检索结果-内蒙古大学图书馆

6th International Symposium on Computer, Consumer and Control, IS3C 2023

作者： Takarabe, Jun'Nosuke Sari, Irawati Nurmala Du, Weiwei Kyoto Institute of Technology Department of Information Science Kyoto Japan University of Brawijaya Malang Department of Informatics Engineering Indonesia

ISBN: (纸本)9798350301953

Immersive experience exhibits such as augmented reality (AR) are a way to enjoy museums and art galleries because this way not only may update information easily but also does not require physical existence. However, 3-dimension (3D) images of AR are difficult to apply with one image as depth information either is unknown, or is cost and time consuming. This paper designs a depth map estimation method from single-view image by using smartphone camera to generate a 3D image in AR. Some functions are added into AR Depth Lab [7] in a personal computer (PC). Then, the improve AR Depth Lab [7] is installed into the smartphone. The depth map can be obtained by using patch-based depth estimation [8] and saved into the smartphone. The appropriate parameters of the proposal such as patch size, the cropped image size and the appropriate image models are set by experiments. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Combining TL and KD for Object Detection Model Compression 13

Combining TL and KD for Object Detection Model Compression

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Peng, Yuhan Lyu, Yan Zhao, Qiangfu The University of Aizu Computer Science and Engineering Aizuwakamatsu965-8580 Japan Muroran Institute of Technology Sciences and Informatics Muroran050a-8585 Japan

ISBN: (纸本)9798350373332

In modern society, object detection tasks have become extremely important due to their numerous applications in fields such as autonomous driving, surveillance, and healthcare. Real-time detection is particularly crucial for many applications. However, with the advancements in deep learning-based object detection methods, high performance often comes with high computational resource requirements, posing challenges for real-time monitoring, especially on resource-constrained devices. To address this issue, we study model compression using both transfer learning (TL) and knowledge distillation (KD). Specifically, we use the YOLOv5n model as a test case to show the basic idea for improving the performance of a small student model using a larger dataset for TL and a larger model for KD. As for KD, we further investigate feature-based and output-based KD. Experimental results show that the small student model can be improved significantly using TL and KD, with the mean Average Precision (mAP0.5) being increased by 13.28% compared to the baseline model. These results demonstrate the effectiveness of TL and KD in achieving high detection performance while reducing computational demands, making them suitable for various real-world applications. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Automated Annotation Assistance for Pidgin Sign Japanese in Sign Language Recognition 23

Automated Annotation Assistance for Pidgin Sign Japanese in ...

引用

23rd International Conference on Cyberworlds, CW 2024

作者： Benitez-Garcia, Gibran Kato, Nobuko Shiraishi, Yuhki Takahashi, Hiroki Tokyo Japan The University of Electro-Communications Graduate School of Informatics and Engineering Tokyo Japan Tsukuba University of Technology Department of Industrial Information Ibaraki Japan

ISBN: (纸本)9798331527174

Japanese Sign Language (JSL) and Manually Coded Japanese (MCJ) are the two main forms of sign language used in Japan. The former differs significantly from spoken Japanese, while the latter closely aligns with spoken syntax. Pidgin Sign Japanese (PSJ) is an intermediate form that heavily relies on nonmanual signals such as facial expressions and head movements for grammatical nuances. Current sign language recognition (SLR) systems predominantly focus on MCJ, neglecting the challenging properties of PSJ. This paper proposes an annotation assistance tool designed to automate the annotation of non-manual and spatial elements in PSJ. Our tool significantly reduces the manual effort required for annotation by using state-of-the-art methods for tracking human pose, hand, and face landmarks, along with recognizing facial action units (FAUs). Validation on a preliminary dataset of 30 videos containing over 90 instances of nonmanual elements demonstrated a 40% reduction in annotation time, highlighting our proposal's efficiency and effectiveness in handling the complexities of PSJ. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Modulated-ISRJ rejection using online dictionary learning for synthetic aperture radar imagery

引用

Journal of Systems engineering and Electronics 2024年第2期35卷 316-329页

作者： WEI Shaopeng ZHANG Lei LU Jingyue LIU Hongwei College of Oceanography and Space Informatics China University of Petroleum(East China)Qingdao 266580China School of Electronics Engineering Xidian UniversityXi’an 710071China School of Electronics and Communication Engineering Shenzhen Campus of Sun Yat-sen UniversityGuangzhou 518107China School of Computer Science and Technology Xidian UniversityXi’an 710071China

In electromagnetic countermeasures circumstances,synthetic aperture radar(SAR)imagery usually suffers from severe quality degradation from modulated interrupt sampling repeater jamming(MISRJ),which usually owes considerable coherence with the SAR transmission waveform together with periodical modulation *** paper develops an MISRJ suppression algorithm for SAR imagery with online dictionary *** the algorithm,the jamming modulation temporal properties are exploited with extracting and sorting MISRJ slices using fast-time *** dictionary learning is followed to separate real signals from jamming *** the learned representation,time-varying MISRJs are suppressed *** simulated and real-measured SAR data are also used to confirm advantages in suppressing time-varying MISRJs over traditional methods.

关键词： synthetic aperture radar(SAR) modulated interrupt sampling jamming(MISRJ) online dictionary learning

来源：评论

学校读者我要写书评

暂无评论

The Optimization of n-Gram Feature Extraction Based on Term Occurrence for Cyberbullying Classification

引用

Data Science Journal 2024年第1期23卷

作者： Setiawan, Yudi Maulidevi, Nur Ulfa Surendro, Kridanto School of Electrical Engineering and Informatics Institute of Technology Bandung Bandung Indonesia

Cyberbullied communications should be bundled since online harassment is growing and has serious implications. High cyberbullying requires strong text classification algorithms to safeguard persons and communities. The n-Gram models language by collecting ‘n’ components, usually words or characters, from a text and detecting how words relate and if major items or sentences are cyberbullying document types. The research improves term value generation and text classification accuracy by extracting features using TF-IDF and n-Gram. The optimum TF-IDF feature extraction pattern demonstrated the usefulness of n-Gram in cyberbullying document classification. This field demands good categorization and feature extraction. Because cyberbullying takes numerous forms and venues, broad classification is essential. To test unigram, bigram, and trigram approaches across text lengths and frequencies, this study uses several parameter values. The research also shows the limitations and gaps in earlier methods and underscores the necessity for various n-Gram parameter values to overcome cyberbullying text complexity. Short-sentence articles, fluctuating data frequencies, and dynamic online interactions necessitate complex solutions. Ideal n-Gram patterns increase cyberbullying text categorization and give context to the field. This research acknowledges cyberbullying’s prevalence and effects, the necessity for effective categorization methods, and current techniques’ limitations, opening the way for more comprehensive and adaptive online harassment combating strategies. © 2024 The Author(s).

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

High-Resolution Art Painting Completion using Multi-Region Laplacian Fusion 6

High-Resolution Art Painting Completion using Multi-Region L...

引用

6th International Symposium on Computer, Consumer and Control, IS3C 2023

作者： Sari, Irawati Nurmala Masaoka, Kei Takarabe, Jun'Nosuke Du, Weiwei Kyoto Institute of Technology Department of Information Science Kyoto Japan University of Brawijaya Department of Informatics Engineering Malang Indonesia

ISBN: (纸本)9798350301953

Image completion has made impressive advancements based on deep learning approaches. However, even with advanced deep learning such as Generative Adversarial Networks (GAN), the restored area is not always optimal due to small-scale texture synthesis in high resolution and inferring missing information about image content from distant contexts, resulting in distorted lines and unnatural colors, especially in art painting completion with complicated structures and textures. Although several precious art paintings have been well-preserved by curators in museums, some frequent damages such as scratches, torn-out areas, and holes are still visible and require challenging physical repairs. Therefore, for practical refinement, some researchers convert them into high-resolution digital paintings to generate crisp brush strokes, textures, shapes, and tones by assuming similarities with the original physical ones. Based on these observations, we propose proceeding with a high-resolution art painting completion by applying a superior traditional method, named Multi-Region Laplacian Fusion. We attempt to recover irregular missing regions expected as the damages of ordinary paintings that often occur. To address high-resolution inpainting, we integrate two completions using the Laplacian pyramid and patch-based propagation. We then apply Alpha blending among both results to yield the fused reaction completion. Our experiments firmly validate the effectiveness of our proposed method to complete art paintings with random irregular missing regions. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Electric Power Prediction of 2D FE Magnetic Spring Energy Harvester Based on Coil using Support Vector Machines

Electric Power Prediction of 2D FE Magnetic Spring Energy Ha...

引用

2024 IEEE International Conference on Electrical Systems for Aircraft, Railway, Ship Propulsion and Road Vehicles and International Transportation Electrification Conference, ESARS-ITEC 2024

作者： Sciuto, Grazia Lo Bijak, Joanna Kowalik, Zygmunt Trawiński, Tomasz Capizzi, Giacomo Viola, Fabio Silesian University of Technology Department of Mechatronic Gliwice Poland University of Catania Department of Electrical Electronics and Informatics Engineering Catania Italy University of Palermo Department of Engineering Palermo Italy

ISBN: (纸本)9798350373905

Magnetic spring energy harvesters are considered to be a promising solution for powering small electronic devices because they employ the magnetic interaction between two fixed permanent magnets and one that is levitated vertically. This paper presents the two dimensional (2D) Finite Element Method (FEM) model of magnetic spring energy harvester based on coil layout. The simulation provides an optimized arrangement of number of turn and geometrical parameters of coil in the magnetic spring. The method based on Support Vector Machine (SVM) is proposed to predict electrical power of magnetic spring and to establish its dependence on the coil parameters. Furthermore an experimental analysis was performed to evaluate the electrical performance of the proposed magnetic spring system. © 2024 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Phylogenetic modelling scripts for identifying script versions

Phylogenetic modelling scripts for identifying script versio...

引用

2023 International Conference on ENTERprise Information Systems, CENTERIS 2023 - International Conference on Project MANagement, ProjMAN 2023 - International Conference on Health and Social Care Information Systems and Technologies, HCist 2023

作者： Salman, Osama A. Hosszu, Gabor Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Electron Devices Muegyetem rkp. 3 BudapestH-1111 Hungary

As the digital and physical worlds connect, machine-learning tools are increasingly being used by businesses and institutions, including archaeological research institutes and museums. The article presents research that, based on the evolution of human scripts, provides a tool for identifying script variants used in old manuscripts and stone inscriptions. This makes the work of paleography institutes and individual researchers more efficient. Using this research, it is possible to provide some information about millions of hitherto unidentified inscriptions using machine learning. The developed and tested method applies the biological phylogenetics tool to script evolution, an area that has yet to be investigated with machine learning tools. The final aim of the research is to use these tools to clarify the connections between many Arabic, Aramaic and Central Iranian script variants. The described procedure gives a new solution to one of the fundamental issues of phylogenetic analysis, feature selection, the effectiveness of which is verified with test runs. The paper presents a new feature selection method to identify the strength or effect of features before phylogenetic processing. This type of dimensionality reduction removes unnecessary features from the dataset for these analyses and interpretations. The method was applied to some versions of Arabic, Aramaic and Middle Iranian scripts, but the procedure is not script-specific. © 2024 The Author(s). Published by Elsevier B.V.

关键词： Arabic Script Aramaic Script Family Clustering Machine Learning Middle Iranian Script Family Phylogenetics Script Identification Scriptinformatics

来源：评论

学校读者我要写书评

暂无评论

Digital Twin Model for Smart Maintenance of Data Center Facilities : Study Literature Review 10

Digital Twin Model for Smart Maintenance of Data Center Faci...

引用

10th International Conference on ICT for Smart Society, ICISS 2023

作者： Ramdani, Dani Supangkat, Suhono Harso Hidayat, Fadhil Purwoadi, Michael Andreas School of Electrical and Informatics Engineering Bandung Institute of Technology Bandung Indonesia National Research and Innovation Agency Jakarta Indonesia

ISBN: (纸本)9798350339543

Digital twin is a technology that supports the implementation of digital transformation. The digital twin was developed to support decision making in various sectors. The digital twin concept is almost 20 years old and continues to evolve for use cases for the technology in new industries. Maintenance is one of the important points of the product life cycle as the origin of the digital twin. The data center facility is one of the supporters of digital transformation which must be able to guarantee the availability of its services. The availability of data center services is affected by the chosen maintenance strategy. This paper will discuss data centers and maintenance strategies as well as definitions, characteristics to examples of implementing digital twins, especially in the case of implementing intelligent maintenance. It is hoped that with the description of this paper, more specific research opportunities related to optimizing the application of digital twins for maintenance specifically used in data center facilities are expected. © 2023 IEEE.

关键词： Maintenance

来源：评论

学校读者我要写书评

暂无评论

The Optimization of Planning and Operation Control: Case Study in East Kalimantan, Indonesia 6

The Optimization of Planning and Operation Control: Case Stu...

引用

6th International Conference on Power engineering and Renewable Energy, ICPERE 2024

作者： Annurrahman, Yoga Fitrah Rahman, Fathin Saifur Hariyanto, Nanang Yasa, I Made Harta Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia PT PLN Indonesia Power Unit Bisnis Pembangkitan Bali Bali Indonesia

ISBN: (纸本)9798331504694

The reliability of the electrical system is one of the most important aspects in ensuring the distribution of electrical power supply, especially in remote and isolated areas. With the increase in customer loads each year, the stability of the power system is quite fluctuating, therefore PLN in this case as the main supplier of electrical power must guarantee the quality of power and the stability of the electrical power system. Therefore, a thorough planning is needed to meet the needs of electrical power, especially in West Kutai Regency, East Kalimantan. This experiment focuses on optimizing the planning and operation control in Melak Isolated Electrical Power System in West Kutai Regency, East Kalimantan. Therefore, the system is more reliable and stable, can meet the needs of the electrical energy supply in the area. Some of the steps taken in this experiment include conducting mathematical modeling of the generating system;determining the objective function;collecting planning data and generator operation dispatch;formulating parameters into objective functions;starting optimization of planning and operation;testing with planning and operation simulations;and analysis of optimization result data. © 2024 IEEE.

关键词： Power distribution planning

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：