Updated on 2025/05/10

写真a

 
Taku Moriyama
 
Organization
Graduate School of Data Science Department of Data Science Associate Professor
School of Data Science Department of Data Science
Title
Associate Professor
Homepage
https://sites.google.com/site/takumoriyamahp/
External link

Degree

  • 数理学博士 ( 九州大学 )

Research Interests

  • ノンパラメトリック統計

  • 統計的推測の漸近理論

  • 極値統計学

  • 応用統計学

Research Areas

  • Informatics / Statistical science

Education

  • Kyushu University

    2016.4 - 2018.3

    　 More details

  • Kyushu University

    2014.4 - 2016.3

    　 More details

  • Kyushu University   School of Sciences   Department of Mathematics

    2010.4 - 2014.3

    　 More details

Research History

  • Yokohama City University   School of Data Science   Associate Professor

    2023.4

    　 More details

  • Tottori University   Assistant Professor

    2019.4 - 2023.3

    　 More details

  • Kyushu University

    2018.4 - 2019.3

    　 More details

Professional Memberships

▼display all

Papers

  • Application of nonparametric approach to extreme value inference in distribution estimation of sample maximum and its properties

    T. Moriyama

    Australian and New Zealand Journal of Statistics   2025

    　More details

    Publishing type：Research paper (scientific journal)  

    Extreme value theory has constructed asymptotic properties of the sample maximum. This article concerns probability distribution estimation of the sample maximum. The traditional approach is parametric fitting to the limiting distribution—the generalised extreme value distribution; however, the model in non-limiting cases is misspecified to a certain extent. We propose a plug-in type of nonparametric estimator that does not need model specification. Asymptotic properties of the distribution estimator are derived. The simulation study numerically investigates the relative performance in finite-sample cases. This study assumes that the underlying distribution of the original sample belongs to one of the Hall class, the Weibull class or the bounded class, whose types of the limiting distributions are all different: the Fréchet, Gumbel or Weibull. It is proven that the convergence rate of the parametric fitting estimator depends on both the extreme value index and the second-order parameter, and gets slower as the extreme value index tends to zero. On the other hand, the rate of the nonparametric estimator is proven to be independent of the extreme value index under certain conditions. The numerical performances of the parametric fitting estimator and the nonparametric estimator are compared, which shows that the nonparametric estimator performs better, especially for the extreme value index close to zero. Finally, we report two real case studies: the Potomac River peak stream flow (cfs) data and the Danish Fire Insurance data.

    DOI： 10.1111/anzs.12436

    Scopus

    researchmap

  • Comparative study on excess distribution estimation in iid settings

    Taku Moriyama

    Communications in Statistics - Theory and Methods   54 ( 7 )   2092 - 2108   2025

    　More details

    Publishing type：Research paper (scientific journal)  

    Abstract.: This study considers excess distribution estimation in iid settings. There are two ways for the estimation; the fitting to the generalized Pareto distribution and the fully non parametric estimation. The fitting estimator is justified by the approximation proven in the extreme value theory; however, the accuracy depends on how extremely large the target is. The non parametric estimator does not need an approximation and has the advantage of wide applicability. This study conducts both theoretical and numerical comparative study on excess distribution estimation. Asymptotic convergence rates of two estimators are obtained, and the mean integrated squared errors are numerically surveyed by simulation study. An illustrative example of Abisko rainfall amount is presented.

    DOI： 10.1080/03610926.2024.2358864

    Scopus

    researchmap

  • Relational analysis of route searches and transportation IC card use

    Mio Hosoe, Masashi Kuwano, Taku Moriyama

    Transportation Research Procedia   82   957 - 970   2025

    　More details

    Publishing type：Research paper (international conference proceedings)  

    Route search data are saved in public transportation route search systems. These data record the potential travel plans of searchers and are expected to serve as a reliable source of information to predict travel demand. However, route search data merely represent latent demand and their relationship with actual traffic demand is not known. The purpose of this study was to identify the relationship between the number of route searches and the number of actual public transportation users to predict traffic demand using route search data. To achieve this, both route search data and transportation IC card data were analyzed for the Kotoden lines that operate in Kagawa Prefecture, Japan. By adopting an approach that combined bivariate state-space and weighted regression models, we extracted the varying hidden relationships between the two seemingly unrelated data types and modeled the behaviorally related parts. The results revealed a positive correlation between sudden surges in the number of route searches and transportation IC card use.

    DOI： 10.1016/j.trpro.2024.12.106

    Scopus

    researchmap

  • Reduction of Potential Boundary Bias in Kernel Cumulative Distribution Estimation in Univariate and Multivariate Settings

    Taku Moriyama

    Journal of Statistical Theory and Practice   18 ( 1 )   2024.3

    　More details

    Publishing type：Research paper (scientific journal)  

    We propose a new method for nonparametric estimation of a probability distribution and its endpoint. As is well known, the kernel distribution estimator suffers from the boundary bias problem when the endpoint is finite. When the support of the density is unknown, it is necessary to estimate it first. Hall and Park (Annals Stat 1460-1479, 2002) proposed estimating the endpoint by using the sample maximum, which is substituted for the endpoint in a density estimator. We propose a new estimator of the endpoint, which is intended to reduce the boundary bias of the distribution estimator. It is demonstrated that the proposed distribution estimator is numerically superior in the sense of an integrated squared error. Moreover, we discuss the extension of the proposed method to a multivariate case. A new method for estimating the joint probability distribution is also free from the boundary bias and performs numerically better than the naive distribution estimator.

    DOI： 10.1007/s42519-024-00367-6

    Scopus

    researchmap

  • Prediction of railroad user count using number of route searches via bivariate state–space modeling

    Masashi Kuwano, Mio Hosoe, Taku Moriyama

    The Journal of Supercomputing   80 ( 4 )   4554 - 4576   2023.9

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

    Conventional demand-prediction methods predominantly rely on past user behaviors to predict regular future transportation demands using acquired user preference data. Nevertheless, predicting unforeseen travel demands arising from bad weather or emergency events remains challenging owing to the absence of data on such future contingencies. This study introduces a method to predict travel demand by leveraging search history data, which potentially signal unforeseen travel requirements. We elucidate the correlation between the search count and integrated circuit (IC) card usage on an aggregate level. Subsequently, we propose a two-stage analytical technique to estimate the number of IC card usages based on route-search counts. Our findings demonstrate that the proposed model has superior accuracy, and the route-search count plays a pivotal role in predicting the number of IC card usages, especially unforeseen shifts in demand.

    DOI： 10.1007/s11227-023-05642-0

    Scopus

    researchmap

    Other Link： https://link.springer.com/article/10.1007/s11227-023-05642-0/fulltext.html

  • A statistical method for estimating piecewise linear sales trends

    Taku Moriyama, Masashi Kuwano, Masahito Nakayama

    Journal of Marketing Analytics   12 ( 2 )   436 - 444   2023.2

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

    Due to the structural breaks in time series, estimated current trend of product sales differs between the case where data for the entire span are used and the case where only the most recent data are used. The purpose of this study is to establish the piecewise linear approximation (PLA) as a trend analysis method that accounts for the structural breaks. PLA uses the complete data to simultaneously estimate the breakpoints and the continuously connected trends, immediately before and after the break. Thus, PLA not only ensures the ease of interpretation of the results, but also eliminates the probability of using discretion by uniquely determining the current trend, making the estimated result reliable. The case study demonstrates the proposition that, several products’ sales trends and the necessity of determining an appropriate time span for data analysis, underwent changes at least once. The method’s validity is demonstrated by showing the changes of the sales trends immediately after analyzed store’s renovation. Data collection from the time period immediately prior to a structural break can help identify the factors changing the product sales.

    DOI： 10.1057/s41270-023-00207-9

    Scopus

    researchmap

    Other Link： https://link.springer.com/article/10.1057/s41270-023-00207-9/fulltext.html

  • 経路検索データを用いた鉄道路線の需要予測モデルの提案 Reviewed

    78 ( 5 )   I_539 - I_551   2023

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Japan Society of Civil Engineers  

    DOI： 10.2208/jscejipm.78.5_i_539

    researchmap

  • Change-point Detection for Accuracy Improvement of Software Reliability Assessment

    Minamino, Y, Danjo, S, Kuwano, M, Moriyama, T, Inoue, S

    The 28th Issat International Conference on Reliability & Quality in Design   279 - 283   2023

    　More details

    Publishing type：Research paper (international conference proceedings)  

    In the software development testing phase, the development manager may intentionally increase or decrease the number of test personnel or change the fault target according to the testing progress. These changes in the testing environment cause changes in the trend of software reliability growth process. Furthermore, changes in the testing environment are one factor that reduces the accuracy of software reliability assessments based on the existing software reliability growth models (SRGMs). Previous studies have proposed several SRGMs that consider a change-point, with many examples of its application to fault-counting data without allowing for the change-point effect; however, the statistical change-point in the data itself is not considered, including its detection methods. This study uses Change Finder, one of the anomaly detection methods, to detect a statistical change-point from the fault-counting data. We apply the detection result to the delayed S-shaped (DSS) SRGM considering a changepoint. The effectiveness of “Change Finder” is confirmed by comparing the goodness-of-fit with a case that considers a change in the testing environment.

    Scopus

    researchmap

  • Change in Travel Demand under the COVID-19 Pandemic using Route-Search History Data Reviewed

    Hosoe, M, Kuwano, M, Moriyama, T

    Proceedings of The 15th international conference of Eastern Asia Society for Transportation Studies   2023

    　More details

  • 全国版と地方版の経路検索サービスにおける検索件数の比較分析 Reviewed

    大江広高, 桑野将司, 細江美欧, 森山卓, 南野友香

    都市計画論文集   57 ( 3 )   1288 - 1294   2022.10

    　More details

  • Trip Purpose Inference Based on the Relationship between Route Search Records and Regional Characteristics Reviewed

    Mio Hosoe, Masashi Kuwano, Taku Moriyama

    International Journal of Intelligent Transportation Systems Research   20 ( 1 )   299 - 308   2022.4

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

    DOI： 10.1007/s13177-022-00295-4

    researchmap

    Other Link： https://link.springer.com/article/10.1007/s13177-022-00295-4/fulltext.html

  • Extraction of Sales Relevance from POS Data Based on Non negative Matrix Factorization with Regularization Reviewed

    Hamaya, S, Minamino, Y, Moriyama, T, Hosoe, M, Kuwano, M

    The 27th Issat International Conference on Reliability & Quality in Design   2022

    　More details

  • Identification of Dates on which Spikes in Route Searches Occurred and Discussion of the Factors Reviewed

    Moriyama, T, Kuwano, M, Hosoe, M

    2022

    　More details

  • Extraction of Power Consumption Patterns using Non-negative Tucker Decomposition Reviewed

    Moriyama, T, Hosoe, M, Kuwano, M, Minamino, Y

    2022 IEEE International Conference on Big Data   2022

    　More details

  • Analysis of Factors Affecting Variation Patterns of Bus Route Search Records Reviewed

    Mio Hosoe, Masashi Kuwano, Taku Moriyama, Kentaro Nakai, Kazunori Sugahara

    Journal of the City Planning Institute of Japan   56 ( 3 )   788 - 794   2021.10

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：The City Planning Institute of Japan  

    DOI： 10.11361/journalcpij.56.788

    researchmap

  • Changes in Consciousness of Users and Drivers brought by Community Car-sharing Service Reviewed

    Masashi Kuwano, Kaho Masutani, Taku Moriyama, Mio Hosoe

    Journal of the City Planning Institute of Japan   56 ( 3 )   850 - 856   2021.10

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：The City Planning Institute of Japan  

    DOI： 10.11361/journalcpij.56.850

    researchmap

  • Causal inference for contemporaneous effects and its application to tourism product sales data Reviewed

    Taku Moriyama, Masashi Kuwano

    Journal of Marketing Analytics   2021.8

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

    DOI： 10.1057/s41270-021-00130-x

    researchmap

    Other Link： https://link.springer.com/article/10.1057/s41270-021-00130-x/fulltext.html

  • バス経路検索数の変動パターンに影響する要因の分析 Reviewed

    細江美欧, 桑野将司, 森山卓, 中井健太郎, 菅原一孔

    都市計画論文集   56 ( 3 )   788 - 794   2021

    　More details

  • コミュニティ・カーシェアリング導入前後における利用者とドライバーの意識変化 Reviewed

    桑野将司, 升谷吏歩, 森山卓, 細江美欧

    都市計画論文集   55 ( 3 )   850 - 856   2021

    　More details

  • Prediction of Railroad User Count Using Number of Route Searches Via Bivariate State–Space Modeling

    Masashi Kuwano, Mio Hosoe, Taku Moriyama

    SSRN Electronic Journal   2021

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Elsevier BV  

    DOI： 10.2139/ssrn.3994304

    researchmap

  • A method for extracting travel patterns using data polishing. Reviewed

    Mio Hosoe, Masashi Kuwano, Taku Moriyama

    Journal of Big Data   8 ( 1 )   2021

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

    <title>Abstract</title>With recent developments in ICT, the interest in using large amounts of accumulated data for traffic policy planning has increased significantly. In recent years, data polishing has been proposed as a new method of big data analysis. Data polishing is a graphical clustering method, which can be used to extract patterns that are similar or related to each other by identifying the cluster structures present in the data. The purpose of this study is to identify the travel patterns of railway passengers by applying data polishing to smart card data collected in the Kagawa Prefecture, Japan. To this end, we consider 9,008,709 data points collected over a period of 15 months, ranging from December 1st, 2013 to February 28th, 2015. This dataset includes various types of information, including trip histories and types of passengers. This study implements data polishing to cluster 4,667,520 combinations of information regarding individual rides in terms of the day of the week, the time of the day, passenger types, and origin and destination stations. Via the analysis, 127 characteristic travel patterns are identified in aggregate.

    DOI： 10.1186/s40537-020-00402-w

    researchmap

    Other Link： http://link.springer.com/article/10.1186/s40537-020-00402-w/fulltext.html

  • 経路検索に現れる移動需要と駅周辺環境の関連性分析 Reviewed

    土木学会論文集D3（土木計画学）   76 ( 5 )   l_377 - l_384   2021

    　More details

  • 交通系ICカードデータからの類似行動の抽出

    細江美欧, 桑野将司, 森山卓, 宮崎耕輔, 伊藤昌毅

    土木学会論文集D3（土木計画学）   76 ( 5 )   l_957 - l_966   2021

    　More details

  • Conditional probability density and regression function estimations with transformation of data Reviewed

    Taku Moriyama, Yoshihiko Maesono

    Bulletin of informatics and cybernetics   52   1 - 25   2020.3

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Kyushu University  

    DOI： 10.5109/2558879

    researchmap

  • New kernel estimators of the hazard ratio and their asymptotic properties Reviewed

    Moriyama Taku, Maesono Yoshihiko

    Annals of the Institute of Statistical Mathematics   72 ( 1 )   187 - 211   2020

    　More details

  • グラフ研磨を用いた乗降パターンによる駅のクラスタリング Reviewed

    細江美欧, 桑野将司, 森山卓

    都市計画論文集   55 ( 3 )   690 - 696   2020

    　More details

  • 中山間地域における行政サービスから見た自動運転技術の導入可能性 Reviewed

    桑野将司, 谷本圭志, 森山卓

    農村計画学会誌   39   245 - 252   2020

    　More details

  • Travel Pattern Extraction from Smart Card Data using Data Polishing Reviewed

    Mio Hosoe, Masashi Kuwano, Taku Moriyama, Kosuke Miyazaki, Masaki Ito

    Proceedings of 2019 IEEE International Conference on Big Data   3563 - 3572   2019

    　More details

    Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

    DOI： 10.1109/BigData47090.2019.9005450

    researchmap

    Other Link： https://dblp.uni-trier.de/db/conf/bigdataconf/bigdataconf2019.html#HosoeKMMI19

  • Smoothed alternatives of the two-sample median and Wilcoxon's rank sum tests Reviewed

    Moriyama Taku, Maesono Yoshihiko

    STATISTICS   52 ( 5 )   1096 - 1115   2018

    　More details

  • Smoothed nonparametric tests and approximations of p-values Reviewed

    Yoshihiko Maesono, Taku Moriyama, Mengxin Lu

    Annals of the Institute of Statistical Mathematics   70 ( 5 )   1 - 14   2017.8

    　More details

    Language：English   Publishing type：Research paper (scientific journal)   Publisher：Springer Tokyo  

    We propose new smoothed sign and Wilcoxon’s signed rank tests that are based on kernel estimators of the underlying distribution function of the data. We discuss the approximations of the p-values and asymptotic properties of these tests. The new smoothed tests are equivalent to the ordinary sign and Wilcoxon’s tests in the sense of Pitman’s asymptotic relative efficiency, and the differences between the ordinary and new tests converge to zero in probability. Under the null hypothesis, the main terms of the asymptotic expectations and variances of the tests do not depend on the underlying distribution. Although the smoothed tests are not distribution-free, making use of the specific kernel enables us to obtain the Edgeworth expansions, being free of the underlying distribution.

    DOI： 10.1007/s10463-017-0614-0

    Web of Science

    Scopus

    researchmap

  • Asymptotic properties of a kernel type estimator of a density ratio Reviewed

    Moriyama Taku, Maesono Yoshihiko

    Bulletin of Informatics and Cybernetics   48   37 - 46   2016

    　More details

▼display all

MISC

  • 超過分布関数の推定量の精度比較について

    森山卓

    統計関連学会連合大会講演報告集   2024   2024

    　More details

  • Change-point Detection of Fault Counting Data Based on Anomaly Detection Methodology for Software Reliability Assessment

    檀上心, 南野友香, 桑野将司, 森山卓, 井上真二

    電子情報通信学会技術研究報告(Web)   123 ( 78(R2023 7-9) )   2023

    　More details

  • 標本最大値の確率分布のセミパラメトリック推定

    森山卓

    統計関連学会連合大会講演報告集   2023   2023

    　More details

  • DEMAND FOCASTING MODEL FOR RAILROAD USING ROUTE-SEARCH HISTORY DATA

    細江美欧, 桑野将司, 森山卓

    土木計画学研究・講演集(CD-ROM)   65   2022

    　More details

  • Product Relevance Analysis from POS Data Using Non Negative Matrix Factorization with Regularization

    浜屋聡太, 南野友香, 森山卓, 細江美欧, 桑野将司

    情報科学技術フォーラム講演論文集   21st   2022

    　More details

  • 標本最大値の確率分布の推定方法について

    森山卓

    統計関連学会連合大会講演報告集   2022   2022

    　More details

  • COMPARISON OF USAGE CHARACTERISTICS BETWEEN NATIONAL AND LOCAL ROUTE SEARCH SERVICES

    大江広高, 桑野将司, 森山卓, 細江美欧, 南野友香

    土木計画学研究・講演集(CD-ROM)   65   2022

    　More details

  • CHANGE OF NEEDS FOR ROUTE BUSES INFLUENCED BY COVID-19 BASED ON ROUTE SEARCH RECORDS

    細江美欧, 桑野将司, 森山卓

    土木計画学研究・講演集(CD-ROM)   66   2022

    　More details

  • A COPULA-BASED RELEVANCE AMALYSIS OF ROUTE SEARCH LOG DATA AND PUBLIC TRANSIT BORDING HISTORY DADA

    小西諒, 桑野将司, 森山卓, 細江美欧

    土木計画学研究・講演集(CD-ROM)   63   2021

    　More details

  • Statistical Trend Analysis of Sales Data with Structural Changes

    中山雅仁, 森山卓, 桑野将司

    情報科学技術フォーラム講演論文集   20th   2021

    　More details

  • ANALYSIS OF THE RELATIONSHIP BETWEEN ROUTE-SEARCH RECORDS AND REGIONAL CHARACTERISTICS

    中井健太郎, 細江美欧, 桑野将司, 森山卓

    土木計画学研究・講演集(CD-ROM)   63   2021

    　More details

  • Characteristic Analyses of Power Consumption using a Time-varying Coefficient Regression Model

    川崎孝智, 森山卓, 桑野将司

    情報科学技術フォーラム講演論文集   20th   2021

    　More details

  • AN ANALYSIS OF THE RELATIONSHIP BETWEEN ROUTE SEARCH LOG DATA AND RAILWAY SMART CARD DATA

    細江美欧, 桑野将司, 森山卓

    土木計画学研究・講演集(CD-ROM)   64   2021

    　More details

  • ANALYSIS OF THE RELATIONSHIP BETWEEN TRANSPORTATION DEMAND BASED ON ROUTE SEARCH RECORDS AND CHARACTERISTICS AROUND RAILWAY STATION

    細江美欧, 桑野将司, 森山卓

    土木計画学研究・講演集(CD-ROM)   61   2020

    　More details

  • EXTRACTION OF FLUCTUATIONS IN LOG DATA IN THE PUBLIC TRANSIT NAVIGATOR SYSTEM BY STATE-SPACE MODEL

    小田島輝知, 桑野将司, 森山卓, 細江美欧

    土木計画学研究・講演集(CD-ROM)   61   2020

    　More details

  • 標本最大値の確率分布推定における漸近的性質

    森山卓

    統計関連学会連合大会講演報告集   2020   2020

    　More details

  • Railway Station Clustering based on Origin-Destination Patterns using Graph Polishing

    細江美欧, 桑野将司, 森山卓

    都市計画論文集(Web)   55 ( 3 )   2020

    　More details

  • EXTRACTION OF SIMILAR BEHAVIOR FROM SMART CARD DATA

    細江美欧, 桑野将司, 森山卓, 宮崎耕輔, 伊藤昌毅

    土木計画学研究・講演集(CD-ROM)   60   2019

    　More details

  • 標本最大値のカーネル型分布推定について

    森山卓

    統計関連学会連合大会講演報告集   2019   2019

    　More details

  • ノンパラメトリックなハザード比推定のバイアス修正について

    森山卓, 前園宜彦

    統計関連学会連合大会講演報告集   2018   237   2018.9

    　More details

    Language：Japanese  

    J-GLOBAL

    researchmap

  • カーネル密度推定における適切な台の推定の必要性

    森山卓

    統計関連学会連合大会講演報告集   2017   9   2017.9

    　More details

    Language：Japanese  

    J-GLOBAL

    researchmap

  • カーネル型推定量の境界と推定精度の改良について

    森山卓

    統計関連学会連合大会講演報告集   2016   225   2016.9

    　More details

    Language：Japanese  

    J-GLOBAL

    researchmap

  • 二標本ノンパラメトリック検定の連続化と有意確率の近似について

    森山卓, 前園宜彦

    統計関連学会連合大会講演報告集   2015   142   2015.9

    　More details

    Language：Japanese  

    J-GLOBAL

    researchmap

  • ノンパラメトリック検定統計量の有意確率と連続化統計量について

    前園宜彦, 森山卓

    統計関連学会連合大会講演報告集   2014   212   2014.9

    　More details

    Language：Japanese  

    J-GLOBAL

    researchmap

▼display all

Research Projects

  • Development of a semiparametric approach to accurate risk assessment and its applications

    Grant number：23K16850  2023.4 - 2027.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Early-Career Scientists

    　 More details

    Grant amount：\4550000 （ Direct Cost: \3500000 、 Indirect Cost：\1050000 ）

    researchmap

  • 地方中小都市における小規模ビッグデータ群の融合による地域政策の立案と評価

    Grant number：23H01637  2023.4 - 2027.3

    日本学術振興会  科学研究費助成事業  基盤研究(B)

    桑野 将司, 谷本 圭志, 森山 卓, 南野 友香, 細江 美欧

    　 More details

    Grant amount：\18200000 （ Direct Cost: \14000000 、 Indirect Cost：\4200000 ）

    researchmap

  • 中小都市における検索履歴データを用いた動学的バス需要予測手法の開発

    Grant number：20H02277  2020.4 - 2023.3

    日本学術振興会  科学研究費助成事業 基盤研究(B)  基盤研究(B)

    桑野 将司, 谷本 圭志, 森山 卓, 伊藤 昌毅, 宮崎 耕輔, 細江 美欧

    　 More details

    Grant amount：\17680000 （ Direct Cost: \13600000 、 Indirect Cost：\4080000 ）

    本研究課題は，交通行動を直接捕捉するデータが不足している地方中小都市を対象に，経路検索サービスの検索履歴データを用いた交通需要予測の可能性を検証するとともに，移動希望に応じたバス運行計画の立案方法を提案することを目的とする．
    初年度の成果から地方中小都市を対象とした検索履歴データを利用しようとすると，経路検索数が発着地の組み合わせや日によっては0件となる0サンプル問題，中心部などの一部の駅を起終点とした経路検索数が多く，郊外部を起終点とした検索数が少ないというデータ偏在性の問題が発生することがわかった．これら検索履歴データの特徴を踏まえたうえで，経路検索行動と駅周辺環境との関連性をBayesian Adaptive Lasso Tobit分位点回帰モデルによって記述し，経路検索数が多くなる都市構成要因を明らかにし，交通系ICカード利用数の多寡に影響する要因との比較をおこなった．その結果，経路検索システムと交通系ICカードでは利用されやすい状況が異なるため，両者を単純に関連づけるようなモデル化では，経路検索数の増減で交通系ICカード利用数の増減は予測できないことがわかった．そこで，（1）2変量状態空間モデルによって経路検索数と交通系ICカード利用数の突発的需要を抽出し，（2）重み付き回帰モデルによって突発的需要変動間の関係性を定量化するという2段階分析方法を構築した．分析の結果，従前モデルとの予測精度の比較から，提案手法の有用性が確認できた．すなわち，経路検索数と交通系ICカード利用数に包含される突発的事象に起因する需要部分を関連づければ，経路検索数を用いることで交通系ICカード利用数の予測精度は高まることを示すことができた．

    researchmap

  • Accurate estimation of the probability distribution of sample maximum and its applications

    Grant number：19K20223  2019.4 - 2023.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research Grant-in-Aid for Early-Career Scientists  Grant-in-Aid for Early-Career Scientists

    　 More details

    Grant amount：\3510000 （ Direct Cost: \2700000 、 Indirect Cost：\810000 ）

    researchmap

Social Activities

  • 学問体験「知の冒険」（鳥取大学附属中学校）

    Role(s)： Lecturer

    2019.11

    　More details