Researcher applying explainable AI and fuzzy logic to predictive maintenance in maritime and naval propulsion systems.
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-13) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Not yet scored: no publication-count or output data is available for this profile. This axis would measure total research output, such as the number of peer-reviewed publications and preprints over time, so no level of productivity can currently be inferred.
Impact—
Not yet scored: citation data is unavailable. This axis would measure the influence of the work through citations, citations-per-paper, and related indicators, so no claim about scholarly impact can be made from the current evidence.
Focus0/100
The radar scores focus at 0, derived from a field distribution split evenly at 0.5/0.5 between 'predictive maintenance / applied machine learning' and 'machine learning (explainable AI / predictive maintenance)'. Both labels describe nearly the same research program — explainable, fuzzy-logic-based machine learning for condition monitoring — so the minimal score likely reflects label granularity rather than genuinely scattered work, and it rests on only two catalog papers.
Collaboration36/100
Collaboration scores 36, based on 5 distinct coauthors across the two catalog papers. Recurring collaborators are Dionisis Kalogeropoulos, Dimitris K. Iakovidis, and Panagiotis G. Kalozoumis, suggesting a small, stable team. On both 2026 arXiv papers Sovatzidi appears in a middle author position and is not the corresponding author, indicating a contributor role within a compact group rather than an independent-led effort.
Activity—
Not yet scored: the underlying data does not include per-year publication counts beyond the two reviewed preprints. This axis would measure publishing cadence and consistency over time, so recent productivity cannot be judged from the available evidence.
Reproducibility20/100
Reproducibility scores 20 (mean across 2 scored papers), and both papers are rated low for reproducibility readiness in the Evolve catalog. Evolve's reviews flag concrete gaps: the naval-propulsion paper's advantage claims are weakened by baseline comparisons and possible data leakage, while the maritime paper reports tied scores (SVM 0.99) without variance statistics, making independent verification of claimed gains difficult.
Research summary
Georgia Sovatzidi is a researcher working at the intersection of explainable artificial intelligence and predictive maintenance, with applications to maritime and naval engineering. The Evolve catalog lists two arXiv preprints from 2026 on which Sovatzidi is a middle-position author and not the corresponding author: 'Explainable Neuro-Fuzzy Prediction for Trustworthy Decision-Making in Maritime' and 'Explainable Predictive Condition-based Maintenance of Naval-Propulsion Systems using Fuzzy Logic'. Both papers combine fuzzy methods — neuro-fuzzy networks and fuzzy decision trees — with explanation techniques such as saliency maps and feature attribution to make maintenance-oriented predictions auditable. The naval-propulsion paper reports 99.24% accuracy on public CODLAG data, although Evolve's review notes that baseline comparisons and possible data leakage weaken its superiority claims; the maritime paper's 'outperforms SOTA' claim is likewise flagged because Table I shows ties (SVM 0.99) and statistics lack variance reporting. Both papers carry a low reproducibility-readiness rating, consistent with a reproducibility score of 20 across two scored papers. The radar records a collaboration score of 36 with five distinct coauthors, and recurring collaborators include Dionisis Kalogeropoulos, Dimitris K. Iakovidis, and Panagiotis G. Kalozoumis. Output, impact, and activity metrics are not yet available.
Collaboration pattern
The two catalog papers share a compact author team: 5 distinct coauthors in total, with Dionisis Kalogeropoulos, Dimitris K. Iakovidis, and Panagiotis G. Kalozoumis appearing repeatedly. This points to a small, stable collaboration cluster around explainable fuzzy-logic machine learning for maritime and naval maintenance. Sovatzidi sits in a middle author position and is not the corresponding author on either paper, consistent with a contributing-member role within this group; the radar's collaboration score is 36.
Research keywords
Highlights
Explainable condition-based maintenance framework for naval propulsion
Neuro-fuzzy explanations for trustworthy maritime decision-making
Timeline
- 2026Co-authored the arXiv preprint 'Explainable Predictive Condition-based Maintenance of Naval-Propulsion Systems using Fuzzy Logic', in a middle author position and not as corresponding author.
- 2026Co-authored the arXiv preprint 'Explainable Neuro-Fuzzy Prediction for Trustworthy Decision-Making in Maritime', likewise as a middle-position, non-corresponding author.
- 2026Both 2026 preprints entered the Evolve review catalog with low reproducibility-readiness ratings, contributing to a reproducibility score of 20 across 2 scored papers.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometric scores come from OpenAlex-based public bibliographic data; no citation, h-index, or output counts were available for this profile.
- Institution and country are absent from the source data; the profile is name-resolved via ORCID 0000-0002-8626-5549 and public bibliographic records, and coverage may be incomplete.
- Only the two arXiv preprints reviewed in the Evolve catalog are covered; other publications, if any, are not reflected here.
- Evolve review verdicts quoted here are reviewer judgments, including criticisms of baseline comparisons, statistical reporting, and potential data leakage.