<?xml version='1.0' encoding='UTF-8'?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-05-14T13:25:07Z</responseDate>
  <request metadataPrefix="jpcoar_1.0" verb="GetRecord" identifier="oai:ipsj.ixsq.nii.ac.jp:00189726">https://ipsj.ixsq.nii.ac.jp/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:ipsj.ixsq.nii.ac.jp:00189726</identifier>
        <datestamp>2025-01-20T01:30:49Z</datestamp>
        <setSpec>1164:5352:9434:9497</setSpec>
      </header>
      <metadata>
        <jpcoar:jpcoar xmlns:datacite="https://schema.datacite.org/meta/kernel-4/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcndl="http://ndl.go.jp/dcndl/terms/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:jpcoar="https://github.com/JPCOAR/schema/blob/master/1.0/" xmlns:oaire="http://namespace.openaire.eu/schema/oaire/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:rioxxterms="http://www.rioxx.net/schema/v2.0/rioxxterms/" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns="https://github.com/JPCOAR/schema/blob/master/1.0/" xsi:schemaLocation="https://github.com/JPCOAR/schema/blob/master/1.0/jpcoar_scm.xsd">
          <dc:title>びまん性肺疾患診断における階層的特徴選択アプローチ</dc:title>
          <dc:title xml:lang="en">A Hierarchical Approach for Feature Selection with Diffuse Lung Disease</dc:title>
          <jpcoar:creator>
            <jpcoar:creatorName>遠藤, 瑛泰</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>永田, 賢二</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>木戸, 尚治</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>庄野, 逸</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Akihiro, Endo</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Kenji, Nagata</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Shoji, Kido</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Hayaru, Shouno</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:subject subjectScheme="Other">MPS一般セッション(2)</jpcoar:subject>
          <datacite:description descriptionType="Other">びまん性肺疾患の診断は医師の目視により CT 画像上の陰影から判断されるが，見られる陰影は多種多様であり，診断が難しい場合がある．このような問題に対して計算機による診断支援を適用させる場合，パターン認識を用いた陰影の識別が有効である．パターン認識においては，入力に不適切な特徴が含まれると汎化性能が低下するおそれがあるので適切な特徴選択が必要である．本研究では，テクスチャ特徴から有効な特徴の組み合わせを検索するというアプローチをとるものとする．一般に特徴選択問題は組み合わせ最適化であるため，特徴数が多い場合，すべての組み合わせの有効性を確認することは困難になる．そこで本研究では，二段階の階層的な特徴選択手法を考える．一段階目の選択では，特徴の特徴の出自による大まかなグループ単位での刈り込みを行い，二段階目では刈り込まれたグループに属する特徴全ての組み合わせを検索するという手法を採っている．評価にはテスト用データにおける状態密度分布を用いて，有効な組み合わせの汎化性能とスパース推定との比較を行った．</datacite:description>
          <datacite:description descriptionType="Other">It is difficult that diagnose Diffuse Lung Disease (DLD) from the textures on the CT image which are diverse. In such cases, pattern recognition using computers is effective. On one hand, unnecessary feature got as input, then there is a risk that the generalization ability being worse. In this research, for DLD classification with texture features, we tried to selected the effective features combination for each class. However, since texture features are too much, it is difficult to check all combinations. Therefore, we approched reducing combinations with a hierarchical feature selection. First, we selected effective combination of groups which include features extracted by a texture analysis. Second, from features in selected group, we selected combination of features. To evaluate selected feature combination, we calcurated test scores about all combinations and compared to Lasso which is one of sparse estimation method.</datacite:description>
          <dc:publisher xml:lang="ja">情報処理学会</dc:publisher>
          <datacite:date dateType="Issued">2018-06-06</datacite:date>
          <dc:language>jpn</dc:language>
          <dc:type rdf:resource="http://purl.org/coar/resource_type/c_18gh">technical report</dc:type>
          <jpcoar:identifier identifierType="URI">https://ipsj.ixsq.nii.ac.jp/records/189726</jpcoar:identifier>
          <jpcoar:sourceIdentifier identifierType="ISSN">2188-8590</jpcoar:sourceIdentifier>
          <jpcoar:sourceIdentifier identifierType="NCID">AA12055912</jpcoar:sourceIdentifier>
          <jpcoar:sourceTitle>研究報告バイオ情報学（BIO）</jpcoar:sourceTitle>
          <jpcoar:volume>2018-BIO-54</jpcoar:volume>
          <jpcoar:issue>33</jpcoar:issue>
          <jpcoar:pageStart>1</jpcoar:pageStart>
          <jpcoar:pageEnd>6</jpcoar:pageEnd>
          <jpcoar:file>
            <jpcoar:URI label="IPSJ-BIO18054033.pdf">https://ipsj.ixsq.nii.ac.jp/record/189726/files/IPSJ-BIO18054033.pdf</jpcoar:URI>
            <jpcoar:mimeType>application/pdf</jpcoar:mimeType>
            <jpcoar:extent>1.6 MB</jpcoar:extent>
            <datacite:date dateType="Available">2020-06-06</datacite:date>
          </jpcoar:file>
        </jpcoar:jpcoar>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
