DfAI: The missing piece of artificial intelligence engineering
Jan 2023, phys.org
https://techxplore.com/news/2023-01-dfai-piece-artificial-intelligence.html
They don't mention digital twins but they should:
DfAI - Design for Artificial Intelligence
It's a data-rich process that captures intelligence throughout the lifecycle of the design, whether it's an airplane or an umbrella. But not enough companies are using it. This group says we need to raise AI literacy in industry, redesign engineering systems to better integrate with AI; and enhance the engineering AI development process.
And as robots take our jobs, they do tend to create new jobs in the process. Enter the "design repository curator".
via Carnegie Mellon University Mechanical Engineering and Re:Build Manufacturing: Glen Williams et al, Design for Artificial Intelligence: Proposing a Conceptual Framework Grounded in Data Wrangling, Journal of Computing and Information Science in Engineering (2022). DOI: 10.1115/1.4055854
Completely unrelated image credit: AI Art - Indian Man Sticking Artist Collection of Stickers on the Wall - 2022
How digital twins could protect manufacturers from cyberattacks
Feb 2023, phys.org
In addition to spotting routine indicators of wear and tear, digital twins could help find something more within manufacturing data, the authors of the study say."Because manufacturing processes produce such rich data sets -- temperature, voltage, current -- and they are so repetitive, there are opportunities to detect anomalies that stick out, including cyberattacks,"
via National Institute of Standards and Technology: E. C. Balta et al, Cyber-Attack Detection Digital Twins for Cyber-Physical Manufacturing Systems. IEEE Transactions on Automation Science and Engineering (2023). DOI: 10.1109/TASE.2023.3243147
Digital twin opens way to effective treatment of inflammatory diseases
Feb 2023, phys.org
In an inflammatory disease like rheumatoid arthritis, Crohn's disease or ulcerative colitis, thousands of genes alter the way they interact in different organs and cell types. Moreover, the pathological process varies from one patient to another with the same diagnosis, and even within the same patient at different times.Every physiological process can be described with mathematical equations [earlier they call them "molecular programs"]. This advanced digital modeling technique can be adjusted to a patient's unique circumstances by analyzing the activity of each and every gene in thousands of individual cells from blood and tissue. Such a digital twin can be used to calculate the physiological outcome if a condition changes, such as the dosage of a drug.In the current study, the researchers combined analyses of a mouse model of rheumatoid arthritis and digital twins of human patients with various inflammatory diseases.
"Even though only the joints were inflamed in mice, we found that thousands of genes changed their activity in different cell types in ten organs, including the skin, spleen, liver and lungs," says Dr. Benson. "As far as I'm aware, this is the first time science has obtained such a broad picture of how many organs are affected in rheumatoid arthritis. This is partly due to the difficulty of physically sampling so many different organs."
via Karolinska Institute Department of Clinical Science, Intervention and Technology: Mikael Benson, Multi-organ single cell analysis reveals an on/off switch system with potential for personalized treatment of immunological diseases, Cell Reports Medicine (2023). DOI: 10.1016/j.xcrm.2023.100956
Advances in brain modeling open a path to digital twin approaches for brain medicine
Mar 2023, phys.org
To create personalized brain models, the researchers use a simulation technology called The Virtual Brain (TVB), which HBP scientist Viktor Jirsa has developed together with collaborators. For each patient, the computational models are created from data of the individually measured anatomy, structural connectivity and brain dynamics.
via Human Brain Project and AMU Marseille: Viktor Jirsa et al, Personalised virtual brain models in epilepsy, The Lancet Neurology (2023). DOI: 10.1016/S1474-4422(23)00008-X
No comments:
Post a Comment