Opening the gallery

01 / Profile
Elgün,if your keyboard allows it :)
I study how AI reasons, generalizes and earns trust
02 / Experience
How I got here
Research experience
Industry experience
Selected honors & awards
Certifications
03 / Research
Publications & Preprints

Primary-Preserving Complementary Module Retrieval Across Formal Mathematics Libraries
Details & authors
Accepted for proceedings · Formal mathematics / semantic retrieval
Retrieval between MathComp/Rocq and mathlib/Lean is not always a one-to-one matching problem. This work studies complementary module retrieval while preserving the primary result, accounting for content distributed across different library boundaries.
Methods
Semantic retrieval · Graph methods · MathComp / Rocq · mathlib / Lean
International Conference on Web Information Systems Engineering (WISE 2026) · Student Track
BibTeX
Primary-Preserving Complementary Module Retrieval Across Formal Mathematics Libraries
@inproceedings{hasanov2026modules,
title = {Primary-Preserving Complementary Module Retrieval Across Formal Mathematics Libraries},
author = {Hasanov, Elgun and Bashirov, Fatulla and El Kadhi, Nahla},
year = {2026},
booktitle = {WISE 2026, Student Track}
}
Asymmetric Cross-Cohort Generalization in Alzheimer's Disease Classification: A Bidirectional External Validation Study
Details & authors
Accepted full paper · Biomedical AI / external validation
A bidirectional external-validation study of Alzheimer's disease classifiers across independent clinical cohorts.
Methods
External validation · Distribution shift · Biomedical AI
IEEE International Symposium on Computer-Based Medical Systems (CBMS 2026)
BibTeX
Asymmetric Cross-Cohort Generalization in Alzheimer's Disease Classification: A Bidirectional External Validation Study
@inproceedings{hasanov2026asymmetric,
title = {Asymmetric Cross-Cohort Generalization in Alzheimer's Disease Classification: A Bidirectional External Validation Study},
author = {Hasanov, Elgun and El Kadhi, Ayman and Safarli, Gulzar and El Kadhi, Nahla},
year = {2026},
booktitle = {IEEE International Symposium on Computer-Based Medical Systems}
}
Leakage-Safe Machine Learning for Alzheimer's Disease Classification with External Validation on ADNI and OASIS
Details & authors
Accepted for oral presentation and proceedings · Paper 337
A leakage-safe machine-learning evaluation across ADNI and OASIS with external validation.
Methods
External validation · Distribution shift · Biomedical AI
KES International Conference
BibTeX
Leakage-Safe Machine Learning for Alzheimer's Disease Classification with External Validation on ADNI and OASIS
@inproceedings{hasanov2026leakagesafe,
title = {Leakage-Safe Machine Learning for Alzheimer's Disease Classification with External Validation on ADNI and OASIS},
author = {Hasanov, Elgun and El Kadhi, Ayman and Safarli, Gulzar and El Kadhi, Nahla},
year = {2026},
booktitle = {KES International Conference}
}
AttentionDep: Knowledge-Infused Attention for Interpretable Depression Severity Assessment from Social Media
Details & authors
Accepted for presentation · Mental-health NLP / interpretable attention
A knowledge-infused attention approach for interpretable depression-severity assessment from social-media text.
Methods
Attention · Knowledge infusion · Mental-health NLP
Earlier version available as an arXiv preprint.
International Conference on Web Information Systems Engineering (WISE 2026) · Main Research Track
BibTeX
AttentionDep: Knowledge-Infused Attention for Interpretable Depression Severity Assessment from Social Media
@inproceedings{hasanov2026attentiondep,
title = {AttentionDep: Knowledge-Infused Attention for Interpretable Depression Severity Assessment from Social Media},
author = {Ibrahimov, Yusif and Anwar, Tarique and Yuan, Tommy and Mutallimov, Turan and Hasanov, Elgun},
year = {2026},
booktitle = {WISE 2026, Main Research Track}
}
Can We Trust LLMs for Mental Health-Based Decisions? A Causality Aware Reliability Analysis
Details & authors
Published · Open access · LLM reliability / causal analysis
An analysis of Qwen2.5-7B's attention in mental-health classification examines whether predictive signals align with domain reasoning. The work identifies a limitation in attention-based causal discovery and studies a correction using contrastive TF-IDF and directed pointwise mutual information.
Methods
Causal analysis · Trustworthy AI · Qwen2.5-7B
Artificial Intelligence for Digital Transformations (AIDT) · pp. 251–263 · DOI: 10.1007/978-3-032-31319-5_17
BibTeX
Can We Trust LLMs for Mental Health-Based Decisions? A Causality Aware Reliability Analysis
@inproceedings{hasanov2026trustllms,
title = {Can We Trust LLMs for Mental Health-Based Decisions? A Causality Aware Reliability Analysis},
author = {Ibrahimov, Yusif and Mutallimov, Turan and Mirzabayov, Seymour and Hasanov, Elgun},
year = {2026},
booktitle = {Artificial Intelligence for Digital Transformations (AIDT)},
doi = {10.1007/978-3-032-31319-5_17}
}
Decision Support through Feature-Aware Ensemble Clustering: A Multi-Algorithm Fusion Framework for Complex Data Analysis
Details & authors
Published · Ensemble clustering / decision support
The framework combines complementary clustering signals while accounting for feature structure, aiming to produce more robust groupings for complex data-analysis workflows.
Methods
Ensemble clustering · Decision support
International Conference on Decision Aid Sciences and Applications (DASA) · pp. 980–986 · DOI: 10.1109/DASA68193.2025.11498998
BibTeX
Decision Support through Feature-Aware Ensemble Clustering: A Multi-Algorithm Fusion Framework for Complex Data Analysis
@inproceedings{hasanov2025ensemble,
title = {Decision Support through Feature-Aware Ensemble Clustering: A Multi-Algorithm Fusion Framework for Complex Data Analysis},
author = {Hasanov, Elgun and El Kadhi, Nahla El Zant},
year = {2025},
booktitle = {International Conference on Decision Aid Sciences and Applications (DASA)},
doi = {10.1109/DASA68193.2025.11498998}
}
Rapid Automated Alzheimer's Disease Classification Using FastSurfer Segmentation and Explainable Machine Learning
Details & authors
Published · Medical imaging / explainable ML
This project connects FastSurfer-derived neuroanatomical features with interpretable machine-learning models to support rapid Alzheimer's disease classification.
Methods
FastSurfer · Explainable ML · Brain segmentation
International Conference on Decision Aid Sciences and Applications (DASA) · pp. 1527–1535 · DOI: 10.1109/DASA68193.2025.11499040
BibTeX
Rapid Automated Alzheimer's Disease Classification Using FastSurfer Segmentation and Explainable Machine Learning
@inproceedings{hasanov2025fastsurfer,
title = {Rapid Automated Alzheimer's Disease Classification Using FastSurfer Segmentation and Explainable Machine Learning},
author = {Safarli, Gulzar and El Kadhi, Ayman and Hasanov, Elgun and El Zant El Kadhi, Nahla},
year = {2025},
booktitle = {International Conference on Decision Aid Sciences and Applications (DASA)},
doi = {10.1109/DASA68193.2025.11499040}
}
AttentionDep: Domain-Aware Attention for Explainable Depression Severity Assessment
Details & authors
Preprint · Earlier version of the WISE 2026 AttentionDep paper
A domain-aware attention model that combines contextual text representations with mental-health knowledge for interpretable, ordinal depression-severity assessment.
Methods
Attention · Knowledge infusion · Mental-health NLP
Earlier version of the WISE 2026 AttentionDep work.
arXiv preprint arXiv:2510.00706 · DOI: 10.48550/arXiv.2510.00706
BibTeX
AttentionDep: Domain-Aware Attention for Explainable Depression Severity Assessment
@article{ibrahimov2025attentiondep,
title = {AttentionDep: Domain-Aware Attention for Explainable Depression Severity Assessment},
author = {Ibrahimov, Yusif and Anwar, Tarique and Yuan, Tommy and Mutallimov, Turan and Hasanov, Elgun},
year = {2025},
journal = {arXiv preprint arXiv:2510.00706},
doi = {10.48550/arXiv.2510.00706}
}No matching publications. Try another title or research area.
*conceptual previews, powered by imagination :)
04 / Blog
Latest from the blog
Practical guides and research notes on building and evaluating AI systems.
Fine-tuning a small language model with LoRA
A practical starting point for supervised fine-tuning: define the task, prepare data, train an adapter, and evaluate the result.
Read article ↗02A leakage-safe evaluation checklist for machine learning
How to keep information from the test set out of preprocessing, model selection, and reported results.
Read article ↗03What changes when a model meets a new dataset?
A practical way to think about external validation, distribution shift, and the limits of internal scores.
Read article ↗















