Search Results 1-20 of 3110

  • PythonでらくらくDeep Learning : Pythonの深層学習ライブラリを使う  [in Japanese]

    平田 隆幸

    Deep learning is one of the key concepts of neural networks in machine learning. Powerful libraries of Python are available for deep learning programming. In the field of pattern recognition, Python i …

    福井大学学術研究院工学系部門研究報告 = Memoir of Faculty of Engineering, University of Fukui (69), 1-9, 2021-03-26

    IR 

  • Research and Development to Lead Business and Society  [in Japanese]

    常樂 諭 , 糟谷 勇児 , 西田 貴紀

    Journal of the Japanese Society for Artificial Intelligence 36(2), 140-146, 2021-03-01

    J-STAGE  JSAI 

  • [COMMENT] The California Internet Consumer Protection and Net Neutrality Act of 2018 (1)  [in Japanese]

    松宮 広和 , MATSUMIYA Hirokazu

    … This Order abolished virtually all the protections for "network neutrality" introduced by the FCC's Open Internet Order of 2015. … In fact, as expressed in the letter to the ranking members of Congress from Internet pioneers and other leaders on December 11, 2017, the abolishment of these rules will bring an imminent threat to the Internet by killing the "virtuous cycle" that drives innovation and investment on the Internet--both at the edges of the network, as well as in the network itself. …

    群馬大学社会情報学部研究論集 (28), 153-173, 2021-03-01

    IR 

  • [COMMENT] The California Internet Consumer Protection and Net Neutrality Act of 2018 (2)  [in Japanese]

    松宮 広和 , MATSUMIYA Hirokazu

    … This Order abolished virtually all the protections for "network neutrality" introduced by the FCC's Open Internet Order of 2015. … In fact, as expressed in the letter to the ranking members of Congress from Internet pioneers and other leaders on December 11, 2017, the abolishment of these rules will bring an imminent threat to the Internet by killing the "virtuous cycle" that drives innovation and investment on the Internet--both at the edges of the network, as well as in the network itself. …

    群馬大学社会情報学部研究論集 (28), 175-187, 2021-03-01

    IR 

  • Autonomous Driving Technology of Crawler Carriers by using AI for Unmanned Construction  [in Japanese]

    飛鳥馬 翼 , 北原 成郎 , 畑本 浩伸

    自動車技術 = Journal of Society of Automotive Engineers of Japan 75(3), 52-58, 2021-03

  • Large Zeeman Splitting in Out-of-Plane Magnetic Field in a Double-Layer Quantum Point Contact

    Terasawa Daiju , Norimoto Shota , Arakawa Tomonori , Ferrier Meydi , Fukuda Akira , Kobayashi Kensuke , Hirayama Yoshiro

    Journal of the Physical Society of Japan 90(2), 024709-1-6, 2021-02

    DOI 

  • Neural Computing on Wireless Networks  [in Japanese]

    WAKAMIYA Naoki

    <p>無線ネットワークの発展と人工知能技術の向上を背景としたIoTシステムの普及がめざましい.高密度かつ大量に配置されたIoTデバイスからなる無線ネットワークを単なる情報収集手段としてではなくあらたな計算資源として活用し情報処理を行うことでIoTシステムの高度化,高機能化や低遅延化,低消費電力化が期待できる.本稿ではニューラルネットワークを組み込むことでニューラルコンピューティングによ …

    IEICE ESS Fundamentals Review 14(4), 308-317, 2021

    J-STAGE 

  • Network model of predictive coding based on reservoir computing for multi-modal processing of visual and auditory signals

    Yonemura Yoshihiro , Katori Yuichi

    … <p>We propose a hierarchical network model based on predictive coding and reservoir computing as a model of multi-modal sensory integration in the brain. … The network is composed of visual, auditory, and integration areas. … Our approach presents a novel dynamical mechanism of the multi-modal information processing in the brain and the fundamental technology for a brain like an artificial intelligence system.</p> …

    Nonlinear Theory and Its Applications, IEICE 12(2), 143-156, 2021

    J-STAGE 

  • Classification of Intraoral X-ray Images Using Artificial Intelligence  [in Japanese]

    Kitano Tomoya , Mori Mizuho , Nishiyama Wataru , Kohinata Kiyomi , Iida Yukihiro , Fujita Hiroshi , Katsumata Akitoshi

    … Intraoral X-ray images were classified based on the ten anatomical regions using deep-learning artificial intelligence. … The LeNet-type deep learning function of the Neural Network Console (Sony Network Communications, Inc.) was employed. … The Structure Search function was used to optimize the structure of the convolutional neural network. …

    Shika Hoshasen 60(2), 53-57, 2021

    J-STAGE 

  • Developing a Novel Recurrent Neural Network Architecture with Fewer Parameters and Good Learning Performance

    YAMADA Kazunori D , LIN Fangzhou , NAKAMURA Tsukasa

    … <p>Recurrent neural networks (RNNs) are among the most promising of the many artificial intelligence techniques now under development, showing great potential for memory, interaction, and linguistic understanding. …

    Interdisciplinary Information Sciences 27(1), 25-40, 2021

    J-STAGE 

  • Development of animal behavior evaluation methods by image analysis  [in Japanese]

    Murata Takahisa , Kobayashi Koji

    … We have been developing the methods to assess mouse behaviors under non-invasive and unrestrained condition, using image analysis, and artificial intelligence. … We next aimed to establish a novel method to detect scratching using deep neural network. … A convolutional recurrent neural network (CRNN) was constructed and trained using labelled images, and then its performance was evaluated. …

    Proceedings for Annual Meeting of The Japanese Pharmacological Society 94(0), 2-S24-3, 2021

    J-STAGE 

  • Self-Organized Subpopulation Based on Multiple Features in Genetic Programming on GPU

    Ono Keiko , Hanada Yoshiko

    … To reconstruct subpopulations, we introduce a novel weighted network based on each normalized feature and utilize network clustering techniques. … Although we can regard similarity as a correlation network between solutions, the use of multiple features incurs high computational costs, however, calculating the similarity is very suitable for parallelization on GPUs. …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 25(2), 177-186, 2021

    J-STAGE 

  • Reconstruction Method for Missing Measurement Data Based on Wasserstein Generative Adversarial Network

    Zhang Changfan , Chen Hongrun , He Jing , Yang Haonan

    … <p>Focusing on the issue of missing measurement data caused by complex and changeable working conditions during the operation of high-speed trains, in this paper, a framework for the reconstruction of missing measurement data based on a generative adversarial network is proposed. …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 25(2), 195-203, 2021

    J-STAGE 

  • Fast and Accurate Driver Action Recognition with Multi-Task Learning of Driver Pose and Action  [in Japanese]

    Nishiyuki Kenta , Hyuga Tadashi , Tasaki Hiroshi , Kinoshita Koichi , Hasegawa Yuki , Yamashita Takayoshi , Fujiyoshi Hironobu

    … We train our network model with multi-task learning includes localizing and detecting each body part of the driver, classifying state of each body part, and recognizing driver action at once. …

    Transactions of the Japanese Society for Artificial Intelligence 36(2), A-K93_1-10, 2021

    J-STAGE 

  • A system for designing removable partial dentures using artificial intelligence. Part 1. Classification of partially edentulous arches using a convolutional neural network

    Takahashi Toshihito , Nozaki Kazunori , Gonda Tomoya , Ikebe Kazunori

    … The purpose of this study was to develop a method for classifying dental arches using a convolutional neural network (CNN) as the first step in a system for designing removable partial dentures.<br><i>Methods:</i> …

    Journal of Prosthodontic Research 65(1), 115-118, 2021

    J-STAGE 

  • Introducing Swish and Parallelized Blind Removal Improves the Performance of a Convolutional Neural Network in Denoising MR Images

    Sugai Taro , Takano Kohei , Ouchi Shohei , Ito Satoshi

    … <p>Purpose: To improve the performance of a denoising convolutional neural network (DnCNN) and to make it applicable to images with inhomogeneous noise, a refinement involving an activation function (AF) and an application of the refined method for inhomogeneous-noise images was examined in combination with parallelized image denoising.</p><p>Methods: Improvements in the DnCNN were performed by three approaches. … One is refinement of the AF of each neural network that constructs the DnCNN. …

    Magnetic Resonance in Medical Sciences, 2021

    J-STAGE 

  • Functionally Enhancement of IPNP(Image Processing Network Programming) for Modifying Appearance Inspection Program  [in Japanese]

    SAKAI Shun , OSADA Hajime , SUZUKI Kohei , AOKI Kimiya

    … Therefore, we had proposed a method for automatic programming of inspection image processing system called "Image Processing Network Programming (IPNP)". …

    Journal of the Japan Society for Precision Engineering 87(2), 206-212, 2021

    J-STAGE 

  • RAMST-CNN: A Residual and Multiscale Spatio-Temporal Convolution Neural Network for Personal Identification with EEG

    ZHU Yuxuan , PENG Yong , SONG Yang , OZAWA Kenji , KONG Wanzeng

    … <p>In this study we propose a method to perform personal identification (PI) based on Electroencephalogram (EEG) signals, where the used network is named residual and multiscale spatio-temporal convolution neural network (RAMST-CNN). … The results show that the proposed method has a higher recognition accuracy even though the network it is based on is lightweight.</p> …

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E104.A(2), 563-571, 2021

    J-STAGE 

  • An Improved Fully Convolutional Network Based on Post-Processing with Global Variance Equalization and Noise-Aware Training for Speech Enhancement

    Li Wenlong , Hirota Kaoru , Dai Yaping , Jia Zhiyang

    … <p>An improved fully convolutional network based on post-processing with global variance (GV) equalization and noise-aware training (PN-FCN) for speech enhancement model is proposed. … Finally, the proposed framework adopts FCN, and the number of parameters is one-seventh of deep neural network (DNN). …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 25(1), 130-137, 2021

    J-STAGE 

  • Variable Expanding Structure for Data Center Interconnection Networks

    Zhang Jianfei , Jiang Yuchen , Liu Yan

    … To guarantee that a data center can provide excellent properties of expanding and routing, the interconnection network of a data center should be designed elaborately. … Herein, we propose a novel structure for the interconnection network of data centers that can be expanded with a variable coefficient, also known as a variable expanding structure (VES). …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 25(1), 13-22, 2021

    J-STAGE 

Page Top