New apps help researchers with statistical analyses of data

1 week 3 days ago
It's a sign of the times: an app store for omics enthusiasts. The Multi-Omics Analysis Portal (MAP) by the end of 2024 will be a one-stop shop for computer applications capable of making sense of various and vast omics data. Genomics, proteomics, lipidomics, transcriptomics—all are welcome.

New code mines microscopy images in scientific articles

2 weeks 3 days ago
Deep learning is a form of artificial intelligence transforming society by teaching computers to process information using artificial neural networks that mimic the human brain. It is now used in facial recognition, self-driving cars and even in the playing of complex games like Go. In general, the success of deep learning has depended on using large datasets of labeled images for training purposes.

NASA noise prediction tool supports users in air taxi industry

3 weeks 1 day ago
Several air taxi companies are using a NASA-developed computer software tool to predict aircraft noise and aerodynamic performance. This tool allows manufacturers working in fields related to NASA's Advanced Air Mobility mission to see early in the aircraft development process how design elements like propellors or wings would perform. This saves the industry time and money when making potential design modifications.

Engineers and OpenAI recommend ways to evaluate large language models for cybersecurity applications

3 weeks 4 days ago
Carnegie Mellon University's Software Engineering Institute (SEI) and OpenAI published a white paper that found that large language models (LLMs) could be an asset for cybersecurity professionals, but should be evaluated using real and complex scenarios to better understand the technology's capabilities and risks. LLMs underlie today's generative artificial intelligence (AI) platforms, such as Google's Gemini, Microsoft's Bing AI, and ChatGPT, released in November 2022 by OpenAI.

Introducing Floorlocator, a system that enhances indoor navigation

1 month ago
Indoor positioning is transforming with applications demanding precise location tracking. Traditional methods, including fingerprinting and sensor-based techniques, though widely used, face significant drawbacks, such as the need for extensive training data, poor scalability, and reliance on additional sensor information. Recent advancements have sought to leverage deep learning, yet issues such as low scalability and high computational costs remain unaddressed.

Researchers develop new control method that optimizes autonomous ship navigation

1 month 1 week ago
The study of ship maneuvering at sea has long been the central focus of the shipping industry. With the rapid advancements in remote control, communication technologies, and artificial intelligence, the concept of Maritime Autonomous Surface Ships (MASS) has emerged as a promising solution for autonomous marine navigation. This shift highlights the growing need for optimal control models for autonomous ship maneuvering.

Using generative AI to improve software testing

1 month 3 weeks ago
Generative AI is getting plenty of attention for its ability to create text and images. But those media represent only a fraction of the data that proliferate in our society today. Data are generated every time a patient goes through a medical system, a storm impacts a flight, or a person interacts with a software application.

Optimal shipping carton utilization

1 month 3 weeks ago
Products ordered online are often shipped in oversized cartons. The size of the overall package is frequently much larger than its contents. For example, a fragrance bottle is shipped in a shoebox-sized package, which has padding to fill the empty space. This is not sustainable.
Checked
3 days ago
The latest news on the software, software development, software sciences and computer science.
Subscribe to Phys.org feed