检索结果-内蒙古大学图书馆

Towards Adversarial Robustness for Multi-Mode Data through Metric Learning

Sensors 2023年第13期23卷 6173页

作者： Khan, Sarwar Chen, Jun-Cheng Liao, Wen-Hung Chen, Chu-Song Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan Social Networks Human-Centered Computing Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan Department of Computer Science National Chengchi University Taipei11605 Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei106319 Taiwan

Adversarial attacks have become one of the most serious security issues in widely used deep neural networks. Even though real-world datasets usually have large intra-variations or multiple modes, most adversarial defense methods, such as adversarial training, which is currently one of the most effective defense methods, mainly focus on the single-mode setting and thus fail to capture the full data representation to defend against adversarial attacks. To confront this challenge, we propose a novel multi-prototype metric learning regularization for adversarial training which can effectively enhance the defense capability of adversarial training by preventing the latent representation of the adversarial example changing a lot from its clean one. With extensive experiments on CIFAR10, CIFAR100, MNIST, and Tiny ImageNet, the evaluation results show the proposed method improves the performance of different state-of-the-art adversarial training methods without additional computational cost. Furthermore, besides Tiny ImageNet, in the multi-prototype CIFAR10 and CIFAR100 where we reorganize the whole datasets of CIFAR10 and CIFAR100 into two and ten classes, respectively, the proposed method outperforms the state-of-the-art approach by 2.22% and 1.65%, respectively. Furthermore, the proposed multi-prototype method also outperforms its single-prototype version and other commonly used deep metric learning approaches as regularization for adversarial training and thus further demonstrates its effectiveness. © 2023 by the authors.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

IoT Attack Detection and Prevention Through Machine Learning System

IoT Attack Detection and Prevention Through Machine Learning...

引用

Communication, Security and Artificial Intelligence (ICCSAI), International Conference on

作者： Kanishk Agrawal Pavan Kumar Reddy Poli Yash Gupta Garv Juneja Adhip Kishen Bopaiah Dinesh Ashok Arani Department of IET CSE Manglayatan University Aligarh Uttar Pradesh India Managing Information Technology Implementations Program management for fortune 6 Healthcare Company USA Department of Computer Science and Information Systems Birla Institute of Technology and Science Pilani India Department of Computer Science and Engineering Maharaja Surajmal Institute of Technology Guru Gobind Singh Indraprastha University Delhi India ICT Trainer Trinity College Bangalore India Manglayatan University Aligarh Uttar Pradesh India

Attacks on web applications are constantly growing in both frequency and severity. Abundant data on the internet stimulates hackers to attempt different types of cyberattacks. Attack detection using conventional approaches and outdated data processing techniques has become outmoded as a result of this development. The purpose of this study is to investigate IoT attacks and discuss the efficient ML technique implementation strategies for restricting security risks. Among different security techniques, Machine learning (ML) systems demonstrated commendable feasibility in improving network and device security for the Internet of Things. The study with contextual research recognises and comprehends that modified “Support Vector Machine (SVM)” as well as “Random Forest (RF)” ML techniques showed optimal performance in IoT attack detection and prevention.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Taxonomy of rough set approaches for rule generation

Taxonomy of rough set approaches for rule generation

引用

International Conference on Engineering and Emerging Technologies (ICEET)

作者： Murni Marbun Opim Salim Sitompul Erna Budhiarti Nababan Poltak Sihombing Graduate Program of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Department of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia

ISBN: (纸本)9781665427159

The rough set method is one of the well-known methods for classifying an object. The rough set method has been used since Pawlak discovered it in 1982. The rough set method can analyze data related to redundant attribute reduction, find the most significant attributes and make decision rules. This article presents a taxonomy of rough set approaches for generating rules. The rough set method in generating rules has been successfully applied in various fields, such as classification, decision analysis of medical data, manufacturing processes, machine operations, predictive data, evaluation of television sets, iris fisher data, trading stock indexes, information systems, learning database systems, scientific diagnostics, force protection, KANSEI Engineering, prediction, customization provider strategy, force stabilizer system, scientific data and vehicle traffic. Several researchers since 2000 have combined the rough set method with other methods or algorithms to get fewer rules and not reduce classification accuracy. The results of combining these methods have been shown to improve the performance of the rough set method.

关键词： TV Manufacturing processes Taxonomy Force Rough sets Prediction algorithms Probability distribution

来源：评论

学校读者我要写书评

暂无评论

Economics of Semantic Communication in Metaverse: An Auction Approach

Economics of Semantic Communication in Metaverse: An Auction...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Zi Qin Liew Hongyang Du Wei Yang Bryan Lim Zehui Xiong Dusit Niyato Han Yu Alibaba-NTU Singapore Joint Research Institute Nanyang Technological Univerity Singapore School of Computer Science and Engineering Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore School of Computer Science and Engineering Nanyang Technological University Singapore

Metaverse provides embodied artificial-reality experience to the users in the virtual spaces. Many innovative and creative services such as virtual conference and tourism have been realized in the digital twins maintained by the virtual service providers (VSP) in Metaverse. Digital twins are digital copies of the physical world constructed virtually by the VSPs using real-world data. For a realistic experience, VSPs need to collect data that is up-to-date and relevant to their services. In this paper, we propose an incentive design framework to support the data trading between VSPs and edge devices. In the auction model, we model the valuation of data by considering data relatedness and data freshness. In our model, the semantic communication model is used to filter the relevant data, and the age of information (AoI) metric is used to assess the data freshness. Results show that by considering the data freshness, our mechanism helps to increase the average update frequency so that the VSPs obtain fresh data for construction of digital twins. Our model ensures the desired properties of individual rationality, incentive compatibility, and budget balance.

关键词： Measurement Metaverse Data integrity Semantics Streaming media information filters Data models

来源：评论

学校读者我要写书评

暂无评论

AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Video Deepfake Detection

arXiv

引用

arXiv 2023年

作者： Shahzad, Sahibzada Adil Hashmi, Ammarah Peng, Yan-Tsung Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan The Department of Computer Science National Chengchi University Taipei11605 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Multimodal manipulations (also known as audiovisual deepfakes) make it difficult for unimodal deepfake detectors to detect forgeries in multimedia content. To avoid the spread of false propaganda and fake news, timely detection is crucial. The damage to either modality (i.e., visual or audio) can only be discovered through multi-modal models that can exploit both pieces of information simultaneously. Previous methods mainly adopt uni-modal video forensics and use supervised pre-training for forgery detection. This study proposes a new method based on a multi-modal self-supervised-learning (SSL) feature extractor to exploit inconsistency between audio and visual modalities for multi-modal video forgery detection. We use the transformer-based SSL pre-trained Audio-Visual HuBERT (AV-HuBERT) model as a visual and acoustic feature extractor and a multi-scale temporal convolutional neural network to capture the temporal correlation between the audio and visual modalities. Since AV-HuBERT only extracts visual features from the lip region, we also adopt another transformer-based video model to exploit facial features and capture spatial and temporal artifacts caused during the deepfake generation process. Experimental results show that our model outperforms all existing models and achieves new state-of-the-art performance on the FakeAVCeleb and DeepfakeTIMIT datasets. © 2023, CC BY.

关键词： Audio acoustics

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning for Keypoint Detection in Low-Resolution Thermal TUG Test Images

arXiv

引用

arXiv 2025年

作者： Chen, Wei-Lun Hsieh, Chia-Yeh Kao, Yu-Hsiang Liu, Kai-Chun Peng, Sheng-Yu Tsao, Yu Research Center for Information Technology Innovation Academic Sinica Taiwan Graduate Institute of Electrical Engineering National Taiwan University Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University Taiwan Department of Electrical Engineering National Taiwan University Taiwan College of Information and Computer Sciences University of Massachusetts AmherstMA01003 United States Department of Electrical Engineering National Taiwan University of Science of Technology Taiwan

This study presents a novel approach to human keypoint detection in low-resolution thermal images using transfer learning techniques. We introduce the first application of the Timed Up and Go (TUG) test in thermal image computer vision, establishing a new paradigm for mobility assessment. Our method leverages a MobileNetV3-Small encoder and a ViTPose decoder, trained using a composite loss function that balances latent representation alignment and heatmap accuracy. The model was evaluated using the Object Keypoint Similarity (OKS) metric from the COCO Keypoint Detection Challenge. The proposed model achieves better performance with AP, AP50, and AP75 scores of 0.861, 0.942, and 0.887 respectively, outperforming traditional supervised learning approaches like Mask R-CNN and ViTPose-Base. Moreover, our model demonstrates superior computational efficiency in terms of parameter count and FLOPS. This research lays a solid foundation for future clinical applications of thermal imaging in mobility assessment and rehabilitation monitoring. Copyright © 2025, The Authors. All rights reserved.

关键词： Thermography (imaging)

来源：评论

学校读者我要写书评

暂无评论

Preprocessing Techniques for Enhancing Vision-Based Detection System for Tire Sidewall Extraction

Preprocessing Techniques for Enhancing Vision-Based Detectio...

引用

International Seminar on Research of information technology and Intelligent Systems (ISRITI)

作者： Jia Hao Loo Veronica Lestari Jauw Chin Seong Lim Khairul-Rijal Sarmin Nunung Nurul Qomariyah Ahmad Nurul Fajar Department of Mechanical Materials and Manufacturing Engineering University of Nottingham Malaysia Malaysia Continental Tyre Technology Centre Malaysia Petaling Jaya Malaysia Computer Science Department School of Computing and Creative Arts Bina Nusantara University Jakarta Indonesia Information System Management Department BINUS Graduate Program-Master Information Systems Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

This study aims to develop a system for extracting crucial information from tire sidewalls using Optical Character Recognition (OCR). Initially, images of tire were captured manually by smartphone cameras, including Redmi 9T, iPhone 11, and Galaxy S23 Ultra. The captured images are then transferred to a computer for storage. Subsequently, these images were cropped according to the boundaries identified by Hough Circle Transform (HCT). The cropped images were then further pre-processed. During the pre-processing phase, geometrical transformation and image sharpening techniques are applied to enhance the clarity and readability of the text images. The text is then extracted using Google Vision, with the extracted text categorized by size, DOT, brand and pattern. The results indicated that the effectiveness of image pre-processing was constrained by the accuracy of circle detection, which reached a maximum rate of 87.1%. This causes parts of the text to be cut out inaccurately, leading to a suboptimal extraction accuracy of 55.65%. It is also observed that the Redmi 9T camera produced inconsistent results compared to other devices. Specifically, the iPhone 11 and Samsung Galaxy S23 Ultra demonstrated superior extraction accuracies of 69.71% and 66.37%, respectively, whereas the Redmi 9T achieved a lower extraction accuracy of 37.76%.

关键词： Accuracy Optical character recognition Text categorization Lighting Transforms US Department of Transportation Cameras Tires Internet Data mining

来源：评论

学校读者我要写书评

暂无评论

Using a hybrid neural network architecture for DNA sequence representation: A study on N4-methylcytosine sites

引用

computers in Biology and Medicine 2024年 178卷 108664-108664页

作者： Nguyen, Van-Nui Ho, Trang-Thi Doan, Thu-Dung Le, Nguyen Quoc Khanh University of Information and Communication Technology Thai Nguyen University Thai Nguyen Viet Nam Department of Computer Science and Information Engineering TamKang University New Taipei251301 Taiwan International Degree Program in Animal Vaccine Technology International College National Pingtung University of Science and Technology Pingtung Taiwan Professional Master Program in Artificial Intelligence in Medicine College of Medicine Taipei Medical University Taipei110 Taiwan Research Center for Artificial Intelligence in Medicine Taipei Medical University Taipei110 Taiwan AIBioMed Research Group Taipei Medical University Taipei110 Taiwan Translational Imaging Research Center Taipei Medical University Hospital Taipei110 Taiwan

N4-methylcytosine (4mC) is a modified form of cytosine found in DNA, contributing to epigenetic regulation. It exists in various genomes, including the Rosaceae family encompassing significant fruit crops like apples, cherries, and roses. Previous investigations have examined the distribution and functional implications of 4mC sites within the Rosaceae genome, focusing on their potential roles in gene expression regulation, environmental adaptation, and evolution. This research aims to improve the accuracy of predicting 4mC sites within the genome of Fragaria vesca, a Rosaceae plant species. Building upon the original 4mc-w2vec method, which combines word embedding processing and a convolutional neural network (CNN), we have incorporated additional feature encoding techniques and leveraged pre-trained natural language processing (NLP) models with different deep learning architectures including different forms of CNN, recurrent neural networks (RNN) and long short-term memory (LSTM). Our assessments have shown that the best model is derived from a CNN model using fastText encoding. This model demonstrates enhanced performance, achieving a sensitivity of 0.909, specificity of 0.77, and accuracy of 0.879 on an independent dataset. Furthermore, our model surpasses previously published works on the same dataset, thus showcasing its superior predictive capabilities. © 2024 Elsevier Ltd

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

CIMulator: Evaluating Neuromorphic Accelerators with HZO FefinFET-Based Synaptic Device

CIMulator: Evaluating Neuromorphic Accelerators with HZO Fef...

引用

International Conference on Green technology and Sustainable Development (GTSD)

作者： Hoang-Hiep Le Hao-Yu Lu Md. Aftab Baig Sourav De Ing-Chao Lin Darsen D. Lu Department of Computer Science and Information Engineering Minghsin University of Science and Technology Hsinchu Taiwan R.O.C Intelligent Computing Industrial Doctorate Program National ChengKung University Tainan Taiwan R.O.C Institute of Microelectronics National ChengKung University Tainan Taiwan R.O.C Department of Computer Science and Information Engineering National ChengKung University Tainan Taiwan R.O.C

ISBN: (数字)9798350386073

ISBN: (纸本)9798350386080

In this study, we use the CIMulator platform to evaluate the performance of neuromorphic accelerators with novel Hf 0.5 Zr 0.5 O 2 (HZO) ferroelectric fin field-effect transistor (FefinFET) as synaptic device. The MNIST handwritten digit dataset is used for training and inference processes in multilayer perceptron (MLP) neural networks. With the highly optimized synaptic device, the results demonstrate high training and inference accuracy, achieving up to 97% for the MLP, approaching the accuracy of software implementations.

关键词： Training Performance evaluation Energy consumption Accuracy Neuromorphic engineering Neural networks Multilayer perceptrons

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Multi-ONU Customers Access Network using Spectrum Slicing and Duplication Techniques 5

Performance Evaluation of Multi-ONU Customers Access Network...

引用

5th International Conference on Emerging Electrical Energy, Electronics and Computing Technologies, ICE4CT 2024

作者： Rahman, Juwairiyyah Abdul Mugunthan, Sivaguru A.L. Hassan, Hasliza Abu Muslim, Norliana Ab-Rahman, Mohammad Syuhaimi Department of Electrical Engineering Faculty of Engineering and Life Sciences Universiti Selangor Selangor Bestari Jaya45600 Malaysia Department of Computer and Communication Technology Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Perak Kampar31900 Malaysia Department of Electrical Electronics and Systems Engineering Faculty of Engineering and Built Environment Universiti Kebangsaan Malaysia Malaysia Electrical and Computer Engineering Program Faculty of Engineering Sohar University PC:311 Sohar Oman

This study aims to increase the number of access users by limiting the sample size to 30 users while ensuring that every Optical Network Unit (ONU) receives data from the Optical Line Terminal (OLT). The proposed solution allows for the determination of power requirements at each ONU based on bus-star topologies, facilitating an increase in user capacity. The power received by each ONU is a critical parameter that system designers must consider when planning the implementation of Fiber to the Home (FTTH), as it impacts the output data in terms of Bit Error Rate (BER) and Signal Quality Factor (QF) for each user. Various parameters were evaluated to ensure that the enhanced network improves scalability while adhering to standard specifications. These parameters included the Q-factor, BER, eye diagram, user count, and received power. The study employed slicing and duplication techniques, utilizing Arrayed Waveguide Grating (AWG) for signal duplication and Wavelength Division Multiplexing for signal slicing. The simulations were conducted using a transmitter operating at a frequency of 1491 nm with a power output of 0 dBm, utilizing the latest version of OptiSystem 20 software. The results highlighted the system's capability to support a total of 73,728 users, meeting stringent performance criteria. Specifically, the system achieved a Q-factor greater than 6, indicating high signal quality, and a bit error rate (BER) lower than 1 × 10-9, ensuring reliable data transmission. For the sampled 30 users, the average Q factor was 8.1527, and the average BER was 5.3648 × 10^-11, with an output power level of -54.278 dBm. Despite an increase in users, the quality of the data supplied to clients remained unchanged. These outcomes underscore the robustness and efficiency of the design in delivering high-capacity, error-resilient optical communication. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Q factor measurement

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：