情報科学科

研究成果

年別の研究成果 1974 1993 2000 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2022

• 349 Conference contribution
• 343 Article
• 54 Conference article
• 44 Paper
• 37 その他
  • 16 Chapter
  • 7 Review article
  • 5 Editorial
  • 3 Book
  • 2 Comment/debate
  • 2 Letter
  • 1 Foreword/postscript
  • 1 Short survey

年別の研究成果

年別の研究成果

検索結果

• 2022

  ε-Approximation of Adaptive Leaning Rate Optimization Algorithms for Constrained Nonconvex Stochastic Optimization

  Iiduka, H., 2022, (Accepted/In press) In: IEEE Transactions on Neural Networks and Learning Systems.

  研究成果: Article › 査読

  • Deep neural networks 100%

• Riemannian stochastic fixed point optimization algorithm

  Iiduka, H. & Sakai, H., 2022, (Accepted/In press) In: Numerical Algorithms.

  研究成果: Article › 査読

  • Fixed-point Algorithm 100%
  • Learning Rate 96%
  • Adaptive Learning 86%
  • Optimization Algorithm 74%
  • Nonsmooth Function 42%

• Use of an artificial intelligence-based rule extraction approach to predict an emergency cesarean section

  Nagayasu, Y., Fujita, D., Ohmichi, M. & Hayashi, Y., 6月 2022, In: International Journal of Gynecology and Obstetrics. 157, 3, p. 654-662 9 p.

  研究成果: Article › 査読

  Open Access

  • Artificial Intelligence 100%
  • Cesarean Section 71%
  • Emergencies 58%
  • Technology 6%
• 2021

  Appropriate Learning Rates of Adaptive Learning Rate Optimization Algorithms for Training Deep Neural Networks

  Iiduka, H., 2021, (Accepted/In press) In: IEEE Transactions on Cybernetics.

  研究成果: Article › 査読

  • Deep neural networks 100%
  • Image classification 27%
  • Deep learning 23%
  • Experiments 18%
  2 被引用数 (Scopus)

• Classification functions for handwritten digit recognition

  Sasao, T., Horikawa, Y. & Iguchi, Y., 2021, In: IEICE Transactions on Information and Systems. E104D, 8, p. 1076-1082 7 p.

  研究成果: Article › 査読

  Open Access

  • Machine learning 100%
  • Classifiers 96%
  • Set theory 87%

• Feasibility study of intersection detection and recognition using a single shot image for robot navigation

  Watanabe, T., Matsutani, K., Adachi, M., Oki, T. & Miyamoto, R., 6月 2021, In: Journal of Image and Graphics(United Kingdom). 9, 2, p. 39-44 6 p.

  研究成果: Article › 査読

  Open Access

  • Navigation 100%
  • Robots 83%
  • Three dimensional computer graphics 55%
  • Classifiers 46%
  • Navigation systems 32%
  3 被引用数 (Scopus)

• Hardware implementation of a Takagi-Sugeno neuro-fuzzy system optimized by a population algorithm

  Dziwiński, P., Przybył, A., Trippner, P., Paszkowski, J. & Hayashi, Y., 1 7月 2021, In: Journal of Artificial Intelligence and Soft Computing Research. 11, 3, p. 243-266 24 p.

  研究成果: Article › 査読

  Open Access

  • Neuro-fuzzy Systems 100%
  • Hardware Implementation 82%
  • Fuzzy systems 56%
  • Field Programmable Gate Array 51%
  • Computer hardware 31%
  1 被引用数 (Scopus)

• Inexact stochastic subgradient projection method for stochastic equilibrium problems with nonmonotone bifunctions: application to expected risk minimization in machine learning

  Iiduka, H., 6月 2021, In: Journal of Global Optimization. 80, 2, p. 479-505 27 p.

  研究成果: Article › 査読

  • Stochastic Equilibrium 100%
  • Projection Method 98%
  • Subgradient Method 91%
  • Machine Learning 88%
  • Risk Minimization 87%

• Performance Analysis of Rough Set-Based Hybrid Classification Systems in the Case of Missing Values

  Nowicki, R. K., Seliga, R., elasko, D. & Hayashi, Y., 1 10月 2021, In: Journal of Artificial Intelligence and Soft Computing Research. 11, 4, p. 307-318 12 p.

  研究成果: Article › 査読

  Open Access

  • Performance Analysis 100%
  • Missing Values 95%
  • Rough Set 86%
  • Repository 28%
  • K-nearest Neighbor 26%

• Riemannian Adaptive Optimization Algorithm and Its Application to Natural Language Processing

  Sakai, H. & Iiduka, H., 2021, (Accepted/In press) In: IEEE Transactions on Cybernetics.

  研究成果: Article › 査読

  • Embeddings (Algorithms) 100%
  • Deep neural networks 80%
  • Experiments 29%
  3 被引用数 (Scopus)

• Stochastic approximation method using diagonal positive-definite matrices for convex optimization with fixed point constraints

  Iiduka, H., 12月 2021, In: Fixed Point Theory and Applications. 2021, 1, 10.

  研究成果: Article › 査読

  Open Access

  • Stochastic Approximation 100%
  • Stochastic Methods 99%
  • Positive definite matrix 98%
  • Convex optimization 92%
  • Convex Optimization 90%

• Sufficient Descent Riemannian Conjugate Gradient Methods

  Sakai, H. & Iiduka, H., 7月 2021, In: Journal of Optimization Theory and Applications. 190, 1, p. 130-150 21 p.

  研究成果: Article › 査読

  • Conjugate gradient method 100%
  • Gradient 86%
  • Conjugate Gradient Method 85%
  • Descent 79%
  • Line Search 63%
  2 被引用数 (Scopus)

• Unified Algorithm Framework for Nonconvex Stochastic Optimization in Deep Neural Networks

  Zhu, Y. & Iiduka, H., 2021, In: IEEE Access. 9, p. 143807-143823 17 p.

  研究成果: Article › 査読

  Open Access

  • Deep neural networks 100%
  • Teaching 9%
  1 被引用数 (Scopus)
• 2020

  Browser fingerprint coding methods increasing the effectiveness of user identification in the web traffic

  Gabryel, M., Grzanek, K. & Hayashi, Y., 1 10月 2020, In: Journal of Artificial Intelligence and Soft Computing Research. 10, 4, p. 243-253 11 p.

  研究成果: Article › 査読

  Open Access

  • Fingerprint 100%
  • Traffic 76%
  • Coding 68%
  • Hash functions 16%
  • Web-based 14%
  9 被引用数 (Scopus)

• Decentralized hierarchical constrained convex optimization

  Iiduka, H., 1 3月 2020, In: Optimization and Engineering. 21, 1, p. 181-213 33 p.

  研究成果: Article › 査読

  • Decentralized 100%
  • Constrained Optimization 87%
  • Constrained optimization 84%
  • Convex optimization 82%
  • Convex Optimization 80%

• Dependence of three-dimensional bottleneck barrier height minimum on threshold voltage fluctuated by ion implantation of source and drain extensions in silicon-on-insulator triple-gate fin-type field-effect transistors

  Tsutsumi, T., 2020, In: Japanese Journal of Applied Physics. 59, SI, SIIE06.

  研究成果: Article › 査読

  • Ion implantation 100%
  • fins 88%
  • Threshold voltage 81%
  • Field effect transistors 78%
  • threshold voltage 69%
  2 被引用数 (Scopus)

• Does deep learning work well for categorical datasets with mainly nominal attributes?

  Hayashi, Y., 11月 2020, In: Electronics (Switzerland). 9, 11, p. 1-10 10 p., 1966.

  研究成果: Article › 査読

  Open Access

  • Deep learning 100%
  • Classifiers 22%
  • Finance 18%
  • Banking 18%
  • Marketing 15%
  1 被引用数 (Scopus)

• Fixed point quasiconvex subgradient method

  Hishinuma, K. & Iiduka, H., 16 4月 2020, In: European Journal of Operational Research. 282, 2, p. 428-437 10 p.

  研究成果: Article › 査読

  • Subgradient Method 100%
  • Fixed Point 92%
  • Quasiconvex 86%
  • Fixed point 51%
  • Constrained Optimization 39%
  4 被引用数 (Scopus)

• Hybrid Riemannian conjugate gradient methods with global convergence properties

  Sakai, H. & Iiduka, H., 12月 2020, In: Computational Optimization and Applications. 77, 3, p. 811-830 20 p.

  研究成果: Article › 査読

  • Conjugate gradient method 100%
  • Conjugate Gradient Method 85%
  • Global Convergence 75%
  • Convergence Properties 72%
  • Python 19%
  4 被引用数 (Scopus)

• IEEE CoG 2019

  Yokoyama, D., 2020, In: Computer Software. 37, 1, p. 73-77 5 p.

  研究成果: Article › 査読

• New unified insights on deep learning in radiological and pathological images: Beyond quantitative performances to qualitative interpretation

  Hayashi, Y., 2020, In: Informatics in Medicine Unlocked. 19, 100329.

  研究成果: Article › 査読

  Open Access

  • Deep Learning 100%
  • Artificial Intelligence 24%
  • Pathology 11%
  • Neoplasms 5%
  4 被引用数 (Scopus)

• One-dimensional convolutional neural networks with feature selection for highly concise rule extraction from credit scoring datasets with heterogeneous attributes

  Hayashi, Y. & Takano, N., 8月 2020, In: Electronics (Switzerland). 9, 8, p. 1-15 15 p., 1318.

  研究成果: Article › 査読

  Open Access

  • Convolutional neural networks 100%
  • Convolution 90%
  • Feature extraction 84%
  • Neural networks 55%
  • Finance 21%
  4 被引用数 (Scopus)

• Parallel computing proximal method for nonsmooth convex optimization with fixed point constraints of quasi-nonexpansive mappings

  Shimizu, K., Hishinuma, K. & Iiduka, H., 4月 2020, In: Applied Set-Valued Analysis and Optimization. 2, 1, p. 1-17 17 p.

  研究成果: Article › 査読

  Open Access

  • Computing Methods 100%
  • Hilbert spaces 93%
  • Proximal Methods 93%
  • Parallel Computing 91%
  • Diminishing 88%
  12 被引用数 (Scopus)

• Performance prediction of wireless vital data collection system for exercisers by a network simulator

  Hamagami, T., Hara, S., Yomo, H., Miyamoto, R., Kawamoto, Y., Shimazaki, T. & Okuhata, H., 6月 2020, In: IEICE Transactions on Communications. E103B, 6, p. 653-661 9 p.

  研究成果: Article › 査読

  • Simulators 100%
  • Experiments 48%
  • Sensor nodes 31%

• Rough Support Vector Machine for Classification with Interval and Incomplete Data

  Nowicki, R. K., Grzanek, K. & Hayashi, Y., 1 1月 2020, In: Journal of Artificial Intelligence and Soft Computing Research. 10, 1, p. 47-56 10 p.

  研究成果: Article › 査読

  Open Access

  • Interval Data 100%
  • Support Vector Machine 91%
  • Incomplete Data 85%
  • Rough Set 79%
  • Rough 71%
  10 被引用数 (Scopus)

• Stochastic Fixed Point Optimization Algorithm for Classifier Ensemble

  Iiduka, H., 10月 2020, In: IEEE Transactions on Cybernetics. 50, 10, p. 4370-4380 11 p., 8744480.

  研究成果: Article › 査読

  • Classifiers 100%
  • Machine learning 17%
  • Set theory 15%
  8 被引用数 (Scopus)

• Training deep neural networks using conjugate gradient-like methods

  Iiduka, H. & Kobayashi, Y., 11月 2020, In: Electronics (Switzerland). 9, 11, p. 1-25 25 p., 1809.

  研究成果: Article › 査読

  Open Access

  • Deep neural networks 100%
  • Constrained optimization 13%
  • Image classification 13%
  • Deep learning 11%
  • Neural networks 7%
  2 被引用数 (Scopus)

• Visual navigation based on semantic segmentation using only a monocular camera as an external sensor

  Miyamoto, R., Adachi, M., Ishida, H., Watanabe, T., Matsutani, K., Komatsuzaki, H., Sakata, S., Yokota, R. & Kobayashi, S., 12月 2020, In: Journal of Robotics and Mechatronics. 32, 6, p. 1137-1153 17 p.

  研究成果: Article › 査読

  Open Access

  • Navigation 100%
  • Cameras 92%
  • Semantics 89%
  • Robots 83%
  • Sensors 67%
  7 被引用数 (Scopus)
• 2019

  A rule extraction approach to explore the upper limit of hemoglobin during anemia treatment in patients with predialysis chronic kidney disease

  Hayashi, Y., Nakajima, K. & Nakajima, K., 2019, In: Informatics in Medicine Unlocked. 17, 100262.

  研究成果: Article › 査読

  Open Access

  • Chronic Renal Insufficiency 100%
  • Anemia 91%
  • Hemoglobins 87%
  • Kidney 21%
  • Therapeutics 17%
  3 被引用数 (Scopus)

• Comparison of object detection schemes using datasets of sports scenes

  Miyamoto, R., Nakamura, Y., Ishida, H., Nakamura, T. & Oki, T., 2019, In: Journal of the Institute of Image Electronics Engineers of Japan. 48, 1, p. 144-152 9 p.

  研究成果: Article › 査読

  • Object detection 100%
  • Sports 98%
  • Deep learning 57%
  • Detectors 50%
  • Image recognition 36%
  1 被引用数 (Scopus)

• Convergence analysis of incremental and parallel line search subgradient methods in hilbert space

  Hishinuma, K. & Iiduka, H., 2019, In: Journal of Nonlinear and Convex Analysis. 20, 9, p. 1937-1947 11 p.

  研究成果: Article › 査読

  • Subgradient Method 100%
  • Hilbert spaces 98%
  • Search Methods 89%
  • Line Search 82%
  • Convergence Analysis 67%

• Detection accuracy of soccer players in aerial images captured from several viewpoints

  Oki, T., Miyamoto, R., Yomo, H. & Hara, S., 3月 2019, In: Journal of Functional Morphology and Kinesiology. 4, 1, 9.

  研究成果: Article › 査読

  Open Access

  • Computer Graphics 100%
  • Humulus 91%
  • Geographic Information Systems 88%
  • Soccer 79%
  • Vital Signs 74%
  3 被引用数 (Scopus)

• Detection of lower albuminuria levels and early development of diabetic kidney disease using an artificial intelligence-based rule extraction approach

  Hayashi, Y., 1 12月 2019, In: Diagnostics. 9, 4, 33.

  研究成果: Article › 査読

  Open Access

  • Artificial Intelligence 100%
  • Albuminuria 88%
  • Diabetic Nephropathies 80%
  • Prediabetic State 72%
  • Albumins 48%
  7 被引用数 (Scopus)

• Distributed optimization for network resource allocation with nonsmooth utility functions

  Iiduka, H., 12月 2019, In: IEEE Transactions on Control of Network Systems. 6, 4, p. 1354-1365 12 p., 8584116.

  研究成果: Article › 査読

  • Distributed Optimization 100%
  • Capacity Constraints 93%
  • Resource Allocation 84%
  • Nonsmooth Function 79%
  • Utility Function 76%
  12 被引用数 (Scopus)

• Incremental and Parallel Machine Learning Algorithms With Automated Learning Rate Adjustments

  Hishinuma, K. & Iiduka, H., 27 8月 2019, In: Frontiers in Robotics and AI. 6, 77.

  研究成果: Article › 査読

  Open Access

  • Learning algorithms 100%
  • Machine learning 88%
  • Constrained optimization 39%
  • Convex optimization 38%
  • Parallel algorithms 22%

• Iterative methods for parallel convex optimization with fixed point constraints

  Sakurai, K., Jimba, T. & Iiduka, H., 1 8月 2019, In: Journal of Nonlinear and Variational Analysis. 3, 2, p. 115-126 12 p.

  研究成果: Article › 査読

  Open Access

  • Parallel Optimization 100%
  • Fixed-point Algorithm 85%
  • Iterative methods 63%
  • Convex optimization 63%
  • Convex Optimization 61%
  5 被引用数 (Scopus)

• Positive-instance driven dynamic programming for treewidth

  Tamaki, H., 1 5月 2019, In: Journal of Combinatorial Optimization. 37, 4, p. 1283-1311 29 p.

  研究成果: Article › 査読

  • Treewidth 100%
  • Dynamic Programming 88%
  • Dynamic programming 85%
  • Separator 70%
  • Separators 63%
  21 被引用数 (Scopus)

• Three-dimensional exploration of the origin of threshold voltage fluctuation of silicon-on-insulator triple-gate fin-type field-effect transistors caused by ion implantation to source and drain extensions

  Tsutsumi, T., 2019, In: Japanese Journal of Applied Physics. 58, SD, SDDE06.

  研究成果: Article › 査読

  • Ion implantation 100%
  • fins 88%
  • Threshold voltage 81%
  • Field effect transistors 78%
  • threshold voltage 69%
  3 被引用数 (Scopus)

• Toward the transparency of deep learning in radiological imaging: Beyond quantitative to qualitative artificial intelligence

  Hayashi, Y., 2019, In: Journal of Medical Artificial Intelligence. 2, September, 19.

  研究成果: Article › 査読

  Open Access
  3 被引用数 (Scopus)

• Two stochastic optimization algorithms for convex optimization with fixed point constraints

  Iiduka, H., 4 7月 2019, In: Optimization Methods and Software. 34, 4, p. 731-757 27 p.

  研究成果: Article › 査読

  • Stochastic Algorithms 100%
  • Stochastic Optimization 98%
  • Optimization Algorithm 88%
  • Convex optimization 88%
  • Convex Optimization 86%
  1 被引用数 (Scopus)
• 2018

  A Comparison Study on Rule Extraction from Neural Network Ensembles, Boosted Shallow Trees, and SVMs

  Bologna, G. & Hayashi, Y., 2018, In: Applied Computational Intelligence and Soft Computing. 2018, 4084850.

  研究成果: Article › 査読

  Open Access

  • Neural Network Ensemble 100%
  • Rule Extraction 81%
  • Multilayer neural networks 46%
  • Multilayer Perceptron 33%
  • Neural networks 27%
  18 被引用数 (Scopus)

• A Method to Detect Bit Flips in a Soft-Error Resilient TCAM

  Syafalni, I., Sasao, T. & Wen, X., 6月 2018, In: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 37, 6, p. 1185-1196 12 p.

  研究成果: Article › 査読

  • Associative storage 100%
  • Static random access storage 8%
  3 被引用数 (Scopus)

• An exact optimization method using ZDDs for linear decomposition of symmetric index generation functions

  Nagayama, S., Sasao, T. & Butler, J. T., 12月 2018, In: IfCoLoG Journal of Logics and their Applications. 5, 9, p. 1849-1866 18 p.

  研究成果: Article › 査読

  • Binary Decision Diagram 100%
  • Binary decision diagrams 89%
  • Exact Method 79%
  • Optimization Methods 71%
  • Decomposition 48%
  3 被引用数 (Scopus)

• A rule extraction study from svm on sentiment analysis

  Bologna, G. & Hayashi, Y., 3月 2018, In: Big Data and Cognitive Computing. 2, 1, p. 1-19 19 p., 6.

  研究成果: Article › 査読

  Open Access

  • Support Vector Machine 100%
  • Sentiment Analysis 74%
  • Sentiment analysis 65%
  • Multilayer neural networks 60%
  • Support vector machines 47%
  10 被引用数 (Scopus)

• Distance duality on some classes of boolean functions

  Stnica, P., Sasao, T. & Butler, J. T., 11月 2018, In: Journal of Combinatorial Mathematics and Combinatorial Computing. 107, p. 181-198 18 p.

  研究成果: Article › 査読

  • Boolean Functions 100%
  • Duality 81%
  • Symmetric Functions 48%
  • Class 30%
  • Set Partition 23%
  8 被引用数 (Scopus)

• High Accuracy-priority Rule Extraction for Reconciling Accuracy and Interpretability in Credit Scoring

  Hayashi, Y. & Oishi, T., 1 10月 2018, In: New Generation Computing. 36, 4, p. 393-418 26 p.

  研究成果: Article › 査読

  • Rule Extraction 100%
  • Credit Scoring 88%
  • Priority Rules 88%
  • Interpretability 73%
  • High Accuracy 57%
  10 被引用数 (Scopus)

• Non-invasive prediction of non-alcoholic steatohepatitis in Japanese patients with morbid obesity by artificial intelligence using rule extraction technology

  Uehara, D., Hayashi, Y., Seki, Y., Kakizaki, S., Horiguchi, N., Tojima, H., Yamazaki, Y., Sato, K., Yasuda, K., Yamada, M., Uraoka, T. & Kasama, K., 1 12月 2018, In: World Journal of Hepatology. 10, 12, p. 934-943 10 p.

  研究成果: Article › 査読

  Open Access

  • Artificial Intelligence 100%
  • Morbid Obesity 86%
  • Fatty Liver 80%
  • Technology 49%
  • Proteostasis 12%
  9 被引用数 (Scopus)

• Optimality and convergence for convex ensemble learning with sparsity and diversity based on fixed point optimization

  Hayashi, Y. & Iiduka, H., 17 1月 2018, In: Neurocomputing. 273, p. 367-372 6 p.

  研究成果: Article › 査読

  • Learning systems 100%
  • Learning 72%
  • Classifiers 69%
  • Quadratic programming 43%
  • Machine Learning 37%
  6 被引用数 (Scopus)

• Origin of threshold voltage fluctuation caused by ion implantation to source and drain extensions of silicon-on-insulator triple-gate fin-type field-effect transistors using three-dimensional process and device simulations

  Tsutsumi, T., 6月 2018, In: Japanese Journal of Applied Physics. 57, 6, 06HC06.

  研究成果: Article › 査読

  • Ion implantation 100%
  • fins 88%
  • Threshold voltage 81%
  • Field effect transistors 78%
  • threshold voltage 69%
  4 被引用数 (Scopus)

• 顔イラストからの特徴点抽出と特徴点に基づく 3 次元顔モデル変形

  Miyamoto, R., Aoki, S., Aoki, R., Nonogaki, K. & Ohtagaki, Y., 2018, In: Journal of the Institute of Image Electronics Engineers of Japan. 47, 3, p. 234-243 10 p.

  研究成果: Article › 査読

  • Error analysis 100%
  • Feature extraction 41%
  • Pixels 40%
  • Color 38%
  • Experiments 19%