Search Results 1-20 of 295

  • Explainable machine learning for the analysis of transport phenomena in top-seeded solution growth of SiC single crystal

    TAKEHARA Yuto , SEKIMOTO Atsushi , OKANO Yasunori , UJIHARA Toru , DOST Sadik

    … Our previous studies have shown that the applications of a static magnetic field and seed rotation are effective in controlling the components of this melt flow and the associated control parameters were optimized effectively using the Bayesian optimization. … In addition, the most sensitive region of the melt flow is determined by using an explainable machine learning technique based on a convolutional neural network and the sensitivity map obtained by SmoothGrad. …

    Journal of Thermal Science and Technology 16(1), JTST0009-JTST0009, 2021

    J-STAGE 

  • Integration of Deep Learning with Smart Contract Security Analysis  [in Japanese]

    芦澤 奈実 , 矢内 直人 , クルーズ ジェイソン ポール , 岡村 真吾

    コンピュータセキュリティシンポジウム2020論文集, 494-501, 2020-10-19

    IPSJ 

  • Static Analysis Based Malware Detection Using Ensemble Neural Networks  [in Japanese]

    樋川 卓也

    コンピュータセキュリティシンポジウム2020論文集, 632-636, 2020-10-19

    IPSJ 

  • Omnidirectional motion classification with mono-static radar using micro-Doppler signatures

    Yang Yang , Hou Chunping , Lang Yue , Sakamoto Takuya , He Yuan , Xiang Wei

    … The results demonstrate that the proposed algorithm outperforms both feature-based and existing deep-learning-based counterparts, and resolve the issue of angle sensitivity in micro-Doppler-based classification. …

    IEEE Transactions on Geoscience and Remote Sensing 58(5), 3574-3587, 2020-05

    IR 

  • Revolutionising Poster Presentations through Digital Technology

    Selwood Jaime

    … Poster presentations are often relegated to a second-class status both as a presentation tool at academic conferences and as a learning device within a classroom. … As the 21st Century enters its third decade and digital technological advances continue to enhance how the world interacts, it seems outdated that poster presentations are still largely confined to a static method of delivery, such as through a paper or cloth medium. …

    Hiroshima Studies in Language and Language Education (23), 217-228, 2020-03-01

    IR  DOI 

  • Static Output Feedback Stabilization of LTI Systems via Neural Ordinary Differential Equations  [in Japanese]

    小林 恒輝 , 小蔵 正輝 , 岸田 昌子 , 和田山 正 , 杉本 謙二

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 119(395), 19-22, 2020-01-27

  • Speech Emotion Recognition Using 3D Convolutions and Attention-Based Sliding Recurrent Networks With Auditory Front-Ends

    Peng Zhichao , Li Xingfeng , Zhu Zhi , Unoki Masashi , Dang Jianwu , Akagi Masato

    … Some previous studies used auditory-based static features to identify emotion while ignoring the emotion dynamics. … To fully utilize the auditory and attention mechanism, we first investigate temporal modulation cues from auditory front-ends and then propose a joint deep learning model that combines 3D convolutions and attention-based sliding recurrent neural networks (ASRNNs) for emotion recognition. …

    IEEE Access (8), 16560-16572, 2020-01-20

    IR 

  • Comparison of the long-term forecasting method of RSSI by machine learning

    Nagao Tatsuya , Hayashi Takahiro , Amano Yoshiaki

    … In the millimeter-wave band, which is expected to be utilized in the future, the received power fluctuates due to quasi-static obstructions such as people and vehicles, but such temporal variations have not been taken into account in conventional methods. … In this paper, we use a variety of machine learning algorithms for comparative evaluation to forecast the temporal fluctuations of radio propagation due to changes in the number of people and vehicles in order to achieve more dynamic spectrum access.</p> …

    IEICE Communications Express 9(11), 553-558, 2020

    J-STAGE 

  • A novel hybrid network model based on attentional multi-feature fusion for deception detection

    FANG Yuanbo , FU Hongliang , TAO Huawei , LIANG Ruiyu , ZHAO Li

    … <p>Speech based deception detection using deep learning is one of the technologies to realize a deception detection system with high recognition rate in the future. … Firstly, the static features of large amounts of unlabeled speech data are input into DAE for unsupervised training. … Secondly, the frame-level features and static features of a small amount of labeled speech data are simultaneously input into the LSTM network and the encoded output part of DAE for joint supervised training. …

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2020

    J-STAGE 

  • The effect of motion-induced subliminal information in insight problem solving  [in Japanese]

    Otagiri Hitoshi , Suzuki Hiroaki

    … The results might suggest that subliminally presented information was stored in a rather static way, and could not be integrated with succeeding subliminal information. …

    Cognitive Studies: Bulletin of the Japanese Cognitive Science Society 27(3), 321-333, 2020

    J-STAGE 

  • Logging Inter-Thread Data Dependencies in Linux Kernel

    KUBOTA Takafumi , AOTA Naohiro , KONO Kenji

    … The logged events are crucially important to learning what happened during a failure. … ditches rigorous static analysis of pointers to detect code locations where inter-thread data dependency can occur. …

    IEICE Transactions on Information and Systems E103.D(7), 1633-1646, 2020

    J-STAGE 

  • ROPminer: Learning-Based Static Detection of ROP Chain Considering Linkability of ROP Gadgets

    USUI Toshinori , IKUSE Tomonori , OTSUKI Yuto , KAWAKOYA Yuhei , IWAMURA Makoto , MIYOSHI Jun , MATSUURA Kanta

    … (2) Static approaches generate false positives because they use heuristic patterns. … In this paper, we propose a method for statically detecting ROP chains in malicious data by learning the target libraries (i.e., the libraries that are used for ROP gadgets). … Our method accelerates its inspection by exhaustively collecting feasible ROP gadgets in the target libraries and learning them separated from the inspection step. …

    IEICE Transactions on Information and Systems E103.D(7), 1476-1492, 2020

    J-STAGE 

  • Present and future perspectives of artificial intelligence: examples of mathematical approaches for analysis of disease dynamics  [in Japanese]

    AIHARA Kazuyuki

    … For example, deep neural network-based deep learning is particularly effective for pattern recognition in static medical images. … Nonlinear data analyses, rather than conventional deep learning, can be more powerful for this type of dynamic disease information. …

    Rinsho Ketsueki 61(5), 549-553, 2020

    J-STAGE  Ichushi Web 

  • Visual Abilities of University Students with Motor Skill Underachievement  [in Japanese]

    古田 久

    … Visual abilities were focused because visual processing plays a critical role in motor control and learning, and differences in visual abilities of students with and without motor skill underachievement were investigated. … Eight kinds of visual abilities were measured, including static visual acuity, kinetic visual acuity, contrast sensitivity, eye movements, depth perception, instantaneous visual perception, the width of the visual field, and eye/hand coordination. …

    埼玉大学紀要. 教育学部 = Journal of Saitama University. Faculty of Education 69(1), 151-165, 2020

    IR  DOI 

  • Rethinking Shulman's Theory of Teacher Knowledge : Process of Theory Development  [in Japanese]

    若松 大輔

    … Most earlier studies described this his theory of teacher knowledge as meaning the "domain of knowledge" (e.g. PCK), which seems static. … These two types of dynamic structure of teacher knowledge require learning by both of "case method" and "practice and reflection". …

    京都大学大学院教育学研究科紀要 (66), 43-56, 2020

    IR 

  • Deep Learning-Based Output Feedback Stabilization  [in Japanese]

    小林 恒輝 , 小蔵 正輝 , 岸田 昌子 , 和田山 正 , 杉本 謙二

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 119(268), 59-62, 2019-11-06

  • Deep Learning-Based Output Feedback Stabilization (ITS)  [in Japanese]

    小林 恒輝 , 小蔵 正輝 , 岸田 昌子 , 和田山 正 , 杉本 謙二

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 119(269), 59-62, 2019-11-06

  • Deep Learning-Based Output Feedback Stabilization  [in Japanese]

    小林 恒輝 , 小蔵 正輝 , 岸田 昌子 , 和田山 正 , 杉本 謙二

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 119(270), 59-62, 2019-11-06

  • A Study on Trend of Packer Used by Malware  [in Japanese]

    岩田 吉弘 , 大坪 雄平 , 萬谷 暢崇

    コンピュータセキュリティシンポジウム2019論文集 (2019), 934-939, 2019-10-14

    IPSJ 

  • Detection of Malicious PowerShell Using a Word Level Language Model  [in Japanese]

    田尻 裕貴 , 三村 守

    コンピュータセキュリティシンポジウム2019論文集 (2019), 170-177, 2019-10-14

    IPSJ 

Page Top