Results 181 to 190 of about 252,836 (257)

A privacy-preserving federated meta-learning framework for cross-project defect prediction in software systems. [PDF]

Sci Rep
Potharlanka JL, Shaik KY, N BK.
europepmc   +1 more source

Resource‐Aware Contrastive Scattering Meta‐Learning for Efficient Few‐Shot Acoustic Anomaly Detection

Advanced Intelligent Systems, EarlyView.
This paper introduces a resource‐aware Contrastive Scattering Meta‐Learning (CSML) framework for acoustic anomaly detection. By leveraging training‐free wavelet scattering and metric‐based meta‐learning, the model achieves competitive performance with only 50 K learnable parameters—a 98% reduction compared to state‐of‐the‐art frameworks—enabling ...
Rami Zewail, Bassem Mokhtar
wiley   +1 more source

A meta-learning framework to mitigate negative transfer in transfer learning applicable to drug design. [PDF]

Sci Rep
Mera A, Vogt M, Bajorath J.
europepmc   +1 more source

Design‐for‐Benchmarking in Soft Robotics: Navigating Component‐System Dichotomy

Advanced Intelligent Systems, EarlyView.
Soft robotics faces a profound evaluation challenge: the Component‐System Dichotomy, where isolated component tests fail to predict integrated performance. This article presents a systematic survey of critical reporting gaps across actuation, sensing, and control.
Matteo Lo Preti, Muhammad Sunny Nazeer, Josh Pinskier, David Howard, Cecilia Laschi   +4 more
wiley   +1 more source

A Meta-Learning-Based Ensemble Model for Explainable Alzheimer's Disease Diagnosis. [PDF]

Diagnostics (Basel)
Al-Bakri FH, Bejuri WMYW, Al-Andoli MN, Ikram RRR, Khor HM, Tahir Z, The Alzheimer's Disease Neuroimaging Initiative.   +6 more
europepmc   +1 more source

Generalized Task‐Driven Design of Soft Robots via Reduced‐Order Finite Element Method‐Based Surrogate Modeling

Advanced Intelligent Systems, EarlyView.
A unified, reusable modeling pipeline enables task‐driven design of soft robots across actuator families and task scenarios. High‐fidelity simulations are compressed into compact pseudo‐rigid‐body joint surrogates, while a design‐conditioned meta‐model generates new surrogates from geometry parameters without rerunning finite element method.
Yao Yao, David Howard, Perla Maiolino
wiley   +1 more source

Leveraging a Meta-Learning Strategy to Advance the Accuracy of Neutralizing Antibodies against Dengue Virus Serotype Prediction. [PDF]

ACS Omega
Charoenkwan P, Pipattanaboon C, Schaduangrat N, Mahmud SMH, Shoombuatong W.   +4 more
europepmc   +1 more source

A Two‐Stage Characterization Pipeline and Open‐Source Framework for Reproducible Tactile Sensing

Advanced Intelligent Systems, EarlyView.
The same soft tactile sensor returns different numbers when embodied in different robots. This is an Embodiment Gap that no shared framework currently captures transparently. A two‐stage characterization pipeline, paired with a FAIR open‐source digital datasheet, decouples intrinsic sensor behavior from embodiment effects and condenses cross‐laboratory
Matteo Lo Preti, Weng Buxiu, Petr Trunin, Muhammad Sunny Nazeer, Lucia Beccai, Perla Maiolino, Cecilia Laschi   +6 more
wiley   +1 more source

Partitioned RIS-Assisted Vehicular Secure Communication Based on Meta-Learning and Reinforcement Learning. [PDF]

Sensors (Basel)
Li H, Wang F, Qian J, Zhu P, Zhou A.
europepmc   +1 more source

Choice experiments on land managers' participation in environmental programs: A systematic review and meta‐analysis of estimate validity

American Journal of Agricultural Economics, EarlyView.
Abstract Discrete choice experiments are increasingly being used to estimate land managers' willingness to accept participation in incentive‐based environmental programs. This is a specific application of discrete choice experiments: the estimation of willingness to accept for a private good (program participation) where respondents have to make trade ...
Anastasio J. Villanueva, Angel Perni, Jesus Barreiro‐Hurle   +2 more
wiley   +1 more source