Arşiv logosu
  • Türkçe
  • English
  • Giriş
    Yeni kullanıcı mısınız? Kayıt için tıklayın. Şifrenizi mi unuttunuz?
Arşiv logosu
  • Koleksiyonlar
  • Sistem İçeriği
  • Analiz
  • Talep/Soru
  • Türkçe
  • English
  • Giriş
    Yeni kullanıcı mısınız? Kayıt için tıklayın. Şifrenizi mi unuttunuz?
  1. Ana Sayfa
  2. Yazara Göre Listele

Yazar "Sener, Leyla" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
Sayfa Başına Sonuç
Sıralama seçenekleri
  • Küçük Resim Yok
    Öğe
    Evidence bound clinical decision support with RAG
    (Gazi Univ, 2025) Sener, Leyla; Yilmaz, Omit; Dikmen, Can; Ari, Ali; Karadag, Teoman
    Large language models are increasingly consulted for scientific and clinical questions, yet ungrounded answers still appear too often to trust them on their own. We built a retrieval-augmented assistant that keeps generation tied to a curated, versioned corpus, and records every step from ingestion to answer. Documents are segmented with a practical, token-aware policy and encoded locally; vectors are stored with provenance so the system can cite or abstain. Queries are embedded, top-k passages are retrieved from a vector store, and a prompt asks the generator to respond only with supported statements or to decline. The components are intentionally swappable: the embedder runs on-premises for privacy, the store supports snapshots for repeatable experiments, and the generator (Gemma/Gemma2) is selected for efficient inference. Beyond the pipeline, we preregister an evaluation plan that measures retrieval quality, answer faithfulness and coverage, with ablations on chunk size, overlap, and k. All code, defaults, and scripts are released so others can reproduce the setup, compare their own choices, and extend the system to new domains. The goal is clear: reduce hallucination by grounding answers in literature, keep costs and latency predictable on a single-GPU server, and make empirical evaluation routine rather than optional. Experimental evaluation confirmed these design claims: the proposed modular RAG achieved Recall@k = 0.86, F1 = 0.79, and Attribution Accuracy = 0.91, significantly outperforming both Classic RAG and LLM-only baselines (p < 0.05). These results validate the framework's reliability, grounding fidelity, and reproducibility for evidence-based clinical decision support.
  • Küçük Resim Yok
    Öğe
    Simultaneous use of transglutaminase and rennet in white-brined cheese production
    (Elsevier Sci Ltd, 2013) Ozer, Barbaros; Hayaloglu, A. Adnan; Yaman, Huyla; Gursoy, Ayse; Sener, Leyla
    The effects of renneting temperature (30 degrees C or 34 degrees C) on textural properties, proteolysis and yield of white-brined cheese made by simultaneous use of microbial transglutaminase (mTG) and rennet were investigated. Incorporation of mTG resulted in higher yield values for experimental cheeses than for the control cheeses at both renneting temperatures. The total solids contents of the cheeses treated with mTG were remarkably lower than the control cheeses; but the former cheeses had higher protein-in-dry matter levels. The TPA profiles of the cheeses showed that the incorporation of mTG led to modification in the textural properties. The development of proteolysis in the cheeses treated with mTG was slightly slower than the control cheeses at both coagulation temperatures. To conclude, the specific action of mTG on milk proteins could be successfully exploited to modify the textural properties and to increase the yield of white-brined cheese. (C) 2013 Elsevier Ltd. All rights reserved.

| İnönü Üniversitesi | Kütüphane | Rehber | OAI-PMH |

Bu site Creative Commons Alıntı-Gayri Ticari-Türetilemez 4.0 Uluslararası Lisansı ile korunmaktadır.


İnönü Üniversitesi, Battalgazi, Malatya, TÜRKİYE
İçerikte herhangi bir hata görürseniz lütfen bize bildirin

DSpace 7.6.1, Powered by İdeal DSpace

DSpace yazılımı telif hakkı © 2002-2026 LYRASIS

  • Çerez Ayarları
  • Gizlilik Politikası
  • Son Kullanıcı Sözleşmesi
  • Geri Bildirim