Search Results 1-20 of 434

  • Predictive Model Construction for Smart Highway Facilities Deterioration Using Data Mining  [in Japanese]

    Nishimura Kazunori , Murakami Chiharu , Murayama Mitsuhiro , Yamaguchi Hiromasa

    … Therefore, we apply a mining technique to the failure data, create a model for predicting deterioration timing, and construct a safety and security environment for road facilities.</p> …

    IEEJ Transactions on Industry Applications 140(10), 746-752, 2020


  • Chloroplast genome mining reveals the phylogeographic structure and diversity of warm-edge <i>Fagus crenata</i> forests  [in Japanese]

    Worth James

    … is a dominant tree of the cool temperate forest biome of Japan that ranges from mountainous areas of southern Kyushu, Shikoku and Honshu to the lowlands of southern Hokkaido. … at the warm-edge limit in southern Kyushu and the Kanto region, often co-occurring with warm temperate tree species, are of particular biogeographical and conservation interest. …

    The Japanese Forest Society Congress 131(0), 234, 2020


  • Image Data Mining for Extracting Relations between Radiomic Features and Subtypes of Breast Cancer  [in Japanese]

    WADA Natsumi , UCHIYAMA Yoshikazu

    … The purpose of this study is to develop image data mining technology to analyze the relationship between image phenotype and genotype of a lesion. … By using CART (Classification and Regression Trees) algorithm with these radiomic features as input data, a classification tree that outputs 5 breast cancer subtypes were automatically generated. … The overall accuracy of the classification tree for identifying 5 breast cancers was 83.7% (41/49). …

    Medical Imaging and Information Sciences 37(2), 28-33, 2020

    J-STAGE  Ichushi Web 

  • Detection of Diagnostic Pathways by Applying Data Mining Method to Health Insurance Claims:Application to rare disease: pulmonary arterial hypertension  [in Japanese]

    TSUKUDA Masafumi , HAMURO Yukinobu

    <p>レセプトデータから、希少疾患である肺動脈性肺高血圧症の診断につながる知見を発見する。レセプトは医療機関が保険者への医療費の請求を目的として作成されるが、近年その利活用が進み、医療データベースも次々と大規模化している。また、これらのデータはID付POSデータと構造はほぼ同様であり、他の商業・サービスの分野で培われた様々な分析手法の応用も可能である。また、患者数が少なく社会的認知度も …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4K3GS301-4K3GS301, 2020


  • Evaluation Index for Constructing User Preferable Decision Tree  [in Japanese]

    TERABE Masahiro , OHTA Tomoaki , YAMANAKA Yuji , MAEDA Terutoshi

    <p>決定木は高速に解釈しやすいモデルを導出できるため,データマイニングの実務においてよく用いられる機械学習手法の一つである.決定木のサイズは,モデルの理解しやすさの面からは小さい方が望ましいが推定精度を重視すると一般に大きくなる傾向になる,というトレードオフが存在する.決定木のサイズを調整する方法として事前および事後の枝刈り法とその基準やパラメータが準備されているが,ユーザにとって好 …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4K3GS302-4K3GS302, 2020


  • Rule Extraction from Decision Tree Ensembles by Answer Set Programming  [in Japanese]

    TAKEMURA Akihiro , INOUE Katsumi

    <p>機械学習分野における課題の一つに,学習済みモデルの解釈性がある.本研究では,解集合プログラミング (Answer Set Programming; ASP) を用いて決定木アンサンブルからルールを抽出する手法を提案する.決定木の構造に対して,ASPに符号化したパターンマイニングの手法を適用することで,ルール集合を宣言的な方法で抽出する.そのため,目的とする集合の性質が複数存在する …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 3E5GS203-3E5GS203, 2020


  • Fast Enumeration of Pairs of Minimal Generators and Their Closure Itemsets  [in Japanese]

    NABESHIMA Takahiro , IWANUMA Koji

    <p>昨今のデータマイニング分野において,データに内在する潜在因子間の関係を抽出する技術の開発は重要なものとなっている.本研究は,その潜在因子間の関係を表現する負の相関ルールの抽出に関する研究を支えるものである.負の相関ルールはデータ中に非常に多く存在するため,負の相関ルールを圧縮して抽出することが重要となる.この技術において重要となる情報が,データ中に存在する,等しい出現トランザクシ …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 2N4OS17a04-2N4OS17a04, 2020


  • Machine Learning based Prediction of DPC from Discharge Summaries  [in Japanese]

    KIMURA Tomohiro , TSUMOTO Shusaku , HIRANO Shoji

    <p>【目的】 退院時要約及び関連する診療情報にテキスト処理と機械学習の手法を適用,各症例のDPCを推定するシステムを開発する。システムによって正確な推定が行われれば,推定と実際のDPCとに相違がある場合に絞り,DPCコーディングに問題があるかを充分な時間で検討することが可能となる。 【方法】 抽出した退院時要約でキーワードの分割表を作成。次いで,対応分析を行い,各キーワードとDPCに …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 2I1GS204-2I1GS204, 2020


  • Tree Model Induction from Texts in Discharge Summaries  [in Japanese]

    TSUMOTO Shusaku , KIMURA Tomohiro , HIRANO Shoji

    … <p>This paper investigates the characteristics of decision trees for discharge summaries classifier, focusing on (1) selection of features in text mining and (2) splitting measures. … The results shows that decision tree induction methods select attributes independently of the importance obtained by morphological analysis, which have small changes in the choice of splitting meatures. …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 1K3ES203-1K3ES203, 2020


  • Acute myocardial infarction (AMI) specificity in high-sensitivity troponin I in psychiatric emergency: Comparative study using biochemical general-purpose-equipment-compatible biomarkers and preparation of diagnostic guide using data mining  [in Japanese]

    NAGAOKA Ai , IZAWA Sachiko , OGURA Tsutomu , NISHIDA Noriko , SATO Syuko , KOYA Keiko , INUO Eriko

    <p>東京都立松沢病院は898床(精神科808床)を抱え,救急受診時の検査として高感度トロポニンI(high sensitive troponin I; hs-TnI)を実施している。hs-TnI導入後の陽性率は,過去に当院で算出した急性心筋梗塞(acute myocardial infarction; AMI)の有病率に比べオッズ比で3倍以上高い。そこで,まずhs-TnI値の信頼性の …

    Japanese Journal of Medical Technology 69(1), 63-68, 2020

    J-STAGE  Ichushi Web 

  • Using a machine learning algorithm to predict acute graft-versus-host disease following allogeneic transplantation

    Arai Yasuyuki , Kondo Tadakazu , Fuse Kyoko , Shibasaki Yasuhiko , Masuko Masayoshi , Sugita Junichi , Teshima Takanori , Uchida Naoyuki , Fukuda Takahiro , Kakihana Kazuhiko , Ozawa Yukiyasu , Eto Tetsuya , Tanaka Masatsugu , Ikegame Kazuhiro , Mori Takehiko , Iwato Koji , Ichinohe Tatsuo , Kanda Yoshinobu , Atsuta Yoshiko

    … The alternating decision tree (ADTree) machine learning algorithm was applied to develop models using the training cohort (70%). … The relatively high reproducibility and low impacts from the interactions among the variables indicate that the ADTree algorithm, along with the other data-mining approaches, may provide tools for establishing risk score. …

    Blood Advances 3(22), 3626-3634, 2019-11-26


  • Complete mitochondrial genomes from transcriptomes: assessing pros and cons of data mining for assembling new mitogenomes

    Giobbe Forni , Guglielmo Puccio , Thomas Bourguignon , Theodore Evans , Barbara Mantovani , Omar Rota-Stabelli , Andrea Luchetti

    … Transcriptome-derived mitogenomes were found highly similar to the conspecific ones obtained from genome sequencing (nucleotide divergence ranging from 0% to 3.5%) and yielded a congruent phylogenetic tree. …

    Scientific Reports 9(1), 14806, 2019-10-15


  • Educational effects of water quality surveys for students studying to be nursing teachers  [in Japanese]

    千田 眞喜子

    花園大学社会福祉学部研究紀要 = Annual report of the Social Welfare Department at Hanazono University (27), 85-92, 2019-03

    IR  Ichushi Web 

  • A Content-Centric Platform for Home Networks

    Pai-Hui Wang , Tse-Han Wang , Shih-Ting Lin , Pei-Wen Chen , Chien-Chao Tseng , Jiun-Long Huang

    IEICE Proceeding Series (59), P2-15, 2019


  • A Content-Centric Platform for Home Networks

    Pai-Hui Wang , Tse-Han Wang , Shih-Ting Lin , Pei-Wen Chen , Chien-Chao Tseng , Jiun-Long Huang

    IEICE Proceeding Series (56), P2-15, 2019


  • Crash Severity Analysis Through Nonparametric Machine Learning Methods

    AGRAWAL Vaibhav , CHATTERJEE Sudipa , MITRA Sudeshna

    … Classification and Regression Tree (CART), Extreme Gradient Boosting (XGBoost) and Support Vector Machines (SVM) have been utilised to identify the critical factors affecting the severity of traffic crashes on the State Highways of India. …

    Journal of the Eastern Asia Society for Transportation Studies 13(0), 2614-2629, 2019


  • 決定木と機械学習の手法を導入した工具カタログマイニングの提案  [in Japanese]

    Asakura Akihito , Yamada Koutarou , Sakuma Taishi , Hirogaki Toshiki , Aoyama Eiichi , Kodama Hiroyuki

    <p>近年のCAD/CAMシステムの発展により,容易にNCプログラムを生成することが可能となったが,加工をする上で重要な切削条件の決定は熟練技能者の知識や経験に頼っているのが現状である.そこで膨大なデータを有する工具カタログに対して,データマイニング手法を適用した切削条件支援システムを提案している.機械学習の決定木とランダムフォレストにより予測モデルを構築し,ケーススタディとして切削条 …

    Proceedings of JSPE Semestrial Meeting 2019A(0), 266-267, 2019


  • Analyses of Factors Affecting Residential Location Choice Based on Consultation of Migrants  [in Japanese]

    Kuwano Masashi

    <p>鳥取市では移住者を増加させるために相談支援窓口の設置や定住促進・Uターン支援の専任相談員を配置するなどの取り組みを行っており,平成18年から平成29年9月までに,3,984世帯の移住検討者からの相談が寄せられている.ここでは,相談世帯の世帯属性や移住を検討する理由,相談内容などが相談記録票として記録されている.さらに,相談に訪れた世帯のうち,実際に鳥取市に移住した1,176世帯に …

    Journal of the City Planning Institute of Japan 54(3), 848-855, 2019


  • Proposal of data mining process for tool catalog data introducing machine learning  [in Japanese]

    SAKUMA Taishi , ASAKURA Akihito , YAMADA Kotaro , HIROGAKI Toshiki , AOYAMA Eiichi , KODAMA Hiroyuki

    … Especially, we look at the data mining method and the tool catalog as a useful big data base which is updated by tool makers because it is easy for CAD/CAM engineers and machine tool operators to obtain it in the manufacturing fields. … In the present report, we proposed the visualization and consideration of cutting condition determination process based on a decision tree method which is one type of statistical analysis method for radius-endmill data base. …

    Transactions of the JSME (in Japanese) 85(877), 19-00215-19-00215, 2019


  • Hierarchical Community Detection in Social Networks Based on Micro-Community and Minimum Spanning Tree

    WANG Zhixiao , HOU Mengnan , YUAN Guan , HE Jing , CUI Jingjing , ZHU Mingjun

    … Most existing hierarchical community detection methods need one or more tunable parameters to control the resolution levels, and the obtained dendrograms, a tree describing the hierarchical community structure, are extremely complex to understand and analyze. … In the paper, we propose a parameter-free hierarchical community detection method based on micro-community and minimum spanning tree. …

    IEICE Transactions on Information and Systems E102.D(9), 1773-1783, 2019


Page Top