Search Results 1-20 of 1477

  • 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 PCPs were compared with the Kruskal-Wallis test (p = 0.05).<br><i>Results:</i> …

    Journal of Prosthodontic Research, 2021


  • Higher Risk Taking and Impaired Probability Judgment in Behavioral Addiction

    Asaoka Yui , Won Moojun , Morita Tomonari , Ishikawa Emi , Goto Yukiori

    … A battery of questionnaires for assessments of cognitive biases and economic decision-making were conducted, as was a psychological test for the assessment of the jumping-to-conclusions bias, using functional near-infrared spectroscopy recordings of prefrontal cortical (PFC) activity. … Results: Although behavioral addicts exhibited stronger cognitive biases than controls in the questionnaire, the difference was primarily due to lower intelligence in the patients. …

    International Journal of Neuropsychopharmacology, 2020-07-23


  • Clinically Feasible and Accurate View Classification of Echocardiographic Images Using Deep Learning

    Kusunose Kenya , Haga Akihiro , Inoue Mizuki , Fukuda Daiju , Yamada Hirotsugu , Sata Masataka

    … The aim of this study was to test two types of input methods for the classification of images, and to test the accuracy of the prediction model for EF in a learning database containing mislabeled images that were not checked by observers. … Our best model (from 10 selected images) classified video views with 98.1% overall test accuracy in the independent cohort. …

    Biomolecules 10(5), 665, 2020-04-25



    仲 沙織

    … A psychological test was conducted to reassess a truant child with developmental disorders during home-visit-support provided by a clinical psychologist with the collaboration of a multidisciplinary team. … Long-term leave from school might have affected the above results, and crystallized intelligence consistent with age was not acquired. …

    鹿児島純心女子大学大学院人間科学研究科紀要 (15), 43-52, 2020-03-31


  • Support System of Cystoscopic Diagnosis for Bladder Cancer Based on Artificial Intelligence

    小島 崇宏 , Atsushi Ikeda , Hirokazu Nosato , Yuta Kochi , Takahiro Kojima , Koji Kawai , Hidenori Sakanashi , Masahiro Murakawa , Hiroyuki Nishiyama

    … Therefore, to improve the quality of bladder cancer diagnosis, we aimed to support the cystoscopic diagnosis of bladder cancer using artificial intelligence (AI).Materials and Methods: A total of 2102 cystoscopic images, consisting of 1671 images of normal tissue and 431 images of tumor lesions, were used to create a dataset with an 8:2 ratio of training and test images. … The performance of the trained classifier was evaluated using test data. …

    Journal of Endourology 34(3), 352-358, 2020-03


  • Development of artificial intelligence system to support soil classification  [in Japanese]

    INAZUMI Shinya , KOJIMA Kazuhiko , HASHIDA Hiroyuki , KATO Takahiro

    … Therefore, for example, if an attempt is made to determine the soil classification without a precise test, certain experiences may be required, and individual differences may appear in the determination. … The purpose of this paper is to show the possibility of image recognition by artificial intelligence using machine learning for the purpose of expanding the use cases of artificial intelligence (AI) in Japan. …

    Japanese Geotechnical Journal 15(3), 653-663, 2020



    BAI Ke , KUMAGAI Takahiro , SASAKI Yu , TASHIRO Tsukasa , KOTOURA Tsuyoshi , TSURUMI Fumitaka

    … We also introduce artificial intelligence technology to estimate soil properties such as the liquid limit based on information such as soil source, wet density, and picture. … The distribution of soil property based on artificial intelligence also showed high accuracy compared with the cone penetration test result.</p> …

    Journal of Japan Society of Civil Engineers, Ser. B3 (Ocean Engineering) 76(2), I_726-I_731, 2020


  • Smartphone Naïve Bayes Human Activity Recognition Using Personalized Datasets

    Gadebe Moses L. , Kogeda Okuthe P. , Ojo Sunday O.

    … Each K category was repeated five times and the algorithm consistently produced the same result for each test. …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 24(5), 685-702, 2020


  • Theoretical Explanation of Recent Empirically Successful Code Quality Metrics

    Kreinovich Vladik , Masmali Omar A. , Nguyen Hoang Phuong , Badreddin Omar

    … <p>Millions of lines of code are written every day, and it is not practically possible to perfectly thoroughly test all this code on all possible situations. …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 24(5), 604-608, 2020


  • Research on Contact Performance of Aviation Electrical Connector under Atmospheric Turbulence

    Luo Yanyan , Wang Guoping , Cai Ming , Zhang Le , Zhang Zhaopan

    … The test method for contact force measurement was determined. … According to the test scheme, the detecting device for the contact force and contact resistance of the electrical connectors was designed, and the turbulence test of the electrical connectors was carried out. …

    IEICE Transactions on Electronics, 2020


  • Classification of Solidification Structure and Prediction of Tensile Strength of Flake Graphite Cast Iron by Neural Network  [in Japanese]

    Kato Masaya , Iwami Yuki , Kanno Toshitake , Ikehara Mizuki , Utida Nozomu

    … Although the method of numerically determining the quality of spheroidal graphite cast iron with nodularity, has been suggested, there is no method to numerically qualify the quality of flake graphite in flake cast iron.</p><p>  In this study, we cast test pieces with a diameter of 30mm to determine the graphite structures of flake graphite casting by AI. …

    Journal of Japan Foundry Engineering Society 92(8), 416-422, 2020


  • Automatic Cell discrimination by Imaging Flow Cytometry and Machine Learning  [in Japanese]

    Matsuoka Yoshikazu

    … <p>Artifi cial intelligence has gained massive attention in research, thanks to extensive development of algorithms and continuing growth of computing power. … This method uses labeled training datasets before classifi cation of test images. … Artifi cial intelligence has gained massive attention in research, thanks to extensive development of algorithms and continuing growth of computing power. …

    Cytometry Research 30(1), 15, 2020


  • Proposal of perspective on "How to use AI-based patent searching tools"  [in Japanese]

    SAKAI Misato

    … <p>I consider "How to deal with AI (Artificial Intelligence) patent search tools" through the opinions of overseas agents, the current status of test collection evaluation, and examples of its introduction to patent administration. …

    The Journal of Information Science and Technology Association 70(7), 355-359, 2020


  • Modeling Sensory Characteristics through Reproduction of Subjective Experience for Auditory Characteristics of People with Autistic Spectrum Disorder  [in Japanese]

    ICHIKAWA Itsuki , NAGAI Yukie , KANAZAWA Hoshinori , YONEKURA Shogo , KUNIYOSHI Yasuo

    … In this article, we discuss about design and evaluation of the model using test video data. …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4Rin192-4Rin192, 2020


  • Factor Analysis of NAFLD with Health Check Data based on BExSAM  [in Japanese]

    OUCHI Kohei , FUJIWARA Koichi , NISHIOJI Kenichi , KANO Manabu

    … Although a lot of studies wes conducted to identify the factors of the emergence and progress of NAFLD, few studies focused on causal relationships of test items of the electronic health record (EHR) data. …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4Rin158-4Rin158, 2020


  • Automatic detection of screen collapse by ensemble learning from images on Web screens.  [in Japanese]

    ONOZUKA Soichi

    … <p>Automated Web application testing generates screenshots as test evidences. …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4Rin181-4Rin181, 2020


  • A study of programming learning improvement using eye tracker  [in Japanese]

    SAKAI Taichi , URANO Shoichi

    … <p>In this paper, we measure gaze data using eye tracker at the time of answering a programming test, and aim to improve the education of programming learning focusing not only on the answer result of the question but also on the answer process. …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4J2GS204-4J2GS204, 2020


  • Click-Through Rate Prediction with Confidence for News Headlines Using Natural Gradient Boosting  [in Japanese]

    NAKAMURA Yuki , SHIBATA Tomohide , KOBAYASHI Hayato , SHIMIZU Nobuyuki , TAGUCHI Hiroaki

    … In order to confirm the usefulness of our proposed method, we perform an evaluation experiment using the A/B test log of news headlines and discuss the relationship between confidence and prediction performance.</p> …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4M2GS503-4M2GS503, 2020


  • Multi-label text classification for risk prediction in contracts  [in Japanese]

    FUJII Mina , ABE Tomohiko , TAKAHASHI Koji , IWAKI Yasuhiro , KATO Tsuneaki

    … On our dataset consisting of over 20k Japanese contracts, in which each clause has 1 ~ 4 label(s) and the labels total 205, our model achieved 31 ~ 64 % accuracy, depending on the number of labels an input text contains, for test data. …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4P3OS802-4P3OS802, 2020


  • Japanese Legal Term Correction using BERT Pretrained Model  [in Japanese]

    YAMAKOSHI Takahiro , KOMAMIZU Takahiro , OGAWA Yasuhiro , TOYAMA Katsuhiko

    … We solve this task with a classifier by regarding the task as a sentence completion test. …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4P3OS805-4P3OS805, 2020


Page Top