Stylianos E. Trevlakis

Matteo Salvatori, Filippo Vannella, Sebastian Macaluso et al.

HandOver (HO) control in cellular networks is governed by a set of HO control parameters that are traditionally configured through rule-based heuristics. A key parameter for HO optimization is the Cell Individual Offset (CIO), defined for each pair of neighboring cells and used to bias HO triggering decisions. At network scale, tuning CIOs becomes a tightly coupled problem: small changes can redirect mobility flows across multiple neighbors, and static rules often degrade under non-stationary traffic and mobility. We exploit the pairwise structure of CIOs by formulating HO optimization as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP) on the network's dual graph. In this representation, each agent controls a neighbor-pair CIO and observes Key Performance Indicators (KPIs) aggregated over its local dual-graph neighborhood, enabling scalable decentralized decisions while preserving graph locality. Building on this formulation, we propose TD3-D-MA, a discrete Multi-Agent Reinforcement Learning (MARL) variant of the TD3 algorithm with a shared-parameter Graph Neural Network (GNN) actor operating on the dual graph and region-wise double critics for training, improving credit assignment in dense deployments. We evaluate TD3-D-MA in an ns-3 system-level simulator configured with real-world network operator parameters across heterogeneous traffic regimes and network topologies. Results show that TD3-D-MA improves network throughput over standard HO heuristics and centralized RL baselines, and generalizes robustly under topology and traffic shifts.

Stylianos E. Trevlakis, Alexandros-Apostolos A. Boulogeorgos, Nestor D. Chatzidiamantis

Optical wireless communications (OWCs) have been recognized as a candidate enabler of next generation in-body nano-scale networks and implants. The development of an accurate channel model capable of accommodating the particularities of different type of tissues is expected to boost the design of optimized communication protocols for such applications. Motivated by this, this paper focuses on presenting a general pathloss model for in-body OWCs. In particular, we use experimental measurements in order to extract analytical expressions for the absorption coefficients of the five main tissues' constitutions, namely oxygenated and de-oxygenated blood, water, fat, and melanin. Building upon these expressions, we derive a general formula for the absorption coefficient evaluation of any biological tissue. To verify the validity of this formula, we compute the absorption coefficient of complex tissues and compare them against respective experimental results reported by independent research works. Interestingly, we observe that the analytical formula has high accuracy and is capable of modeling the pathloss and, therefore, the penetration depth in complex tissues.

Alexandros-Apostolos A. Boulogeorgos, Stylianos E. Trevlakis, Sotiris A. Tegos et al.

Machine learning (ML) empowers biomedical systems with the capability to optimize their performance through modeling of the available data extremely well, without using strong assumptions about the modeled system. Especially in nano-scale biosystems, where the generated data sets are too vast and complex to mentally parse without computational assist, ML is instrumental in analyzing and extracting new insights, accelerating material and structure discoveries, and designing experience as well as supporting nano-scale communications and networks. However, despite these efforts, the use of ML in nano-scale biomedical engineering remains still under-explored in certain areas and research challenges are still open in fields such as structure and material design and simulations, communications and signal processing, and bio-medicine applications. In this article, we review the existing research regarding the use of ML in nano-scale biomedical engineering. In more detail, we first identify and discuss the main challenges that can be formulated as ML problems. These challenges are classified into the three aforementioned main categories. Next, we discuss the state of the art ML methodologies that are used to countermeasure the aforementioned challenges. For each of the presented methodologies, special emphasis is given to its principles, applications, and limitations. Finally, we conclude the article with insightful discussions, that reveal research gaps and highlight possible future research directions.