News

EurekAlert!
eurekalert.org > news-releases > 1112757

AI-based prediction of train-induced environmental vibration with limited measurements

3+ hour, 31+ min ago   (380+ words) This study presents a transfer learning'based method for predicting train-induced environmental vibration. The method applies data fusion to combine physics-based numerical simulations and limited measurement data within a neural network. It reduces the heavy reliance of conventional machine learning'based models…...

EurekAlert!
eurekalert.org > news-releases > 1109671

New machine learning method refines peach fruit quality trait analysis

1+ mon, 4+ day ago   (627+ words) This study leverages advanced genomics and machine learning to refine the understanding of key fruit quality traits in peaches. Using whole-genome resequencing data from an F1 progeny of two distant peach cultivars, the researchers constructed an ultra-high-density genetic map, identifying key…...

EurekAlert!
eurekalert.org > news-releases > 1105852

American Physical Society to launch new open access journal on AI and machine learning in scientific research

1+ mon, 3+ week ago   (192+ words) PRX Intelligence will publish high-impact research on artificial intelligence and machine learning that advances the physical sciences image:The American Physical Society is launching PRX Intelligence, a highly selective open access journal that will welcome manuscripts on AI and machine…...

EurekAlert!
eurekalert.org > news-releases > 1106327

Artificial intelligence can improve psychiatric diagnosis

Artificial intelligence can improve psychiatric diagnosis1+ mon, 3+ week ago   (218+ words) Using large language models (LLMs) is one approach to analysing language-mediated illness descriptions. The team used the LLMs GPT-3, Llama and BERT to analyse both the structure and content of four clinical questionnaires. The study was based on data from…...

EurekAlert!
eurekalert.org > news-releases > 1105628

Causal machine learning reveals the impact of renewables on electricity prices

2+ mon, 2+ day ago   (135+ words) image:Comparison of raw correlations (dashed) and causal effects (solid) of wind on UK day-ahead prices. Lines show the price change (GBP/MWh) from +1 GWh of predicted wind for the delivery hour across penetration levels; shading shows 80% CIs. Results reveal…...

EurekAlert!
eurekalert.org > news-releases > 1104511

Machine learning identify promising COFs for helium purification.

2+ mon, 1+ week ago   (283+ words) Credit: Zenan Shi, et al. Helium is a valuable gas that plays crucial roles in a large variety of modern industry or scientific research, including low-temperature superconductivity, nuclear magnetic resonance, semiconductor manufacturing, and aerospace applications. It is extremely scarce and…...

EurekAlert!
eurekalert.org > news-releases > 1104464

Machine learning takes biochar dye cleanup to the next level

2+ mon, 1+ week ago   (378+ words) Credit: Chong Liu, Paramasivan Balasubramanian, Xuan Cuong Nguyen, Jingxian An, Sai Praneeth, Pengyan Zhang & Haiming Huang Industrial dyes used in textiles, plastics, paper, and cosmetics make wastewater vividly colored and potentially toxic. Many of these dyes resist normal treatment, threatening…...

EurekAlert!
eurekalert.org > news-releases > 1100559

Order from disordered proteins

3+ mon, 1+ week ago   (536+ words) Researchers at Harvard and Northwestern have developed a machine learning method that can design intrinsically disordered proteins with custom properties, addressing nearly 30% of all human proteins that are currently out of reach of AI tools like AlphaFold. The new approach…...

EurekAlert!
eurekalert.org > news-releases > 1100120

Machine learning sharpens earthquake risk assessment maps for Tokyo

3+ mon, 2+ week ago   (147+ words) Researchers train a model to accurately predict soil properties and the risk of soil liquefaction in high-resolution 3D maps image:This map depicts the predicted types of soil in Tokyo with an unprecedented level of detail. Such maps are essential for…...

EurekAlert!
eurekalert.org > news-releases > 1100071

Multi-omics machine learning can detect ALS 10 years before symptom appears

3+ mon, 2+ week ago   (782+ words) image:Multi-Omics Mechine Learning Can Detect ALS 10 Years Before Symptom Appears view more Anew studyapplying multi-omics techniques and machine learning identified 33 plasma proteins that differ significantly in patients with amyotrophic lateral sclerosis (ALS). The findings suggest ALS could be detected…...