Brian Kenji Iwana

Brian Kenji Iwana

Associate Professor

Kyushu University
Human Interface Laboratory
Department of Advanced Information Technology
Faculty of Information Science and Electrical Engineering
Graduate Program of Interdisciplinary Policy Analysis and Design

Links

Research Interests

  • Document recognition
  • Character recognition
  • Design using machine learning
  • Time series classification
  • Neural networks
  • Dynamic programming
  • Natural Language Processing

Research

Dynamic Weights for Neural Networks

Dynamic weight alignment for convolutional neural networks

This work optimizes the convolution in a Convolutional Neural Network (CNN) using dynamic programming to align the weights to the inputs. I showed that using dynamically aligned weights, it is possible to improve the accuracy of temporal CNNs.

Dynamic Time Warping Neural Network (DTW-NN)

A Dynamic Time Warping Neural Network (DTW-NN) is a feedforward neural network for time series recognition. A DTW-NN is designed to overcome temporal distortions by replacing the standard linear inner product of a multi-layer perceptron with a nonlinear kernel-like function, namely DTW.

Pattern Representation and Feature Extraction

Time series feature extraction

Dynamic Time Warping (DTW) is normally used as a robust distance measure for distance-based time series recognition methods. However, in this work, we use the local distances between elements in a DTW operation as features for multi-modal Convolutional Neural Networks (CNN).

Prototype selection for dissimilarity space embedding using AdaBoost

Dissimilarity Space Embedding (DSE) involves representing patterns as distances to other patterns instead of the raw features. In this work, I proposed embedding time series into DSE using Dynamic Time Warping (DTW) as a distance function. Next, we reduced the dimensionality and increased the accuracy of the DSE using AdaBoost.

Convolutional Neural Network Explainability

Book genre classification

In this research, I tackled two tasks: 1) book genre classification based on cover images and 2) understanding how the Convolutional Neural Network (CNN) was able to classify the book.

Softmax Gradient Layer-wise Relevance Propagation (SGLRP)

This research improves a popular method of Convolutional Neural Network (CNN) visualization called Layer-wise Relevance Propagation (LRP) by exploiting the gradient of softmax as the relevance signal.

Time Series Data Augmentation

Time series data augmentation for neural networks

I performed an extensive empirical survey on time series data augmentation methods for temporal neural networks. In this work, 6 temporal neural network structures are used with 12 data augmentation methods on all 128 UCR Time Series Archive datasets.

Discriminative Guided Warping

This research proposes a new pattern mixing-based data augmentation method that warps the values of one pattern to the time steps of another pattern. In addition, we use a discriminator to determine the teacher pattern to be mixed in order to directly improve generalization.

Publications

International Journals (Refereed)

  1. Ke Xiao, Anna Zhu, Brian Kenji Iwana, and Cheng-Lin Liu, "Scene text recognition via dual character counting-aware visual and semantic modeling network," Science China Information Sciences, vol. 67, no. 3, pp. 139101:1-139101:1, 2024.
    [BibTeX] [DOI]
  2. Guangtao Lyu, Kun Liu, Anna Zhu, Seiichi Uchida, Brian Kenji Iwana, "FETNet: Feature erasing and transferring network for scene text removal," Pattern Recognition, vol. 140, pp. 109531, 2023.
    [BibTeX] [PDF] [DOI] [GitHub]
  3. Shinnosuke Matsuo, Xiaomeng Wu, Gantugs Atarsaikhan, Akisato Kimura, Kunio Kashino, Brian Kenji Iwana, Seiichi Uchida, "Deep Attentive Time Warping," Pattern Recognition, vol. 136, pp. 109201, 2023.
    [BibTeX] [PDF] [DOI]
  4. Yuchen Zheng, Brian Kenji Iwana, Muhammad Imran Malik, Sheraz Ahmed, Wataru Ohyama, and Seiichi Uchida, "Learning the micro deformations by max-pooling for offline signature verification," Pattern Recognition, vol. 118, pp. 108008, 2021.
    [BibTeX] [PDF] [DOI]
  5. Brian Kenji Iwana and Seiichi Uchida, "An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks," PLOS ONE, vol. 16, no. 7, pp. e0254841, 2021.
    [BibTeX] [PDF] [DOI] [GitHub]
  6. Seokjun Kang, Seiichi Uchida, Brian Kenji Iwana, "Tunable U-Net: Controlling image-to-image outputs using a tunable scalar value," IEEE Access, vol. 9, pp. 103279-103290, 2021.
    [BibTeX] [PDF] [DOI]
  7. Seokjun Kang, Brian Kenji Iwana, Seiichi Uchida, "Complex image processing with less data—Document image binarization by integrating multiple pre-trained U-Net modules," Pattern Recognition, vol. 109, pp. 107577, 2021.
    [BibTeX] [PDF] [DOI]
  8. Gantugs Atarsaikhan, Brian Kenji Iwana, and Seiichi Uchida, "Guided neural style transfer for shape stylization," PLOS ONE, vol. 15, no. 6, pp. e0233489, 2020.
    [BibTeX] [PDF] [DOI]
  9. Anna Zhu, Xiongbo Lu, Xiang Bai, Seiichi Uchida, Brian Kenji Iwana, and Shengwu Xiong, "Few-Shot Text Style Transfer via Deep Feature Similarity," IEEE Transactions on Image Processing, vol. 29, pp. 6932-6946, 2020.
    [BibTeX] [DOI]
  10. Adriano Lucieri, Huzaifa Sabir, Shoaib Ahmed Siddiqui, Syed Tahseen Raza Rizvi, Brian Kenji Iwana, Seiichi Uchida, Andreas Dengel, and Sheraz Ahmed, "Benchmarking Deep Learning Models for Classification of Book Covers," SN Computer Science, vol. 1, no. 139, pp. 1--16, 2020.
    [BibTeX] [PDF] [DOI]
  11. Brian Kenji Iwana, Volkmar Frinken, and Seiichi Uchida, "DTW-NN: A novel neural network for time series recognition using dynamic alignment between inputs and weights," Knowledge-Based Systems, vol. 188, pp. 104971, 2020.
    [BibTeX] [PDF] [DOI]
  12. Brian Kenji Iwana and Seiichi Uchida, "Time series classification using local distance-based features in multi-modal fusion networks," Pattern Recognition, vol. 97, pp. 107024, 2020.
    [BibTeX] [PDF] [DOI]
  13. Yuchen Zheng, Brian Kenji Iwana, and Seiichi Uchida, "Mining the Displacement of Max-pooling for Text Recognition," Pattern Recognition, vol. 93, pp. 558-569, 2019.
    [BibTeX] [PDF] [DOI]
  14. Brian Kenji Iwana, Kaspar Riesen, Volkmar Frinken, and Seiichi Uchida, "Efficient temporal pattern recognition by means of dissimilarity space embedding with discriminative prototypes," Pattern Recognition, vol. 64, pp. 268-276, 2017.
    [BibTeX] [PDF] [DOI]
  15. Anna Zhu, Guoyou Wang, Yangbo Dong, and Brian Kenji Iwana, "Detecting text in natural scene images with conditional clustering and convolution neural network," Journal of Electronic Imaging, vol. 24, no. 5, pp. 053019, 2015.
    [BibTeX] [PDF] [DOI]

International Conferences (Refereed)

  1. Yoh Yamashita and Brian Kenji Iwana, "Test Time Augmentation as a Defense Against Adversarial Attacks on Online Handwriting," International Conference on Document Analysis and Recognition (ICDAR), 2024.
    [BibTeX]
  2. Karthikeyan Suresh and Brian Kenji Iwana, "Using Motif-Based Features to Improve Signal Classification with Temporal Neural Networks," Asian Conference on Pattern Recognition (ACPR), pp. 123–136, 2023.
    [BibTeX] [DOI]
  3. Wei Pan, Anna Zhu, Xinyu Zhou, Brian Kenji Iwana, Shilin Li, "Few shot font generation via transferring similarity guided global style and quantization local style," International Conference on Computer Vision (ICCV), pp. 19449-19459, 2023.
    [BibTeX] [PDF] [DOI] [GitHub]
  4. Brian Kenji Iwana and Akihiro Kusuda, "Vision Conformer: Incorporating Convolutions into Vision Transformer Layers," International Conference on Document Analysis and Recognition (ICDAR), pp. 54–69, 2023.
    [BibTeX] [PDF] [DOI] [GitHub]
  5. Yusuke Nagata, Brian Kenji Iwana, and Seiichi Uchida, "Contour Completion by Transformers and Its Application to Vector Font Data," International Conference on Document Analysis and Recognition (ICDAR), pp. 490–504, 2023.
    [BibTeX] [PDF] [DOI]
  6. Anna Zhu, Zhanhui Yin, Brian Kenji Iwana, Xinyu Zhou, Shengwu Xiong, "Text Style Transfer based on Multi-factor Disentanglement and Mixture," ACM Multimedia (ACMMM), pp. 2430-2440, 2022.
    [BibTeX] [DOI]
  7. Daisuke Oba, Brian Kenji Iwana, Shinnosuke Matsuo, "Dynamic Data Augmentation with Gating Networks for Time Series Recognition," International Conference on Pattern Recognition (ICPR), pp. 3034-3040, 2022.
    [BibTeX] [PDF] [DOI]
  8. Brian Kenji Iwana, "On Mini-Batch Training with Varying Length Time Series," International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 4483-4487, 2022.
    [BibTeX] [PDF] [DOI] [GitHub]
  9. Shinnosuke Matsuo, Xiaomeng Wu, Gantugs Atarsaikhan, Akisato Kimura, Kunio Kashino, Brian Kenji Iwana, and Seiichi Uchida, "Attention to Warp: Deep Metric Learning for Multivariate Time Series," International Conference on Document Analysis and Recognition (ICDAR), pp. 350-365, 2021.
    [BibTeX] [PDF] [DOI]
  10. Taiga Miyazono, Daichi Haraguchi, Seiichi Uchida, and Brian Kenji Iwana, "Font Style that Fits an Image -- Font Generation Based on Image Context," International Conference on Document Analysis and Recognition (ICDAR), pp. 569-584, 2021.
    [BibTeX] [PDF] [DOI]
  11. Wensheng Zhang, Yan Zheng, Taiga Miyazono, Seiichi Uchida, and Brian Kenji Iwana, "Towards Book Cover Design via Layout Graphs," International Conference on Document Analysis and Recognition (ICDAR), pp. 642–657, 2021.
    [BibTeX] [PDF] [DOI] [GitHub]
  12. Kaigen Tsuji, Seiichi Uchida, Brian Kenji Iwana, "Using Robust Regression to Find Font Usage Trends," ICDAR Workshop on Machine Learning (ICDAR-WML), pp. 126-141, 2021.
    [BibTeX] [PDF] [DOI]
  13. Shinnosuke Matsuo, Brian Kenji Iwana, and Seiichi Uchida, "Self-Augmented Multi-Modal Feature Embedding," International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 3995-3999, 2021.
    [BibTeX] [PDF] [DOI]
  14. Brian Kenji Iwana and Seiichi Uchida, "Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher," International Conference on Pattern Recognition (ICPR), pp. 3558-3565, 2021.
    [BibTeX] [PDF] [DOI] [GitHub]
  15. Keisuke Kanda, Brian Kenji Iwana, and Seiichi Uchida, "What is the Reward for Handwriting? --- Handwriting Generation by Imitation Learning," International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 109-114, 2020.
    [BibTeX] [PDF] [DOI]
  16. Hiroki Tokunaga, Brian Kenji Iwana, Yuki Teramoto, Akihiko Yoshizawa, and Ryoma Bise, "Negative Pseudo Labeling using Class Proportion for Semantic Segmentation in Pathology," European Conference on Computer Vision (ECCV), pp. 430-446, 2020.
    [BibTeX] [PDF] [DOI]
  17. Masaya Ikoma, Brian Kenji Iwana, and Seiichi Uchida, "Effect of Text Color on Word Embeddings," International Workshop on Document Analysis Systems (DAS), pp. 341--355, 2020.
    [BibTeX] [PDF] [DOI]
  18. Seokjun Kang, Brian Kenji Iwana, and Seiichi Uchida, "ACMU-Net: Advanced Cascading Modular U-Nets incorporated Squeeze and Excitation Blocks," International Workshop on Document Analysis Systems (DAS), pp. 118--130, 2020.
    [BibTeX] [DOI]
  19. Gantugs Atarsaikhan, Brian Kenji Iwana, and Seiichi Uchida, "Neural Style Difference Transfer and Its Application to Font Generation," International Workshop on Document Analysis Systems (DAS), pp. 544-558, 2020.
    [BibTeX] [PDF] [DOI]
  20. Daichi Haraguchi, Shota Harada, Yuto Shinahara, Brian Kenji Iwana, and Seiichi Uchida, "Character-independent font identification," International Workshop on Document Analysis Systems (DAS), pp. 497--511, 2020.
    [BibTeX] [PDF] [DOI]
  21. Yirong Zhao and Brian Kenji Iwana, "Implementation and evaluation of classes incorporating drama approach methods for interactive learning in a primary school setting," International Conference on Education, Research and Innovation (ICERI), pp. 4007-4014, 2019.
    [BibTeX] [DOI]
  22. Brian Kenji Iwana, Ryohei Kuroki, and Seiichi Uchida, "Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation," ICCV Workshops, pp. 4176-4185, 2019.
    [BibTeX] [PDF] [DOI] [GitHub]
  23. Seokjun Kang, Brian Kenji Iwana, Seiichi Uchida, "Cascading Modular U-Nets for Document Image Binarization," International Conference on Document Analysis and Recognition (ICDAR), pp. 675-680, 2019.
    [BibTeX] [PDF] [DOI]
  24. Kohei Baba, Seiichi Uchida, and Brian Kenji Iwana, "On the Ability of a CNN to Realize Image-to-Image Language Conversion," International Conference on Document Analysis and Recognition (ICDAR), pp. 448-453, 2019.
    [BibTeX] [PDF] [DOI]
  25. Ryo Nakao, Brian Kenji Iwana, and Seiichi Uchida, "Selective Super-Resolution for Scene Text Images," International Conference on Document Analysis and Recognition (ICDAR), pp. 401-406, 2019.
    [BibTeX] [PDF] [DOI]
  26. Taichi Sumi, Brian Kenji Iwana, Hideaki Hayashi, and Seiichi Uchida, "Modality Conversion of Handwritten Patterns by Cross Variational Autoencoders," International Conference on Document Analysis and Recognition (ICDAR), pp. 407-412, 2019.
    [BibTeX] [PDF] [DOI]
  27. Xiaomeng Wu, Akisato Kimura, Brian Kenji Iwana, Seiichi Uchida, and Kunio Kashino, "Deep Dynamic Time Warping: End-to-End Local Representation Learning for Online Signature Verification," International Conference on Document Analysis and Recognition (ICDAR), pp. 1103-1110, 2019.
    [BibTeX] [DOI]
  28. Yuchen Zheng, Wataru Ohyama, Brian Kenji Iwana, and Seiichi Uchida, "Capturing Micro Deformations from Pooling Layers for Offline Signature Verification," International Conference on Document Analysis and Recognition (ICDAR), pp. 1111-1116, 2019.
    [BibTeX] [PDF] [DOI]
  29. Brian Kenji Iwana and Seiichi Uchida, "Dynamic Weight Alignment for Temporal Convolutional Neural Networks," International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 3827-3831, 2019.
    [BibTeX] [PDF] [DOI]
  30. Shailza Jolly, Brian Kenji Iwana, Ryohei Kuroki, and Seiichi Uchida, "How do Convolutional Neural Networks Learn Design?," International Conference on Pattern Recognition (ICPR), pp. 1085-1090, 2018.
    [BibTeX] [PDF] [DOI]
  31. Brian Kenji Iwana, Minoru Mori, Akisato Kimura, and Seiichi Uchida, "Introducing Local Distance-based Features to Temporal Convolutional Neural Networks," International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 92-97, 2018.
    [BibTeX] [PDF] [DOI] [GitHub]
  32. Yuchen Zheng, Brian Kenji Iwana, and Seiichi Uchida, "Discovering Class-Wise Trends of Max-Pooling in Subspace," International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 98-103, 2018.
    [BibTeX] [PDF] [DOI]
  33. Gantugs Atarsaikhan, Brian Kenji Iwana, and Seiichi Uchida, "Contained Neural Style Transfer for Decorated Logo Generation," International Workshop on Document Analysis Systems (DAS), pp. 317-322, 2018.
    [BibTeX] [PDF] [DOI]
  34. Kotaro Abe, Brian Kenji Iwana, Viktor Gösta Holmér, and Seiichi Uchida, "Font Creation Using Class Discriminative Deep Convolutional Generative Adversarial Networks," Asian Conference on Pattern Recognition (ACPR), pp. 232-237, 2017.
    [BibTeX] [PDF] [DOI]
  35. Jinho Lee, Brian Kenji Iwana, Shota Ide, Hideaki Hayashi, and Seiichi Uchida, "Globally Optimal Object Tracking with Complementary Use of Single Shot Multibox Detector and Fully Convolutional Network," Pacific-Rim Symposium on Image and Video Technology (PSIVT), pp. 110-122, 2017.
    [BibTeX] [PDF] [DOI]
  36. Gantugs Atarsaikhan, Brian Kenji Iwana, Atsushi Narusawa, Keiji Yanai, and Seiichi Uchida, "Neural font style transfer," ICDAR Workshop on Machine Learning (ICDAR-WML), pp. 51-56, 2017.
    [BibTeX] [PDF] [DOI]
  37. Brian Kenji Iwana, Letao Zhou, Kumiko Tanaka-Ishii, and Seiichi Uchida, "Component Awareness in Convolutional Neural Networks," International Conference on Document Analysis and Recognition (ICDAR), pp. 394-399, 2017.
    [BibTeX] [PDF] [DOI]
  38. Seiichi Uchida, Shota Ide, Brian Kenji Iwana, and Anna Zhu, "A further step to perfect accuracy by training CNN with larger data," International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 405-410, 2016.
    [BibTeX] [PDF] [DOI]
  39. Brian Kenji Iwana, Volkmar Frinken, and Seiichi Uchida, "A Robust Dissimilarity-Based Neural Network for Temporal Pattern Recognition," International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 265-270, 2016.
    [BibTeX] [PDF] [DOI]
  40. Brian Kenji Iwana, Seiichi Uchida, Kaspar Riesen, and Volkmar Frinken, "Tackling Temporal Pattern Recognition by Vector Space Embedding," International Conference on Document Analysis and Recognition (ICDAR), pp. 816-820, 2015.
    [BibTeX] [PDF] [DOI]

Japan Domestic Journals and Conferences (Refereed and Non-Refereed)

  1. Sangjun Han, Brian Kenji Iwana, Satoru Uchida, "Classification of Polysemous and Homograph Word Usages using Semi-Supervised Learning," Annual Conference of the Association for Natural Language Processing (NLP), pp. 2409-2413, 2023.
    [BibTeX] [PDF]
  2. Wensheng Zhang, Seiichi Uchida, and Brian Kenji Iwana, "Towards Book Cover Design via Layout Graphs," Meeting on Image Recognition and Understanding (MIRU), 2021.
  3. Kaigen Tsuji, Seiichi Uchida, and Brian Kenji Iwana, "Analysis of Historical Changes in the Fonts on Movie Posters," Meeting on Image Recognition and Understanding (MIRU), 2021.
  4. Shinnosuke Matsuo, Xiaomeng Wu, Gantugs Atarsaikhan, Akisato Kimura, Kunio Kashino, Brian Kenji Iwana, and Seiichi Uchida, "Deep Metric Learning Based on Attention Model for Multivariate Time Series," Meeting on Image Recognition and Understanding (MIRU), 2021.
  5. Yirong Zhao, Brian Kenji Iwana, and Kun Qian, "Drama Approach as an Educational Practice in Secondary Education: A Case Study in a Japanese Middle School," Joint Journal of the National Universities in Kyushu, Education and Humanities, vol. 6, no. 1/2, pp. 4--25, 2020.
    [BibTeX] [PDF]
  6. Kohei Baba, Brian Kenji Iwana, and Seiichi Uchida, "画像に基づく言語変換," Meeting on Image Recognition and Understanding (MIRU), 2019.
  7. Brian Kenji Iwana, and Seiichi Uchida, "Judging a Book by its Cover," Kyushu University Education Reform Symposium, 2018.
  8. Letao Zhou, Brian Kenji Iwana, Kumiko Tanaka-Ishii, and Seiichi Uchida, "Component Detection in Chinese Character Using CNN," IEICE Technical Report, 2017.
  9. Brian Kenji Iwana and Seiichi Uchida, "Judging a Book by its Cover," Meeting on Image Recognition and Understanding (MIRU), 2016.

Preprints (Non-Refereed)

  1. Joonho Lee, Kumar Shridhar, Brian Kenji Iwana, Seokjun Kang, and Seiichi Uchida, "ProbAct: A Probabilistic Activation Function for Deep Neural Networks," ArXiv, no. 1905.10761, 2019.
    [BibTeX] [arXiv]
  2. Brian Kenji Iwana, Syed Tahseen Raza Rizvi, Sheraz Ahmed, Andreas Dengel, and Seiichi Uchida, "Judging a Book by its Cover," ArXiv, no. 1610.09204, 2017.
    [BibTeX] [arXiv] [GitHub]
  3. Jinho Lee, Brian Kenji Iwana, Shouta Ide, and Seiichi Uchida, "Globally Optimal Object Tracking with Fully Convolutional Networks," ArXiv, no. 1612.08274, 2016.
    [BibTeX] [arXiv]

Patents

  1. Xiaomeng Wu, Shogo Kimura, Kunio Kashino, Brian Kenji Iwana, Seiichi Uchida, "LEARNING APPARATUS, COLLATION APPARATUS, LEARNING METHOD, COLLATION METHOD, AND PROGRAM," Japan Patent Office, no. 2019-16133, 2022.
    [BibTeX] [Patent]

Grants

  1. Brian Kenji Iwana, "Tackling real-world time series using dynamic neural networks," 科学研究費 若手研究, no. 23K16949, 2023.
    [Grant]
  2. Brian Kenji Iwana, "Dynamic Neural Architecture Warping for Time Series Recognition," 科学研究費 若手研究, no. 21K17808, 2021.
    [Grant]
  3. Brian Kenji Iwana, "Tackling Real-World Data with Multi-Modal Representation and Augmentation," QR プログラム わかばチャレンジ, no. 01252, 2021.

Activities

International Journals

  1. Associate Editor, Springer Nature Computer Science
  2. Reviewer, Elsevier Pattern Recognition
  3. Reviewer, Elsevier Neural Networks
  4. Reviewer, Elsevier Knowledge-Based Systems
  5. Reviewer, Elsevier Applied Soft Computing
  6. Reviewer, Elsevier Automation in Construction
  7. Reviewer, Elsevier Pattern Recognition Letters
  8. Reviewer, IEEE Trans. Systems, Man and Cybernetics: Systems
  9. Reviewer, IEEE Access
  10. Reviewer, MDPI Remote Sensing
  11. Reviewer, International Journal on Document Analysis and Recognition
  12. Reviewer, IEICE Trans. Information and Systems

International Conferences

  1. Program Committee, Int. Conf. on Document Analysis and Recognition, 2021, 2023, 2024
  2. Reviewer, Int. Conf. on Acoustics, Speech, and Signal Processing, 2023
  3. Senior Program Committee Member, Int. Conf. on Frontiers of Handwriting Recognition, 2022
  4. Reviewer, Winter Conference on Applications of Computer Vision, 2022
  5. Reviewer, Int. Conf. on Pattern Recognition, 2018, 2022
  6. Program Committee, Int. Workshop on Document Analysis Systems, 2018, 2020, 2022
  7. Program Committee, AAAI Conf. on Artificial Intelligence, 2021
  8. Program Committee, ICDAR Workshop on Machine Learning, 2017, 2019, 2021
  9. Program Committee, Int. Conf. on Frontiers of Handwriting Recognition, 2020
  10. Session Chair, Joint Workshop on Machine Perception and Robotics, 2018
  11. Sub-Reviewer, Int. Conf. on Document Analysis and Recognition, 2015

Scholar

  1. Completion of the Graduate Education and Research Training Program in Decision Science for a Sustainable Society (九州大学 持続可能な社会を拓く決断科学大学院プログラム), Kyushu University, Japan
    [Link]

Awards

  1. Best Interactive Session, Kohei Baba, Brian Kenji Iwana, and Seiichi Uchida, "画像に基づく言語変換," Meeting on Image Recognition and Understanding (MIRU), Osaka, Japan, 2019
  2. Best Student Paper Award (Track), Shailza Jolly, Brian Kenji Iwana, Ryohei Kuroki, and Seiichi Uchida, "How do Convolutional Neural Networks Learn Design?," Int. Conf. on Pattern Recognition, Beijing, China, 2018
  3. Bronze Prize, Brian Kenji Iwana, Seiichi Uchida, "Judging a Book by its Cover," Kyushu University Education Reform Symposium, Fukuoka, Japan, 2017

Teaching

  1. Lecturer, "Fundamentals of Computer Systems A/B," Kyushu University, Japan, 2020, 2021, 2022, 2023, 2024
  2. Invited Lecture, "Fundamentals of Electrical Engineering and Computer Science I," Kyushu University, Japan, 2023
  3. Instructor, "Fundamentals of Electrical Engineering and Computer Science I," Kyushu University, Japan, 2022
  4. Lecturer, "Pattern Recognition and Data Processing," Kyushu University, Japan, 2018, 2019, 2020, 2021, 2022
  5. Invited Lecture, "Time Series Classification with Distance-based Neural Networks," NTT Communication Labs, Japan, 2018
  6. Guest Lecturer, "Image Processing," Kyushu University, Japan, 2017
  7. Guest Lecturer, "Pattern Recognition," Kyushu University, Japan, 2016

Curriculum Vitae

Education:

Ph.D., Information Science

Kyushu University, Fukuoka city, Fukuoka, Japan

B.S., Computer Engineering

University of California Irvine, Irvine, California, USA

Employment:

Associate Professor (2020 - Current)

Assistant Professor (2018 - 2020)

Information Science and Electrical Engineering, Kyushu University, Fukuoka city, Fukuoka, Japan
  • Associate Professor at the Human Interface Laboratory.
  • Research Interest: Pattern Recognition, Machine Learning, Artificial Neural Networks, Document Analysis and Recognition, Time Series Recognition

Software Developer (2010 - 2014)

National Aeronautics and Space Administration, Mountain View, California, USA
  • Developed data management and data interfacing applications for NASA scientists.
  • Skills: PHP, CodeIgniter, Bootstrap 3, MySQL, Jquery, Witango, FileNet eForms

Software Developer (2007 - 2009)

Talisman LBS, LLC, Honolulu, Hawaii, USA
  • Worked as a full stack application developer.
  • Skills - Ruby on Rails, MySQL, HTML, Prototype JS, Apache

IT Consultant (2005 - 2007)

Elite Development Group, Aliso Viejo, California, USA
  • Set up, maintain, and troubleshoot networks and domains for small to medium size businesses on multiple OS platforms.
  • Skills: Windows Server 2000, Active Directory, security, networking