检索结果-内蒙古大学图书馆

27th International Conference on Knowledge Based and Intelligent information and engineering Sytems, KES 2023

作者： Kakizaki, Toma Oeda, Shinichi Advanced Course of Control and Information Engineering National Institute of Technology Kisarazu College 11-1 Kiyomidaihigashi 2-chome Chiba Kisarazu City Japan Department of Information and Computer Engineering National Institute of Technology Kisarazu College 11-1 Kiyomidaihigashi 2-chome Chiba Kisarazu City Japan

To use an intelligent tutoring system (ITS) in an educational setting effectively, it is necessary to understand the skill status of students and recommend appropriate questions. Existing studies focused on improving the performance of ITS using student modeling to estimate the skill status of students. Knowledge tracing (KT) is the mainstream student modeling method, and deep learning approaches such as deep knowledge tracing and self-attentive knowledge tracing have been studied extensively in recent years. These models take only the questions solved by the student and the correct or incorrect answers to those questions as input;they do not assume the use of other features. In this study, we perform student modeling using DeepFM and FiBiNET that combines factorization machines and deep learning. Our results indicate that these models are more accurate than KT because of their ability to cope with sparse data and consider pairwise feature interactions, and more suited for real-world applications than KT. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： DeepLearning Educational data mining Factorization machines Intelligent tutoring system Knowledge tracing Student modeling

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Source Code Classification and Visualization of Decision Rationales 28th

Deep Learning-based Source Code Classification and Visualiza...

引用

28th International Conference on Knowledge Based and Intelligent information and engineering Systems, KES 2024

作者： Oeda, Shinichi Mitsumori, Seiya Department of Information and Computer Engineering National Institute of Technology Kisarazu College 11-1 Kiyomidaihigashi 2-chome Kisarazu City Chiba Japan Advanced Course of Control and Information Engineering National Institute of Technology Kisarazu College 11-1 Kiyomidaihigashi 2-chome Kisarazu City Chiba Japan

In programming education, it is crucial to provide instruction that is tailored to students' proficiency levels. For this purpose, an objective evaluation of each student's coding ability is essential. Additionally, it is necessary to understand the characteristics of source code written by both beginners and advanced students. Previous research has successfully converted the structural information of source code into graphs and assessed coding skills using deep learning, achieving high accuracy. However, it remains unclear which specific structural elements significantly influence these assessments. This study addresses this gap by transforming source code into abstract syntax trees and developing a model that uses Graph Convolutional Networks to categorize code as either beginner or advanced users based on learned structural information. Furthermore, we apply Integrated Gradients to visualize the decision-making basis of our model and elucidate the structural characteristics distinguishing source code written by beginner and advanced users. © 2024 The Authors.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A student modeling method combining Deep Learning and forgetting models with Knowledge Tracing 27

A student modeling method combining Deep Learning and forget...

引用

27th International Conference on Knowledge Based and Intelligent information and engineering Sytems, KES 2023

作者： Oeda, Shinichi Hasegawa, Shunichi Department of Information and Computer Engineering National Institute of Technology Kisarazu College 11-1 Kiyomidaihigashi 2-chome Chiba Kisarazu City Japan Advanced Course of Control and Information Engineering National Institute of Technology Kisarazu College 11-1 Kiyomidaihigashi 2-chome Chiba Kisarazu City Japan

Educational Data Mining (EDM) aims to enhance education by analyzing learners' skills and question difficulty levels using machine learning methods. Knowledge Tracing (KT), a subfield of EDM, utilizes Hidden Markov Models to estimate learners' abilities and predict their performance on unseen questions. While deep learning methods, such as bi-directional RNNs, have improved KT's accuracy, they may lack interpretability from an educational psychology perspective. Item Response Theory (IRT), widely used in educational statistics, offers greater explanatory potential. This study proposes a model that integrates the concept of forgetting into IRT for improved accuracy and explainability in Knowledge Tracing using bi-directional RNNs. The forgetting concept is based on Ebbinghaus' forgetting curve theory. Three experiments were conducted using synthetic data to compare a model from a previous study, a model based on the proposed method, and a model that combines the previous study's model with IRT but excludes the forgetting concept. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Deep Learning Educational Data Mining Intelligent Tutoring System Item Response Theory Knowledge Tracing Student Modeling

来源：评论

学校读者我要写书评

暂无评论

Modelling a moving land-sea boundary using adaptive mesh refinement 10

Modelling a moving land-sea boundary using adaptive mesh ref...

引用

10th Coasts, Marine Structures and Breakwaters Conference 2013: From Sea to Shore - Meeting the Challenges of the Sea

作者： Furuyama, Shoichi Maihara, Yusuke Dept. of Electronics and Information Engineering Toyama National College of Technology 1-2 Ebie-Neriya Imizu Toyama933-0293 Japan Toyama National College of Technology Advanced Course of Control Information System Engineering 1-2 Ebie-Neriya Imizu Toyama933-0293 Japan

ISBN: (纸本)9780727759771

High resolution calculation for the Tsunami run-up simulation at Toyama-bay in Japan is achieved by using Adaptive Mesh Refinement (AMR) method. The method is tested at Hamana-lake for the tide simulation, the water level rising simulation at Toyama-bay and Tsunami runs-up simulation at Toyama-bay. AMR generated the fine mesh at the boundary line between the water and the land. In the case of the tide simulation at Hamana-lake, the reasonably agreement result with the experimental data was given by using the AMR. In the case of water level rising simulation, the method kept the reasonably constant of the total number of calculation meshes by deleting the fine meshes at the far from the interested region, and the method was applied Tsunami run-up simulation at the Toyama-bay.

关键词： Water levels

来源：评论

学校读者我要写书评

暂无评论

Absolute longitudinal distance measurement verification of a standard polystyrene nanoparticle near a surface in water by means of multi-wavelength evanescent field 22

Absolute longitudinal distance measurement verification of a...

引用

22nd International Conference of the European Society for Precision engineering and Nanotechnology, EUSPEN 2022

作者： Blattler, Aran Khajornrungruang, Panart Suzuki, Keisuke Baba, Akiyoshi Goto, Daiki Graduate School of Computer Science and System Engineering Mechanical Information Science and Technology Course Kyushu Institute of Technology Fukuoka Japan Department of Intelligent and Control Systems Advanced Mechanical Division Kyushu Institute of Technology Fukuoka Japan Center of Microelectronic System Kyushu Institute of Technology Fukuoka Japan School of Computer Science and System Engineering Advanced Mechanical Course Kyushu Institute of Technology Fukuoka Japan

ISBN: (纸本)9781998999118

In the wet semiconductor process, abrasive nanoparticles are widely used in the chemical mechanical polishing (CMP) process to polish wafer surfaces for high planarization. During polishing, nanoparticles move with a high-speed three-dimensional (3D) position in the solution. In the 3D particles's moving positions, Z is a perpendicular longitudinal distance between the surface to the nanoparticle that plays a significant role in polishing, which could not be measured by general microscopy without longitudinal scanning. To understand nanoparticle phenomena near-surface, we have proposed and developed the apparatus with real-time fastmotion tracking on optical multi-wavelength evanescent fields microscopy to measure the 3D motion of the nanoparticle in water without scanning. In euspen's 2020, we could verify the relative distance ?Z of nanoparticles in water, but the absolute distance Z is unknown yet. In this manuscript, we have therefore developed an invisible nano-step height in water to verify the absolute height Z of an individual nanoparticle. The invisible nano-step height in water is made from an optical resin with a refractive index of 1.35 that is close to a refractive index of water to avoid unnecessary light during experimental verification. The nano-step height was less than 100 nm on a glass surface, fabricated using nanoimprint lithography. Polystyrene f100 nm standard particles in water were used to verify the height Z. The results of height Z of nanoparticles could be measured less than 100 nm with the measurement uncertainty ±10 nm (2s), which is related to the interferometer result of the nano-step height. © European Society for Precision engineering and Nanotechnology, Conference Proceedings - 22nd International Conference and Exhibition, EUSPEN 2022. All rights reserved.

关键词： Nanoparticles

来源：评论

学校读者我要写书评

暂无评论

ArrivieW: an application for general-purpose information presentation by using position and azimuth sensors 9

ArrivieW: an application for general-purpose information pre...

引用

9th IEEE Global Conference on Consumer Electronics, GCCE 2020

作者： Saito, Yasuyuki Uchiyama, Miki Okuzumi, Jun Suzuki, Norihiko National Institute of Technology Kisarazu College Dept. of Information Engineering Kisarazu Japan National Institute of Technology Kisarazu College Advanced Course of Control and Information Engineering Kisarazu Japan Shibayama Ancient-tomb and Clay-image Museum Shibayama-machi Board of Education Shibayama-machi Japan NS Support Office Nara Japan

ISBN: (纸本)9781728198026

In this study, we are trying to develop an Android application for general-purpose information presentation by using position and azimuth sensors. A researcher at Waseda University identified where all the 766 photos taken at the beginning of excavation in Tonozuka and Himezuka ancient tombs in Shibayama Town in 1956. In our laboratory, ARTonoHime was developed that took advantage of its feature. It is an Android application by using an augmented reality (AR) technology that presents the photos, descriptions, and reading voices at the time of excavation at the exact location where the photos were taken. Later, by using GPS data and azimuth data, the system was expanded to GPS-TonoHime which does not need markers. Currently, GPS-TonoHime directly embeds content such as photos and data such as location information in the application. In addition, since GPS-TonoHime does not show the current position on the map, it is necessary to directly instruct users where to proceed. Therefore, we aim to build a system that allows anyone to easily present information by adding a file selection function on the application. In addition, the system displays the current position on the guide map so that anyone can easily understand how and in which direction to reach the visiting point. Therefore, this system can be used anywhere and is useful as teaching materials in various subjects in school, commercial applications, etc. © 2020 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Development of elastomer-based incremental sheet forming method for curved products

引用

Procedia Manufacturing 2018年 15卷 1184-1191页

作者： Hiroki Ichihara Akio Sekiguchi Advanced Course of Control and Information Engineering National Institute of Technology Kisarazu College Kisarazu 292-0041 Japan Department of Control Engineering National Institute of Technology Kisarazu College Kisarazu 292-0041 Japan

A novel methodology based on the elastomer-based incremental sheet forming method was developed to employ oblique two-point incremental forming. In order to evaluate the effectiveness of the develped method, several experiments have been conducted for curved products. Our experiments with the proposed method reveal that the material displacements do not only occur along the straight projection line, but also arise along the curved projection path.

关键词： Computer Aided Manufacturing Incremental sheet forming Urethane elastomer Dieless Tool-trajectory Two-point incremental forming Oblique incremental forming Material displacement

来源：评论

学校读者我要写书评

暂无评论

Non-contact Head Gesture Maneuvering System for Electric Wheelchair using a Depth Sensor

Non-contact Head Gesture Maneuvering System for Electric Whe...

引用

International Conference on Sensing Technology

作者： Hirofumi Ohtsuka Tatsuya Kato Koki Shibasato Takahiro Kashimoto Department of Control and Information Systems Engineering National Institute of Technology Kumamoto College Advanced Course of Electronics and Information Systems Engineering National Institute of Technology Kumamoto College

ISBN: (纸本)9781479963157

Population of elderly people has been increasing not only in Japan but also in many countries. For the purpose of expanding the active field of them and persons with disabilities, and of improving their quality of life (QOL), the development of an intelligent wheelchair has been intensively studied. In this research, a new maneuver interface of the electric wheelchair instead of the joy-stick is considered. To develop such an interface, this paper deals with a simple non-contact detection method of horizontal head gesture motion using a depth sensor.

关键词： Electric wheelchair Gestures Disabled Persons Maneuvering inspection methods aged person Head Sensors

来源：评论

学校读者我要写书评

暂无评论

Log-Data Clustering Analysis for Dropout Prediction in Beginner Programming Classes

引用

Procedia Computer Science 2017年 112卷 614-621页

作者： Shinichi Oeda Genki Hashimoto Department of Information and Computer Engineering National Institute of Technology Kisarazu College Advanced Control and Information Engineering Course National Institute of Technology Kisarazu College 11-1 Kiyomidaihigashi 2-chome Kisarazu City Chiba Japan

Educational data mining (EDM) involves the application of data mining, machine learning, and statistics to information generated from an educational setting. In most school education, one teacher teaches many students. A periodic examination is used as a method to confirm that students have acquired skills. However, it is difficult to grasp the status of the student from each lesson, since examinations cannot be carried out easily. On the other hand, in programming classes, the students’ history of UNIX commands and source-code editing can be easily and automatically stored as log-data. Therefore, attempts have been made to estimate the student’s performance from this log-data, although their estimation accuracy is not high. In this research, we aim to extract those students who cannot keep up with programming lessons, rather than estimating the student’s performance from the log-data. Specifically, we propose a method for predicting dropouts using outlier detection to cluster data with unsupervised learning.

关键词： Educational data mining Dropout prediction Dynamic time warping k-means++ UNIX command history

来源：评论

学校读者我要写书评

暂无评论

Method of Rut Detection Using Lasers and In-Vehicle Stereo Camera

Method of Rut Detection Using Lasers and In-Vehicle Stereo C...

引用

International Conference on Intelligent Informatics and Biomedical Sciences

作者： Toshiki Kage Kousuke Matsushima Advanced Engineering School Mechanical and Electrical Systems Engineering Advanced Course National Institute of Technology Kurume College Department of Control and Information Systems Engineering National Institute of Technology Kurume College

ISBN: (纸本)9781479985630

This paper reports a new method of rut detection using lasers and in-vehicle stereo camera. In this method, we detects ruts by performing various image processings for the images included laser lines that is irradiated to the road surface. The algoristhm presented have ensures that it is to reduce the processing time and cost in comparison with convensional methods.

关键词： Rut detection Computer vision Inspection vehicle

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：