<?xml version="1.0" encoding="UTF-8"?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns="http://purl.org/rss/1.0/" xmlns:dc="http://purl.org/dc/elements/1.1/">
  <channel rdf:about="https://hdl.handle.net/20.500.14279/12776">
    <title>DSpace Collection:</title>
    <link>https://hdl.handle.net/20.500.14279/12776</link>
    <description />
    <items>
      <rdf:Seq>
        <rdf:li rdf:resource="https://hdl.handle.net/20.500.14279/35210" />
        <rdf:li rdf:resource="https://hdl.handle.net/20.500.14279/35124" />
        <rdf:li rdf:resource="https://hdl.handle.net/20.500.14279/35109" />
        <rdf:li rdf:resource="https://hdl.handle.net/20.500.14279/32477" />
      </rdf:Seq>
    </items>
    <dc:date>2026-05-07T09:03:44Z</dc:date>
  </channel>
  <item rdf:about="https://hdl.handle.net/20.500.14279/35210">
    <title>Learning from the Rare: Overcoming Class  Imbalance in Archaeological Object Detection with  Boosting Methods</title>
    <link>https://hdl.handle.net/20.500.14279/35210</link>
    <description>Title: Learning from the Rare: Overcoming Class  Imbalance in Archaeological Object Detection with  Boosting Methods
Authors: Argyrou, Argyro; Fasson, Federico; Farinetti, Emeri; Papakonstantinou, Apostolos; Alexakis, Dimitrios; Agapiou, Athos
Abstract: Detecting surface potsherds using low-altitude remote sensing is challenging due to severe class &#xD;
imbalance and limited training data. This study explores boosting algorithms—Adaptive &#xD;
Boosting (AdaBoost) and Extreme Gradient Boosting (XGBoost)—to maximize detection recall&#xD;
for archaeological prospection in the Western Megaris landscape, Greece. Models were trained &#xD;
on only 15% of available data to simulate realistic field conditions. Evaluation emphasized recall oriented metrics (precision, recall, F1-score, AUC) for the minority class, addressing the accuracy &#xD;
paradox where high overall accuracy masks poor rare-class performance. Threshold &#xD;
optimization enabled AdaBoost and XGBoost to achieve substantially improved recall compared &#xD;
to baseline methods, with detection-to-ground-truth ratios of 2.5 and 3.2 respectively, reflecting &#xD;
deliberate prioritization of recall over precision for exploratory survey purposes. Results &#xD;
demonstrate that boosting methods with application-specific threshold optimization offer &#xD;
practical screening tools for flagging high-probability areas in archaeological landscape survey, &#xD;
enhancing field survey efficiency in data-constrained environments requiring expert validation.</description>
    <dc:date>2025-01-01T00:00:00Z</dc:date>
  </item>
  <item rdf:about="https://hdl.handle.net/20.500.14279/35124">
    <title>Inscription parameters in bulk polymer</title>
    <link>https://hdl.handle.net/20.500.14279/35124</link>
    <description>Title: Inscription parameters in bulk polymer
Authors: Ioannou, Andreas; Kalli, Kyriacos; Yerolatsitis, Stephanos
Abstract: The research explores critical laser parameters—including pulse energy and repetition rate, -and their influence on the polymer's refractive index modification, structural integrity, and optical performance. The plane-by-plane FSL inscription technique is employed to achieve high spatial resolution and controlled material modifications. Various polymers, such as PMMA (Polymethyl-methacrylate), PC (Polycarbonate), PSU (Polysulfone), FEP (Fluorinated-Ethylene-Propylene), were selected for their suitability in biomedical and specifically for implantation in the brain and spinal cord within the Move2Treat's context.
Description: Microscope images and characterization of femtosecond laser modified bulk polymers for the optimization of inscription of optical structures.</description>
    <dc:date>2025-02-27T00:00:00Z</dc:date>
  </item>
  <item rdf:about="https://hdl.handle.net/20.500.14279/35109">
    <title>Inscription parameters in bulk polymers</title>
    <link>https://hdl.handle.net/20.500.14279/35109</link>
    <description>Title: Inscription parameters in bulk polymers
Authors: Ioannou, Andreas; Kalli, Kyriacos; Yerolatsitis, Stephanos
Abstract: The research explores critical laser parameters—including pulse energy and repetition rate, -and their influence on the polymer's refractive index modification, structural integrity, and optical performance. The plane-by-plane FSL inscription technique is employed to achieve high spatial resolution and controlled material modifications. Various polymers, such as PMMA (Polymethyl-methacrylate), PC (Polycarbonate), PSU (Polysulfone), FEP (Fluorinated-Ethylene-Propylene), were selected for their suitability in biomedical and specifically for implantation in the brain and spinal cord within the Move2Treat's context.
Description: Microscope images and characterization of femtosecond laser modified bulk polymers for the optimization of inscription of optical structures.</description>
    <dc:date>2025-02-27T00:00:00Z</dc:date>
  </item>
  <item rdf:about="https://hdl.handle.net/20.500.14279/32477">
    <title>Tombs and necropoleis of Cyprus: a corpus of the Hellenistic and Roman burial grounds</title>
    <link>https://hdl.handle.net/20.500.14279/32477</link>
    <description>Title: Tombs and necropoleis of Cyprus: a corpus of the Hellenistic and Roman burial grounds
Authors: Lysandrou, Vasiliki; Agapiou, Athos
Abstract: The dataset contains geospatial information for hundreds of single tombs and necropoleis of Hellenistic and Roman periods from across Cyprus. The data were collected by the first author for the needs of her PhD thesis. The dataset is deposited on KTISIS and is hereby made available to future research efforts for update. There is substantial reuse potential pertaining to research on Cyprus as well as the wider Mediterranean in areas ranging from ancient topography and demography to funerary material culture and burial artefacts and customs.
Description: The record is publicly accessible, but files are restricted to users with access. To request access to data please contact vasiliki.lysandrou@cut.ac.cy and athos.agapiou@cut.ac.cy</description>
    <dc:date>2024-01-01T00:00:00Z</dc:date>
  </item>
</rdf:RDF>

