluster analysis technique for grouping materials based on both basic features and targeted properties