Results 181 to 190 of about 11,251,274 (296)

Integrating Reinforcement Learning With Explainable Artificial Intelligence for Real‐Time Clinical Decision Support in Dynamic Healthcare Environments

open access: yesAdvanced Intelligent Systems, EarlyView.
A hybrid Reinforcement Learning–Explainable AI framework integrates SHAP and LIME explanations directly into a Deep Q‐Network inference loop for real‐time ICU decision support. Trained on 18 142 mechanically ventilated stays from the eICU database, the system attains 93.0% decision accuracy, 20% fewer errors than RL alone, and a 91% clinician trust ...
Jannatul Ferdaus Disha   +2 more
wiley   +1 more source

Contact Force Estimation in Human–Robot Collaboration: A Case Study on Heavyweight Robotic Manipulators

open access: yesAdvanced Intelligent Systems, EarlyView.
The method presented in this paper provides a practical sensorless solution for estimating both contact force and contact location using only standard joint encoders and an available robot dynamic model. By reformulating the contact estimation problem using a single scalar equivalent contact parameter, the approach enables fast and robust computation ...
Thanh‐Quan Ta, Shyh‐Leh Chen
wiley   +1 more source

Ecoefficiency Analysis and Regression in Data Conversion for Spiking Neural Network Training

open access: yesAdvanced Intelligent Systems, EarlyView.
The environmental footprint of spiking neural networks is quantified during dataset encoding and training for autonomous driving regression across three benchmarks. Temporal depth emerges as the dominant driver of energy consumption and CO2 emissions, while the accuracy–energy trade‐off proves dataset‐dependent. On conventional hardware, spiking models
Fernando S. Martínez   +3 more
wiley   +1 more source

A Soft Robotic Finger With Deep Learning‐Enhanced Tactile Sensing for Texture and Softness Recognition

open access: yesAdvanced Intelligent Systems, EarlyView.
Inspired by human touch, a tendon‐driven soft robotic finger combines multimodal tactile sensing and deep learning to simultaneously perceive texture and softness on deformable surfaces. A CNN‐LSTM model fuses pressure, accelerometer, and gyroscope signals to accurately classify material properties, achieving up to 95.4% texture and 97.0% softness ...
Gorkem Anil Al   +3 more
wiley   +1 more source

Benchmarking Data‐Driven Control of Octopus‐Inspired Soft Arms in Underwater Environment

open access: yesAdvanced Intelligent Systems, EarlyView.
Underwater soft robots present safe, compliant interaction, yet reproducible control remains scarce. This work presents an open benchmark for octopus‐inspired arms: a smooth, velocity‐diverse data‐collection scheme produces a compact dataset to train a vanilla policy.
Muhammad Sunny Nazeer   +6 more
wiley   +1 more source

Home - About - Disclaimer - Privacy