Results 201 to 210 of about 214,906 (281)

Deformable Attention Multiscale Feature Fusion Network‐Dehaze: An Adaptive Image Dehazing Method Based on Deformable Attention Multiscale Fusion Network

Advanced Intelligent Systems, EarlyView.
This paper presents the deformable attention multiscale feature fusion network‐dehaze adaptive image dehazing network, which integrates three core modules (revised residual shrinkage unit, multiscale attention, cross‐scale feature fusion). It incorporates deformable convolution and multiscale attention mechanisms to address the detail loss issue of ...
Ruipeng Wang, Yajun Chen, Hao Liu, Mingrui Li, Zhiqi Li   +4 more
wiley   +1 more source

Track-to-Track Fusion for Cooperative Perception Using Collective Perception Messages. [PDF]

Sensors (Basel)
Castelino RM, Pradhan S, Hahn A.
europepmc   +1 more source

System Identification of Robotic Fish Swimming Reveals Roles of Reactive and Resistive Fluid Force in Two Distinct Swimming Gaits

Advanced Intelligent Systems, EarlyView.
System identification and particle image velocimetry reveal how a modular robotic fish changes thrust physics across gaits. A traveling‐wave, fish‐like motion draws thrust from resistive drag, while a resonant standing‐wave motion is driven by reactive pressure.
Donghao Li, Hankun Deng, Kundan Panta, Azar Panah, Bo Cheng   +4 more
wiley   +1 more source

A Soft Robotic Jellyfish with Decoupled Actuators for Agile 3D Locomotion

Advanced Intelligent Systems, EarlyView.
This study presents a soft robotic jellyfish featuring a functionally decoupled actuation architecture. By separating propulsion, steering, and vertical regulation into independent modules, the robot overcomes conventional coupled‐motion limitations. Utilizing a passive‐valve‐based differential drag strategy and lateral water jets, it achieves agile 3D
Zhuoheng Li, Ze Huang, Salvador Pané, Josep Puigmartí‐Luis, Jiwan Kim, Ji‐Hun Bae, Bumjin Jang   +6 more
wiley   +1 more source

Breaking through safety performance stagnation in autonomous vehicles with dense learning. [PDF]

Nat Commun
Feng S, Zhu H, Sun H, Yan X, He L, Yang J, Su G, Li B, Li S, Wang L, Shen S, Liu HX.   +11 more
europepmc   +1 more source

Shapley Additive Explanation for Local Class Differentiation: Local Explainability for Class Differentiation in Classification Models

Advanced Intelligent Systems, EarlyView.
An instance‐level, model‐agnostic explanation of class differentiation is introduced through SHAP‐LCD, linking probability shifts to feature‐wise Shapley contributions. The method operates on tabular and image data and is released in a fully reproducible implementation, offering a transparent way to examine, at each instance, why predictive models ...
Roxana M. Romero Luna, Hugo A. Ordoñez Erazo, Carlos A. Cobos Lozada   +2 more
wiley   +1 more source

Vehicle driving area detection and sensor data preprocessing based on deep learning. [PDF]

PLoS One
Zhou J, Xu N, Wu X.
europepmc   +1 more source

Driver Behavior Modeling with Subjective Risk‐Driven Inverse Reinforcement Learning

Advanced Intelligent Systems, EarlyView.
A subjective risk‐driven inverse reinforcement learning framework is proposed to model driver decision‐making. It infers drivers' risk perception and risk tolerance from driving data. A learnable risk threshold is used to regulate decisions, enabling interpretable and human‐like driving behavior decisions.
Yang Liang, Zichao Wang, Zhiwei He, Qingquan Wei, Yong Zuo, Linzhen Nie, Zhishuai Yin   +6 more
wiley   +1 more source

A Mixture of Experts Model for Third-Party Pipeline Intrusion Detection Using DAS. [PDF]

Sensors (Basel)
Zhu S, Fu M, Zhang H, Jiao H, Zhao Y, Wu Z, Wang H, Song B.   +7 more
europepmc   +1 more source