检索结果-内蒙古大学图书馆

A METHOD FOR IMPROVING THE ACCURACY OF SFM 3D MEASUREMENTS BY RANDOM PATTERN PROJECTION

AIJ Journal of Technology and Design 2023年第71期29卷 533-537页

作者： Sugano, Miki Kakizaki, Ken'ichi Tominaga, Yasumasa Araki, Shunsuke Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Japan

SfM can reconstruct the 3D shape of an object with high accuracy if there are many feature points on the surface to be measured. However, in the field of architecture, there is a problem that building surfaces are beautifully preserved and the shape cannot be reconstructed because of the small number of feature points. In this study, we proposed a method to improve the measurement accuracy of SfM by projecting a random pattern on a wall surface and distributing a large number of feature points. Experiments confirmed that the measurement accuracy was as good as that of a laser scanner. © 2023 Architectural Institute of Japan. All rights reserved.

关键词： 3D measurement Measurement accuracy Pattern projection Point cloud Random pattern SfM

来源：评论

学校读者我要写书评

暂无评论

A deep learning framework for automatic assessment of presence in virtual reality using multimodal behavioral cues

引用

Neural Computing and Applications 2025年第8期37卷 6283-6303页

作者： Pannattee, Peerawat Shimada, Shogo Yem, Vibol Nishiuchi, Nobuyuki Graduate School of Systems Design Tokyo Metropolitan University Tokyo191-0065 Japan Graduate School of Science and Technology Degree Program in Systems and Information Engineering University of Tsukuba Ibaraki3058573 Japan

Effective development of virtual reality (VR) applications is heavily reliant on the evaluation of user experience (UX). However, traditional methods such as questionnaires have inherent limitations which hinder their ability to capture nuanced behavioral responses and impede the agility of VR content creation: They are time-consuming, burdensome for users, and require significant human effort for interpretation. This study introduces an automated framework aimed at addressing the limitations of questionnaire-based evaluations to assess UX in VR. Our primary focus is to validate the concept of this framework through assessment of the sense of presence (SOP), a crucial psychological perception with significant impact on VR UX. Our proposed framework utilizes a deep neural network (DNN) to analyze patterns in multimodal behavioral cues, including facial expressions, head movements, and hand movements, to predict scores from the Igroup Presence Questionnaire (IPQ). Additionally, we introduce two statistical profiles: the Visual Entropy Profile (VEP), which offers insights into visual complexity by depicting scene entropy, and the Experiential Presence Profile (EPP), which is designed to capture users’ historical SOP levels to enable personalized baseline and sensitivity estimation. The proposed framework achieves a significant correlation between actual and predicted IPQ scores, with a Spearman’s rank correlation coefficient of 0.7303, showcasing the potential of DNNs in analyzing complex behavioral signals and automating SOP assessment. This study represents a pioneering effort in leveraging DNNs for the automatic assessment of SOP and paves the way for future advances in automatically assessing VR UX and unlocking new opportunities in the field. © The Author(s) 2025.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Hardware Acceleration for Embedded Scripting programming Language ‘mruby/c’

Computer Software

引用

computer Software 2024年第2期41卷 60-79页

作者： Maeda, Hiroyuki Tanaka, Kazuaki Fukuoka Industrial Technology Center Japan Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Japan

In this paper, we propose hardware acceleration to improve a performance of scripting programming languages for embedded developments. Scripting programming languages enable more efficient software developments and scripting programming languages are used in several system developments such as IoT developments. However, scripting programming languages are an interpreted language and the program is executed by a virtual machine, so it takes a long time to execute. Therefore, we implemented hardware acceleration for scripting programming language "mruby/c" targeting small embedded devices. The hardware acceleration supports bottleneck processing of a virtual machine of mruby/c, execution speeds are improved. This paper describes the configuration of the hardware acceleration for mruby/c and the performance evaluation. © 2024 Japan Society for Software science and Technology. All rights reserved.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Experimental evaluation of MIMO configurations in indoor visible light communications under the consideration of illumination

Optics Continuum

引用

Optics Continuum 2025年第4期4卷 789-803页

作者： Esteban Farfán-Guillén, David Camporez, Higor Silva, Jair Adriano Lima Castellano Rodriguez, Juan Camilo Pohl, Alexandre De Almeida Prado CPGEI–Graduate Program in Electrical Engineering and Computer Science Federal University of Technology Paraná Curitiba80230–901 Brazil Graduate Program in Electrical Engineering Federal University of Espírito Santo Vitória29075-960 Brazil

Visible light communications (VLC) enable wireless data transmission using existing light-emitting diode (LED) illumination. This experimental study evaluates the performance of multiple input and multiple output (MIMO) configurations in indoor VLC systems by analyzing their impact on both communication and illumination. Various MIMO setups (2 × 2, 3 × 2, and 4 × 2) are compared against single input single output (SISO), and single input multiple outputs (SIMO) schemes, using commercial LED luminaires as transmitters. While the 4 × 2 MIMO configuration demonstrates superior overall performance, intermediate configurations like 3 × 2 or 2 × 2 MIMO offer an attractive trade-off between system complexity and performance enhancement, particularly in scenarios with space or cost constraints. The results show that MIMO configurations significantly outperform SISO systems, achieving reliable communication (BER ≤ 10−3) at practical indoor distances of up to 2 meters while maintaining illumination levels above 300 lux, where conventional SISO setups do not meet these dual requirements. These findings demonstrate the practical feasibility of MIMO-VLC systems for indoor deployments. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Frequency division multiplexing Modulation techniques Multiple input multiple output Quadrature amplitude modulation Signal processing Visible light communications

来源：评论

学校读者我要写书评

暂无评论

Dynamic Sampling-Based Meta-Learning Using Multilingual Acoustic Data for Under-Resourced Speech Recognition

引用

IEEE Access 2024年 12卷 106070-106083页

作者： Hsieh, I-Ting Wu, Chung-Hsien Zhao, Zhe-Hong National Cheng Kung University Graduate Program of Multimedia Systems and Intelligent Computing Tainan70101 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

Under-resourced automatic speech recognition (ASR) has become an active field of research and has experienced significant progress during the past decade. However, the performance of under-resourced ASR trained by existing methods is still far inferior to high-resourced ASR for practical applications. In this paper, speech data from languages that share the most phonemes with the under-resourced language are selected as supplementary resources for meta-training based on the Model-Agnostic Meta-Learning (MAML) strategy. Besides supplementary language selection, this paper proposes a dynamic sampling method instead of the original random sampling method to select support and query sets for each task in MAML to improve meta-training performance. In this study, Taiwanese is selected as the under-resourced language, and the speech corpus of five languages, including Mandarin, English, Japanese, Cantonese, and Thai, are chosen as supplementary training data for acoustic model training. The proposed dynamic sampling approach uses phonemes, pronunciation, and speech recognition models as the basis to determine the proportion of each supplementary language to select helpful utterances for MAML. For evaluation, with the selected utterances from each supplementary language for meta-training, we obtained a Word Error Rate of 20.24% and a Syllable Error Rate of 8.35% for Taiwanese ASR, which were better than the baseline model (26.18% and 13.99%) using only the Taiwanese corpus and other methods. © 2013 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Effect of Graphite Addition on Microstructure, Mechanical Properties and Thermal Properties of Injection Molded AZ91D Alloy+1

引用

Materials Transactions 2024年第4期65卷 374-380页

作者： Hideshima, Yasutoshi Maeda, Fumiya Fukuta, Tadao Ozaki, Koichi Course of Advanced Systems Engineering Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja719-1197 Japan Process Technology Development Department Technology Development Division Seiko Epson Corp. Suwa399-0211 Japan Department of Systems Engineering Faculty of Computer Science and Systems Engineering Okayama Prefectural University Soja719-1197 Japan

Magnesium chips were coated with a high concentration of graphite using a binder and were used as the raw material for injection molding. The microstructure of the magnesium injection-molded product with added graphite exhibited a dispersion of needle-like graphite particles. No significant voids were observed at the interfaces between the graphite and the matrix. The addition of more than 0.5 mass% graphite decreased the proof stress and tensile strength of the injection-molded products. The Young’s modulus of the graphite-added products tended to decrease with an increase in the graphite content, which is consistent with the lower limit of the rule of mixtures. The thermal conductivity of the 6.9 mass% graphite-added product increased compared with that of the AZ91D magnesium alloy and the coefficient of linear thermal expansion decreased. Both values are within a range that satisfied the rules of mixtures. © 2024 The Japan Institute of Metals and Materials.

关键词： Thermal expansion

来源：评论

学校读者我要写书评

暂无评论

DFNet: Dense fusion convolution neural network for plant leaf disease classification

引用

Agronomy Journal 2024年第3期116卷 826-838页

作者： Faisal, Muhamad Leu, Jenq-Shiou Avian, Cries Prakosa, Setya Widyawan Köppen, Mario Department of Electronic and Computer Engineering (ECE) National Taiwan University of Science and Technology Taipei City Taiwan Department of Computer Science and Systems Engineering (CSSE) Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka Iizuka-shi Japan

The early identification of plant diseases is crucial for preventing the loss of crop production. Recently, the advancement of deep learning has significantly improved the identification of plant leaf diseases. However, most approaches depend on a single convolutional neural network (CNN) to extract the leaf features, ignoring the opportunity to take full advantage of the feature richness available in the images. This paper explores a novel CNN model with multiple automated feature extractors, namely, dense fusion CNN (DFNet), for classifying plant leaf diseases. DFNet aims to increase the diversity of extracted features in order to improve discrimination. Instead of using a single-CNN model, DFNet relies on a double-pretrained CNN model, MobileNetV2 and NASNetMobile, as the feature extractor. The features extracted from each CNN are fused in the fusion layer using a fully connected network. The proposed method was evaluated using corn (Zea mays L.) and coffee (Coffea canephora) leaf disease datasets and compared to the existing models. The experiment showed that DFNet is superior and consistent to other CNN methods by achieving an accuracy of 97.53% for corn leaf diseases and 94.65% for coffee leaf diseases. © 2023 The Authors. Agronomy Journal © 2023 American Society of Agronomy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Global-Local Consistency for Cost-Effective Anomaly Localization with Point Annotations 16

Global-Local Consistency for Cost-Effective Anomaly Localiza...

引用

16th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2024

作者： Nakanishi, Keiichi Katafuchi, Ryoya Tokunaga, Terumasa Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Kyushu Institute of Technology Faculty of Computer Science and Systems Engineering Iizuka Japan

ISBN: (纸本)9798350377903

Creating pixel-level ground-truth (GT) masks is quite costly for deep learning-based image segmentation. Specialists in areas such as anomaly detection and medical diagnostics face difficulties in producing many GT masks due to limited resources. To reduce this burden, we propose a cost-effective image segmentation framework with point annotations (CoSPA) that performs image segmentation with only point annotations. Point annotations refer to the partial and sparse labeled coordinates in an image. The key idea is to ensure consistency between the predictions for the same coordinates from the two different networks of CoSPA. This new consistency enables the CoSPA to improve segmentation performance and extend to semi-supervised learning. For the MVTec AD dataset, we verified the cost-effectiveness of CoSPA through an anomaly detection task. We demonstrated that the point annotating costs were reduced by 80% compared to creating GT masks. Subsequently, the CoSPA realized by 87% of the mean Intersection over Union (mIoU) achieved using the fully supervised method, DeepLabV3+. Moreover, the mIoU of CoSPA using only 30% of all point annotations defeated that of the unsupervised method, PaDiM. This study offers a new direction for economic anomaly localization. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Control Displaying of Web Push Notifications Inducing Users to Phishing Websites 7

Control Displaying of Web Push Notifications Inducing Users ...

引用

7th IEEE Conference on Dependable and Secure Computing, DSC 2024

作者： Sato, Masaya Mandai, Ryuki Okayama Prefectural University Faculty of Computer Science and Systems Engineering Soja Japan Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja Japan

ISBN: (纸本)9798331540289

The number of phishing websites is increasing, and the methods used to direct users to these sites are becoming more diverse. As web push notifications become more widespread, adversaries have begun using them as a method to direct users to phishing websites, known as phishing web push notifications. While protection against other phishing methods has been widely studied, countermeasures against phishing web push notifications remain an ongoing research topic. In this paper, we explore a method to control the display of web push notifications to protect users from phishing attempts. To minimize the cost of implementing and introducing the control mechanism, we utilized a browser extension to manage the display of web push notifications. We employed a keyword-based approach to detect and prevent the display of suspicious web push notifications. Our experimental results demonstrated that the proposed method effectively blocks phishing notifications. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

A Study on DDoS Attacks Detection on IoT Devices Using Machine Learning for Microcontrollers

A Study on DDoS Attacks Detection on IoT Devices Using Machi...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Mwaura, Jedidah Araki, Shunsuke Kakizaki, Ken'Ichi Kyushu Institute of Technology Graduate School of Computer Science and Systems Engineering FuKuoka Japan Kyushu Institute of Technology Faculty of Computer Science and Systems Engineering Fukuoka Japan

ISBN: (纸本)9798350324136

In recent years, there has been a proliferation of Internet of Things (IoT) devices, and so has been the attacks on them. In this paper we will propose a methodology to detect Distributed Denial of Service (DDoS) attacks on IoT devices using Machine Learning for Microcontrollers. We will discuss a model which we made for Arduino Nano 33 BLE Sense using Machine Learning for Microcontrollers. Additionally, we will discuss results of our proposal in detecting DDoS attacks on IoT devices. Lastly, we will describe the feasibility of our model on IoT devices. © 2024 IEEE.

关键词： DDoS IoT Machine Learning TinyML

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：