Maastricht University researcher applying deep learning to federated clustering and space situational awareness.
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-16) 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—
Output metrics are not yet available: the underlying data provides no publication counts, venue history, or yearly totals for this researcher. This axis would measure the volume and consistency of the publication record over time.
Impact—
Impact data is insufficient for scoring: no citation counts, h-index, or per-paper influence signals exist in the current snapshot. This axis would measure how widely the recorded work is cited and taken up by other research.
Focus0/100
The focus axis scores 0 because the raw field distribution is an exact 0.5/0.5 split between computer vision/astronomy (space situational awareness) and machine learning (federated and unsupervised learning) — maximal breadth with no dominant field. The two cataloged 2026 preprints confirm this dual-track pattern, one paper per field, so the portfolio currently reads as exploratory rather than concentrated.
Collaboration44/100
With a collaboration score of 44, the record shows a moderate-size network: 8 distinct coauthors across the cataloged work, including Angela Cratere, Luca Ghilardi, Vishnu Reddy, Francesco Dell'Olio, Roberto Furfaro, Morris Stallmann, Marcin Pietrasik, and Anna Wilbik. Both 2026 preprints list him as a middle author without corresponding status, suggesting a contributor role within teams rather than a lead-author collaboration pattern so far.
Activity—
Activity metrics are not yet available: the data lacks a full yearly publication timeline, so recent-year cadence cannot be scored. This axis would measure publishing tempo and continuity across the most recent years.
Reproducibility78/100
Reproducibility is the strongest measured axis, at a mean score of 78 across two assessed papers. Evolve rates the federated deep clustering preprint as high readiness, while the space-situational-awareness variational-autoencoder paper is medium, its roughly fourfold stacked-SNR gains resting on self-made surrogate data. The 78 average signals methods and settings described well enough for independent replication, though only two papers back this figure.
Research summary
Charalampos S. Kouzinopoulos is a researcher at Maastricht University whose recorded work spans two evenly weighted lines of inquiry: computer vision for astronomy — specifically space situational awareness (SSA) — and machine learning, with emphasis on federated and unsupervised learning. The field distribution in the underlying bibliometric data splits exactly 0.5/0.5 between these two areas, and Evolve's catalog contains two of his 2026 arXiv preprints, one per field, in both of which he appears as a middle-listed, non-corresponding author. The first, Federated Deep Clustering Networks for High-Dimensional and Heterogeneous Data, extends deep clustering networks to the federated setting using synthetic data and a UMAP-based loss; Evolve's review notes strong results on non-IID MNIST but weaker USPS NMI than the FDEC baseline, and no privacy analysis. The second applies variational autoencoders within a Tiny-U-Net pipeline to star removal and background inpainting for faint object detection, reporting roughly fourfold stacked-SNR gains that rest on self-made surrogate data. His reproducibility profile is comparatively strong — a mean readiness score of 78 across two assessed papers — while collaboration scores moderately at 44 on a pool of 8 distinct coauthors.
Collaboration pattern
The visible collaboration pattern is a moderate-size network of 8 distinct coauthors, including Angela Cratere, Luca Ghilardi, Vishnu Reddy, Francesco Dell'Olio, Roberto Furfaro, Morris Stallmann, Marcin Pietrasik, and Anna Wilbik. In both cataloged 2026 preprints Kouzinopoulos is a middle author without corresponding status, pointing to a contributor role within research teams rather than an established lead-author pattern.
Research keywords
Highlights
Federated deep clustering for non-IID, high-dimensional data
Variational autoencoders for faint object detection in space situational awareness
Timeline
- 2026Releases an arXiv preprint on Federated Deep Clustering Networks for high-dimensional and heterogeneous data, extending deep clustering to the federated setting.
- 2026Publishes an arXiv preprint applying variational autoencoders to faint object detection for space situational awareness.
- 2026Both preprints are reviewed into the Evolve catalog with reproducibility assessments, contributing to a mean readiness score of 78 across two 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.
- Radar scores are computed from public bibliometric data only; citation-based axes (output, impact, activity) lack sufficient data and are not scored.
- The profile rests on two 2026 arXiv preprints reviewed by Evolve; no peer-reviewed venue records are included in this snapshot.
- The reproducibility mean of 78 is based on only two assessed papers.
- Identity is name-resolved from public bibliographic data (ORCID 0000-0001-8829-504X); both cataloged papers list a middle, non-corresponding authorship position.