Faculty Profiles - KUDO, Hiroaki

Papers - KUDO, Hiroaki

Division display 1 - 20 of about 481 ／ All the affair displays >>

A comprehensive study on supervised single-channel noisy speech separation with multi-task learning Reviewed

Shaoxiang Dang, Tetsuya Matsumoto, Yoshinori Takeuchi, Hiroaki Kudo

Speech Communication Vol. 167 ( 103162 ) 2025.2

Multicrystalline informatics: a methodology to advance materials science by unraveling complex phenomena Reviewed

Usami, N., Kutsukake, K., Kojima, T., Kudo, H., Yokoi, T., & Ohno, Y.

Science and Technology of Advanced Materials Vol. 25 ( 1 ) 2024.9

Multicrystalline Informatics Applied to Multicrystalline Silicon for Unraveling the Microscopic Root Cause of Dislocation Generation Reviewed

Kenta Yamakoshi, Yutaka Ohno, Kentaro Kutsukake, Takuto Kojima, Tatsuya Yokoi, Hideto Yoshida, Hiroyuki Tanaka, Xin Liu, Hiroaki Kudo, Noritaka Usami

Advanced Materials Vol. 36 ( 8 ) page： e2308599 2023.12

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

Abstract

A comprehensive analysis of optical and photoluminescence images obtained from practical multicrystalline silicon wafers is conducted, utilizing various machine learning models for dislocation cluster region extraction, grain segmentation, and crystal orientation prediction. As a result, a realistic 3D model that includes the generation point of dislocation clusters is built. Finite element stress analysis on the 3D model coupled with crystal growth simulation reveals inhomogeneous and complex stress distribution and that dislocation clusters are frequently formed along the slip plane with the highest shear stress among twelve equivalents, concentrated along bending grain boundaries (GBs). Multiscale analysis of the extracted GBs near the generation point of dislocation clusters combined with ab initio calculations has shown that the dislocation generation due to the concentration of shear stress is caused by the nanofacet formation associated with GB bending. This mechanism cannot be captured by the Haasen‐Alexander‐Sumino model. Thus, this research method reveals the existence of a dislocation generation mechanism unique to the multicrystalline structure. Multicrystalline informatics linking experimental, theoretical, computational, and data science on multicrystalline materials at multiple scales is expected to contribute to the advancement of materials science by unraveling complex phenomena in various multicrystalline materials.

DOI： 10.1002/adma.202308599

Web of Science

Scopus

PubMed

3D CNN and grad-CAM based visualization for predicting generation of dislocation clusters in multicrystalline silicon Reviewed

Kyoka Hara, Takuto Kojima, Kentaro Kutsukake, Hiroaki Kudo, Noritaka Usami

APL machine learning 2023.9

A machine learning-based prediction of crystal orientations for multicrystalline materials Reviewed

Kyoka Hara, Takuto Kojima, Kentaro Kutsukake, Hiroaki Kudo, Noritaka Usami

APL machine learning 2023.6

Estimation of Crystal Orientation of Grains on Polycrystalline Silicon Substrate by Recurrent Neural Network Reviewed

Hikaru Kato, Soichiro Kamibeppu, Takuto Kojima, Tetsuya Matsumoto, Hiroaki Kudo, Yoshinori Takeuchi, Kentaro Kutsukake, Noritaka Usami

IEEJ Transactions on Electrical and Electronic Engineering Vol. 17 ( 11 ) page： 1685 - 1687 2022.11

Improved Speech Separation Performance from Monaural Mixed Speech Based on Deep Embedding Network Reviewed

Dang Shaoxiang, Matsumoto Tetsuya, Kudo Hiroaki, Takeuchi Yoshinori

IEEJ Transactions on Electronics, Information and Systems Vol. 142 ( 6 ) page： 643 - 649 2022.6

Language：English Publishing type：Research paper (scientific journal) Publisher：The Institute of Electrical Engineers of Japan

<p>Speech separation refers to the separation of mixed utterances in which multiple people are speaking simultaneously. This topic was created to address the cocktail party problem, and it has also evolved into a front-end procedure for speech-related research recently. There are two types of models for addressing it: classification methods and regression methods. Classification methods avoid considering the permutation problem, and regression methods are more precise. Deep clustering (DC) is a common deep learning classification technique that uses a deep embedding network to embed signals in the underlying manifold and allows signals with similar properties to cluster together in the embedded space. The ideal binary mask (IBM) supervises the model. Even if it is entirely isolated via supervised binary masking, this setting is susceptible to mistake. To remedy this flaw, this paper proposes a network with two modules based on deep embedding. More precise masks, such as the ideal ratio mask (IRM), can now be used instead of IBM. Furthermore, the cascade structure may preserve DC's high performance. On average, the suggested model beats the original DC model by 1.55dB in SNR, 4.45dB in SDR, 4.41dB in SDRi, 0.16 in STOI, and 0.3 in PESQ on a mixture of Japanese Newspaper Article Sentences (JNAS). Finally, a comparison is made with ChimeraNet which has a similar structure, the results prove the proposed model's superiority over previous DC-related studies.</p>

DOI： 10.1541/ieejeiss.142.643

Scopus

CiNii Research

Occurrence Prediction of Dislocation Regions in Photoluminescence Image of Multicrystalline Silicon Wafers Using Transfer Learning of Convolutional Neural Network Reviewed

Hiroaki KUDO , Tetsuya MATSUMOTO , Kentaro KUTSUKAKE , Noritaka USAMI

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences Vol. E104.A ( 6 ) page： 857 - 865 2021.6

Occlusion Avoidance Behavior During Gazing at a Rim Drawn by Blue-Yellow Opposite Colors Reviewed

Miho SHINOHARA, Yukina TAMURA, Shinya MOCHIDUKI, Hiroaki KUDO, Mitsuho YAMADA

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences Vol. E104.A ( 6 ) page： 897 - 901 2021.6

Application of artificial neural network to optimize sensor positions for accurate monitoring: an example with thermocouples in a crystal growth furnace Reviewed

Abderahmane Boucetta,Kentaro Kutsukake,Takuto Kojima,Hiroaki Kudo,Tetsuya Matsumoto,Noritaka Usami

Applied Physics Express Vol. 12 ( 12 ) page： 125503 2019.11

Eye Movement Measurement of Gazing at the Rim of a Column in Stereo Images with Yellow-Blue Equiluminance Random Dots Reviewed

Shinya MOCHIDUKI, Ayaka NUNOMURA, Hiroaki KUDO, Mitsuho YAMADA

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Vol. E102-A ( 9 ) page： 1196-1204 2019.9

3D visualization and analysis of dislocation clusters in multicrystalline silicon ingot by approach of data science Reviewed

Yusuke Hayama, Tetsuya Matsumoto, Tetsuro Muramatsu, Kentaro Kutsukake, Hiroaki Kudo, Noritaka Usami

Solar Energy Materials and Solar Cells Vol. 189 page： 239-244 2019.1

Application of weighted Voronoi diagrams to analyze nucleation sites of multicrystalline silicon ingots Reviewed

Tetsuro Muramatsu, Yusuke Hayama, Kentaro Kutsukake, Kensaku Maeda, Tetsuya Matsumoto, Hiroaki Kudo, Kozo Fujiwara, Noritaka Usami

Journal of Crystal Growth Vol. 499 page： 62-66 2018.10

Study on Incongruence between Binocular Images when Gazing at the Rim of a Column with Equiluminance Random Dots Reviewed

Shinya MOCHIDUKI, Reina WATANABE, Miyuki SUGANUMA, Hiroaki KUDO, Noboru OHNISHI, Mitsuho YAMADA

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Vol. E101-A ( 6 ) page： 884-891 2018.6

Extraction of Spoken Mathematical Formulas in Slides for Real-Time Captioning Reviewed

Hironori Kawaguchi, Yoshinori Takeuchi, Tetsuya Matsumoto, Hiroaki Kudo, Noboru Ohnishi

The IEICE Transactions on Information and Systems (Japanese Edition) Vol. J97-D ( 5 ) page： 1035-1043 2014.5

A Novel Method for Exploring Patch-level Context to Improve Image Categorization Performance Reviewed

Shuang BAI, Tetsuya MATSUMOTO, Yoshinori TAKEUCHI, Hiroaki KUDO, and Noboru OHNISHI

IEEJ Transactions on Electronics, Information and Systems C Vol. 133 ( 12 ) page： 2264-2274 2013.12

Informative patches sampling for image classification by utilizing bottom-up and top-down information Reviewed

Shuang BAI, Tetsuya MATSUMOTO, Yoshinori TAKEUCHI, Hiroaki KUDO, and Noboru OHNISHI

Machine Vision and Applications Vol. 24 page： 959-970 2013.7

Incorporating Contextual Information into Bag-of-Visual-Words Framework for Effective Object Categorization Reviewed

Shuang BAI, Tetsuya MATSUMOTO, Yoshinori TAKEUCHI, Hiroaki KUDO, and Noboru OHNISHI

IEICE Transactions on Information and Systems Vol. E95-D ( 12 ) page： 3060-3068 2012.12

Incorporating Top-Down Guidance for Extracting Informative Patches for Image Classification Reviewed

Shuang BAI, Tetsuya MATSUMOTO, Yoshinori TAKEUCHI, Hiroaki KUDO, and Noboru OHNISHI

IEICE Transactions on Information and Systems Vol. E95-D ( 3 ) page： 880-883 2012.3

Detecting Partial Duplications in an Image - The Improvement of Estimating RotationAngle and reversal - Reviewed

Kei Toimizawa, Tetsuya Matsumoto, Hiroaki Kudo, Yoshinori Takeuchi, Noboru Ohnishi

IEEJ Trans. EIS Vol. 131 ( 12 ) page： 2121-2122 2011.12

　 PREV - NEXT 　

<KUDO, Hiroaki>

Papers - KUDO, Hiroaki