Driver Behavior Modeling with Subjective Risk‐Driven Inverse Reinforcement Learning
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 +6 more
wiley +1 more source
A novel optimized fuzzy neural network for enhanced topology control in k-connected mobile adhoc networks. [PDF]
Agrawal SS, Rathi R, Siddiqui SA.
europepmc +1 more source
3D‐Printed Shark‐Inspired Soft–Hard Hybrid Underwater Robot With Buoyancy Control and Onboard Vision
A fully self‐contained shark‐inspired underwater robot is developed using 3D‐printed soft–hard hybrid structures, servo‐driven propulsion, and pump‐based buoyancy control. The platform achieves three‐dimensional locomotion and onboard vision‐based target tracking, offering a reproducible and accessible framework for biomimetic underwater robot research.
Shotaro Saito +3 more
wiley +1 more source
Hybrid fuzzy machine learning models optimized with meta-heuristics for accurate EEG-based neurological assessment. [PDF]
Lak M +4 more
europepmc +1 more source
HTFC gets 3D refractive index tomograms of flowing cells. Label‐free monocytes are engineered to express patterns of cytoplasmic vacuoles. From the tomogram, an efficient dimensionality reduction is operated. Interpretable features are extracted to classify the expression severity of phenotypes coexisting in each cell, visually represented by a seven ...
Marika Valentino +9 more
wiley +1 more source
Lightweight image encryption for wireless sensor networks using optimized elliptic curve and fuzzy logic. [PDF]
Zarei M +3 more
europepmc +1 more source
Neuromorphic Denoising with Fully Analog Memristive In‐Memory Computing
This article borrows the concepts of episodic memory in human brains to experimentally implement a memristor‐based neuromorphic denoising process. A homogeneous memristor processing unit is experimentally demonstrated for both temporal storage and neural network computation, imitating the synapses in the human brain.
Daijing Shi +5 more
wiley +1 more source
Trajectory Tracking Control for Subsea Mining Vehicles Based on Fuzzy PID Optimised by Genetic Algorithms. [PDF]
Bu H, Wu M, Liu B, Yan Z.
europepmc +1 more source
Complex dynamics, often avoided in electromechanical design, can enhance soft robotics. We develop durable magnetic soft actuators operating in tunable dynamic regimes, enabling random number generation, stochastic computing, and time‐series prediction.
Eduardo Sergio Oliveros‐Mata +14 more
wiley +1 more source
Assessment of influencing factors of college and universities' teaching effects using fuzzy and deep learning techniques. [PDF]
He Z, Zhang X, Zhang Z, Lin Y, Yu B.
europepmc +1 more source

