ΕΛ EN
Home | People | Herodotou, Herodotos
145
Scholarly Works
43%
OA Ratio
39%
Collaborative Ratio
Scholar

Herodotou, Herodotos

Associate Professor

Department of Electrical Engineering, Computer Engineering and Informatics

20
H-index (Scopus)
5931
Scholar Citations

Scholarly Works

Research Output

Recent Publications

Resilient Port Operations in Limassol Port, Cyprus: Evaluating the Impact of Global Disruptions on Short Sea Shipping

Michaelides M., Herodotou H., Baltatzidis G.
Publishing year: 2026
Journal article
Sustainability Switzerland, 2026, Volume 18, Issue 13
Scopus
This study examines the operational resilience of Limassol Port, Cyprus’s primary maritime hub, amid disruptions caused mainly by the COVID-19 pandemic. Utilizing high-resolution port-level data from 2018 to 2025, we evaluate performance across five key performance indicators: port calls, anchorage utilization, berth utilization, waiting times, and arrival punctuality. The analysis adopts a longitudinal approach, spanning pre-pandemic, peak-pandemic, post-pandemic, and recent phases, while differentiating impacts across vessel categories. Unlike many regional ports, Limassol’s cruise sector exhibited unique counter-cyclical growth, with calls doubling during the pandemic as the port transitioned into a strategic safe haven and repositioning base. This surge normalized over the 2024–2025 period as temporary operational disruptions resolved. Conversely, container and Ro-Ro (roll-on/roll-off) segments demonstrated robust stability, achieving rapid post-pandemic normalization, while bulk and tanker operations exhibited higher volatility linked to shifting commodity demands. These findings, validated through one-way analysis of variance (ANOVA) and Cohen’s d effect sizes, underscore the adaptive capacity of mid-sized Mediterranean hubs. The study concludes that operational flexibility, coupled with enhanced digital coordination and strategic capacity planning, is essential for maintaining the resilience of short sea shipping networks during global crises.

Real-time Verification of Container Seal Integrity using Deep Learning

Michaelides M., Herodotou H., Cassera A., Vasileiadis S., Orphanides K., Yu S.
Publishing year: 2026
Conference paper
Proceedings of the 21st Conference on Computer Science and Intelligence Systems Fedcsis 2026, 2026
Scopus
Pages 155-164
Container seal integrity verification represents a critical yet underexplored challenge in maritime logistics security. Early theft detection is critical for minimizing operational delays, reducing costs, and ensuring safety in global maritime logistics. This work presents a deep learning-based methodology for real-time detection of container seals during crane unloading operations at container terminals. We develop and deploy two specialized YOLOv12-based object detection models: one for identifying container doors in motion and another for detecting in-place security fixtures, such as standard locks, container seals, and customs seals. Our models are trained and evaluated on a real-world dataset curated from video feeds captured at the EUROGATE Container Terminal in Limassol Port, Cyprus. The system is designed for robust performance under realistic terminal conditions, including variable lighting and motion. Our models achieve high detection accuracy across variable weather conditions, with mAP50 scores of 0.95 for container door detection and 0.74 for seal detection, substantially outperforming existing benchmarks. These findings underscore the practical potential of our methodology for enhancing the efficiency and security of automated maritime logistics.

Machine Learning-Based Caching and Tiering in Modern Data Storage Systems: A Survey

Herodotou H., Kakoulli E., Savva G.
Publishing year: 2026
Journal article
ACM Computing Surveys, 2026, Volume 58, Issue 11
Scopus
Modern data storage systems contain numerous media devices (e.g., DRAM, NVRAM, SSDs, and HDDs) organized into multi-level caches and storage tiers to optimize the performance-to-cost ratio. Traditional caching policies for eviction, admission, and prefetching, as well as tiering policies for data placement and migration, offer simplicity but struggle to adapt to the dynamic and complex access patterns observed in modern data-intensive applications. As a result, machine learning (ML)-based policies have recently gained popularity due to their ability to make predictions and proactively optimize caching and tiering operations. These ML techniques not only increase cache hit rates and reduce latency but also provide scalable, cost-effective solutions that intelligently place data across different storage media. This manuscript reviews the state-of-the-art ML-based caching and tiering approaches, examining their theoretical foundations and practical implementations. It also presents the most common features for each policy type, the most popular baselines for comparison, and the typical evaluation metrics. Finally, it discusses emerging trends and outlines potential directions for future research in data storage systems.

First Overlap Formulation and Perturbative Results for Supersymmetric QCD

M Costa, E Antoniou, H Herodotou, E Ioannou, C Kartoudes, ...
Publishing year: 2026
Other
arXiv preprint arXiv:2611.07745, 2026, 2026
Google Scholar

Exploring seasonal coastal water quality parameter interactions through the self-organizing map neural network in eastern Mediterranean: Lebanon as a case study

Michaelides M., Herodotou H., Hassoun A.E.R., Hadjisolomou E., Ghanem A., Mina R., Fakhri M.
Publishing year: 2026
Journal article
Marine Pollution Bulletin, 2026, Volume 228
Scopus
Coastal water pollution poses significant environmental challenges, leading to severe ecological and public health consequences. Thus, new assessment tools should be developed and refined to manage water quality more efficiently. In this paper, we present the results of Self-Organizing Map (SOM) neural network models used to simulate interactions among several water quality parameters, monitored at 35 coastal stations in the South-Eastern Mediterranean Sea, namely in Lebanon. Four seasonal SOM models were developed and calibrated based on the available dataset ( n = 1087). The SOM's visualization of the Component Planes (CPs) enabled the examination of water-quality parameter interactions and associations on a seasonal basis. Additionally, Pearson correlation analysis between the SOM's Best Matching Units was calculated for each monitored parameter to augment the CPs analysis. SOM's clustering of data samples and assessment of human activities near the associated monitoring stations enabled the evaluation of the potential effects of existing human activities in nearby areas for each monitoring station. Specifically, the seasonal models revealed spatial-seasonal patterns at stations located near specific land-use settings, such as ANT-2 (near a river mouth), SEL-2 (near a chemical plant), and BEY-6 (public beach), which may be associated with degraded coastal water quality in Lebanon. Overall, this paper demonstrates that the SOM model can reveal parameter interactions and hig...

DARO: An Auction-Based Multi-Agent Reinforcement Learning Framework for Task Scheduling in the Cloud Continuum

Herodotou H., Castellini J., Strasser P., Touloupou M., Hassan S.M.U., Kalousis A.
Publishing year: 2026
Conference paper
International Conference on Cloud Computing and Services Science Closer Proceedings, 2026, Volume 1
Scopus
Pages 293-300
The increasing heterogeneity and dynamism of cloud-edge-IoT infrastructures demand scalable, intelligent scheduling strategies that go beyond traditional centralized approaches. This paper presents DARO, a distributed, asynchronous scheduling framework that leverages multi-agent reinforcement learning (MARL) to enable autonomous, cooperative task allocation across the cloud continuum. DARO integrates natively with Kubernetes, introducing a decentralized, auction-based mechanism in which node-local agents submit bids for incoming tasks based on partial observations and a learned policy. The agents are trained using a value decomposition method (QMIX) under the centralized training-decentralized execution paradigm. We formalize the problem as a decentralized partially observable Markov decision process (Dec-POMDP), design a multi-factor reward function to guide learning, and implement the system within a high-fidelity Kubernetes simulator. The experimental evaluation demonstrates that the agents effectively learn balanced and resource-efficient task placement strategies. DARO demonstrates strong potential to serve as a robust scheduling layer for dynamic and large-scale distributed environments.

145
Unique publications
43.4%
Open access (63 publications; 37 without information)
38.6%
With other institutions (56 publications; 53 without information)

H-Index Reports

Index type Scopus Google Scholar Web of Science
H-index 20 30 1
H5-index 10 16 1
H10-index 14 23 1

Publications per year and source

No description yet.
Faculty
Faculty of Engineering and Technology
Department
Department of Electrical Engineering, Computer Engineering and Informatics
Title
Associate Professor