检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3336-3349页

作者： Chen, Liuyin Lu, Di Zhai, Jianxue Cai, Kaican Wang, Long Zhang, Zijun City University of HongKong School of Data Science Hong Kong Nanfang Hospital Southern Medical University Department of Thoracic Surgery Guangzhou510515 China University of Science and Technology Beijing Department of Computer Science and Technology Beijing100083 China University of Science and Technology Beijing Shunde Graduate School Foshan China

Lung function evaluation is important to many medical applications, but conducting pulmonary function tests is constrained by different conditions. This article presents a pioneer study of an integrated invertible deep learning method for lung function estimation via using computed tomography (CT) images. First, the projection method is proposed to flatten the three-dimensional (3-D) image onto a two-dimensional (2-D) plane, with preserving location information in 3-D. Next, the MBConv transformer-based encoder-decoder structure is developed to extract latent features. Finally, we develop an invertible normalizing flow (NF) model to infer lung function based on the extracted features and design two loss functions for two directions. The method enables both estimating the lung function based on CT images and metadata as well as generating the corresponding simulated CT image according to the lung function. Computational studies show that the proposed regression model outperforms all state-of-the-art image regression models. A comprehensive comparative analysis also demonstrates the effectiveness of using generated images and confirms the superiority of the proposed method. To the best of our knowledge, this work is the first of its kind in combining encoder-decoder network with NFs to ensure the effectiveness of the fully invertible framework, especially in lung CT image analysis. © 2020 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

RobustFace: a novel image restoration technique for face adversarial robustness improvement

引用

Multimedia Tools and Applications 2025年第11期84卷 8965-8993页

作者： Sadu, Chiranjeevi Das, Pradip K. Yannam, V Ramanjaneyulu Nayyar, Anand Department of Computer Science and Engineering RGUKT Nuzvid Andhra Pradesh Nuzvid India Department of Computer Science and Engineering IIT Guwahati Assam Guwahati India School of Technology Woxsen University Telangana Hyderabad India Graduate School Faculty of Information Technology Duy Tan University Da Nang550000 Viet Nam

Machine Learning (ML) models, particularly Deep Learning (DL), have made rapid progress and achieved significant milestones across various applications, including numerous safety-critical contexts. However, these models have recently been discovered to be susceptible to adversarial attacks, which are well-crafted input images. The primary objective of this paper is to propose a novel methodology titled "RobustFace", which is based on deep image restoration networks, that significantly improves the facial adversarial robustness of various image-classification models. Adversarial images are created using the Private Fast Gradient Sign Method (P-FGSM), StyleGAN and Fast Landmark Manipulation (FLM) methods. The adversarial images are then enhanced using deep image restoration networks to bring back them into the original space. The encoded weighted local magnitude patterns (WLMP) are extracted and provided to different types of classifiers to detect facial adversarial images from the clean images. The effectiveness of RobustFace has been demonstrated on two real-world datasets and experimental outcomes show that it significantly improves facial adversarial robustness on all evaluating classifiers. It improves the highest classification accuracy from 98.75% to 99.00% on P-FGSM attacks, from 77.94% to 85.25% on adversarial attacks generated by StyleGAN and from 65.52% to 69.50% for FLM attacks. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Dataset Genreratoin for Semantic Segmentation from 3D Scanned Data Considering Domain Gap 9

Dataset Genreratoin for Semantic Segmentation from 3D Scanne...

引用

9th International Conference on Control, Decision and Information Technologies, CoDIT 2023

作者： Wada, Marin Adachi, Miho Ueda, Yuriko Miyamoto, Ryusuke Graduate School of Science and Technology Dept. of Computer Science Japan School of Science and Technology Meiji University Dept. of Computer Science Kawasaki Japan

ISBN: (纸本)9798350311402

An autonomous moving scheme with semantic information extracted from images captured by the monocular camera was proposed, providing accurate results of semantic segmentation. A training dataset must accommodate the moving environment to train a classifier for autonomous moving. However, preparing a large-scale dataset composed of images having pixel-wise manually-annotated class labels is impractical. We generated datasets automatically from 3D point clouds, for reducing manpower. The dataset had significant problems: domain gap and shadows. Therefore, style transfer is incorporated in the proposed scheme to bridge the gap to resolve this problem. Moreover, pseudo shadows were added to improve the classification accuracy of testing images with shadows. Experimental results using 3D point clouds and testing images taken around Tsukuba City showed that classification accuracy was improved by the proposed scheme. The classification accuracy of the sidewalk, the most significant class for autonomous moving at the Tsukuba Challenge, was 95.7%. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Synonym Replacement Augmentation for Handling Data Imbalance in Personality Classification 8

Synonym Replacement Augmentation for Handling Data Imbalance...

引用

8th International Conference on Information technology, Information Systems and Electrical Engineering, ICITISEE 2024

作者： Pradana, Rilo Chandra Suhartono, Derwin Bina Nusantara University Binus Graduate Program Master of Computer Science Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350368970

The Myers-Briggs Type Indicator (MBTI) classification is a widely utilized instrument for personality assessment. However, it frequently encounters challenges due to imbalanced data distributions across personality dimensions. It is paramount to address this issue to enhance the accuracy and reliability of personality predictions. Most current research in this field is focused on data balancing techniques, such as oversampling and undersampling, which have been demonstrated to enhance model performance. Nevertheless, there is a dearth of research exploring text augmentation methods, particularly synonym replacement, for this purpose. This study examines the efficacy of synonym replacement as a data augmentation technique for MBTI classification. Experiments are conducted with varying levels of synonym replacement (10%, 30%, 50%, 70%, and 90%) to assess its impact on model accuracy and F1 scores across the four MBTI dimensions. Our findings indicate that low levels of synonym replacement, particularly at 10% to 50%, can enhance the performance of the model in predicting MBTI dimensions. On the other hand, a higher number of replaced words in the synonym replacement augmentation can harm the model's performance. These observations suggest that synonym replacement can effectively address data imbalance in MBTI classification, although its application must be tailored to specific personality dimensions. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach to Malware Classification Using Byte n-grams on IoT Devices 19

Machine Learning Approach to Malware Classification Using By...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Yama, Yuto Uda, Ryuya Graduate School of Bionics Computer and Media Science Tokyo University of Technology Graduate School 1404–1 Katakuramachi Hachioji Tokyo192–0982 Japan

ISBN: (纸本)9798331507817

Malware for IoT devices has become popular in recent years. Many detection methods have been proposed to detect the malware, mainly using machine learning, but they are not designed to work on IoT devices and are often implemented using Python. Running a Python program requires the installation of a package, which is impractical given the memory and storage size of IoT devices. In addition, methods that require decompilation, static and dynamic analysis of test samples are difficult to run on IoT devices. Therefore, in this research, we propose a method implemented in C/C++ so that malware detection using byte n-grams and machine learning can be run on IoT devices, and then resource consumption can be measured. Byte n-gram methods are good approaches to detect malware without knowing the execution environment. Moreover, the Top-L approach to information gain can be effectively applied to reduce storage and memory consumption. As a result of the evaluation, when using an SVM model with Top-50000 that maintains effective classification accuracy, the memory consumption was 71.91MB and the storage consumption was 1.3GB, which can be implemented in IoT devices. © 2025 IEEE.

关键词： C++ (programming language)

来源：评论

学校读者我要写书评

暂无评论

Formal Security Verification for Searchable Symmetric Encryption Using ProVerif 18

Formal Security Verification for Searchable Symmetric Encryp...

引用

18th International Symposium on Information Theory and Its Applications, ISITA 2024

作者： Mieno, Takehiko Okazaki, Hiroyuki Arai, Kenichi Futa, Yuichi Yamamoto, Hiroaki Graduate School of Medicine Science and Technology Shinshu University Epson Avasys Corporation Japan Graduate School of Science and Technology Shinshu University Japan Graduate School of Engineering Nagasaki University Japan School of Computer Science Tokyo University of Technology Japan Shinshu University Faculty of Engineering Japan

ISBN: (纸本)9784885523519

With the rapid proliferation of various cloud storage services in recent years, the development of technology to efficiently search data while ensuring its confidentiality during cloud usage is an important issue. The technology that enables keyword searches on encrypted files using previously set keywords is called searchable symmetric encryption (SSE). In this paper, we propose a method formally representing encrypted document, and verify the security of SSE using the formal verification tool ProVerif. Our proposed method considers the channel-type terms of ProVerif as a Document that includes different keywords to verify the indistinguishability of encrypted documents. © 2024 The Institute of Electronics, Information and Communication Engineers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rough-to-Fine Model-based Non-contact Heart Rate Estimation using MIMO FMCW Radar

Rough-to-Fine Model-based Non-contact Heart Rate Estimation ...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Shi, Xintong Bouazizi, Mondher Ohtsuki, Tomoaki Keio University Graduate School of Science and Technology Japan Keio University Department of Information and Computer Science Japan

ISBN: (纸本)9798350351255

MIMO FMCW Radar, a non-contact heart rate (HR) monitoring technology, has emerged as one of the superior alternatives to contact-based sensors, providing precise HR estimation without the drawbacks of discomfort or privacy concerns, and excelling in diverse environmental conditions. Recent HR estimation studies using conventional methods have achieved high accuracy but face challenges with lengthy processing times and sensitivity to experimental conditions, affecting real-time application and robustness. A previous Deep learning (DL)-based approach improves on these aspects but is limited by the range resolution of SISO FMCW Radar and the requirement for close positioning of subjects. Additionally, this method has inability to utilize contextual information from adjacent time windows restricts its effectiveness for time series analysis. Thus, our proposed method combines a Curve-Length (CL) approach with a DL rough-to-fine model, addressing the limitations of previous studies and improving HR estimation accuracy and robustness. This integrated process begins with human location detection through a CL-based approach and is followed by a two-phase rough-to-fine HR estimation. The experimental results show significant improvement over the conventional methods. © 2024 IEEE.

关键词： deep learning heart rate estimation MIMO FMCW radar rough-to-fine model

来源：评论

学校读者我要写书评

暂无评论

Effect of Varied Datasets on Training of a Segmentation Model Used in Visual Navigation

Effect of Varied Datasets on Training of a Segmentation Mode...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Wada, Marin Adachi, Miho Miyamoto, Ryusuke Graduate School of Science and Technology Dept. of Computer Science Japan Meiji University School of Science and Technology Dept. of Computer Science Kawasaki Japan

ISBN: (纸本)9798350324457

A visual navigation method based on results of semantic segmentation showed interesting results in previous researches. The most significant problem of the method is that the moving performance is affected by the segmentation accuracy, which strongly depends on the training data even though SOTA methods are adopted. To create high-quality dataset for this application without huge human efforts, the authors tries to generate datasets for semantic segmentation from a 3D scanned data composed of colored point clouds. In this study, we investigate what kinds of variations are effective to construct a classifier: variation of augmentation considering shadows, shooting angles, and shooting locations. Experimental results using actual images for evaluation and generated dataset for training captured at the course of Tsukuba Challenge, which is the famous competition for autonomous moving robots in Japan, showed that adding shadows in training datasets improved the mIoU but random changes to the shooting angle and location did not always work well. By the result, it is shown that augmentation considering the characteristic of the target environment becomes important for practical use. © 2023 IEEE.

关键词： 3D scanned data dataset generation semantic segmentation visual navigation

来源：评论

学校读者我要写书评

暂无评论

Model of Text-to-Text Transfer Transformer for Hadith Question Answering System 11

Model of Text-to-Text Transfer Transformer for Hadith Questi...

引用

11th International Conference on Information technology, computer and Electrical Engineering, ICITACEE 2024

作者： Sulistio, Bambang Suhartono, Derwin Soeparno, Haryono Budiharto, Widodo Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Computer Science Program Jakarta11480 Indonesia

ISBN: (纸本)9798350389289

The advancement of Artificial Intelligence (AI), notably in Natural Language Processing (NLP), has been remarkable. Among its applications, Question-Answering (QA) systems stand out, assisting users in accessing pertinent information across various topics, including religious contexts. Religion plays a significant role in providing guidance on moral values to modern society, such as tolerance, compassion and social norms. Religious practices taught by religion serve as significant foundations for addressing the increasingly advancing influence of technology. The primary goal of this paper is to create a question-answering system proficient in analyzing user inquiries and precisely extracting data from translated Indonesian Hadith datasets. This research endeavors to enhance question-answering accuracy through Deep Learning techniques. Employing pre-processing methods, the system interprets user query intents. Furthermore, the Text-to-Text Transfer Transformer (T5), a text-based language Transformer model, is utilized to streamline the retrieval process for Hadith-related queries based on relevant subjects. The research findings demonstrate the precision of answers through BLEU and ROUGE scores. The novelty of this study lies in the creation of a dataset of hadith translations in Indonesian and the fine-tuning of the T5 model that has been trained using a dataset of questions and answers based on these translations. This research demonstrates the following evaluation scores: BLEU: 0.606, ROUGE-1: 0.702, ROUGE-2: 0.548, and ROUGE-L: 0.701, indicating that the answers generated by this particular research model are better compared to those produced using the standard mT5 model. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Survey on Hypergraph Mining: Patterns, Tools, and Generators

引用

ACM Computing Surveys 2025年第8期57卷 1-36页

作者： Lee, Geon Bu, Fanchen Eliassi-Rad, Tina Shin, Kijung Kim Jaechul Graduate School of Ai Korea Advanced Institute of Science and Technology Seoul Korea Republic of School of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon Korea Republic of Khoury College of Computer Sciences Northeastern University Boston United States

Hypergraphs, which belong to the family of higher-order networks, are a natural and powerful choice for modeling group interactions in the real world. For example, when modeling collaboration networks, which may involve not just two but three or more people, the use of hypergraphs allows us to explore beyond pairwise (dyadic) patterns and capture groupwise (polyadic) patterns. The mathematical complexity of hypergraphs offers both opportunities and challenges for hypergraph mining. The goal of hypergraph mining is to find structural properties recurring in real-world hypergraphs across different domains, which we call patterns. To find patterns, we need tools. We divide hypergraph mining tools into three categories: (1) null models (which help test the significance of observed patterns), (2) structural elements (i.e., substructures in a hypergraph such as open and closed triangles), and (3) structural quantities (i.e., numerical tools for computing hypergraph patterns such as transitivity). There are also hypergraph generators, whose objective is to produce synthetic hypergraphs that are a faithful representation of real-world hypergraphs. In this survey, we provide a comprehensive overview of the current landscape of hypergraph mining, covering patterns, tools, and generators. We provide comprehensive taxonomies for each and offer in-depth discussions for future research on hypergraph mining. © 2025 Copyright held by the owner/author(s).

关键词： Taxonomies

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：