no code implementations • 25 Feb 2024 • Mengen Luo, Ercan Engin Kuruoglu
Federated learning's poor performance in the presence of heterogeneous data remains one of the most pressing issues in the field.
no code implementations • 25 Feb 2024 • Mengen Luo, Chi Xu, Ercan Engin Kuruoglu
Performance degradation owing to data heterogeneity and low output interpretability are the most significant challenges faced by federated learning in practical applications.
Out of Distribution (OOD) Detection Personalized Federated Learning
no code implementations • 27 Jan 2024 • Yi Yan, Changran Peng, Ercan Engin Kuruoglu
The LMS-GNN is a combination of adaptive graph filters and Graph Neural Networks (GNN).
no code implementations • 18 Nov 2023 • Junping Hong, Ercan Engin Kuruoglu
Bayesian neural networks use random variables to describe the neural networks rather than deterministic neural networks and are mostly trained by variational inference which updates the mean and variance at the same time.
no code implementations • 12 Nov 2023 • Radwa Adel, Ercan Engin Kuruoglu
In this study, we used graph frequency analysis of cancer genetic signals defined on a co-expression network to describe the spectral properties of underlying cancer systems.
no code implementations • 1 Nov 2023 • Yi Yan, Ercan Engin Kuruoglu
The processing of signals on graph edges is challenging considering that Graph Signal Processing techniques are defined only on the graph nodes.
no code implementations • 1 Oct 2023 • Fengfan Zhao, Ercan Engin Kuruoglu
An increasingly important brain function analysis modality is functional connectivity analysis which regards connections as statistical codependency between the signals of different brain regions.
no code implementations • 7 Jun 2023 • Mutong Li, Ercan Engin Kuruoglu
This article introduces a novel probability distribution model, namely Complex Isotropic {\alpha}-Stable-Rician (CI{\alpha}SR), for characterizing the data histogram of synthetic aperture radar (SAR) images.
no code implementations • 8 Mar 2023 • Mutong Li, Ercan Engin Kuruoglu
SAR technology has been intensively implemented for geo-sensing and mapping purposes due to its advantages of high azimuthal resolution and weather-independent operation compared to other remote sensing technologies.
no code implementations • 1 Mar 2022 • Yi Yan, Radwa Adel, Ercan Engin Kuruoglu
In this paper, we introduce an adaptive graph normalized least mean pth power (GNLMP) algorithm for graph signal processing (GSP) that utilizes GSP techniques, including bandlimited filtering and node sampling, to estimate sampled graph signals under impulsive noise.
no code implementations • 29 Sep 2021 • Chun Lin Kuo, Ercan Engin Kuruoglu, Wai Kin Victor Chan
In this work, we reduce network complexity by pruning and structure optimization.