Details of a Researcher - HAMAGAMI Tomoki

Dam Inflow Prediction Model using Self Low Rank Adaptation

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

Ikuma Sosuke, Jo Tei, Chin Yo, Fukai Hironobu, Takase Nobuaki, Hamagami Tomoki

IEEJ Transactions on Electronics, Information and Systems 145 ( 2 ) 207 - 213 2025.2

Soft intelligent systems based on stretchable hybrid devices integrated with machine learning

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

Isano, Y; Takaya, M; Kurotaki, Y; Matsuda, R; Miyake, Y; Takano, T; Isoda, Y; Hamagami, T; Kuribaya … Show more authors

DEVICE 2 ( 9 ) 2024.9

Language：Japanese Publishing type：Research paper (scientific journal) Joint Work

Estimation of Multi-Expert Sperm Assessments Using Video Recognition Based Model Trained by EMD Loss

Hayato Nakagawa; Takuro Fujii; Yasushi Yumura; and Tomoki Hamagami

IEEE Access 2024.8 [Reviewed]

Document-to-Document Retrieval Using Self-Retrieval Learning and Automatic Keyword Extraction

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (scientific journal) Joint Work

Seki, Y; Hamagami, T

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2024.8 [Reviewed]

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

Latent Denoising Diffusion GAN: Faster sampling, Higher image quality

LUAN THANH TRINH, TOMOKI HAMAGAM

IEEE Access 12 78161 - 78172VOLUME 2024.5 [Reviewed]

3D Ship Hull Design Direct Optimization Using Generative Adversarial Network

Authorship：Corresponding author Language：English Publishing type：Research paper (scientific journal) Single Work

3D Ship Hull Design Direct Optimization Using Generative Adversarial Network

Luan Thanh Trinh, Tomoki Hamagami, and Naoya Okamoto

Journal of Advanced Computational Intelligence and Intelligent Informatics. 28 ( 3 ) 2024.5 [Reviewed]

Authorship：Corresponding author Language：English Publishing type：Research paper (scientific journal) Single Work

Trinh, LT; Hamagami, T; Okamoto, N

JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS 28 ( 3 ) 693 - 703 2024.5

DOI Web of Science CiNii Research

Language：English Publishing type：Research paper (scientific journal) Publisher：富士技術出版株式会社 Joint Work

The direct optimization of ship hull designs using deep learning algorithms is increasingly expected, as it proposes optimization directions for designers almost instantaneously, without relying on complex, time-consuming, and expensive hydrodynamic simulations. In this study, we proposed a GAN-based 3D ship hull design optimization method. We eliminated the dependence on hydrodynamic simulations by training a separate model to predict ship performance indicators. Instead of a standard discriminator, we applied a relativistic average discriminator to obtain better feedback regarding the anomalous designs. We add two new loss functions for the generator: one restricts design variability, and the other sets improvement targets using feedback from the performance estimation model. In addition, we propose a new training strategy to improve learning effectiveness and avoid instability during training. The experimental results show that our model can optimize the form factor by 5.251% while limiting the deterioration of other indicators and the variability of the ship hull design.

Automated Sperm Assessment Framework and Neural Network Specialized for Sperm Video Recognition

T Fujii, H Nakagawa, T Takeshima, Y Yumura, T Hamagami

Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision 2024.1

Latent Denoising Diffusion GAN: Faster Sampling, Higher Image Quality

Authorship：Last author Language：English Publishing type：Research paper (international conference proceedings) Single Work

Trinh, LT; Hamagami, T

IEEE ACCESS 12 78161 - 78172 2024

Language：Japanese Publishing type：Research paper (scientific journal) Joint Work

Motion Recognition System Based on Hard-Soft Hybrid Stretchable Devices and Machine Learning

Isano Yuji, Takaya Maika, Kurotaki Yuta, Matsuda Ryosuke, Miyake Yusuke, Takano Tamami, Isoda Yutak … Show more authors

The Proceedings of Mechanical Engineering Congress, Japan 2024 ( 0 ) J224-03 2024

Language：Japanese Publishing type：Research paper (scientific journal) Publisher：The Japan Society of Mechanical Engineers Joint Work

Task Head to Reduce Domain Shift with a Noise Imposition Mechanism and Low Dimensional Features Following a Normal Distribution

Takuro FUJII, Tomoki HAMAGAMI

Journal of Information Processing 64 ( 12 ) 1668 - 1677 2023.12 [Reviewed]

Authorship：Last author Language：Japanese Publishing type：Research paper (scientific journal) Single Work

今月の臨床 AIがもたらす産婦人科医療の変革生殖医療 AIによる精子評価支援システムの開発

湯村寧, 竹島徹平, 濱上知樹

臨床婦人科産科 77 ( 12 ) 1207 - 1215 2023.12

Ordinal Regression Based on the Distributional Distance for Tabular Data

Language：The in addition, foreign language Publishing type：Research paper (scientific journal) Publisher：株式会社医学書院 Joint Work

Tajima Yoshiyuki, Hamagami Tomoki

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS E106D ( 3 ) 357 - 364 2023.3 [Reviewed]

DOI Web of Science CiNii Research

Language：English Publishing type：Research paper (scientific journal) Publisher：一般社団法人電子情報通信学会 Joint Work

Ordinal regression is used to classify instances by considering ordinal relation between labels. Existing methods tend to decrease the accuracy when they adhere to the preservation of the ordinal relation. Therefore, we propose a distributional knowledge-based network (DK-net) that considers ordinal relation while maintaining high accuracy. DK-net focuses on image datasets. However, in industrial applications, one can find not only image data but also tabular data. In this study, we propose DK-neural oblivious decision ensemble (NODE), an improved version of DK-net for tabular data. DK-NODE uses NODE for feature extraction. In addition, we propose a method for adjusting the parameter that controls the degree of compliance with the ordinal relation. We experimented with three datasets: WineQuality, Abalone, and Eucalyptus dataset. The experiments showed that the proposed method achieved high accuracy and small MAE on three datasets. Notably, the proposed method had the smallest average MAE on all datasets.

AIがもたらす産婦人科医療の変革生殖医療　AIによる精子評価支援システムの開発

湯村寧, 濱上知樹

臨床婦人科産科 77 1207 - 1215 2023

CiNii Research

Language：The in addition, foreign language Publishing type：Research paper (scientific journal) Joint Work

A New XGBoost Inference with Boundary Conditions in Real Estate Price Prediction

Iwai Koichi, Hamagami Tomoki

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 17 ( 11 ) 1613 - 1619 2022.7 [Reviewed]

Reinforcement Learning for POMDP Environments Using State Representation with Reservoir Computing

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

Yamashita Kodai, Hamagami Tomoki

JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS 26 ( 4 ) 562 - 569 2022.7 [Reviewed]

DOI Web of Science CiNii Research

Language：English Publishing type：Research paper (scientific journal) Publisher：富士技術出版株式会社 Joint Work

One of the challenges in reinforcement learning is regarding the partially observable Markov decision process (POMDP). In this case, an agent cannot observe the true state of the environment and perceive different states to be the same. Our proposed method uses the agent’s time-series information to deal with this imperfect perception problem. In particular, the proposed method uses reservoir computing to transform the time-series of observation information into a non-linear state. A typical model of reservoir computing, the echo state network (ESN), transforms raw observations into reservoir states. The proposed method is named dual ESNs reinforcement learning, which uses two ESNs specialized for observation and action information. The experimental results show the effectiveness of the proposed method in environments where imperfect perception problems occur.

Opticalflow Estimation for Deformable Object Utilizing Superpixels and Motion Estimation Using Phase Correlation and CNN

Oishi Nobuya, Hamagami Tomoki

IEEJ Transactions on Electronics, Information and Systems 142 ( 1 ) 100 - 107 2022.1 [Reviewed]

Adversarial Inverse Reinforcement Learning to Estimate Policies from Multiple Experts

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

Yamashita Kodai, Hamagami Tomoki

IEEJ Transactions on Electronics, Information and Systems 141 ( 12 ) 1405 - 1410 2021.12 [Reviewed]

Learning Transferable Policy in Reinforcement Learning for Vehicle Velocity Tracking Control

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

Natsu Yukiya, Hamagami Tomoki, Kanke Masayasu, Yoshida Kento, Niwakawa Makoto

IEEJ Transactions on Electronics, Information and Systems 141 ( 12 ) 1492 - 1499 2021.12 [Reviewed]

Classification Model Considering Misclassification Based on Distributional Distance Between Labels

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

Tajima Yoshiyuki, Hamagami Tomoki

IEEJ Transactions on Electronics, Information and Systems 141 ( 9 ) 1048 - 1054 2021.9 [Reviewed]

Bayesian Network Oriented Transfer Learning Method for Credit Scoring Model

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

Iwai Koichi, Akiyoshi Masanori, Hamagami Tomoki

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 16 ( 9 ) 1195 - 1202 2021.9 [Reviewed]

Reservoir Computing for Scalable Hardware with Block-Based Neural Network

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

Lee Kundo, Hamagami Tomoki

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 16 ( 12 ) 1594 - 1602 2021.8 [Reviewed]

Research Group Introduction: Hamagami Laboratory, Dept. of Math., Phys., Electrical Engineering and Computer Science, Graduate School of Engineering Science, Yokohama National University

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

IEEJ Transactions on Industry Applications 141 ( 2 ) NL2_8 - NL2_8 2021.2

Terms Completion based on Nonnegative Matrix Factorization for Care Planning Support System

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

We are working on intelligent systems engineering with AI for the realization of intelligent social systems and intelligent medical and care support systems. This article introduces these efforts and cases.

Other Link： https://ci.nii.ac.jp/naid/130007979771

Koki Hyodo, Tomoki Hamagami

62 ( 1 ) 369 - 377 2021.1 [Reviewed]

Language：Japanese Publishing type：Research paper (scientific journal) Joint Work

Other Link： http://id.nii.ac.jp/1001/00208905/

Ordinal Regression Based on the Distributional Distance Between Labels

Tajima Yoshiyuki, Hamagami Tomoki

2021 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) 1482 - 1488 2021 [Reviewed]

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

連載 FOCUS 〔シリーズ〕産婦人科と先端テクノロジー人工知能(AI)の生殖補助医療への応用-精子探索・選別支援システムの開発

湯村寧, 竹島徹平, 黒田晋之介, 山本みずき, 佐々木勇人, 濱上知樹

臨床婦人科産科 74 ( 5 ) 505 - 510 2020.5

Language：The in addition, foreign language Publishing type：Research paper (scientific journal) Publisher：株式会社医学書院 Joint Work

特集専門医はもういらない?　せまりくるAI時代 10.AIによる生殖補助医療

湯村寧, 竹島徹平, 黒田晋之介, 山本みずき, 佐々木勇人, 濱上知樹

産婦人科の実際 69 ( 5 ) 489 - 493 2020.5

Wave-making Resistance Estimation Through Deep Learning Considering the Distribution of Ship Figure

Language：The in addition, foreign language Publishing type：Research paper (scientific journal) Publisher：金原出版 Joint Work

Li Xin, Arai Hiroshi, Hamagami Tomoki

IEEJ Transactions on Electronics, Information and Systems 140 ( 3 ) 391 - 397 2020.3 [Reviewed]

Block-Based Neural Network Optimization with Manageable Problem Space

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

A method for the estimation of wave-making resistance from the hull form and Froude number through deep learning is proposed. At the same time, this research also gives a solution when the data are skewed, which solves the problem of low generalization performance. The reduction of wave-making resistance is an essential issue in hull form design. However, the estimation of wave-making resistance is a time-consuming task that depends on experimental measurements. To enable direct estimation of the wave resistance from hull form, deep learning, which enables end-to-end learning, is an effective approach. The proposed method has two phases. First, auto-encoders, which reduce the dimension of the offset and the profile data, are generated, while performing to the skewed offset data, use an improved sampling method. Subsequently, after the regularization of these data, a deep neural net for regression estimation of wave-making resistance is generated. The results of evaluation experiments show that the proposed method can estimate wave-making resistance with high precision.

Other Link： https://ci.nii.ac.jp/naid/130007804400

Lee Kundo, Hamagami Tomoki

電気学会論文誌Ｃ（電子・情報・システム部門誌） 140 ( 1 ) 68 - 74 2020.1 [Reviewed]

Structured Feature Derivation for Transfer Learning on Credit Scoring

Language：English Publishing type：Research paper (scientific journal) Publisher：一般社団法人電気学会 Joint Work

In this paper, a simple method based on Genetic Algorithm (GA) is proposed to evolve Block-Based Neural Network (BbNN) model. A BbNN consists of a 2-D array of memory-based modular component NNs with flexible structures and internal configuration that can be implemented in reconfigurable hardware such as a field programmable gate array (FPGA). The network structure and the weights are encoded in bit strings and globally optimized using the genetic operators. Asynchronous BbNN (ABbNN), which is a new model of BbNN, suggests high-performance BbNN by utilizing parallel computation and pipeline architecture. ABbNN's operating frequency is stable for all scales of the network, while conventional BbNN's is decreasing according to the network size. However, optimization by the genetic algorithm requires more iterations to find a solution with increasing problem space and the memory access in GA operation is one of the causes degrading the performance. ABbNN optimized with the proposed evolutionary algorithm is applied on general classifiers to verify the effectiveness with increasing problem space. The proposed method is confirmed by experimental investigations and compared with the conventional genetic algorithm.

Other Link： https://ci.nii.ac.jp/naid/130007779188

Iwai Koichi, Akiyoshi Masanori, Hamagami Tomoki

2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) 818 - 823 2020 [Reviewed]

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

Brock-Based Neural Network High Speed Optimization

Kundo Lee, Tomoki Hamagami

Proceedings of the 23rd Asia Pacific Symposium on Intelligent and Ebolutionary Systemus 12 79 - 92 2019.12 [Reviewed]

Sperm Detection with Robustness to Overlap of Distributions by using Adaptive Thresholded Boosting

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

Sasaki Hayato, Yamamoto Mizuki, Takeshima Teppei, Yumura Yasushi, Hamagami Tomoki

IEEJ Transactions on Electronics, Information and Systems 139 ( 12 ) 1461 - 1467 2019.12 [Reviewed]

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

Automatic sperm detection is in high demand for supporting Testicular Sperm Extraction (TESE). On the other hand, detection of sperms in samples of TESE is difficult because there are a lot of germ cells resembling sperms. This paper realizes automatic sperm detection for TESE by using Adaptive Thresholded Boosting (ATBoost) which is robust to overlap of feature distributions between positive samples and negative samples. In this paper, we evaluated our sperm detection method in two stages from the view point of robustness to the overlap. First, we quantitatively evaluated the overlap of the feature distributions in TESE in the metric of Bayes error rate. Second, we evaluated robustness of our sperm detection method as for the overlap. These two results show that our sperm detection method is very effective for TESE.

Other Link： https://ci.nii.ac.jp/naid/130007754486

An Improved Auto-encoder Based on 2-Level Prioritized Experience Replay for High Dimension Skewed Data

Xin Li, Tomoki Hamagami

Symposium on Intelligent and Evolutionary Systems 12 93 - 105 2019.12 [Reviewed]

High performance Block-Based Neural Network Model by pipelined parallel communication

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

Vol.139 ( 9 ) 1059 - 1065 2019.9 [Reviewed]

Language：Japanese Publishing type：Research paper (scientific journal) Joint Work

Other Link： https://doi.org/10.1541/ieejeiss.139.1059

単語重みを用いたアソシエーション分析に基づく文書分類のための自動的クエリ拡張

安永翼 , 山田雄基 , 濱上知樹

情報処理学会論文誌 60 ( 3 ) 880 - 889 2019.3 [Reviewed]

Language：Japanese Publishing type：Research paper (scientific journal) Joint Work

Permalink http://id.nii.ac.jp/1001/00195320/
安永翼 , 山田雄基 , 濱上知樹
単語重みを用いたアソシエーション分析に基づく文書分類のための自動的クエリ拡張
情報処理学会論文誌,60(3),880-889 (2019-03-15) , 1882-7764 (2019.3)
(3月掲載のためまだDOIがついておらず、Permalinkとなっているが意味は同じ)

注目領域に基づいたCNNの特徴マップに対する正則化

足立一樹, 濱上知樹

電子情報通信学会和文論文誌 D J102-D ( 3 ) 185 - 193 2019.3 [Reviewed]

Language：Japanese Publishing type：Research paper (scientific journal) Joint Work

DOI: 10.14923/transinfj.2018PDP0023
足立一樹, 濱上知樹
注目領域に基づいたCNNの特徴マップに対する正則化
電子情報通信学会和文論文誌 D Vol.J102-D, No.3, pp.185-193 (2019.3)

検出率最適化のためのBoostingにおける適応的しきい値調整

佐々木勇人, 濱上知樹

電子情報通信学会論文誌 D J102-D ( 2 ) 68 - 78 2019.2 [Reviewed]

Language：Japanese Publishing type：Research paper (scientific journal) Joint Work

DOI: 10.14923/transinfj.2018JDP7036
佐々木勇人, 濱上知樹
検出率最適化のためのBoostingにおける適応的しきい値調整
電子情報通信学会論文誌 D Vol.J102-D No.2 pp.68-78 (2019.2)

Improvement in estimation accuracy of impedance with electrical and ultrasonic multiimaging systems

Fumiya Hamatsu Akira Kimoto Tomoki Hamagami

Electronics and Communication in Japan 101 ( 8 ) 11 - 18 2018.8 [Reviewed]

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

Theoretical adaptation of multiple rule-generation in XCS

Masaya Nakata, Will Browne, Tomoki Hamagami

GECCO '18 Proceedings of the Genetic and Evolutionary Computation Conference 482 - 489 2018.7 [Reviewed]

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

Development of sperm searching system using artificial intelligence in assisted reproductive technology

Takeshima T., Kuroda S., Yamamoto M., Murase M., Yumura Y., Sasaki H., Hamagami T.

HUMAN REPRODUCTION 33 148 - 148 2018.7

Web of Science

Language：Japanese Publishing type：Research paper (scientific journal) Joint Work

電気・超音波マルチイメージングにおけるインピーダンス推定精度の向上

濱津文哉, 木本晃, 濱上知樹

電気学会論文誌Ｅ（センサ・マイクロマシン部門誌） 138 ( 3 ) 93 - 99 2018.3 [Reviewed]

From the Perspective of Machine Learning ‐ Current Situation and Expectation of Deep Learning and IoT

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

HAMAGAMI Tomoki

The Journal of The Institute of Electrical Engineers of Japan 138 ( 5 ) 280 - 283 2018

Aimed for the Safety of Marine Traffic in Tokyo Bay. Visiting Tokyo Wan Vessel Traffic Service Center

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

Other Link： https://ci.nii.ac.jp/naid/130006729311

HAMAGAMI Tomoki, OKAZAKI Masaya, KURIHARA Keisuke, YASUNAGA Tsubasa

The Journal of The Institute of Electrical Engineers of Japan 138 ( 3 ) 128 - 131 2018

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

Other Link： https://ci.nii.ac.jp/naid/130006406948

Performance oriented Block-Based Neural Network Model by parallelized neighbor's communication

Lee Kundo, Hamagami Tomoki

2018 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) 1623 - 1628 2018

Language：Japanese Publishing type：Research paper (scientific journal) Joint Work

Investigation about control of false positive rate for automatic sperm detection in assisted reproductive technology

Sasaki Hayato, Nakata Masaya, Yamamoto Mizuki, Takeshima Teppei, Yumura Yasushi, Hamagami Tomoki

2018 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) 1964 - 1969 2018

Language：Japanese Publishing type：Research paper (scientific journal) Joint Work

A call triage support system for emergency medical service using multiple random forests

T.Yasuda, Y.Yamada, F.Hamatsu, T.Hamgami

Transactions on Electrical and Electronic Engineering 12 S67 - S73 2017.12 [Reviewed]

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

One-class Support Vector Machineを用いたクラス集合逐次作成法による回転機の異常検知

中尾浩二, 外山達斎, 林孝則, 堀貴雅, 濱上知樹

産業応用部門誌 137 ( 12 ) 858 - 865 2017.12 [Reviewed]

Language：English Publishing type：Research paper (scientific journal) Publisher：電気学会 Joint Work

Effect of Parameter Sharing for Multimodal Deep Autoencoders

H.Sasaki, M.Nakata, F.Hamatsu, T.Hamagami

Proc. of IEEE SMC2017 2017.10

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

An Analysis of Rule Deletion Scheme in XCS on Reinforcement Learning Problem

Masaya Nakata and Tomoki Hamagami

Journal of Advanced Computational Intelligence and Intelligent Informatics 21 ( 5 ) 876 - 884 2017.9 [Reviewed]

Language：English Publishing type：Research paper (scientific journal) Publisher：Fuji Technology Press Ltd. Joint Work

A rotating machinery fault sign detection method by using multi-level one-class SVMs

K.Nakao, T.Toyama, T.Hayashi, T.Hamagami

The international conference on electrical and engineering 2017.7

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

Extraction of contours in ultrasound images using a particle filter with limited contour presence range

F.Hamatsu, T.Tanaka, T.Hamagami

The international conference on electrical and engineering 2017.7

Language：English Publishing type：Research paper (international conference proceedings) Publisher：F.Hamatsu, T.Tanaka, T.Hamagami Joint Work

A ResearAbout Anomaly Detection Method for Multidimensional Time Series Data

X.Li, F.Hamatsu, T.Hamagami

Proc. On The international conference on electrical and engineerin 2017.7

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

Theoretical XCS parameter settings of learning accurate classifiers

M.Nakata, W.Browne, T. Hamagami, K.Takadama

Proc. of GECCO2017 473 - 480 2017.7

Language：English Publishing type：Research paper (international conference proceedings) Publisher：ACM Joint Work

Construction of visual codebook to speed up visual-based simultaneous localization and mapping

Hayato Sasaki, Fumiya Hamatsu, Tomoki Hamagami

Journal of International Council on Electrical _ _Engineering 7 2017.6

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

深層学習による小袖屏風画像の特徴分析

濱上知樹,澤田和人

人工知能学会誌 32 ( 3 ) 408 - 413 2017.4 [Reviewed] [Invited]

Language：Japanese Publishing type：Research paper (scientific journal) Joint Work

準エキスパート集団からのアンサンブル逆強化学習

冨田真司，濱津文哉，濱上知樹

電気学会電子情報システム部門論文誌C 137 ( 4 ) 667 - 673 2017.4 [Reviewed]

Language：Japanese Publishing type：Research paper (scientific journal) Joint Work

Construction of visual codebook for speeding up visual-based Simultaneous Localization and Mapping

Hayato Sasaki, Fumiya Hamatsu, Tomoki Hamagami

Proc. of The International Conference on Electrical Engineering 2016 2016 2016.7

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

Construction of the severity decision system combining Balanced Random Forest and Decision Tree

Yuki Yamada, Fumiya Hamatsu, Tomoki Hamagami

Proc. of The International Conference on Electrical Engineering 2016 2016 ( 90530 ) 2016.7

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

Examination of skill-based learning by inverse reinforcement learning using evolutionary process

Hiroaki Tsunekawa, Takuo Suzuki, Tomoki Hamagami

Proceedings of 2015 IEEE 9th International Conference on Intelligent Systems and Control 2015 ( 9 ) 2015.9

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

複雑ネットワークの指標値に基づくソフトウェア品質分析

中村光宏，濱上知樹

電気学会電子情報システム部門論文誌C 135 ( 5 ) 553 - 558 2015.5 [Reviewed]

Language：Japanese Publishing type：Research paper (scientific journal) Publisher：電気学会 Joint Work

派生開発におけるソフトウェアシステムの品質メトリクスとして，複雑ネットワークの指標を用いた評価方法を提案した。母体となるシステムの複雑性を複数のネットワークメトリクスを組み合わせて評価することで，将来的なバグの発生数とリファクタリングによる改善効果を定量的に把握できるようになる。実際のプロジェクトのコードを用いた評価によって，従来のメトリクスでは評価できなかった改変時の変化をとらえることができるようになった。

Structural classification and similarity measurement of malware

Hongbo Shi,Tomoki Hamagami, Katsunari Yoshioka,Haoyuan Xu,Kazuhiro Tobe,Shigeki Goto

IEEJ Transactions on Electrical and Electronic Engineering 9 ( 6 ) 621 - 632 2014.11 [Reviewed]

Language：English Publishing type：Research paper (scientific journal) Publisher：IEEJ Joint Work

Context awareness by unit-type evolutionary Petri net for team medical care support

Takuo Suzuki, Tomoki Hamagami

IEEE International Conference on Systems, Man, and Cybernetics 2014 385 - 390 2014.10 [Reviewed]

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

Intelligent Call Triage System with Algorithm Combining Decision-Tree and SVM

Soft Computing in Machine Learning 273 21 - 31 2014.3 [Reviewed] [Invited]

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

Fundamental study of inverse reinforcement learning from sub-experts in evolutionary process

Hiroaki Tsunekawa, Tomoki Hamagami

International Symposium on Artificial Life and Robotics 280 - 285 2014.1 [Reviewed]

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

Transfer Learning for Q-learning by Using Similarity of Phase Structure in State Spaces

Masato Takeishi, Tomoki Hamagami

International Symposium on Artificial Life and Robotics GS11 ( 6 ) 2014.1 [Reviewed]

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

Multi-agent base Restoration Algorithm for Power Distribution Network in Multiple Failure Cases

Kaori Tada,Tomoki Hamagami

Proc. of The International Conference on Electrical Engineering FP0597 210 - 215 2013.6 [Reviewed]

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

A new robust technique for constructing intelligent environment using video image

Naoki Someya, Tomoki Hamagami

The Journal of International Council on Electrical Engineering 3 ( 2 ) 187 - 191 2013.4 [Reviewed]

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

A Method for Classifying Packets into Network Flows Based on GHSOM

Shi Hongbo, Hamagami Tomoki, Xu Haoyuan, Yu Ping, Wu Yonghe

MOBILE NETWORKS & APPLICATIONS 17 ( 6 ) 730 - 739 2012.12 [Reviewed]

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

Genetic algorithm sampling the solution space selectively depending on difficulty of power distribution network restoration

Kato Yoshifumi, Hamagami Tomoki

ELECTRONICS AND COMMUNICATIONS IN JAPAN 95 ( 2 ) 16 - 24 2012.2 [Reviewed]