Results 191 to 200 of about 1,851,693 (313)
This study presents a multitask strategy for plastic cleanup with autonomous surface vehicles, combining exploration and cleaning phases. A two‐headed Deep Q‐Network shared by all agents is traineded via multiobjective reinforcement learning, producing a Pareto front of trade‐offs.
Dame Seck +4 more
wiley +1 more source
Applying fairness in subnational carbon budget allocations. [PDF]
Lackner T +4 more
europepmc +1 more source
A Robotic Urinary Bladder Enabling Volume Monitoring and Assisted Micturition
An implantable robotic bladder is presented that can store urine in an origami‐designed enclosure. An inductance sensing principle can monitor and transfer the urine volume in real‐time. It can actively expand based on the amount of urine collected from kidneys and apply on‐demand mechanical compression to assist urination.
Izadyar Tamadon +4 more
wiley +1 more source
Deep brain stimulation for Parkinson's disease in Thailand: cost, utility and policy implications for universal health coverage. [PDF]
Aungsumart S +5 more
europepmc +1 more source
Review of Memristors for In‐Memory Computing and Spiking Neural Networks
Memristors uniquely enable energy‐efficient, brain‐inspired computing by acting as both memory and synaptic elements. This review highlights their physical mechanisms, integration in crossbar arrays, and role in spiking neural networks. Key challenges, including variability, relaxation, and stochastic switching, are discussed, alongside emerging ...
Mostafa Shooshtari +2 more
wiley +1 more source
Starting Up Clinical Trials in Emergency Medicine: Advice and Acronyms for New Investigators. [PDF]
Southerland LT +6 more
europepmc +1 more source
Quantization‐aware training creates resource‐efficient structured state space sequential S4(D) models for ultra‐long sequence processing in edge AI hardware. Including quantization during training leads to efficiency gains compared to pure post‐training quantization.
Sebastian Siegel +5 more
wiley +1 more source
A Framework for Budget-Constrained Zero-Day Cyber Threat Mitigation: A Knowledge-Guided Reinforcement Learning Approach. [PDF]
Basak M, Shin GY.
europepmc +1 more source
We address multilayer PCB anomaly detection for smart manufacturing by physical reservoir computing with HfO2‐based memristors. Crystallinity‐tuned HfO2 suppresses ferroelectricity while preserving the high‐k insulating state and confers strong short‐term memory.
Yongho Lee +7 more
wiley +1 more source

