|西井 龍映（にしい りゆうえい）||データ更新日：2018.06.01|
教授 ／ マス・フォア・インダストリ研究所 数学テクノロジー先端研究部門
|1.||西井 龍映, サポートベクター回帰における変数選択, 統計関連学会連合大会, 2017.09, [URL].|
|2.||Ryuei Nishii, Feature Selection of Support Vector Regression Based on Information Theoretic Criteria, The SIAM Workshop on Parameter Space Dimension Reduction, 2017.07.|
|3.||西井 龍映, Statistical analysis of global gene expression data and applications to plant growth, I2CNER Annual Meeting, 2017.02.|
|4.||西井 龍映, 太陽風が弱い地震の引き金であることの統計的検証, 科研費研究集会, 2017.01.|
|5.||西井 龍映, 深沢 祐太, Support Vector Machineにおける変数選択基準, 科研費研究集会, 2016.11.|
|6.||T. Nakamoto, R. Nishii, S. Eguchi , The prediction of ellipsoids for color matching problem, 科研費研究集会, 2016.11.|
|7.||Ryuei Nishii, Shojiro Tanaka, Overall review of statistical spatial relations of neighbor cells in deforestation models by human population and topographic attributes, 統計数理研究所共同研究集会, 2016.10.|
|8.||西井 龍映, ベイジアンネットワークによる構造学習と材料品質への応用ー統計的手法の産業界への貢献ー, 日本機械学会, 2016.09.|
|9.||西井 龍映, Detection of hub genes by sparse modeling of gene expression time series, I2CNER-IMI Joint Symposium, 2016.05, [URL].|
|10.||Shojiro Tanaka, Ryuei Nishii, Review on the methodology to explore functional forms of deforestation, 統計数理研究所共同研究集会, 2015.11, [URL].|
|11.||江田 智尊, Ryuei Nishii, Support Vector Machineにおける変数選択基準, 統計関連学会連合大会, 2015.09, [URL].|
|12.||Shojiro Tanaka, Ryuei Nishii, Incorporation of gridded data into the analysis of remotely-sensed images: Basic quantitative strategy to analyze deforestation by population growth, IEEE International Geoscience and Remote Sensing Symposium 2015, 2015.07, [URL].|
|13.||Ryuei Nishii, Shojiro Tanaka, Unified modeling based on SVM and SVR for prediction of forest area ratio by human population density and relief energy, IEEE International Geoscience and Remote Sensing Symposium 2015, 2015.07, [URL].|
|14.||Ryuei Nishii, Deforestation Modeling based on Statistical and Machine Learning Approaches, ISM symposium on ecological statistics, 2015.02, Deforestation is caused by various factors. In the literature, the impact of human activities as well as geographic circumstances on forests has been extensively discussed. We have studied statistical models for prediction of forest area ratio by covariates: human population density and relief energy observed in a grid-cell system. Parametric non-linear regression functions of the covariates were used for predicting forest coverage ratio and cubic spline functions were also used for detection of small fluctuation of regression functions. Furthermore, zero-one inflated distributions were proposed for classification of each site into one of three categories: completely-deforested, fully-forest-covered or partly-deforested areas. These methods took the spatial dependency into the modeling, which is not an easy task.
Our aim here is to substitute the previous statistical approach for machine learning approach based on SVM (support vector machine) and SVR (support vector regression). SVM will be used for classification of each site into one of the above-mentioned categories, and SVR for prediction of the forest coverage ratio. The proposed approach implements a neighbors' effect into the modeling easily. By our numerical study, it will be shown that the performance of the machine learning methods is comparable or superior to that of the statistical methods.
|15.||西井 龍映, 田中章司郎, Re-evaluation of topographic attributes with human population in deforestation framework with spatial dependency, 統計数理研究所 共同研究集会, 2014.12.|
|16.||Satoru Koda, Ryuei Nishii, Matsui Hidetoshi, Kohei Hamamura, Keiichi Mochida, Yoshihiko Onda, Tetsuya Sakurai, Takuhiro Yoshida, Stability assessment of short time series with periodism and its applications to detection of circadian rhythm of global gene expression data , INTERNATIONAL CONFERENCE ON MATHEMATICS, STATISTICS, AND FINANCIAL MATHEMATICS 2014, 2014.11.|
|17.||西井 龍映, ベイズモデルと環境空間データへの応用, 気候モデルの農業への応用2: 作物収量予測への統計的アプローチ, 2014.01, [URL].|
|18.||内 大介, 西井 龍映, Pan Qin, Logistic regression and MCMC for contextual classification of hyperspectral imagery, 科研費研究集会 ｢大規模で非定常な時系列・時空間データのモデル化とその推定・検定・予測法の研究｣, 2013.12, [URL].|
|19.||西井 龍映, 今さら聞けない統計解析, EDSFair 2013 , 2013.11, [URL].|
|20.||西井 龍映, 時系列回帰モデルのモデル選択とその応用, 応用数理学会 , 2013.09, [URL].|
|21.||Ryuei Nishii, Pan Qin, Daisuke Uchi, Nonlinear Bayesian unmixing of geospatial data based on Gibbs sampling, IEEE IGARSS 2013, 2013.07, [URL].|
|22.||Shojiro Tanaka, Ryuei Nishii, Effect evaluation of topographic attributes on forest coverage ratio based on digital elevation model
, IEEE IGARSS 2013, 2013.07, [URL].
|23.||Pan Qin, Kojiro Yanase, 西井 龍映, Multi-hour-ahead prediction of Dst index using nonlinear autoregressive models with exogenous variables, Japan Geoscience Union Meeting 2013, 2013.05.|
|24.||Shojiro Tanaka, Ryuei Nishii, Formulation of spatio-temporal dataset for human population and land-use/land-cover analysis on a grid-cell basis, 2012 4th International Conference on Environmental Science and Information Application Technology, 2012.12, Main driving force to land-use/land-cover change on the earth should be human activities, and the land-cover change represents a major source and a major element of global environmental change. In order to analyze this vital spatio-temporal phenomenon quantitatively, multidimensional real dataset is crucial. There are many cross-sectional datasets for ground verification purposes in the field of satellite remote sensing, but there should be very few datasets that contain both socio-economic data, amongst all, human population, and land-use/land-cover information together in time series on the same areas. Hence we formulated the dataset with use of population census data of every five years and housing trend research data also in every five years, both of which are in the form of grid-cells. .|
|25.||Ryuei Nishii, Daiki Miyata, and Shojiro Tanaka, Statistical frameworking of deforestation models based on human population density and relief energy, SPIE Remote Sensing 2012, 2012.09, [URL], This paper establishes a statistical framework of forest coverage models for spatio-temporal data. The forest
coverage ratio of grid-cell data is modeled by taking human population density and relief energy as explanatory
variables. The likelihood of the forest ratios is decomposed by the product of two likelihoods. The first likelihood
discussed by Nishii and Tanaka (2010) is due to trinomial logistic distributions on three categories: the ratios take
zero, one, or values between zero and one. We consider a precise modeling to the second likelihood for partlydeforested
ratios by considering a) spline functions to the additive mean structure, b) wide spatial dependency
of normal error terms, and c) an extended logistic type transform to the forest ratio. For spatio-temporal data,
we implement auto-regressive terms based on the ratios observed in past. The proposed model was applied to
real grid-cell data and resulted significant improvement compared to our previous model..
|26.||細坪 護挙, 西井 龍映
, 統計関連学会連合大会, 2012.09, [URL], 1988年から9時点における科研費採択と国公立大学教員の属性(所属大学,学位,職位,異動回数等)との関係をポアソン回帰,負の二項回帰,およびそれらのゼロインフレート版, ロジスティック回帰により考察する。.
|27.||Mohamad Huzaimy Bin Jusoh, 湯元 清文, Pan Qin, 西井 龍映, Nurul Shazana Abdul Hamid, Relationship between Solar Wind Parameters and Seismic Activities, Japan Geoscience Union Meeting 2012, 2012.05.|
|28.||野本裕太朗, Pan Qin, 西井 龍映, Mohamad Huzaimy Bin Jusoh, 湯元 清文, Relationship between Solar Wind Parameters and Seismic Activities, Japan Geoscience Union Meeting 2012, 2012.05.|
|29.||Ryuei Nishii, Statistical modeling of hyper-dimensional data and spatio-temporal data, Forum of Math for Industry 2011, 2011.10, [URL].|
|30.||白井 将博, 篠崎 裕昭, 西井 龍映, 江口 真透, マルコフ確率場に基づくカテゴリ被覆率のロジスティック型推定, 統計関連学会連合大会, 2011.09, .|
|31.||宮田大毅, 西井龍映, 田中章司郎 , 森林被覆率の非線形回帰モデリング, 統計関連学会連合大会, 2011.09, 地表面メッシュで観測された森林被覆率を当該メッシュの人口密度および起伏量の非線形回帰モデルを, スプライン関数で平均構造を記述した空間依存性をもつ誤差で表現した. 最適モデルにより森林減少に関する新しい知見が得られた..|
|32.||Ryuei Nishii, Statistical deforestation modeling based on zero-one inflated distributions with spatial dependence
, Forum for Interdisciplinary Mathematics 2010, 2010.12, [URL].
|33.||Shojiro TANAKA and Ryuei NISHII, An application of novel zero-one inflated distributions with spatial dependence for the deforestation modeling, 統計関連学会連合大会, 2010.09, [URL].|
|34.||Ryuei Nishii, An application of novel zero-one inflated distributions with spatial dependence for the deforestation modeling, IEEE IGARSS 2010, 2010.07, [URL].|
|35.||Pan Qin, Zi-Jiang Yang, Ryuei Nishii, Predictive control for dual-rate systems based on lifted state-space model identified by N4SID method, IEEE Conference on Decision and Control, 2009.12, [URL], We address a novel predictive control strategy for dual-rate systems in which the input updating period is different from the output sampling period based on lifted state-space model identified by a modified Numerical Subspace State-Space IDentification (N4SID). There are three steps in the predictive control strategy. Firstly, lifted state-space models are identified for dual-rate systems by the modified N4SID. Based on the identified lifted state-space model, we construct predictors which can predict the output of dual-rate systems in multi-step ahead. Combining the predictors with an objective function minimization, predictive control laws for dual-rate systems are derived..|
|36.||Ryuei Nishii and Tomohiko Ozaki, Contextual unmixing of geospatial data based on Markov random fields and conditional random fields, Whispers 2009, 2009.08.|
|37.||Ryuei Nishii, Tomohiko Ozaki, and Yoko Sawamura, Semi-supervised Contextual Classification and Unmixing of Hyperspectral Data based on Mixture Distributions, IEEE IGARSS 2009, 2009.07.|
|38.||Ryuei Nishii, Semi-Supervised Contextual Unmixing of Geospatial Data
, IASC 2008, 2008.12, [URL].
|39.||R. Nishii, Contextual Image Classification based on Statistics and Machine Learning, The 4th International Conference on Information and Communication Technology and Systems 2008, 2008.08, [URL].|
|40.||R. Nishii, Y. Sawamura, A. Nakamoto, and S. Kawaguchi, Contextual unmixing of geospatial data based on Gaussian mixture models and Markov random fields, IEEE IGARSS 2008, 2008.07, [URL].|
|41.||Shojiro TANAKA, Ryuei NISHII, Non-linear regression models to identify functional forms of deforestation, IEEE IGARSS 2008, 2008.07, [URL].|
|42.||Ryuei Nishii, Shinto Eguchi, Shuji Kawaguchi, Supervised classification of multispectral and hyperspectral images by statistical machine learning, COE , 2007.10.|
|43.||Shojiro Tanaka, Ryuei Nishii, Spatial logit models of deforestation due to population and relief energy in East Asia, IEEE IGARSS 2007, 2007.07.|
|44.||Shuji Kawaguchi, Ryuei Nishii, Hyperspectral image classification by Recursive Spatial Boosting based on the bootstrap method
, IEEE IGARSS 2007, 2007.07.
|45.||Ryuei Nishii, Shuji Kawaguchi, AdaBoost with different costs for misclassification and its applications to
contextual image classification, IEEE IGARSS 2006, 2006.09.
|46.||Shuji Kawaguchi, K. Yamazaki, Ryuei Nishii, Contextual unsupervised classification of remotely sensed imagery with mixels, SPIE, 2006.09.|
|47.||S. Tanaka, Ryuei Nishii, Extended spatial logit models of deforestation due to population and relief
energy in East Asia, SPIE, 2006.09.
|48.||Ryuei Nishii, Contextual image classification based on spatial boosting, IEEE, 2006.08.|
|49.||Shuji Kawaguchi, Ryuei Nishii, Hyperspectral image classification by AdaBoost with decision stumps based on composed feature variables., IEEE IGARSS 2006, 2006.08.|
|50.||Ryuei Nishii, Supervised Image Classification based on AdaBoost with Contextual Weak Classifiers, IEEE, 2004.09.|
|51.||R. Nishii, Contextual Image Segmentation based on AdaBoost and Markov Random Fields, IEEE, 2003.07.|
|52.||西井 龍映, リモートセンシング画像への統計的手法の応用, 応用統計学会, 2003.05.|
|53.||西井 龍映，森崎 洋二, 多重分光画像による画像分割とその応用, 日本統計学会, 2002.09.|
|54.||R. Nishii, Fusion of contextual classification and the existing classification result, IEEE, 2002.06.|
|55.||Y. Morisaki and R. Nishii, Contextual data fusion based on Markov random fields and its applications to image enhancement, Eighth International Conference on Statistics, Combinatorics and Related Areas, 2001.12.|
|56.||R. Nishii and Y. Morisaki, Spatial discriminant analysis based on power-elliptic distributions and power transformation, IEEE, 2001.07.|
|57.||Y. MORISAKI and R. NISHII, Multivariate image-enhancement by cokriging, International Conference on "Statistics, Combinatrics and Related Areas", 2000.12.|
|58.||R. Nishii and S. Tanaka, Spatial discrimination based on the ground truth with mixed categories, IEEE, 2000.07.|
|59.||R. Nishii, Selection of feature variables in spatial discrimination of remotely-sensed satellite imagery, IEEE, 1999.06.|
|60.||S. Tanaka and R. Nishii, Incorporation of human dimension into the analysis of remotely-sensed images, IEEE, 1999.06.|
|61.||S. Kusanobu, R. Nishii, H. Kawasaki, N. Yamaguchi, M. Ohtaki, Mortality map of lung cancer based on statistical spatial models, INTECOL, 1998.07.|
|62.||S. Tanaka and R. Nishii, Analysis of deforestation by spatial model with human population interactions, INTECOL, 1998.07.|