Updated on 2022/08/04

 
TOKUNAGA Terumasa
 
Scopus Paper Info  
Total Paper Count: 0  Total Citation Count: 0  h-index: 6

Citation count denotes the number of citations in papers published for a particular year.

Affiliation
Faculty of Computer Science and Systems Engineering Department of Artificial Intelligence
Job
Associate Professor
External link

Research Interests

  • neuroscience

  • Statistical Machine Learning

  • Image Analysis

  • Bayesian Inference

  • Anomaly detection

Research Areas

  • Informatics / Perceptual information processing

Undergraduate Education

  • 2006.03   Kyushu University   Faculty of Science   Graduated   Japan

Post Graduate Education

  • 2011.03   Kyushu University   Doctoral Program   Completed   Japan

  • 2008.03   Kyushu University   Master's Course   Completed   Japan

Degree

  • Kyushu University  -  Doctor of Science   2011.03

Biography in Kyutech

  • 2019.04
     

    Kyushu Institute of Technology   Faculty of Computer Science and Systems Engineering   Department of Artificial Intelligence   Associate Professor  

  • 2015.04
    -
    2019.03
     

    Kyushu Institute of Technology   Faculty of Computer Science and Systems Engineering   Department of Systems Design and Informatics   Associate Professor  

Biography before Kyutech

  • 2018.10 - 2022.03   Japan Science and Technology Agency   Japan

  • 2018.08 - 2019.03   Kyushu University   International Center for Space Weather Science and Education   Visiting Associate Professor   Japan

  • 2018.04 - 2019.03   Research Organization of Information and Systems, The Institute of Statistical Mathmatics   Data Science Center for Creative Design and Manufacturing   Visiting Associate Professor   Japan

  • 2013.05 - 2015.03   Research Organization of Information and Systems, The Institute of Statistical Mathmatics   Research and Development Center for Data Assimilation   Specially Appointed Assistant Professor   Japan

  • 2012.04   Meiji University   Meiji Institute for Advanced Study of Mathematical Science   visiting researcher   Japan

  • 2012.04 - 2013.04   Research Organization for information Science and Technology   Other Staff   Japan

  • 2011.04 - 2012.03   Meiji University   Meiji Institute for Advanced Study of Mathematical Science   Postdoctoral Researcher   Japan

▼display all

Academic Society Memberships

  • 2013.04   情報処理学会MPS研究会   Japan

  • 2020.10   日本分子生物学会   Japan

  • 2016.10   The Seismologocal Society of Japan   Japan

  • 2014.07 - 2018.03   The International Society for Computational Biology   United States

  • 2013.08   日本統計学会   Japan

  • 2012.04   日本測地学会   Japan

  • 2006.04   地球電磁気・地球惑星圏学会   Japan

  • 2006.04   Japan Geoscience Union   Japan

▼display all

Papers

  • 半教師あり二値分類のためのクラス事前確率を用いたコスト関数の提案 Reviewed

    中西 慶一, 徳永 旭将

    第25回画像の認識・理解シンポジウム ( 情報処理学会コンピュータビジョンとイメージメディア(CVIM)研究会 )   2022.07

     More details

    Authorship:Last author, Corresponding author   Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)

    日本   姫路   2022.07.25  -  2022.07.28

    本稿は半教師あり二値分類のための新しいコスト関数を 提案する. 提案するコスト関数は, Focal Loss を半教師あり分類のために拡張した損失関数とクラス事前確率罰則項 から構成される. クラス事前確率罰則項を導入することで, ラベルなしデータにおける正例の割合がわかる場合, その 事前情報を直接的に推論に活用することが可能である. 提 案するコスト関数の有用性を評価するため, CIFAR-10 を 用いた画像二値分類試験を行った. その結果, 少量のラベ ルありデータセットや不均衡なデータセットにおいて, 提 案するコスト関数は既存のコスト関数と比べて優れた性能を示すことを確認した.

    Other Link: https://sites.google.com/view/miru2022/program#h.44rbhnwbmvlj

  • Identifying Snowfall Clouds at Syowa Station, Antarctica via a Convolutional Neural Network Reviewed International journal

    Kazue Suzuki, Masaki Shimomura, Kazuyuki Nakamura, Naohiko Hirasawa, Hironori Yabuki, Takashi Yamanouchi, Terumasa Tokunaga

    Advances in Artificial Intelligence - Selected Papers from the Annual Conference of Japanese Society of Artificial Intelligence (JSAI 2020) ( Springer International Publishing )   1357 ( 1 )   78 - 83   2021.07

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    Japan   オンライン  

    This study evaluated the impact of Atmospheric River (AR) clouds on snowfall amounts based on limited observation data to estimate the surface mass balance (SMB) of Antarctica. To accomplish this, we attempted to identify the snowfall cloud at Syowa Station, Antarctica. We constructed a new convolutional neural network (CNN) architecture with multinomial and binary classifications for National Oceanic and Atmospheric Administration (NOAA) Advanced Very High Resolution Radiometer (AVHRR) images over five years. The CNN was based on VGG16, and concatenate layers were added as the inception module. We replaced all the convolution layers with global average pooling to reduce the number of parameters. Based on the positive CNN sample re- sult, the multinomial classification emphasized the entire cloud structure, while the binary classification focused on cloud continuity. The results indicated accuracies of 71.00% and 65.37% for binary and multinomial classifications, respectively.

    DOI: 10.1007/978-3-030-73113-7_7

    Other Link: https://link.springer.com/chapter/10.1007/978-3-030-73113-7_7

  • Signal and Noise Separation from Satellite Magnetic Field Data through Independent Component Analysis: Prospect of Magnetic Measurements without Boom and Noise Source Information Reviewed International journal

    Shun Imajo, Masahito Nosé, Mari Aida, Haruhisa Matsumoto, Nana Higashio, Terumasa Tokunaga , Ayako Matsuoka

    Journal of Geophysical Research: Space Physics ( American Geophysical Union )   126 ( 5 )   2021.04

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    We propose an application of the independent component analysis (ICA) to separate satellite-induced time-varying stray fields from magnetic field data obtained using onboard multiple magnetometers. The ICA is a method for estimating source signals at multiple sites so that the estimated source signals can become statistically independent of each other. Since stray field variations are statistically independent of external natural field variations, the ICA method is expected to separate the natural variations from stray fields. Thus, we applied the ICA to magnetic field data from the first Quasi-Zenith Satellite, which has two triaxial fluxgate magnetometers, without using an extendable boom. First, we removed the long-period trend from the original data to create detrended data. Then, we applied the FastICA algorithm to the detrended data and obtained six independent components (ICs). The stray fields were successfully separated into three ICs (noise ICs), and the natural signals were represented by the other three ICs (signal ICs). Finally, we restored the observed signals from the signal ICs, and confirmed that the natural phenomena variations were not altered by the processing step. We also proposed a selection method of the noise ICs using the C coefficient, which is the coefficient of the variance of the mixing vectors. There was a large difference in C between the ICs whose C coefficients are the largest 3rd and 4th ones. Overall, these results demonstrate the possibility that the ICA method can support for boom-less magnetic observations in future satellite missions.

    DOI: 10.1029/2020JA028790

    Scopus

    Other Link: https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2020JA028790

  • Image-Based Plant Disease Diagnosis with Unsupervised Anomaly Detection Based on Reconstructability of Colors Reviewed International journal

    Ryoya Katafuchi, Terumasa Tokunaga

    Proceedings of International Conference on Image Processing and Vision Engineering ( SciTePress )   1   112 - 120   2021.04

     More details

    Authorship:Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)

    オンライン   オンライン   2021.04.28  -  2021.04.30

    DOI: 10.5220/0010463201120120

    arXiv

  • Identifying the Snowfall Cloud at Syowa Station, Antarctica via a Convolutional Neural Network

    SUZUKI Kazue, SHIMOMURA Masaki, NAKAMURA Kazuyuki, HIRASAWA Naohiko, YABUKI Hironori, YAMANOUCHI Takashi, TOKUNAGA Terumasa

    Proceedings of the Annual Conference of JSAI ( The Japanese Society for Artificial Intelligence )   2020 ( 0 )   3F1ES205 - 3F1ES205   2020.01

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    <p>This study evaluated snowfall values based on limited observation data to estimate the surface mass balance (SMB) of Antarctica. To accomplish this, we attempted to identify the snowfall cloud at Syowa Station, Antarctica. We constructed a new convolutional neural network (CNN) architecture with multinomial and binary classifications and added National Oceanic and Atmospheric Administration (NOAA)/Advanced Very High Resolution Radiometer (AVHRR) images over five years. The CNN was based on VGG16, and concatenate layers were added as the inception module. We replaced all the convolution layers with global average pooling to reduce the number of parameters. Based on the positive CNN sample result, the multinomial classification emphasized the entire cloud structure, while the binary classification focused on cloud continuity. The results indicated accuracies of 71.00% for binary and 65.37% for multinomial classifications.</p>

    DOI: 10.11517/pjsai.JSAI2020.0_3F1ES205

    CiNii Article

    Other Link: https://ci.nii.ac.jp/naid/130007857079

  • Cohesive and anisotropic vascular endothelial cell motility driving angiogenic morphogenesis Reviewed

    Takubo N., Yura F., Naemura K., Yoshida R., Tokunaga T., Tokihiro T., Kurihara H.

    Scientific Reports   9 ( 1 )   2019.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    Vascular endothelial cells (ECs) in angiogenesis exhibit inhomogeneous collective migration called “cell mixing”, in which cells change their relative positions by overtaking each other. However, how such complex EC dynamics lead to the formation of highly ordered branching structures remains largely unknown. To uncover hidden laws of integration driving angiogenic morphogenesis, we analyzed EC behaviors in an in vitro angiogenic sprouting assay using mouse aortic explants in combination with mathematical modeling. Time-lapse imaging of sprouts extended from EC sheets around tissue explants showed directional cohesive EC movements with frequent U-turns, which often coupled with tip cell overtaking. Imaging of isolated branches deprived of basal cell sheets revealed a requirement of a constant supply of immigrating cells for ECs to branch forward. Anisotropic attractive forces between neighboring cells passing each other were likely to underlie these EC motility patterns, as evidenced by an experimentally validated mathematical model. These results suggest that cohesive movements with anisotropic cell-to-cell interactions characterize the EC motility, which may drive branch elongation depending on a constant cell supply. The present findings provide novel insights into a cell motility-based understanding of angiogenic morphogenesis.

    DOI: 10.1038/s41598-019-45666-2

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85068037379&origin=inward

  • An Inspirational Collaboration between Measurements, Mathematical Modeling and Data Science for Image Analysis Invited Reviewed

    TOKUNAGA Terumasa

    Journal of The Society of Instrument and Control Engineers   58 ( 3 )   166 - 170   2019.01

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.11499/sicejl.58.166

    CiNii Article

    Other Link: https://ci.nii.ac.jp/naid/130007616866

  • The cloud patterns in the snowfall conditions around Syowa Station, Antarctica detected by Convolutional Neural Network

    Suzuki Kazue, Tokunaga Terumasa, Fukuchi Misaki, Hirasawa Naohiko, Yamanouchi Takashi

    Summaries of JSSI and JSSE Joint Conference on Snow and Ice Research ( The Japanese Society of Snow and Ice / Japan Society for Snow Engineering )   2019 ( 0 )   2019.01

     More details

    Language:English   Publishing type:Research paper (conference, symposium, etc.)

    DOI: 10.14851/jcsir.2019.0_119

    CiNii Article

    Other Link: https://ci.nii.ac.jp/naid/130007743208

  • SPF-CellTracker: Tracking Multiple Cells with Strongly-Correlated Moves Using a Spatial Particle Filter Reviewed

    15 ( 6 )   1822 - 1831   2018.11

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.1109/TCBB.2017.2782255

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85038382107&origin=inward

  • SPF-CellTracker: Tracking multiple cells with strongly-correlated moves using a spatial particle filter Reviewed

    Osamu Hirose, Shotaro Kawaguchi, Terumasa Tokunaga, Yu Toyoshima, Takayuki Teramoto, Sayuri Kuge, Takeshi Ishihara, Yuichi Iino, Ryo Yoshida

    IEEE/ACM Transactions on Computational Biology and Bioinformatic   2017.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)

  • 線虫の全脳活動データに対する位相解析

    岩崎 唯史, 寺本 孝行, 大江 紗, 徳永 旭将, 広瀬 修, S. Wu, 豊島 有, ジャン ムンソン, 吉田 亮, 飯野 雄一, 石原 健

    2017年度日本物理学会第72回年次大会講演集 ( 一般社団法人日本物理学会 )   2017.03

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)

    日本   大阪   2017.03.17  -  2017.03.20

    DOI: https://doi.org/10.11316/jpsgaiyo.72.1.0_2817

  • Accurate Automatic Detection of Densely Distributed Cell Nuclei in 3D Space Reviewed

    Toyoshima Y., Tokunaga T., Hirose O., Kanamori M., Teramoto T., Jang M.S., Kuge S., Ishihara T., Yoshida R., Iino Y.

    PLoS Computational Biology   12 ( 6 )   2016.06

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    To measure the activity of neurons using whole-brain activity imaging, precise detection of each neuron or its nucleus is required. In the head region of the nematode C. elegans, the neuronal cell bodies are distributed densely in three-dimensional (3D) space. However, no existing computational methods of image analysis can separate them with sufficient accuracy. Here we propose a highly accurate segmentation method based on the curvatures of the iso-intensity surfaces. To obtain accurate positions of nuclei, we also developed a new procedure for least squares fitting with a Gaussian mixture model. Combining these methods enables accurate detection of densely distributed cell nuclei in a 3D space. The proposed method was implemented as a graphical user interface program that allows visualization and correction of the results of automatic detection. Additionally, the proposed method was applied to time-lapse 3D calcium imaging data, and most of the nuclei in the images were successfully tracked and measured.

    DOI: 10.1371/journal.pcbi.1004970

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84978903985&origin=inward

  • Automated detection and tracking of many cells by using 4D live-cell imaging data Reviewed

    Tokunaga T., Hirose O., Kawaguchi S., Toyoshima Y., Teramoto T., Ikebata H., Kuge S., Ishihara T., Iino Y., Yoshida R.

    Bioinformatics   30 ( 12 )   2014.06

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.1093/bioinformatics/btu271

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84902509846&origin=inward

  • Data Assimilation for Reconstructing a Whole Neuronal System of C. Elegans : The Current State and Issue Invited Reviewed

    Terumasa Tokunaga, Ryo Yoshida, Yuishi Iwasaki

    Journal of The Japan Society for Simulation Technology ( Japan Society for Simulation Technology )   32 ( 4 )   287 - 294   2013.12

     More details

    Authorship:Corresponding author   Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (other)

    J-GLOBAL

  • Extraction of groove feelings from drum data using non-negative matrix factorization Reviewed

    125 - 130   2012.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)

    DOI: 10.1109/SCIS-ISIS.2012.6505312

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84877794120&origin=inward

  • Separation of stationary and non-stationary sources with a generalized eigenvalue problem Reviewed

    33   7 - 20   2012.09

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.1016/j.neunet.2012.04.001

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84863869958&origin=inward

  • Annual and semi-annual Sq variations at 96° MM MAGDAS I and II stations in Africa Reviewed

    64 ( 6 )   425 - 432   2012.01

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.5047/eps.2011.10.013

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84876370337&origin=inward

  • Onset time determination of precursory events in time series data by an extension of Singular Spectrum Transformation Invited Reviewed

    5 ( 1 )   46 - 60   2011.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=80053970902&origin=inward

  • Pi 2 waves simultaneously observed by Cluster and CPMN ground-based magnetometers near the plasmapause Reviewed International journal

    Hideaki Kawano, Shin-ichi Ohtani, Teiji Uozumi, Terumasa Tokunaga, Akimasa Yoshikawa, Kiyohum Yumoto, E. A. Lucek, M. Andre, the CPMN group

    Annales Geophysicae ( European Geophysical Union )   29 ( 9 )   1663 - 1672   2011.09

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    DOI: https://doi.org/10.5194/angeo-29-1663-2011

  • AKR modulation and global Pi2 oscillation Reviewed

    116 ( 6 )   2011.01

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.1029/2010JA016042

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=79959755995&origin=inward

  • Detecting precursory events in time series data by an extension of singular spectrum transformation Reviewed

    366 - 374   2010.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=79958702189&origin=inward

  • Propagation characteristics of Pi 2 pulsations observed at high- And low-latitude MAGDAS/CPMN stations: A statistical study Reviewed

    Uozumi T., Abe S., Kitamura K., Tokunaga T., Yoshikawa A., Kawano H., Marshall R., Morris R.J., Shevtsov B.M., Solovyev S.I., McNamara D.J., Liou K., Ohtani S., Itonaga M., Yumoto K.

    Journal of Geophysical Research: Space Physics   114 ( 11 )   2009.11

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    The objective of this study is to understand better the propagation of Pi 2 waves in the nighttime region. We examined Pi 2 oscillations that showed high correlation between high- and low-latitude Magnetic Data Acquisition System/Circum Pan-Pacific Magnetometer Network stations (correlation coefficient: |γ| ≥ 0.75). For each horizontal component (H and D) we examined the magnetic local time (MLT) dependence of the delay time of high-latitude Pi 2 oscillations that corresponds to the highest correlation with the low-latitude Pi 2 oscillation. We found the delay time of the high-latitude H showed remarkable MLT dependence, especially in the premidnight sector: we found that in the premidnight sector the high-latitude H oscillation tends to delay from the low-latitude oscillation (<100 s). On the other hand, the delay time of the high-latitude D oscillation was not significant (∼±10 s) in the entire nighttime sector. We propose a Pi 2 propagation model to explain the observed delay time of high-correlation highlatitude H. The model quantitatively explains the trend of the event distribution. We also examined the spatial distribution of high-correlation Pi 2 events relative to the center of auroral breakups. It was found that the high-correlation Pi 2 events tend to occur away from the center of auroral breakups by more than 1.5 MLT. The present result suggests that the high-correlation H component Pi 2 oscillations at high latitude are a manifestation of forced Alfvén waves excited by fast magnetosonic waves. Copyright 2009 by the American Geophysical Union.

    DOI: 10.1029/2009JA014163

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=72149099064&origin=inward

  • A new index to monitor temporal and long-term variations of the equatorial electrojet by MAGDAS/CPMN real-time data: EE-index Reviewed

    Uozumi T., Yumoto K., Kitamura K., Abe S., Kakinami Y., Shinohara M., Yoshikawa A., Kawano H., Ueno T., Tokunaga T., McNamara D., Ishituka J.K., Dutra S.L.G., Damtie B., Doumbia V., Obrou O., Rabiu A.B., Adimula I.A., Othman M., Fairos M., Otadoy R.E.S.

    Earth, Planets and Space   60 ( 7 )   785 - 790   2008.01

     More details

    Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.1186/BF03352828

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=52149085015&origin=inward

  • Global features of Pi 2 pulsations obtained by independent component analysis Reviewed

    Tokunaga T., Kohta H., Yoshikawa A., Uozumi T., Yumoto K.

    Geophysical Research Letters   34 ( 14 )   2007.07

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (scientific journal)

    DOI: 10.1029/2007GL030174

    Scopus

    Other Link: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=34548580614&origin=inward

▼display all

Conference Prsentations (Oral, Poster)

  • A Class-prior probability regularization with an extended Focal Loss for efficient Semi-supervised classification

    A Class-prior probability regularization with an extended Focal Loss for efficient Semi-supervised classification

    The 3rd International Sympojium on Neuromorphic AI Hardware 

     More details

    Event date: 2022.03.18 - 2022.03.19   Language:English   Country:Japan  

  • Atmospheric Riverによる南極域へのエアロゾル輸送(1)

    鈴木 香寿恵, 原圭 一郎, 徳永 旭将, 後藤 大輔, 平沢 尚彦, 山内 恭

    気象学会2021年度秋季大会  日本気象学会

     More details

    Event date: 2021.12.02 - 2021.12.08   Language:Japanese  

    近年,水蒸気輸送と豪雨(雪)には対流性の雲が連なって形成されるAtmospheric River(AR)が関連していると考えられるようになり,南極域においても極方向の水蒸気フラックス強化となる背景場とARの観測事例が報告されている[1].そこで,昭和基地の降雪時にARと判別できる雲画像を用いたCNNによる自動識別に取り組んできた[2].また,客観解析データを用いた全球規模のARとエアロゾル輸送の関連について報告がされており,Aerosol Atmospheric River (AAR)となって高濃度エアロゾルが輸送されることが示されている.本研究では,これまで行ってきたARによる水蒸気輸送だけではなく,陸起源と考えられる大気中微量物質の輸送も同時に捉え,大気による物質輸送過程を機械学習による予測モデルを構築することを目指す.まずは,ARとエアロゾル輸送の関連について2009年のブリザードイベントについて調べた.

  • LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection

    The 24th Information-Based Induction Sciences Workshop 

     More details

    Event date: 2021.11.10 - 2021.11.13   Language:Japanese  

  • CNNを用いた顔認識に対するマスク着用の影響と改善方法の検討

    溝田 十悟, 徳永 旭将

    第24回情報論的学習理論ワークショップ (IBIS2021)  電子情報通信学会 情報論的学習理論と機械学習研究会

     More details

    Event date: 2021.11.10 - 2021.11.13   Language:Japanese  

  • 複数の脈波抽出領域と独立成分分析を用いたサーマルカメラによる非接触バイタルセンシング手法の提案

    野見山 陸, 徳永 旭将

    第24回情報論的学習理論ワークショップ (IBIS2021)  電子情報通信学会 情報論的学習理論と機械学習研究会

     More details

    Event date: 2021.11.10 - 2021.11.13   Language:Japanese  

  • 言語の違いに頑健なText-to-Imageモデルの構築に向けた展望

    仲地 早司, 徳永 旭将

    第24回情報論的学習理論ワークショップ (IBIS2021)  電子情報通信学会 情報論的学習理論と機械学習研究会

     More details

    Event date: 2021.11.10 - 2021.11.13   Language:Japanese  

  • Aurora Image Segmentation with Deep PNU Learning

    The 150 th SGEPSS General Assembly 

     More details

    Event date: 2021.10.31 - 2021.11.04   Language:Japanese  

  • Observation and simulation of C. elegans whole-brain neural activities

     More details

    Event date: 2021.09.21 - 2021.09.23   Language:English  

    C. elegans is a model organism in which the structure (connectome) of the whole nervous system composed of 302 neurons has been determined. We performed whole-brain imaging by spinning disk confocal microscope combined with piezo objective positioner to obtain calcium imaging data of the whole head neurons. Further, we modeled the dynamics of neuronal ensembles based on the observed activity data and connectome data. As a result, we could perform virtual ablation of neurons or particular connections to gain insights into the information flow through the neural circuits.

  • Simultaneous measurements of membrane voltage and intracellular Ca2+ of AWA neurons by a gene encoded voltage indicator and GCaMP

    Takeshi Ishihara, Noriko Sato, Terumasa Tokunaga

    23rd International C.elegans conference  Genetics Society of America

     More details

    Event date: 2021.06.21 - 2021.06.24   Language:English  

    Measurement of neuronal activities in non-invasive and unanesthetized condition is important for understanding neuronal function in intact animals. Ca2+ imaging by fluorescent gene encoded calcium indicators (GECI) are a powerful way to measure neuronal activities in C. elegans. Although Ca2+ imaging revealed important aspects in neuronal functions, the measurement of neuronal membrane voltage is important to understand the neuronal functions. Furthermore, the relations of change of membrane voltages and changes of Ca2+ has not been fully understood. Recently, several types of gene encoded voltage indicators (GEVI) that are derived from 7TM proteins used for optogenetics has been developed to measure changes of membrane voltage in living animals. Even though the fluorescence of these GEVIs is dim, they showed fast time constants and relatively high fluorescent change depend on voltages. Among those GEVIs, we use paQuasAr3 for the voltage measurement, because it shows relatively higher fluorescence with other superior characteristics.
    Since AWA, one of the olfactory sensory neurons, which is responsible for diacetyl sensation, was reported to show all-or-none action potentials (Liu et al. 2018), we firstly analyzed AWA voltage changes induced by diacetyl. We found that fluorescence of paQuasAr3 expressed in AWA cell body is changed in response to diacetyl stimulation with high reproducibility. At the beginning of the stimulation, the transient increase and decrease of fluorescence intensity was observed, whereas the relatively higher fluorescence intensity was sustained during the stimulation. To elucidate relations between the Ca2+ responses and the voltage responses, we made wild-type animals expressing paQuasAr3 and GCaMP6f in AWA neurons, and measured both fluorescence at a cell body simultaneously. We found that the changes of paQuasAr3 started faster than the changes of GCaMP. These analyses will give insights on the neuronal functions in informational processing.

  • Development of training data with collaboration of observation, numerical simulation and machine leaning for space plasma phenomena forecast model

    Keiichiro FUKAZAWA, Tomoki KIMURA Terumasa TOKUNAGA, Shinya NAKANO

    Japan Geoscience Union Meeting 2021  Japan Geoscience Union

     More details

    Event date: 2021.05.30 - 2021.06.06   Language:Japanese  

  • 線虫C.elegansの細胞レベルの 膜電位/カルシウム同時イメージング 確立に向けて Invited

    徳永 旭将, 石原 健, 佐藤 則子, 岩崎 唯史

    第2回分子サイバネティクス研究会,第46回分子ロボティクス定例研究会  学術変革領域(A)「分子サイバネティクス」

     More details

    Event date: 2021.05.10   Language:Japanese  

  • Image-based Plant Disease Diagnosis with Unsupervised Anomaly Detection Based on Reconstructability of Colors

    Ryoya Katafuchi, Terumasa Tokunaga

    International Conference on Image Processing and Vision Engineering  Institute for Systems and Technologies of Information, Control and Communication

     More details

    Event date: 2021.04.28 - 2021.04.30   Language:English  

    This paper proposes an unsupervised anomaly detection technique for image-based plant disease diagnosis. The construction of large and publicly available datasets containing labeled images of healthy and diseased crop plants led to growing interest in computer vision techniques for automatic plant disease diagnosis. Al- though supervised image classifiers based on deep learning can be a powerful tool for plant disease diagnosis, they require a huge amount of labeled data. The data mining technique of anomaly detection includes un- supervised approaches that do not require rare samples for training classifiers. We propose an unsupervised anomaly detection technique for image-based plant disease diagnosis that is based on the reconstructability of colors; a deep encoder-decoder network trained to reconstruct the colors of healthy plant images should fail to reconstruct colors of symptomatic regions. Our proposed method includes a new image-based framework for plant disease detection that utilizes a conditional adversarial network called pix2pix and a new anomaly score based on CIEDE2000 color difference. Experiments with PlantVillage dataset demonstrated the superiority of our proposed method compared to an existing anomaly detector at identifying diseased crop images in terms of accuracy, interpretability and computational efficiency.

  • 機械学習・数値シミュレーション・観測融合による宇宙プラズマ現象予測モデル開発に向けた学習データの整備 Invited

    深沢 圭一郎, 木村 智樹, 徳永 旭将, 中野 慎也

    2020年度ISEE研究集会「太陽地球圏環境予測のためのモデル研究の展望」  名古屋大学宇宙地球環境研究所

     More details

    Event date: 2021.03.25   Language:Japanese  

  • Overlapping Cluster Analysis of Whole-Brain Imaging Data of C.elegans: Detection of Functional Hub Neuron

     More details

    Event date: 2021.03.12 - 2021.03.15   Language:Japanese  

  • 独立成分分析を用いた人工衛星干渉磁場の分離: 伸展物と事前情報を用いない磁場観測

    今城 峻, 能勢 正仁, 相田 真里, 松本 晴久, 東尾 奈々, 徳永 旭将, 松岡 彩子

    統計数理研究所共同研究集会 「宇宙地球環境の理解に向けての統計数理的アプローチ」  統計数理研究所, 名古屋大学宇宙地球環境研究所,名古屋大学数理データ科学教育研究センター

     More details

    Event date: 2020.12.08   Language:Japanese  

  • An image processing pipeline for quantifying spatiotemporal evolution of voltage responses inside a single cell of C. elegans

    Terumasa Tokunaga, Noriko Sato, Yuishi Iwasaki, Takeshi Ishihara

    The 43rd Annual Meeting of the Molecular Biology Society of Japan  The Molecular Biology Society of Japan

     More details

    Event date: 2020.12.02 - 2020.12.04  

  • 非対称的な相互作用を持つマルコフ確率場を変形モデルとした非剛体イメージレジストレーション技術の開発

    長村徹, 徳永旭将

    第23回情報論的学習理論ワークショップ  電子情報通信学会 情報論的学習理論と機械学習研究会

     More details

    Event date: 2020.11.23 - 2020.11.26   Language:English  

  • GLCICによる欠損補間に基づく教師なし画像異常検知法の提案

    深町 悠貴, 徳永 旭将

    第23回情報論的学習理論ワークショップ  電子情報通信学会 情報論的学習理論と機械学習研究会

     More details

    Event date: 2020.11.23 - 2020.11.26   Language:Japanese  

  • 宇宙プラズマ現象予測モデル開発に向けた機械学習・数値シミュレーション・観測による学習データの整備

    深沢 圭一郎, 木村 智樹, 徳永 旭将, 中野 慎也

    第148回 地球電磁気・地球惑星圏学会総会及び講演会  地球電磁気・地球惑星圏学会

     More details

    Event date: 2020.11.01 - 2020.11.04   Language:English  

    The machine learning has become a powerful tool to find the relation between variables thanks to the deep learning technique. This performs greatly in the classification, regression and recently generative modeling in the engineering and commercial areas. However, due to the satisfaction of physical laws in the scientific research area, the application of machine learning has some difficulties. In particular, the generative modeling is very sensitive to scientific data since the generated data is not guaranteed by the physical laws.
    To overcome these problems, we have tried to apply machine learning to space plasma physics. In the observation there are many lacks data in space and time. Using the technique of GAN (Generative Adversarial Networks), we have challenged to represent the lack data of aurora image by ASI (All-Sky Imager) of THEMIS. Now we use the natural training data not only the observation data and we have obtained the smooth represented data, however these data cannot satisfy the physical laws. Then we prepare the training data of only observation.
    From this thought the preparing the training data is the most important for machine learning. Then we have prepared the global simulation data of magnetosphere using real solar wind data for the generation and forecast the configuration of the magnetosphere. These data are the very large size and time elapsed data so that the data set cannot be stored in often case and usual machine learning cannot treat these data set. However recently there are 3D CNN (convolutional neural network) and RNN (recurrent neural network) which can be trained by 3D data set and these data set may become very important. In this study, we show the database of this data set data, representation of the auroral image and their status.

  • Development of Deformable Image Registration Technique using MRFs Based Deformation Model with Asymmetric Interaction

    IIBMP2020 

     More details

    Event date: 2020.09.01 - 2020.09.03   Language:Japanese  

  • GANに基づくCIEDE2000異常度スコアを用いた色異常検知方法の提案

    片渕 凌也, 徳永 旭将

    第23回画像の認識・理解シンポジウム  電子情報通信学会パターン認識・メディア理解(PRMU)研究専門委員会

     More details

    Event date: 2020.08.02 - 2020.08.05   Language:Japanese  

    本論文では, 色に現れる異常の検出を目的とした, 教師なし異常検出方法を提案する. 提案手法では, 敵対的生成ネットワークに基づく教師なし学習に基づき, 色の再構成可能性を評価することで, 正常データでは見られなかった色の異常の検知を行う. また, 色の再構成可能性の評価のため, CIEDE2000 色差に基づく異常度スコアを提案する. 実験では, PlantVillage データセットを用いた病気の植物とその病変領域の検出に対して提案手法の性能評価を行い,ベースラインである AnoGAN との比較を行う. 実験の結果, 提案手法が色の異常検知問題に対して検出性能, 解釈可能性および計算効率性の観点から AnoGAN より優れた性能を発揮することを示す.

  • All-Sky Imagerデータの複数の脈動パッチを包括的に追跡するためのパイプライン

    野見山 陸, 三好 由純, 遠山 航平, 小川 泰信, 細川 敬祐, 徳永 旭将

    第23回 画像の認識・理解シンポジウム  電子情報通信学会パターン認識・メディア理解(PRMU)研究専門委員会

     More details

    Event date: 2020.08.02 - 2020.08.05   Language:Japanese  

  • Signal and Noise Separation from Satellite Magnetic Field Data Using Independent Component Analysis: Prospect of Magnetic Measurements without Mast and Noise Source Information

    Shun Imajo, Masahito Nosé, Mari Aida, Haruhisa Matsumoto, Nana Higashio, Terumasa Tokunaga, Ayako Matsuoka

    JpGU-AGU Joint Meeting 2020  Japan Geoscience Union Meeting

     More details

    Event date: 2020.07.12 - 2020.07.16   Language:English  

    We propose an application of the independent component analysis (ICA) to separate satellite- induced time-varying noises from magnetic data obtained by onboard multiple magnetometers. The ICA is a method of estimating source signals observed at multiple sites so that estimated source signals are statistically independent of each other. Since satellite noises are clearly independent of external natural variations, the ICA is expected to separate the satellite noises. We applied the ICA to the magnetic data measured by the first Quasi-Zenith Satellite (QZS-1) that has two triaxial fluxgate magnetometers without an extendable mast. First, we removed the long-period trend from the original data. Then, we applied the FastICA to the detrended data and obtained six independent components (ICs). Satellite-induced noises were successfully classified into three ICs (noise ICs). Natural signals are represented by the rest three ICs (signal ICs). Finally, we restored the observed signals from the signal ICs. We confirmed that amplitude and waveform of natural phenomena were not altered by the processing. We also proposed the method of automatic determination of noise ICs using the D score, which is similar to the normalized coefficient of variance of the mixing vectors. We confirmed that the three largest D scores, which give the noise ICs, are much larger than the three smallest D, which give the signal ICs. The automatic determination of noise ICs by this method was 95% identical to that by visual inspection. These results demonstrated that the ICA method can provide for mast-less magnetic observations in future satellite missions.

  • Identifying the Snowfall Cloud at Syowa Station, Antarctica via a Convolutional Neural Network

    Kazue Suzuki, Masaki Shimomura, Kazuyuki Nakamura, Naohiko Hirasawa, Hironori Yabuki, Takashi Yamanouchi, Terumasa Tokunaga

    The 34th Annual Conference of the Japanese Society for Artificial Intelligence  The Japanese Society for Artificial Intelligence

     More details

    Event date: 2020.06.09 - 2020.06.12   Language:English  

  • A Pipeline for Comprehensive Tracking of Pulsating Patches in All-Sky Imager Data

    JpGU - AGU Joint Meeting 2020  Japan Geoscience Union

     More details

    Event date: 2020.05.24 - 2020.05.28   Language:English  

  • 映像IoT技術による赤ちゃん見守りシステム

    村田 健史, 深沢 圭一郎, 徳永 旭将, 水原 隆道, 野見山 陸, Somnuk Phon-Amnuaisuk

    第151回情報システムと社会環境研究発表会 

     More details

    Event date: 2020.02.28   Language:Japanese  

  • Whole-brain calcium imaging analyses of dynamics of neural network in C. elegans

    Yuko Murakami, Suzu Oe, Motonari Ichinose, Takayuki Teramoto, Yu Toyoshima, Terumasa Tokunaga, Osamu Hirose, Stephan Wu, Jang Moon-Song, Hirofumi Sato, Sayuri Kuge, Yuishi Iwasaki, Ryo Yoshida, Yuichi Iino, Takeshi Ishihara

     More details

    Event date: 2019.12.18 - 2019.12.20   Language:Japanese  

  • Whole neuronal analyses of the behavioral switching depending on associative learning in C. elegans

     More details

    Event date: 2019.12.18 - 2019.12.20   Language:Japanese  

  • Application of Machine Learning to magnetospheric physics and preparation of training data for global magnetospheric configuration and physics

    Keiichiro Fukazawa, Tomoki Kimura, Terumasa Tokunaga, Shinya Nakano

    AGU Fall Meeting 2019  America Geophysics Union

     More details

    Event date: 2019.12.09 - 2019.12.13   Language:English  

  • 全脳カルシウムイメージングによる線虫の神経動態解析

    村上 悠子, 大江 紗, 寺本 孝行, 豊島 有, 徳永 旭将, Stephan Wu, 広瀬 修, Jang Moon-Sun, 佐藤 博文, 金森 真奈美, 久下 小百合, 岩崎 唯史, 吉田 亮, 飯野 雄一, 石原 健

    第42回日本分子生物学会年会  日本分子生物学会

     More details

    Event date: 2019.12.03 - 2019.12.06   Language:Japanese  

  • 線虫の連合学習の記憶に基づく行動スイッチング:中枢神経回路活動可視化による解析

    大江 紗, 村上 悠子, 寺本 孝行, 豊島 有, 徳永 旭将, Stephan Wu, 広瀬 修, Moon-Sun Jang, 佐藤 博文, 金森 真奈美, 久下 小百合, 岩崎 唯史, 吉田 亮, 飯野 雄一, 石原 健

    第42回日本分子生物学会年会  日本分子生物学会

     More details

    Event date: 2019.12.03 - 2019.12.06   Language:Japanese  

  • Analyzing whole-brain dynamics of C. elegans with statistical approach

    Yuko Murakami, Suzu Oe, Takayuki Teramoto, Yu Toyoshima, Terumasa Tokunaga, Osamu Hirose, Stephen Wu, Moon-Sun Jang, Hirofumi Sato, Manami Kanamori, Sayuri Kuge, Yuishi Iwasaki, Ryo Yoshida, Yuichi Iino, Takeshi Ishihara

    The 20th International Conference on Systems Biology 

     More details

    Event date: 2019.11.01 - 2019.11.05   Language:English  

  • CNNを用いた南極域における降雪時の雲パターン検出

    鈴木 香寿恵, 徳永 旭将, 福地 岬稀,平沢 尚彦,矢吹 裕伯,山内 恭

    日本気象学会2019年度秋季大会  日本気象学会

     More details

    Event date: 2019.10.28 - 2019.10.31   Language:Japanese  

  • ディープラーニングによる南極昭和基地周辺における降雪をもたらす雲の検出

    鈴木 香寿恵, 徳永 旭将, 福地 岬稀,平沢 尚彦,矢吹 裕伯,山内 恭

    氷雪研究大会2019  日本氷雪学会

     More details

    Event date: 2019.09.08 - 2019.09.11   Language:Japanese  

  • LSTMを用いた分類問題における判断根拠可視化の検討

    齊藤 剛史, 徳永 旭将

    第22回画像の認識・理解シンポジウム (MIRU2019) 

     More details

    Event date: 2019.07.29 - 2019.08.01   Language:Japanese  

  • Exploring the information processing of neural network through whole-brain activity-imaging of C. elegans

    Yu Toyoshima,Hirofumi Sato,Manami Kanamori,Stephen Wu,Moon-Sun Jang,Yuko Murakami,Suzu Oe,Terumasa Tokunaga, Osamu Hirose, Sayuri Kuge,Takayuki Teramoto,Yuishi Iwasaki,Ryo Yoshida,Takeshi Ishihara,Yuichi Iino

     More details

    Event date: 2019.07.25 - 2019.07.28   Language:English  

  • 線虫の全脳活動データ解析: 使っているシナプス結合と使っていないシナプス結合

    岩崎唯史, 佐藤博文, 豊島有, 大江紗, 村上悠子, 寺本孝行, Stephen Wu, 徳永旭将, ジャンムンソン, 吉田亮, 石原健, 飯野雄一

    日本物理学会第74回年次大会  日本物理学会

     More details

    Event date: 2019.03.14 - 2019.03.17   Language:Japanese  

  • 線虫の連合学習の記憶に基づく行動スイッチング:中枢神経回路の活動可視化による解析

    大江紗

    第41回日本分子生物学会年会  日本分子生物学会年会

     More details

    Event date: 2018.11.28 - 2018.11.30   Language:Japanese  

  • 再帰型ニューラルネットワークを用いた太陽風パラメータからのサブストーム規模の予測

    河村光次郎

    地球電磁気・地球惑星圏学会第144回総会及び講演会  地球電磁気・地球惑星圏学会

     More details

    Event date: 2018.11.23 - 2018.11.27   Language:Japanese  

  • カーネル密度関数の局所変形に基づくトポロジー保存可能なイメージアライメント手法の開発に向けて

    綿島正剛

    第21回情報論的学習理論ワークショップ  電子情報通信学会 情報論的学習理論と機械学習 (IBISML) 研究会

     More details

    Event date: 2018.11.04 - 2018.11.07   Language:Japanese  

  • Analyzing whole neural activities to elucidate the mechanisms underlying sensory integration

    Asia Pacific Worm Meeting 2018 

     More details

    Event date: 2018.07.09 - 2018.07.12   Language:English  

  • The detection of cloud pattern in the Antarctic using Convolution Neural Network for estimation of the snowfall amount

    Kazue Suzuki

    15th Annual Meeting Asia Oceania Geosciences Society  Asia Oceania Geosciences Society

     More details

    Event date: 2018.06.03 - 2018.06.08   Language:English  

  • ベイズ推定による楽曲間内挿に基づく和音モーフィング法の提案

    榎田皓太

    火の国情報シンポジウム2018 

     More details

    Event date: 2018.03.01 - 2018.03.02   Language:Japanese  

  • カーネル 密度関数の局所変形に基づく線状構造物に対する非剛体イメージアライメント手 法の開発

    徳永旭将

    第20回情報論的学習理論ワークショップ  電子情報通信学会 情報論的学習理論と機械学習研究会

     More details

    Event date: 2017.11.08 - 2017.11.10   Language:Japanese  

  • カーネル密度関数 の局所変形に基づく線状構造物に対する非剛体イメージアライメント手法の開発

    綿島正剛

    日本統計関連学会連合大会2017  日本統計関連学会連合

     More details

    Event date: 2017.09.03 - 2017.09.06   Language:Japanese  

  • 線虫の全脳イメー ジングによる行動を制御する情報処理機構の解析

    大江 紗

    第40回日本神経科学大会  日本神経科学学会

     More details

    Event date: 2017.07.20 - 2017.07.23   Language:English  

  • 線虫の全脳活動データに対する位相解析

    岩崎 唯史, 寺本 孝行, 大江 紗, 徳永 旭将, 広瀬 修, S. Wu, 豊島 有, ジャン ムンソン, 吉田 亮, 飯野 雄一, 石原 健

    2017年度日本物理学会第72回年次大会  日本物理学会

     More details

    Event date: 2017.03.17 - 2017.03.20   Language:Japanese  

    線虫C. elegansの神経系は302個の神経細胞から構成され,そのうち約170個が頭部に集中している.頭部に存在するこれら神経細胞の同時イメージングデータに対して,同期/非同期オーダーパラメータを用いた位相解析,および類似度行列に基づいたクラスタ解析を行った.本発表ではこれらの結果について報告する.また,シナプス結合に異常がある変異体での結果と野生型での結果の違いについても言及する.

▼display all

Works

Lectures

  • 高性能かつコストエフェクティブな外観検査AIに向けた 統計的機械学習の先進的応用

    EICE SIS研6月研究会  2022.06  PSJ-AVM

     More details

    Event date: 2022.06.09 - 2022.06.10   Language:Japanese   Presentation type:Invited lecture   Venue:九州工業大学若松地区  

  • 線虫C.elegansの細胞レベルの膜電位/カルシウム同時イメージング確立に向けて

    第2回分子サイバネティクス,第46回分子ロボティクス定例研究会  2021.05  分子ロボティクス研究会

     More details

    Event date: 2021.05.10   Language:Japanese   Presentation type:Invited lecture   Venue:オンライン  

  • バイオイメージ解析におけるベイズ統計と機械学習の応用

    名古屋大学宇宙地球環境研究所研究集会 「宇宙環境の理解に向けての統計数理的アプローチ」  2017.12  名古屋大学

     More details

    Presentation type:Invited lecture   Venue:名古屋大学  

  • 時空間パターン理解のためのベイズ統計・スパース推定の応用

    京都大学・学術情報メディアセンターセミナー  2017.10  京都大学・学術情報メディアセンター

     More details

    Presentation type:Invited lecture   Venue:京都大学吉田キャンパス  

  • Whole neural network analysis of C. elegans using an automated image processing pipeline

    International Workshop on Quantitative Biology 2017 At Keio University  2017.04  Japanese society for quantitative biology

     More details

    Presentation type:Invited lecture  

  • バイオイメージ解析におけるベイズ統計の応用

    生命機能数理モデル検討会  2014.05  大阪大学免疫学フロンティア研究センター

     More details

    Presentation type:Invited lecture   Venue:大阪大学免疫学フロンティア研究センター  

  • 4次元動態計測データからの神経細胞活動度の自動定量化

    第一回腫瘍分子生物学•生命情報共同セミナー  2014.03  金沢大学がん進展制御研究所

     More details

    Presentation type:Invited lecture  

▼display all

Grants-in-Aid for Scientific Research

  • 外観検査AIを迅速に構築する外部駆動型視覚注視機構の確立

    Grant number:22K12169  2022.04 - 2025.03   基盤研究(C)

  • カーネル密度関数の局所変形による汎用的イメージアライメント法の開発

    Grant number:15K16087  2015.04 - 2017.03   若手研究(B)

     詳細を見る

    研究課題番号:15K16087
    医療画像や生物画像を想定し、異なる測定環境で得られた画像同士を共通の座標系に変換する”イメージ·アライメント”の開発を行う。既存のイメージ·アライメント法では、複雑な形状の物体を計測した画像や、画像の一部に欠損や不明 瞭な領域を含む画像に対しては、適切なアライメントができないという問題があった。本研究計画では、カーネル密度関数の局所変形という新たな観点から、高精度かつ汎用性の高いイメージ· アライメント法を提案する。

Contracts

  • 学習型動態モーフィングによる神経間シグナル伝達特性の解明(JST戦略的創造研究推進事業「さきがけ」)

    2018.10 - 2022.03

     More details

    Grant type:Consigned research

    高速共焦点顕微鏡により計測されたCaイオンイメージングデータから、本来の時空間解像度を超えて動態を推定する”学習型動態モーフィング技術”の研究を行う。提案技術は、ベイズ推論に基づき動きや変形場を推定する”非剛体イメージレジストレーション”、複数の時空間解像度で計測されたイメージングデータを機械学習により統合する”深さ補間”、”画像超解像”技術から成る。それにより、ギャップ結合と化学シナプス結合のいずれが用いられたかをCaイメージングデータから判別する技術を確立する。さらに、宇宙科学に関するサブテーマを設定し、汎用性の実証と領域内外への水平展開を狙う。

  • 半導体検査装置に関する機械的、画像処理的性能向上に関する研究

    2022.04 - 2025.03

     More details

    Grant type:Joint research

  • 観測・数値シミュレーション・機械学習の融合による宇宙プラズマ現象予測モデルの開発

    2018.06 - 2019.03

     More details

    Grant type:Other joint research

    本研究では、飛翔体による宇宙プラズマ観測データと数値プラズマシミュレーションを、機械学習によって統合的に解析することで、「低空間次元・小観測数・単地点観測」という観測データを時空間に拡張し、そこで起きる現象の変動を抽出することを目的とする(研究代表:深沢圭一郎, 京都大学)。

  • Hisaki観測・数値シミュレーション・機械学習の融合による宇宙プラズマ現象理解につながる手法の研究開発

    2018.04 - 2019.03

     More details

    Grant type:Other joint research

Other External Funds

  • NOAA/AVHRR雲画像を用いた降雪をもたらす雲の検出法および降雪量の推定

    2019.07 - 2020.03

    情報システム研究機構: ROIS-DS Joint Research Program  

  • 観測・数値シミュレーション・機械学習の融合による宇宙プラズマ現象予測モデルの開発

    2019.07 - 2020.03

    情報システム研究機構: ROIS-DS Joint Research Program  

  • 女性とこどものこころとからだの健康サポート

    2019.01 - 2022.03

    革新的イノベーション創出プログラム(COI STREAM)  

Other Research Activities

  • 論文査読

    2017.05
    -
    2017.06

     More details

    画像電子学会誌VC特集号のショートペーパーの査読

Career of Research abroad

  • 宇宙プラズマ環境場データの機械学習に基づく地球磁気圏応答特性の解明

    ジョンズホプキンス大学応用物理学研究所  Project Year:  2019.11.14 - 2020.03.20

Activities of Academic societies and Committees

  • 情報処理学会MPS研究会   情報処理学会数理モデル化と問題解決検討会運営委員  

    2013.04 - 2017.03

Social activity outside the university

  • ベイジアンモデル応用: トラッキング

    Role(s):Lecturer

    九州工業大学  社会人向けデータサイエンス7日間集中講義  オンライン  2021.03.18

     More details

    Audience: Researchesrs, General, Company

    Type:Seminar, workshop

  • 先端的な科学計測とデータサイエンスの理想的な協働へ向けて

    Role(s):Lecturer

    公益社団法人日本技術士会九州本部北九州地区支部  公益社団法人日本技術士会九州本部北九州地区支部2021年3月度CPD  北九州環境ミュージアム  2021.03.13

     More details

    Audience: Researchesrs, General, Company

    Type:Lecture

    北九州環境ミュージアムにおいて, 公益社団法人日本技術士会九州本部北九州地区支部2021年3月度CPDに講師として参加し, 「先端的な科学計測とデータサイエンスの理想的な協働へ向けて」という題目で講演を行った。

  • 九州大学理学府地球惑星科学専攻特別講義

    Role(s):Lecturer

    九州大学  九州大学  2019.08.28 - 2019.08.30

     More details

    Audience: College students, Graduate students

    Type:Other

  • 2014年統計数理研究所公開講座

    2014.12.08 - 2014.12.09

     More details

    Type:Seminar, workshop