Non-coding RNA classifier
| dc.contributor.advisor | Maglogiannis, Ilias | |
| dc.contributor.advisor | Μαγκλογιάννης, Ηλίας | |
| dc.contributor.author | Vasilas, Konstantinos | |
| dc.contributor.author | Βασιλάς, Κωνσταντίνος | |
| dc.date.accessioned | 2024-03-11T13:28:39Z | |
| dc.date.available | 2024-03-11T13:28:39Z | |
| dc.date.issued | 2024-02 | |
| dc.identifier.uri | https://dione.lib.unipi.gr/xmlui/handle/unipi/16264 | |
| dc.identifier.uri | http://dx.doi.org/10.26267/unipi_dione/3686 | |
| dc.format.extent | 69 | el |
| dc.language.iso | en | el |
| dc.publisher | Πανεπιστήμιο Πειραιώς | el |
| dc.rights | Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα | * |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/gr/ | * |
| dc.title | Non-coding RNA classifier | el |
| dc.type | Master Thesis | el |
| dc.contributor.department | Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Ψηφιακών Συστημάτων | el |
| dc.description.abstractEN | This thesis presents a simplified yet effective deep learning model for the classification of non-coding RNAs (ncRNAs). Non-coding RNAs play a vital role in gene regulation and are associated with various biological processes and diseases. The complexity and diversity of ncRNAs make their classification a challenging task. To tackle this, a new neural network model called NCC was developer specifically designed to recognize patterns in ncRNA sequences as well as an updated collection of non-coding RNA sequences datasets to train and test the proposed architecture. The NCC model’s performance, when bench marked against traditional classifiers and existing RNA tools, revealed a 6% improvement in accuracy over the previously best-performing models, reaching 92.69% accuracy, along with slight enhancements in reliability, while still retaining its uncomplicated architecture. This model was trained and evaluated using a newly developed dataset that is ten times larger than the conventional dataset, achieving an accuracy rate exceeding 98%. The model’s accuracy and interpretability hold potential for future research in genomic analysis and the identification of novel ncRNAs. | el |
| dc.contributor.master | Προηγμένα Συστήματα Πληροφορικής | el |
| dc.subject.keyword | Non-coding | el |
| dc.subject.keyword | RNA | el |
| dc.subject.keyword | AI | el |
| dc.subject.keyword | Classification | el |
| dc.date.defense | 2024-02-29 |
Αρχεία σε αυτό το τεκμήριο
Αυτό το τεκμήριο εμφανίζεται στις ακόλουθες συλλογές
-
Τμήμα Ψηφιακών Συστημάτων
Department of Digital Systems
Εκτός από όπου διευκρινίζεται διαφορετικά, το τεκμήριο διανέμεται με την ακόλουθη άδεια:
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα