Search Results 1-20 of 214

  • Case Studies of Learning Analytics in University Education  [in Japanese]

    島田 敬士

    … New pradigms are expected for improving education and learning based on data-driven approaches. … Educational big data is collected via learning support systems. … Various information processing technologies are applied to analyze the teaching and learning logs, and effective feedbacks are given to teachers and students. … This paper introduces advanced case studies of learning analytics in university education. …

    情報処理学会論文誌教育とコンピュータ(TCE) 6(2), 16-24, 2020-06-15

    IPSJ 

  • FORECASTING CYBER THREATS THROUGH THE TEXT MINING ANALYSIS OF POLITICAL NEWS AND SECURITY LOGS

    CHOI HEEYOUNG , KANG JUYOUNG , PARK SANGUN

    ICIC express letters. Part B, Applications : an international journal of research and surveys 11(6), 577-586, 2020-06

  • High Speed Error Log Control Method in In-memory Cluster Computing Platform

    Ryuichi Saito , Shinichiro Haruyama

    … In this research, we propose a method that notifies administrators with only information needed to understand the situation in a short period by eliminating duplications of numerous application error logs for that period and clustering messages using an unsupervised learning k-means method with an in-memory cluster computing framework "Apache Spark." By implementing this method, we can demonstrate that it is possible to eliminate duplications of error messages by 93% on an average compared with conventional methods. …

    情報処理学会論文誌データベース(TOD) 13(2), 2020-04-16

    IPSJ 

  • <Research Paper>Blending Listening and Autonomous Learning: Digital Study-Portfolios (in E3 Classes)

    LEES David , LeBLANC Catherine

    … This research investigates the students' and instructors' perspectives on the use of digital study-portfolios (also known as e-learning logs) in E3 Seminar Participation and Academic Discussion classes. …

    京都大学国際高等教育院紀要 = Kiyô : The Institute for Liberal Arts and Sciences Bulletin, Kyoto University (3), 1-22, 2020-03

    IR  DOI 

  • Learning from the Future : Multimodal Communication and Video Self Modelling in the Presentation Classroom

    Herke Michael

    … Student viewing logs collected at the end of the treatment indicate that participants recognize the value of multimodal communication, experience VSM as an effective learning mechanism and find their improved presentation skills useful across the curriculum. …

    摂大人文科学 = The Setsudai review of humanities and social sciences (27), 75-92, 2020-01

    IR 

  • Observations on Learning Through Kindergarten Teaching Practice : Focus on Notes From On-the-job Training logs  [in Japanese]

    原田 博子

    筑紫女学園大学研究紀要 = Journal of Chikushi Jogakuen University (15), 171-180, 2020

  • Distance Learning for Nurses: Using Learning Analytics to Build a Learning Support Program

    Saeki Yagi Machiko , Murakami Reiko , Tsuzuku Shigeki , Suzuki Mitsue , Nakano Hiroshi , Suzuki Katsuaki

    … <p>In the past decade, Japan's nurses have benefitted from an increase in distance learning opportunities. … However, there is little information on course completion and successful learning outcomes, making it difficult to implement appropriate measures that support distance learning, such as orientation courses and mentoring from faculties. …

    The Journal of Information and Systems in Education 19(1), 1-8, 2020

    J-STAGE 

  • Detecting and Understanding Online Advertising Fraud in the Wild

    KANEI Fumihiro , CHIBA Daiki , HATO Kunio , YOSHIOKA Katsunari , MATSUMOTO Tsutomu , AKIYAMA Mitsuaki

    … These features are used to construct a machine-learning model for detecting fraudulent ad requests. … We evaluated our proposed method by using ad-request logs observed within an actual ad network. …

    IEICE Transactions on Information and Systems E103.D(7), 1512-1523, 2020

    J-STAGE 

  • An Analysis of National Exam Candidates' Learning Using Digital Textbooks Logs.  [in Japanese]

    TANAKA Masaaki , KANDA Azusa

    <p>2019年4月より学校教科書法が改正され、2020年の4月から小学校でデジタル教科書の利用が始まった。筆者が所属する学園の看護師養成課程では、それよりも5年早い2015年からデジタル教科書の利用を始めた。ただ、全ての教科書ではなく、50冊中39冊がデジタル教科書、11冊が従来の紙の教科書から始められた。さらに、2016年からはデジタル教材も追加された。これらのサービスは電子書籍配 …

    Preprints of the Information Professional Symposium 2020(0), 71-76, 2020

    J-STAGE 

  • The Integrated Development Environment for Incorporating a Model of Deep Learning into Robots.:The Proposal of a Framework to Exchange Data  [in Japanese]

    KODAMA Ryuichiro , HIROSE Tsuyoshi , NAGASE Masayuki , KAWAGUCHI Shinobu , SUGA Yuki , OGATA Tetsuya

    … In this paper, we introduce the IDE, and suggest the system to exchange logs and data for learning in the IDE.</p> …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 2D5OS18b02-2D5OS18b02, 2020

    J-STAGE 

  • A Miscellaneous Joint-Learning Model for Audience Segmentation in Online Advertising  [in Japanese]

    CHEN Weichang , YOSHIHARA Thomas , KUROYANAGI Shigeru , ZHUANG Yan

    … <p>Audience segmentation in online advertising is most often generated from browsing information found on server logs and identifiers like cookies. … Traditional classification models further have deficits in learning heterogeneous features such as browsing history together with text. …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 1K5ES203-1K5ES203, 2020

    J-STAGE 

  • Improving product search by multi-task learning using access log  [in Japanese]

    SHIMIZU Hitoshi , IWATA Tomoharu

    … We propose a method to improve product search using access logs. … Using features obtained from products and queries and access logs as learning data, a neural network is trained to display frequently accessed products at high rank. … There are multiple types of access logs, such as not only conversions, but also carts and clicks. … We experimentally confirmed that training data other than the target type can improve learning to rank.</p> …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 1E4GS904-1E4GS904, 2020

    J-STAGE 

  • High Speed Error Log Control Method in In-memory Cluster Computing Platform

    Saito Ryuichi , Haruyama Shinichiro

    … In this research, we propose a method that notifies administrators with only information needed to understand the situation in a short period by eliminating duplications of numerous application error logs for that period and clustering messages using an unsupervised learning k-means method with an in-memory cluster computing framework "Apache Spark." By implementing this method, we can demonstrate that it is possible to eliminate duplications of error messages by 93% on an average compared with conventional methods. …

    Journal of Information Processing 28(0), 310-319, 2020

    J-STAGE 

  • IoT Malware Analysis and New Pattern Discovery Through Sequence Analysis Using Meta-Feature Information

    WU Chun-Jung , HUANG Shin-Ying , YOSHIOKA Katsunari , MATSUMOTO Tsutomu

    … To address this problem, we sought to develop an alternative means of investigation by using the telnet logs of IoT honeypots and analyzing malware without executing it. … We employ both unsupervised or supervised learning algorithms and text-mining algorithms for handling unstructured data. …

    IEICE Transactions on Communications E103.B(1), 32-42, 2020

    IR  J-STAGE 

  • A Report on Facilitating Online English Vocabulary Learning with a Quiz  [in Japanese]

    高橋 有加

    … One way to facilitate vocabulary learning outside of class is online vocabulary learning courses. … This paper reports an attempt to facilitate online vocabulary learning with vocabulary quizzes in class, mainly focusing on the results of questionnaires about the online vocabulary material presented and the vocabulary quiz used.The participants were 93 first-year students enrolled in compulsory English reading classes at Hiroshima University. …

    広島外国語教育研究 = Hiroshima studies in language and language education (23), 31-44, 2020

    IR  DOI 

  • An Attempt to Read Network Traffic with Doc2vec

    Mamoru Mimura

    … To address this problem, neural networks can be applied to perform feature learning. … Doc2vec is one of these models that learn fixed-length feature representation from variable-length documents and has been applied to proxy logs. … To address this problem, neural networks can be applied to perform feature learning. … Doc2vec is one of these models that learn fixed-length feature representation from variable-length documents and has been applied to proxy logs. …

    情報処理学会論文誌 60(11), 2019-11-15

    IPSJ 

  • pAUC Maximization Method for Malware Detection  [in Japanese]

    西山 泰史 , 熊谷 充敏 , 藤野 昭典 , 神谷 和憲

    コンピュータセキュリティシンポジウム2019論文集 (2019), 503-510, 2019-10-14

    IPSJ 

  • Anomaly Detection for Alert Logs with Word Embeddings  [in Japanese]

    江田 智尊 , 及川 孝徳 , 古川 和快 , 村上 雅彦

    コンピュータセキュリティシンポジウム2019論文集 (2019), 443-450, 2019-10-14

    IPSJ 

  • Using Seq2Seq Model to Detect Infection Focusing on Behavioral Features of Processes

    Shun Tobiyama , Yukiko Yamaguchi , Hirokazu Hasegawa , Hajime Shimada , Mitsuaki Akiyama , Takeshi Yagi

    … By applying Seq2Seq models stepwise, our proposal can compress behavioral logs and extract abstracted behavioral features. … We present an experimental evaluation using logs when actual malware is executed. …

    情報処理学会論文誌 60(9), 2019-09-15

    IPSJ 

  • Analysis of learning logs in lectures and self-studies  [in Japanese]

    渡邊 栄治 , 尾関 孝史 , 小濱 剛

    映像情報メディア学会技術報告 = ITE technical report 43(30), 65-70, 2019-09

Page Top