Results 171 to 180 of about 324,181 (265)

A new two-parameter family of discrete distributions. [PDF]

open access: yesHeliyon
Haddari A, Zeghdoudi H, Pakyari R.
europepmc   +1 more source

Forecasting Research Trends Using Knowledge Graphs and Large Language Models

open access: yesAdvanced Intelligent Systems, EarlyView.
When research trends can be anticipated, academia and industry are able to allocate limited resources more effectively and accelerate innovation. By constructing knowledge graphs using large language models, this study analyzes the time evolution of nuclear materials research concepts and suggests a data‐driven approach of forecasting research trends ...
Maciej Tomczak   +7 more
wiley   +1 more source

CoRoFR: Community Detection of Feature Graph Improves Feature Selection Using Robust Fuzzy Rough Set

open access: yesAdvanced Intelligent Systems, EarlyView.
In machine learning, features often function as communities in many tasks, especially in medicine. However, existing feature selection methods struggle to mine feature collaborations, which can boost predictive performance. Moreover, they are noise‐sensitive, leading to suboptimal feature selection and accuracy degradation.
Duanyang Feng   +4 more
wiley   +1 more source

BCFW tilings and cluster adjacency for the amplituhedron. [PDF]

open access: yesProc Natl Acad Sci U S A
Even-Zohar C   +5 more
europepmc   +1 more source

Enhanced Embolic Signal Analysis through Ensemble Deep Learning Techniques Utilizing Transfer Learning and Layer Freezing Strategies

open access: yesAdvanced Intelligent Systems, EarlyView.
A 10‐convolutional neural network ensemble using transfer learning and layer freezing analyzes 400 Doppler‐ultrasound spectrograms to distinguish speckle, artifact, and ESs. Soft and hard voting drive performance to 96.7% accuracy and 96.5% F1, highlighting a practical route for early embolus detection and stroke‐risk mitigation.
M. Ikbal Karadeli   +3 more
wiley   +1 more source

MO‐hHHO: Multi‐Objective Hybrid Harris Hawks Optimization for Prediction of Coronary Artery Disease

open access: yesAdvanced Intelligent Systems, EarlyView.
This article proposes a novel Multi‐Objective hybrid Harris Hawks Optimization (MO‐hHHO) algorithm for simultaneous feature selection and hyperparameter tuning in heart disease classification. The approach leverages adaptive exploration‐exploitation strategies to enhance convergence efficiency.
Anu Ragavi Vijayaraj   +1 more
wiley   +1 more source

Symbolic Reservoir Computing within Memristive Crossbar Arrays as a Cellular Automata

open access: yesAdvanced Intelligent Systems, EarlyView.
In quest of a neuro‐symbolic system with both strong intelligent computing capability and better explainability, a memristor crossbar array‐based cellular automata (symbolic model) for reservoir computing (neural network) is proposed and experimentally demonstrated using an algorithm–hardware codesign approach.
Yunpeng Guo   +8 more
wiley   +1 more source

Home - About - Disclaimer - Privacy