Search Results 1-20 of 477

  • Institutional Design and Conjunctural Causations : Causal Conditions for Adoption of a Dispute Settlement Mechanism in International Institutions

    Fujita Taisuke

    … Under what conditions, then, do international institutions adopt this institutional design? … Although previous studies on this research question have analyzed the effects of several conditions/ variables and commonly employed regression analysis methods, they have reached different conclusions. … The lack of consensus could be caused by their implicit assumption (accompanying their choice of method) that conditions have effects that are independent from each other. …

    経営と経済 99(1-4), 135-160, 2020-02

    IR 

  • Factor Analysis of Nitrogen Oxides Emissions in Coal Fired Power Plant with LiNGAM  [in Japanese]

    SAITO Tatsuki , FUJIWARA Koichi

    <p>石炭は他の化石燃焼に比べ埋蔵量が多く,長期的安定供給が可能であり,日本の電力の約1/4は石炭火力発電によって供給されている.しかし、石炭は産地により性状が異なること,燃料に含まれる窒素分が他の化石燃料に比べ多く,燃焼の際に生じるNOxの発生量が多いなどの問題がある.そのため,NOx排出量は石炭火力発電の操業にあたり,緻密な制御が求められる.NOxの発生量は理論上石炭性状から傾向が …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4M3GS1303-4M3GS1303, 2020

    J-STAGE 

  • Does increasing an athletes' strength improve sports performance? A critical review with suggestions to help answer this, and other, causal questions in sport science

    Steele James , Fisher James , Crawford Derek

    … One area of interest is the role that muscular strength, and thus approaches to improve this (i.e. resistance training), has upon sports performance. … <i><b>Design & … <i><b>Results</b></i>: Muscular strength typically differentiates elite and non-elite athletes, and is correlated with proxy measures of sports performance. …

    Journal of Trainology 9(1), 20, 2020

    J-STAGE 

  • Weight compression MAC accelerator for effective inference of deep learning

    Maki Asuka , Miyashita Daisuke , Sasaki Shinichi , Nakata Kengo , Tachibana Fumihiko , Suzuki Tomoya , Deguchi Jun , Fujimoto Ryuichi

    … <p>Many studies of deep neural networks have reported inference accelerators for improved energy efficiency. … We propose methods for further improving energy efficiency while maintaining recognition accuracy, which were developed by the co-design of a filter-by-filter quantization scheme with variable bit precision and a hardware architecture that fully supports it. …

    IEICE Transactions on Electronics, 2020

    J-STAGE 

  • DATA DRIVEN DYNAMIC RELIABILITY ANALYSIS BASED ON SPATIOTEMPORAL FEATURE EXTRACTION WITH MODE DECOMPOSITION: APPLICATION FOR EFFECTIVE STRESS DYNAMIC ANALYSIS  [in Japanese]

    OTAKE Yu , SHIGENO Kyohei , WATANABE Shinya , HIGO Yosuke , MURAMATSU Shogo

    <p> 著者らは,偶発荷重時における土構造物のロバスト性やレジリエンス性を評価し,意思決定に導くための枠組みづくりを進めている.その一環として,本論文では,計算コストが大きい高度な数値解析の代替モデルの構築方法とそれを用いた信頼性解析法を提案している.ここでは,数値解析結果(応答値)時系列のモード分解により時空間の特徴を縮約することで,土構造物の時空間の特徴を有した代替モデルを提案して …

    Journal of Japan Society of Civil Engineers, Ser. C (Geosphere Engineering) 76(2), 142-157, 2020

    J-STAGE 

  • Data analysis of farmer-centric on-farm experimentation using Bayesian inference  [in Japanese]

    Tanaka Takashi S. T.

    Abstracts of Meeting of the CSSJ 249(0), 78-78, 2020

    J-STAGE 

  • Development of an application, <i>Bombyx mori</i> tool for ortholog picking (BmTOP)

    Ohno Mizuki , Kawamoto Munetaka , Sahara Ken

    … orthologs from assembled RNA sequencing (RNA-seq) data in species of interest. … tool for ortholog picking) is composed of 6 steps, 1) tblastx analysis using <i>B. … gene models 2017, 2) alignment of the first hit and assignment of the <i>B. …

    Journal of Insect Biotechnology and Sericology 89(1), 1_001-1_007, 2020

    J-STAGE 

  • Bayesian Inference for Path Following Control of Port-Hamiltonian Systems with Training Trajectory Data

    OKURA Yuki , FUJIMOTO Kenji , MARUTA Ichiro , SAITO Akio , IKEDA Hidetoshi

    … <p>This paper describes a procedure to design a path following controller of port-Hamiltonian systems based on a training trajectory dataset. … The trajectories are generated by human operations, and the training data consist of several trajectories with variations. … Then we design a deterministic controller for path following control from the model. …

    SICE Journal of Control, Measurement, and System Integration 13(2), 40-46, 2020

    J-STAGE 

  • Bayesian Inverse Reinforcement Learning for Demonstrations of an Expert in Multiple Dynamics:Toward Estimation of Transferable Reward  [in Japanese]

    Nakata Yusuke , Arai Sachiyo

    … <p>Though a reinforcement learning framework has numerous achievements, it requires a careful shaping of a reward function that represents the objective of a task. … There is a class of task in which an expert could demonstrate the optimal way of doing, but it is difficult to design a proper reward function. …

    Transactions of the Japanese Society for Artificial Intelligence 35(1), G-J73_1-10, 2020

    J-STAGE 

  • On-Device Deep Learning Inference for Efficient Activity Data Collection

    Mairittha Nattaya , Mairittha Tittaya , Inoue Sozo

    … Labeling activity data is a central part of the design and evaluation of human activity recognition systems. … The performance of the systems greatly depends on the quantity and "quality" of annotations; …

    Sensors 19(15), 3434-1-3434-20, 2019-08-05

    IR 

  • Molecular Design in Chemical Industry  [in Japanese]

    磯村 哲 , 山下 博史

    人工知能 : 人工知能学会誌 : journal of the Japanese Society for Artificial Intelligence 34(3), 358-363, 2019-05

  • A construction of the fourth order rotatable designs invariant under the hyperoctahedral group

    Yamamoto Hirotaka , Hirao Masatake , Sawa Masanori

    Journal of Statistical Planning and Inference (200), 63-73, 2019-05

    IR 

  • Multi-objective optimization of pipe-routing to suppress the piping vibration due to the turbulent flow  [in Japanese]

    FUJISHIMA Shuhei , UEMICHI Akane , YAMASAKI Yudai , KANEKO Shigehiko , TAKAHASHI Shiro

    … <p>At the design stage of pipe-routing in a plant, it is necessary to arrange pipes as short as possible avoiding the obstacles and suppress the turbulent flow-induced vibration within the limit of regulation. … In this study, three objective functions were formulated and applied to the genetic algorithm (GA) to obtain the optimal layout of a single pipe without branches. …

    The Proceedings of Mechanical Engineering Congress, Japan 2019(0), J09105P, 2019

    J-STAGE 

  • Design Evaluation of Learning Type Fuzzy Inference Using Trapezoidal Membership Function  [in Japanese]

    IRIE Honoka , HAYASHI Isao

    <p>三角形メンバシップ関数の一般形である台形型メンバシップ関数を採用したファジィ推論(台形型ファジィ推論)の汎用精度は高い.また,ファジィ推論を用いた学習型ファジィクラスタリングは,学習によりクラス識別領域を調整できるので,データ投入ごとに認識精度を高めることができる.学習では,前件部のメンバシップ関数と後件部のシングルトン実数値を調整する.しかし,ファジィ推論を実際の問題に適用する …

    Journal of Japan Society for Fuzzy Theory and Intelligent Informatics 31(6), 908-917, 2019

    J-STAGE 

  • An efficient ReRAM-based inference accelerator for convolutional neural networks via activation reuse

    Chen Yan , Zhang Jing , Xu Yuebing , Zhang Yingjie , Zhang Renyuan , Nakashima Yasuhiko

    … <p>In this paper, a novel resistive random access memory (ReRAM) based accelerator is proposed for convolution neural network (CNN) inference accelerations. … We then develop a ReRAM-based CNN accelerator that can well suit the dataflow to reduce the cost of ReRAM access. … Evaluation results show that the proposed design achieves 1.8× energy saving and 2.8× bandwidth saving compared with a state-of-the-art PipeLayer accelerator.</p> …

    IEICE Electronics Express 16(18), 20190396-20190396, 2019

    J-STAGE 

  • Neuromorphic Computing Systems: From CMOS To Emerging Nonvolatile Memory

    Yang Chaofei , Qiao Ximing , Chen Yiran

    … <p>The end of Moore's Law and von Neumann bottleneck motivate researchers to seek alternative architectures that can fulfill the increasing demand for computation resources which cannot be easily achieved by traditional computing paradigm. … As one important practice, neuromorphic computing systems (NCS) are proposed to mimic biological behaviors of neurons and synapses, and accelerate computation of neural networks. …

    IPSJ Transactions on System LSI Design Methodology 12(0), 53-64, 2019

    J-STAGE 

  • A Sustainable Training Method of Metacognitive Skills in Daily Lab Activities Using Gaze-aware Reflective Meeting Reports

    Ogino Ryo , Hayashi Yuki , Seta Kazuhisa

    … In general, teaching metacognitive skills is difficult because of the implicit nature of thinking. … To promote learners' metacognitive activities, we researched and confirmed that, when critically reading a learner's paper, the learner's and expert's eye-movement information contributed to enhancing the learner's metacognitive inference activities (MIA) and metacognitive knowledge. …

    The Journal of Information and Systems in Education 18(1), 16-26, 2019

    J-STAGE 

  • Aerodynamic performance prediction using artificial intelligence for automotive 2D design proposal  [in Japanese]

    Hattori Yuki , Azuma Daisuke , Matsumoto Megumi , Okutsu Yasuhiko , Hamamoto Naoki

    <p>自動車の外観設計はデザイン性と空力性能を両立させることが重要である.しかしデザイン案から空力性能を調査するには多大な時間とコストを要する.<br/>そこでデザインスケッチおよびCFDによる圧力分布画像からCD値を推定する人工知能システムを開発した.<br/>本システムは,畳み込みニューラルネットワークによる特徴量抽出器,および分類器で構成されている.< …

    PROCEEDINGS OF THE ANNUAL CONFERENCE OF JSSD 66(0), 330, 2019

    J-STAGE 

  • A Fuzzy Inference-Based Spiking Neural Network for Behavior Estimation in Elderly Health Care System

    Shao Shuai , Kubota Naoyuki

    … We chose to use environmental sensors to estimate the behavior of older adults. … We found that traditional methods have difficulty solving the problem of excessive indoor environmental differences in different households. … By modifying the sensitivity of input using a fuzzy inference system, we can solve the problem without additional training. …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 23(3), 528-535, 2019

    J-STAGE 

  • Crystalizing Effect of Simulated Annealing on Boltzmann Machine

    Shibata Hiroki , Ishikawa Hiroshi , Takama Yasufumi

    … <p>This paper proposes a method to estimate the posterior distribution of a Boltzmann machine. … Due to high feature extraction ability, a Boltzmann machine is often used for both of supervised and unsupervised learning. … It is expected to be suitable for multimodal data because of its bi-directional connection property. …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 23(3), 474-484, 2019

    J-STAGE 

Page Top