Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
6GxAID: Integrating 6G Networks and eXplainable Artificial Intelligence for Drone-Based Assistance in Emergency Situations
0
Zitationen
5
Autoren
2025
Jahr
Abstract
Explainable Artificial Intelligence (xAI) encompasses a set of techniques to make AI model decisions more transparent and interpretable for humans while promoting transparency and trust. By leveraging emerging xAI techniques to improve the use of the 6<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> Generation (6G) networks for critical applications, particularly drone-based assistance in emergency scenarios, a novel scheme called 6GxAID is proposed. The proposed scheme is validated through a telemedicine use case for diabetes management, where drones operate in resource-constrained environments and rely on satellite backhaul for data transmission in areas with limited terrestrial network coverage. By adopting SHapley Additive exPlanations-based xAI methods, the proposed scheme enables effective feature selection to minimize the size of transmitted data while maintaining high learning accuracy. This approach optimizes energy efficiency for resource-constrained devices and reduces satellite bandwidth consumption, ensuring reliable and scalable operations during emergencies.
Ähnliche Arbeiten
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
2018 · 6.348 Zit.
The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)
2014 · 6.229 Zit.
Brain tumor segmentation with Deep Neural Networks
2016 · 3.176 Zit.
Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images
2016 · 2.607 Zit.
Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations
2017 · 2.491 Zit.