Counting trees from space with artificial intelligence

Trees shape climate, biodiversity, rural livelihoods, and the global bioeconomy, yet many remain invisible to today’s large-scale monitoring systems. Most satellite products describe forests as broad ...
Business Wire

Toshiba Starts Sample Shipments of New “SmartMCD™” Series Product Integrating Microcontroller and Motor Driver

KAWASAKI, Japan--(BUSINESS WIRE)--Toshiba Electronic Devices & Storage Corporation (“Toshiba”) has started to ship engineering samples of “TB9M030FG,” the latest addition to its “SmartMCD™” [1] series ...
PNAS

Dual-encoder contrastive learning accelerates enzyme discovery

While nature has evolved enzymes to carry out a vast array of chemical transformations, selecting the ideal protein to initiate an enzyme engineering campaign often presents a significant challenge, ...
The Lancet

Artificial intelligence-based pathological model for pan-cancer lymph node metastasis detection: a multicentre diagnostic study with retrospective and prospective validation

dDepartment of Pathology, Zhujiang Hospital of Southern Medical University, Guangzhou, China eDepartment of Pathology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China ...
Frontiers

A comparative accuracy study of multimodal LLMs, VLM and agent-based framework for pulmonary nodule detection on chest radiographs

This study included 9 models: Llama 3.2 Vision 90B, Claude 3.5 Sonnet, Claude 3.7 Sonnet, Gemini 2.0 Pro Experimental, Perplexity, CXR-LLaVA, XrayGPT, BiomedCLIP, MedRAX. Each model determined ...
GitHub

selimsef/dfdc_deepfake_challenge

In general solution is based on frame-by-frame classification approach. Other complex things did not work so well on public leaderboard. MTCNN detector is chosen due to kernel time limits. It would be ...
Electronics Weekly

SPS 2025: 0.01°optical encoder IC

iC-Haus will demonstrate its latest 26bit resolution optical encoder IC at SPS next month in Nuremberg. iC-RT2624, as it will be known, is aimed at both housed and kit encoders, and will achieve its ...
Scientific Research Publishing

Graph Neural Networks for Anomaly Detection in Cloud Infrastructure ()

Cloud infrastructure anomalies cause significant downtime and financial losses (estimated at $2.5 M/hour for major services). Traditional anomaly detection methods fail to capture complex dependencies ...
PNAS

High-rate quantum key distribution with compact state preparation and detection

Practical quantum communication demands high performance without reliance on bulky or cryogenic hardware. We propose a single-step polarization- and intensity-encoding scheme together with an ...
IEEE

Research on Ship Anomaly Detection Algorithm Based on Transformer-GSA Encoder

Abstract: As global economies continue to expand, maritime trade is projected to double by the year 2050. In this context, the development of a new generation of maritime intelligent supervision ...
C&EN

QuanFormer: A Transformer-Based Precise Peak Detection and Quantification Tool in LC-MS-Based Metabolomics

State Key Laboratory of Cellular Stress Biology, Institute of Artificial Intelligence, School of Life Sciences, Faculty of Medicine and Life Sciences, National Institute for Data Science in Health and ...