Results 191 to 200 of about 283,349 (325)
This study presents a robot‐assisted remote rehabilitation system for postoperative ankle fractures. The 2.634 kg modular system uses wireless control and deep learning to predict force delays, achieving 100 Hz control (normalized root mean square error ≤ 10.89%).
Zhiyuan He +4 more
wiley +1 more source
Enhanced significant wave height prediction in the Southern Ocean using an ANFIS model optimized with subtractive clustering. [PDF]
Hakimi A, Farjami H.
europepmc +1 more source
Cyclic Proofs for Linear Temporal Logic [PDF]
Kokkinis Ioannis, Studer Thomas
openaire +3 more sources
Haptic Perception via the Dynamics of a Flexible Body Inspired by an Ostrich's Neck
Inspired by avian anatomy, this study uses a flexible robotic neck to investigate haptic perception driven by musculoskeletal dynamics. By applying physical reservoir computing, the robot encodes external force interactions into its body dynamics, allowing effective object classification.
Kazashi Nakano +3 more
wiley +1 more source
A hybrid deep learning and fuzzy logic framework for feature-based evaluation of english Language learners. [PDF]
Zhao X.
europepmc +1 more source
Synthesis of Real-Time Observers from Past-Time Linear Temporal Logic and Timed Specification
Charles Lesire +3 more
openalex +2 more sources
Memristive Chaotic Circuit for Information Processing Through Time
A chaotic circuit that exploits the nonlinear characteristics of a memristive device is realized in hardware. The circuit response evolves through simple periodic, multiperiod, and chaotic regimes. The circuit also displays fading memory property. Finally, the circuit is used in a reservoir computing architecture to demonstrate nonlinear classification
Manuel Escudero +2 more
wiley +1 more source
Myelin-Proteinoids Interactions in Neural Signaling. [PDF]
Mougkogiannis P, Adamatzky A.
europepmc +1 more source
Real‐Time and Rapid Dynamic Missile Identification Utilizing a TiOx Memristor Array
Real‐time missile target identification is demonstrated using an artificial intelligence model based on step‐weighted long–short‐term memory networks and a TiOx memristor array. The approach classifies five projectile types with enhanced early‐stage prediction through data augmentation and custom training strategies. Achieving 94.4% accuracy, the model
Mingyu Kim, Gwanyeong Park, Gunuk Wang
wiley +1 more source

