Researchers have built a deep reinforcement learning system called HE-FDDQN that personalizes college students' physical training with 92.5 percent accuracy...

Researchers converted millions of LendingClub loan records into structure-aware grayscale images and showed that a hybrid convolutional neural network and...

Researchers combined UV–Vis–NIR spectroscopy with machine learning and metaheuristic wavelength selection to detect toxic para-phenylenediamine adulteration in henna non-destructively.

Researchers have developed a dual-stream convolutional neural network that fuses RGB imagery with vectorized Error Level Analysis and CBAM attention...

Researchers at Yunnan University have developed SFMD-Net, a DINOv3-based AI framework that fuses semantic and frequency features to detect small,...

A new classifier called CABLE-kNN caches local neighborhood evidence during training and neutralizes class priors, beating ordinary kNN on imbalanced...

An agent-based simulation of a tourism platform ecosystem shows that AI interventions significantly raise visitor spending and numbers but fail...

Researchers have built a lightweight AI system that detects epileptic seizures in EEG recordings from patients it has never seen,...

A hybrid AI model that reasons about park spaces as interconnected graphs before generating images produces urban green space layouts...

Researchers have developed MuHP-DLNet, a multi-stage deep learning network with a damage-aware dynamic loss that improves the detection and segmentation...