Katerina Gkirtzou

Dr. Katerina Gkirtzou

Institute for Language and Speech Processing, Athena Research and Innovation Center In Information Communication & Knowledge Technologies, Marousi, Greece
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 June 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
YKYiannis Kiouvrekis
Yiannis Kiouvrekis
Katerina GkirtzouKaterina Gkirtzou
Katerina Gkirtzou
SZSotiris Zikas
Sotiris Zikas
DKDimitris Kalatzis
Dimitris Kalatzis
TPTheodor Panagiotakopoulos
Theodor Panagiotakopoulos
IFIoannis Filippopoulos
Ioannis Filippopoulos
In the evolving landscape of green shipping, the accurate estimation of shaft power is critical for reducing fuel consumption and greenhouse gas emissions. This study presents an explainable machine learning framework for shaft power prediction, utilising real-world Internet of Things (IoT) sensor data collected from nine (9) Very Large Crude Carriers (VLCCs) over a 36-month period. A diverse set of models—ranging from traditional algorithms such as Decision Trees and Support Vector Machines to advanced ensemble methods like XGBoost and LightGBM—were developed and evaluated. Model performance was assessed using the coefficient of determination (R2) and RMSE, with XGBoost achieving the highest accuracy (R2=0.9490, RMSE 888) and LightGBM being close behind (R2=0.9474, RMSE 902), with both substantially exceeding the industry baseline model (R2=0.9028, RMSE 1500). Explainability was integrated through SHapley Additive exPlanations (SHAP), offering detailed insights into the influence of each input variable. Features such as draft, GPS speed, and time since last dry dock consistently emerged as key predictors. The results demonstrate the robustness and interpretability of tree-based methods, offering a data-driven alternative to traditional performance estimation techniques and supporting the maritime industry’s transition toward more efficient and sustainable operations.

24 June 2025 in Electronics
Verified
Journal Article
Open access
PDF file
SZSotiris Zikas
Sotiris Zikas
Katerina GkirtzouKaterina Gkirtzou
Katerina Gkirtzou
IFIoannis Filippopoulos
Ioannis Filippopoulos
DKDimitris Kalatzis
Dimitris Kalatzis
TPTheodor Panagiotakopoulos
Theodor Panagiotakopoulos
YKYiannis Kiouvrekis
Yiannis Kiouvrekis
This paper presents a comparative analysis of machine learning-based methods for predicting shaft power in ships, a key factor in optimizing ship performance. Accurate shaft power prediction facilitates efficient operations, reducing fuel consumption, emissions, and maintenance costs, aligning with environmental regulations and promoting sustainable maritime practices. The proposed approach evaluates three machine learning methods, analyzing 431 models to determine the most accurate and reliable option for VLCC tankers. XGBoost emerged as the top-performing model, delivering a 13% improvement in accuracy over traditional methods. Using the SHAP framework, key factors influencing shaft power predictions—such as GPS speed, draft, days from dry dock, and wave height—were identified, enhancing model transparency and decision-making clarity. This explainability fosters trust in the use of AI within marine engineering. The results demonstrate that machine learning can optimize maintenance scheduling by reducing unnecessary cleaning procedures, mitigating propulsion system wear, and improving reliability. By using predictive insights, ship operators can achieve better fuel efficiency, lower emissions, and cost savings. The study underscores the potential of explainable machine learning models as transformative tools for ship performance monitoring, supporting greener and more efficient maritime operations.

9 July 2024 in Swedish Aerospace Conference, FT2025
Verified
Conference Paper
Open access
PDF file
MGMaria Gavriilidou
Maria Gavriilidou
SPStelios Piperidis
Stelios Piperidis
DGDimitrios Galanis
Dimitrios Galanis
KPKanella Pouli
Kanella Pouli
PLPenny Labropoulou
Penny Labropoulou
Katerina GkirtzouKaterina Gkirtzou
Katerina Gkirtzou
This paper presents the CLARIN:EL infrastructure, which comprises three pillars: the language resources and technologies Platform, the Portal and the Knowledge Centre. It serves as a com-prehensive and interoperable environment that supports language-related research in the fields of language technology, language studies, digital humanities, and political and social sciences. The Platform facilitates deposition, curation and sharing of digital language resources (catering for providers’ needs), and access to and automatic processing of these resources (catering for con-sumers’ needs). The Portal offers informative material about CLARIN:EL and support services to the community, including dissemination, awareness raising and training activities. The Knowledge Centre promotes digital literacy in the scientific domains served, by providing infor-mation on studies, educational and training material and publications. This paper discusses the CLARIN:EL pillars, the technical architecture, its design and implementation principles, the functionalities offered to the users, the support activities provided, usage analytics and future steps.

1 January 2023 in Rasprave Instituta za hrvatski jezik i jezikoslovlje
Verified
Journal Article
Open access
PDF file
PLPenny Labropoulou
Penny Labropoulou
DLDavid Lindemann
David Lindemann
CKChristiane Klaes
Christiane Klaes
Katerina GkirtzouKaterina Gkirtzou
Katerina Gkirtzou
This paper presents LexMeta, a metadata model for the description of lexical resources, such as dictionaries, word lists, glossaries, etc., to be used in language data catalogues mainly targeting the lexicographic and broader humanities communities b...

2 November 2022
Verified
Book Chapter
Open access
PDF file
DGDimitris Galanis
Dimitris Galanis
PLPenny Labropoulou
Penny Labropoulou
IRIan Roberts
Ian Roberts
MDMiltos Deligiannis
Miltos Deligiannis
LVLeon Voukoutis
Leon Voukoutis
SPStelios Piperidis
Stelios Piperidis
The ELG platform enables producers of language resources and language technology tools and services to upload, describe, share, and distribute their services and products as well as to describe their companies, academic organisations and projects. This chapter presents the functionalities offered through web-based user interfaces for describing LT resources or related entities with metadata and for managing their publication. It gives a detailed description of the options that providers of LT tools can exploit to integrate them into ELG as ready-to-deploy services and the tools that ELG offers in their support during the preparation, upload and integration phases. The tools and packaging recommendations for resources to be uploaded in ELG are also presented. The chapter concludes with a discussion of functionalities offered to providers by ELG and other related platforms.

Verified
Journal Article
Open access
PDF file
SZSotiris Zikas
Sotiris Zikas
Katerina GkirtzouKaterina Gkirtzou
Katerina Gkirtzou
TPTheodor Panagiotakopoulos
Theodor Panagiotakopoulos
YKYiannis Kiouvrekis
Yiannis Kiouvrekis
Neurosymbolic AI (NeSy AI) seeks to integrate the strengths of symbolic reasoning with computational learning methods, addressing fundamental challenges of each paradigm in isolation. Existing surveys have primarily organized this growing body of research by architecture. The systematic evaluation of NeSy systems against the foundational questions about knowledge–learning interaction raised in the literature has received far less attention. This paper introduces a multi-axis analytical framework that combines the six-type taxonomy proposed by Kautz with four foundational dimensions derived from the open questions raised by van Harmelen: the mode of integration between symbolic and computational learning components, the use of symbolic priors for learning, the enforcement of symbolic constraints for safety and bias prevention, and the production of symbolic knowledge from learning. Complemented by a systematic reasoning categorization (deductive, inductive, abductive), this framework is applied to categorize and analyze 70 NeSy papers. The analysis reveals that while symbolic priors for learning are widely adopted in the surveyed corpus, symbolic constraints for safety and fairness remain significantly underexplored despite being among the most frequently cited motivations for NeSy research. Task-level abductive reasoning is virtually absent, appearing in only three of the 70 systems, all but one from 2026. Fully integrated architectures (Kautz Type 6) remain scarce and largely theoretical, and bidirectional knowledge–learning interaction is rare. Six concrete gaps are identified, providing specific directions for future research in neurosymbolic AI.