Volume 11, Issue 3
This issue brings together three studies addressing emerging challenges in biomedical sensing, network optimization and deep learning for long time-series data. The papers emphasize practical and efficient solutions, covering antenna design for breast microwave imaging, many-objective optimization of virtual network functions, and generative approaches for long-sequence data augmentation. They also explore accessible healthcare technologies, improved network performance and data availability for predictive applications. Across these areas, the contributions share a focus on systematic evaluation, optimization, reliability and real-world applicability. Collectively, they demonstrate how advanced engineering and computational methods can support efficient, robust and application-oriented solutions to contemporary technological challenges.
Download Complete Issue
Front Cover
Editorial Board
Editorial
Table of Contents
The Impact of Antenna Design on Breast Microwave Imaging
Breast microwave sensing (BMS) systems offer a low-cost and efficient alternative to current reast cancer screening methods. However, reported performance varies widely due to differences in system configuration, antenna design, measurement protocols, and image reconstruction techniques. This study evaluates the impact of antenna design on key image quality metrics using a controlled experimental platform. Spatial…
Read More Many-objective Placement Optimization in Virtual Network Functions
Network Functions Virtualization (NFV) poses the VNF placement problem under multiple, potentially conflicting objectives, such as Quality of Service (QoS), costs, and resource efficiency. This work treats VNF placement as a many-objective optimization problem (MaOP) and presents two primary contributions: (i) a correlation analysis of state-of-the-art objectives to reduce dimensionality while maintaining representativeness, resulting in…
Read More Enhancing Long Time-Series Data Augmentation with Generative Adversarial Networks
With the development of deep learning, time-series-related tasks have been increasingly applied across various fields. However, time-series data used in the medical and semiconductor industries are often different from those in daily life, with high sampling frequencies and very long sequence lengths, and collecting such data is usually very challenging. Therefore, data augmentation is a…
Read More