Federated learning based non-invasive human activity recognition using channel state information
AR Khan, SM Bokhari, S Sohaib… - Available at SSRN …, 2023 - papers.ssrn.com
This paper proposes a privacy-aware indoor human activity recognition (HAR) using
federated learning (FL-HAR). To overcome privacy and communication costs issues, FL …
federated learning (FL-HAR). To overcome privacy and communication costs issues, FL …
Landmark based Outliers Detection in Pervasive Applications
K Kolomvatsos… - 2021 12th International …, 2021 - ieeexplore.ieee.org
The combination of the Internet of Things and the Edge Computing gives many opportunities
to support innovative applications close to end users. Numerous devices present in both …
to support innovative applications close to end users. Numerous devices present in both …
Proactive Attack Detection at the Edge through an Ensemble Deep Learning Model
P Fountas, M Papathanasaki… - … (IUCC/CIT/DSCI …, 2021 - ieeexplore.ieee.org
The new form of the Web involves numerous devices present in two infrastructures, ie, the
Internet of Things (IoT) and the Edge Computing (EC) infrastructure. IoT devices are adopted …
Internet of Things (IoT) and the Edge Computing (EC) infrastructure. IoT devices are adopted …
A Proactive Uncertainty driven Model for Tasks Offloading
M Papathanasaki, P Fountas… - arXiv preprint arXiv …, 2022 - arxiv.org
The ever-increasing demands of end-users on the Internet of Things (IoT), often cause great
congestion in the nodes that serve their requests. Therefore, the problem of node …
congestion in the nodes that serve their requests. Therefore, the problem of node …
An Uncertainty-Driven Proactive Self-Healing Model for Pervasive Applications
M Papathanasaki, P Fountas, K Kolomvatsos - Network, 2022 - mdpi.com
The ever-increasing demand for services of end-users in the Internet of Things (IoT) often
causes great congestion in the nodes dedicated to serving their requests. Such nodes are …
causes great congestion in the nodes dedicated to serving their requests. Such nodes are …
FedFusionQuant (FFQ): Federated Learning with Feature Fusion and Model Quantisation for Human Activity Recognition using CSI
Human Activity Recognition (HAR) using channel state information (CSI) is crucial for
advancing healthcare applications, enabling non-invasive monitoring for improved patient …
advancing healthcare applications, enabling non-invasive monitoring for improved patient …
A Soft Method for Outliers Detection at the Edge of the Network
K Kolomvatsos, C Anagnostopoulos - arXiv preprint arXiv:2103.00179, 2021 - arxiv.org
The combination of the Internet of Things and the Edge Computing gives many opportunities
to support innovative applications close to end users. Numerous devices present in both …
to support innovative applications close to end users. Numerous devices present in both …