Results 231 to 240 of about 121,464 (311)

Multivariate Contrastive Predictive Coding with Sliding Windows for Disease Prediction from Electronic Health Records

open access: yesAdvanced Intelligent Systems, EarlyView.
Adaptive multi‐indicator contrastive predictive coding is introduced as a self‐supervised pretraining framework for multivariate EHR time series. An adaptive sliding‐window algorithm and 2D convolutional neural network encoder capture localized temporal patterns and global indicator dependencies, enabling label‐efficient disease prediction that ...
Hongxu Yuan   +3 more
wiley   +1 more source

Optisense: Computational Optimization for Strain Sensor Placement in Wearable Motion Tracking Systems

open access: yesAdvanced Intelligent Systems, EarlyView.
A computational framework for optimizing strain sensor placement in wearable motion tracking systems is presented. By combining dense strain mapping with a genetic algorithm, the method discovers counterintuitive yet highly effective configurations that reduce joint angle error by 32%.
Minu Kim   +4 more
wiley   +1 more source

Dual Entropy Source Physical Unclonable Functions of Reconfigurable Feedback Field‐Effect Transistors with Polycrystalline Silicon Channels

open access: yesAdvanced Intelligent Systems, EarlyView.
Physically unclonable functions (PUFs) of reconfigurable feedback field‐effect transistors (R‐FBFETs) with polycrystalline silicon channels are designed for dual entropy sources. The uniqueness and reliability of the dual entropy source PUF are verified by inter‐ and intra‐Hamming distances of 49.13% and 3.47%, respectively, as well as NIST statistical
Taeho Park   +4 more
wiley   +1 more source

QS4D: Quantization‐Aware Training for Efficient Hardware Deployment of Structured State‐Space Sequential Models

open access: yesAdvanced Intelligent Systems, EarlyView.
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

Bio‐to‐Robot Transfer of Fish Sensorimotor Dynamics via Interpretable Model

open access: yesAdvanced Intelligent Systems, EarlyView.
This study demonstrates how a biologically interpretable model trained on real‐fish muscle activity can accurately predict the motion of a robotic fish. By linking real‐fish sensorimotor dynamics with robotic fish, the work offers a transparent, data‐efficient framework for transferring biological intelligence to bioinspired robotic systems.
Waqar Hussain Afridi   +6 more
wiley   +1 more source

Home - About - Disclaimer - Privacy