Results 111 to 120 of about 8,673 (229)
An adaptive multi-scale spatio-temporal graph network for robust MOOC dropout prediction. [PDF]
Duan Y, Chen X.
europepmc +1 more source
We present a novel AI‐integrated implantation‐on‐chip platform that enables mimicking and monitoring the maternal–fetal interactions at the early phases of human embryo implantation with high spatiotemporal resolution. The complexity of the trophoblast invasion process was addressed by conducting the analysis at global (rate of invasion) and local ...
Joanna Filippi +12 more
wiley +1 more source
Dynamic Graph Neural Network for Vehicle Trajectory Prediction and Driving Intent Recognition. [PDF]
Wu S, Wang Y, Gong Y.
europepmc +1 more source
Learning Time Embedding for Temporal Knowledge Graph Completion
Jinglu Chen +4 more
openaire +1 more source
Human‐in‐the‐Loop Swarms: A Bionic Swarm Approach to Real‐World Soil Mapping
This article introduces the “Bionic Swarm,” a novel system that lowers the barriers to real‐world swarm validation by abstracting difficult hardware tasks to app‐guided human agents. We demonstrate the system's utility through the experimental validation of a geotechnical soil‐mapping swarm algorithm and show superior performance to baseline approaches
Petras Swissler +5 more
wiley +1 more source
Transforming oncology clinical trial matching through neuro-symbolic, multi-agent AI and an oncology-specific knowledge graph: a prospective evaluation in 3804 patients. [PDF]
Loaiza-Bonilla A +6 more
europepmc +1 more source
Cteno‐Bot: An Untethered Metachronally Swimming Robot With Magnetoactive Propulsors
We present Cteno‐bot, an untethered ctenophore‐inspired robot which swims using metachronally coordinated appendages. A single mechanism controls up to 216 magnetoactive propulsors via a dynamically varying magnetic field. We show that the swimming speed of the robot can be increased without a corresponding increase in power requirement, simply by ...
David J. Peterman, Margaret L. Byron
wiley +1 more source
An agentic AI‐driven decision‐support framework for prosumers is proposed, integrating PV generation, load profiling, and multihorizon optimization within a four‐agent architecture. The approach significantly reduces grid dependence, enhances self‐sufficiency and prevents system oversizing.
Adela BÂRA, Simona‐Vasilica OPREA
wiley +1 more source
Physics-guided contrastive temporal graph learning for anomaly detection and root-cause localization in industrial control systems. [PDF]
Rajalakshmi M, Velmurugan T.
europepmc +1 more source
The phase discontinuity problem—where the cyclic nature of phase angles causes catastrophic errors near the ±π boundary—is a fundamental obstacle in learning‐based reconfigurable intelligent surface (RIS) optimization. A phase‐aware hybrid CNN–LSTM framework resolves this by decomposing phase predictions into sine–cosine components, mapping circular ...
Seda Savaşçı Şen +3 more
wiley +1 more source

