检索结果-内蒙古大学图书馆

European Signal Processing Conference (EUSIPCO)

作者： Marco Huber Philipp Terhöst Florian Kirchbuchner Naser Damer Arjan Kuijper Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany Norwegian University of Science and Technology Gjϕvik Norway

ISBN: (数字)9789082797091

ISBN: (纸本)9781665467995

A decisive factor for face recognition performance is face image quality (FIQ). It describes the utility of face images for automatic recognition. While this FIQ has conventionally been considered as a scalar for the whole image, emerging works suggest assessing pixel-level FIQs to provide higher explainability. However, the value of pixel-level qualities as a measure of utility (value for recognition) is not yet investigated. In this work, we address this by presenting two evaluation schemes, deletion evaluation curve (DEC) and insertion evaluation curve (IEC). The DEC investigates the change in recognition performance as pixels are deleted based on their quality. Complementary, the IEC reports the change in recognition performance as pixels are inserted based on their quality into a blurred image. Since pixel-level face image quality assessment (PLFIQA) methods assign high values to pixels that contain discriminant information, the recognition performance should decrease or increase when they are removed or added, respectively. We have successfully demonstrated the proposed evaluation scheme on two face recognition solutions by comparing a recently proposed PLFIQA method to a random baseline. With the growing interest in explainable face recognition, the proposed metrics will enable adequate comparison of future advances in pixel-level quality assessment.

关键词： Image quality Measurement Image recognition Face recognition Biological system modeling IEC Europe

来源：评论

学校读者我要写书评

暂无评论

Ranking of attributes—comparative study based on data from stylometric domain

引用

Procedia computer science 2022年 207卷 2737-2746页

作者： Beata Zielosko Urszula Stańczyk Krzysztof Żabiński Institute of Computer Science University of Silesia in Katowice Będzińska 39 41-200 Sosnowiec Poland Department of Graphics Computer Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 2A 44-100 Gliwice Poland

The area of feature selection methods constantly expands along with the development of artificial intelligence domain, and has great impact on almost every field, whenever data is processed and explored. The paper presents research where a ranking method was proposed, inspired by an approach which comes from an algorithm for induction of decision rules. The ranking procedure was based on calculation of standard deviation for attributes, taking into account assigned class labels. This method was compared with another ranking mechanism, a modified version of popular Relief algorithm, with incorporating characteristics of variables by supervised discretisation. Comparison of obtained results included the aspect of knowledge representation as well as the perspective of the accuracy for constructed rule-based classifiers. The experiments were performed on datasets from stylometry domain, where authorship attribution was considered as a classification task, and stylometric descriptors as characteristic features defining writing styles of authors.

关键词： Feature selection Ranking of attributes Relief Standard deviation Decision rules Stylometry Supervised discretisation Authorship attribution

来源：评论

学校读者我要写书评

暂无评论

Multispectral Imaging for Differential Face Morphing Attack Detection: A Preliminary Study

Multispectral Imaging for Differential Face Morphing Attack ...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Raghavendra Ramachandra Sushma Venkatesh Naser Damer Narayan Vetrekar R. S. Gad Norwegian University of Science and Technology (NTNU) Gjøvik Norway AiBA AS Gjøvik Norway Fraunhofer Institute for Computer Graphics Research Germany School of Physical and Applied Sciences Goa University Goa India

Face morphing attack detection is emerging as an increasingly challenging problem owing to advancements in high-quality and realistic morphing attack generation. Reliable detection of morphing attacks is essential because these attacks are targeted for border control applications. This paper presents a multispectral framework for differential morphing-attack detection (D-MAD). The D-MAD methods are based on using two facial images that are captured from the ePassport (also called the reference image) and the trusted device (for example, Automatic Border Control (ABC) gates) to detect whether the face image presented in ePassport is morphed. The proposed multi-spectral D-MAD framework introduce a multispectral image captured as a trusted capture to acquire seven different spectral bands to detect morphing attacks. Extensive experiments were conducted on the newly created Multispectral Morphed Datasets (MSMD) with 143 unique data subjects that were captured using both visible and multispectral cameras in multiple sessions. The results indicate the superior performance of the proposed multispectral framework compared to visible images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Dimension to University Education The Metaversity

A New Dimension to University Education The Metaversity

引用

International Conference on computer Theory and Applications (ICCTA)

作者： Yousry S. Elgamal Professor of Computer Engineering senior consultant at The Arab Academy for Science and Technology and Chairman of the Computer Scientific Society (CSS) Alexandria Egypt

For a generation that has grown up with short-lived social media content. The key to learning is engagement. The metaverse is a short shared virtual environment that people access via internet, creating the sense of virtual *** that metaverse offer to colleges include: making educational resources affordable, enhancing student performance, making virtual interactions more like real ones, enabling experimentation with hard-to-create phenomena, increasing accessibility for remote students, and attracting young *** fall, 10 American universities got a free ticket for entry, as part of its $10M Meta Immersive Learning Project. Other universities worldwide have already started their metaversity programs in Hong Kong, Japan, France, Qatar, Brazil, South Korea, China, and Nigeria. Metaversity is also making the dawn of a new eduoconomy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PFMRC: A Unified MRC Framework for Chinese Named Entity Recognition via Semantic Feature Fusion

PFMRC: A Unified MRC Framework for Chinese Named Entity Reco...

引用

Artificial Intelligence, Robotics, and Communication (ICAIRC), IEEE International Conference on

作者： Zhenrong Deng Jinglin Zhang Yannan Xiao Shiwei Wei Guangxi Key Laboratory of Images and Graphics Intelligent Processing Guilin University of Electronic Technology Guilin China Nanning Research Institute Guilin University of Electronic Technology Guilin China School of Computer Science and Engineering Guilin University of Aerospace Technology Guilin China

ISBN: (数字)9798331531225

ISBN: (纸本)9798331531232

The landscape of natural language processing (NLP) has been revolutionized by advancements that enable the upstream training of knowledge-rich models for downstream tasks, particularly named entity recognition (NER). Traditional NER approaches, treating it as a sequence labeling problem, often fail to deeply understand the whole text and to capture syntactic nuances of text. To address these issues, we introduce PFMRC, a novel machine reading comprehension (MRC) framework that leverages the strengths of both contextual semantics and syntactic information for enhanced NER performance. PFMRC employs a dual-pronged feature extraction strategy, utilizing RoBERTa and BiGRU to encode text features for contextual semantic information and representing them as node features of the graph structure, and a weighted embedding representation to translate syntactic dependencies into graph-structured edge features. Our model further incorporates Graph Attention Networks (GAT) to harmonize node and edge features, facilitating a nuanced understanding of text. The integration of prior knowledge and the modeling of intricate syntactic relationships through Graph Attention Networks (GAT) not only improves entity recognition accuracy but also enriches the feature representation, leading to more robust NER outcomes. Extensive experiments on three Chinese datasets demonstrate PFMRC's superior performance over state-of-the-art models.

关键词： Training Accuracy Translation Semantics Refining Named entity recognition Syntactics Feature extraction Solids Robots

来源：评论

学校读者我要写书评

暂无评论

Message from conference chair

Proceedings - 2022 Algorithms, Computing and Mathematics Con...

引用

Proceedings - 2022 Algorithms, Computing and Mathematics Conference, ACM 2022 2022年 VIII页

作者： Geetha, G. Professor and Dean School of Computer Science and Information Technology Jain University Bengaluru India

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2023年 31卷 54-70页

作者： Zezario, Ryandhimas E. Fu, Szu-Wei Chen, Fei Fuh, Chiou-Shann Wang, Hsin-Min Tsao, Yu National Taiwan University Department of Computer Science and Information Engineering Taipei10617 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei115024 Taiwan Microsoft VancouverBCV6B 5C6 Canada Southern University of Science and Technology Department of Electrical and Electronic Engineering Shenzhen518055 China Academia Sinica Research Center for Information Technology Innovation Taipei11529 Taiwan Chung Yuan Christian University Jointly Appointed Professor with the Department of Electrical Engineering Taoyuan32023 Taiwan

This study proposes a cross-domain multi-objective speech assessment model, called MOSA-Net, which can simultaneously estimate the speech quality, intelligibility, and distortion assessment scores of an input speech signal. MOSA-Net comprises a convolutional neural network and bidirectional long short-Term memory architecture for representation extraction, and a multiplicative attention layer and a fully connected layer for each assessment metric prediction. Additionally, cross-domain features (spectral and time-domain features) and latent representations from self-supervised learned (SSL) models are used as inputs to combine rich acoustic information to obtain more accurate assessments. Experimental results show that in both seen and unseen noise environments, MOSA-Net can improve the linear correlation coefficient (LCC) scores in perceptual evaluation of speech quality (PESQ) prediction, compared to Quality-Net, an existing single-Task model for PESQ prediction, and improve LCC scores in short-Time objective intelligibility (STOI) prediction, compared to STOI-Net, an existing single-Task model for STOI prediction. Moreover, MOSA-Net can be used as a pre-Trained model to be effectively adapted to an assessment model for predicting subjective quality and intelligibility scores with a limited amount of training data. Experimental results show that MOSA-Net can improve LCC scores in mean opinion score (MOS) predictions, compared to MOS-SSL, a strong single-Task model for MOS prediction. We further adopt the latent representations of MOSA-Net to guide the speech enhancement (SE) process and derive a quality-intelligibility (QI)-Aware SE (QIA-SE) approach. Experimental results show that QIA-SE outperforms the baseline SE system with improved PESQ scores in both seen and unseen noise environments over a baseline SE model. © 2014 IEEE.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Shielding NLP Systems: An In-depth Survey on Advanced AI Techniques for Adversarial Attack Detection in Cyber Security

Shielding NLP Systems: An In-depth Survey on Advanced AI Tec...

引用

Automation, Computing and Renewable Systems (ICACRS), International Conference on

作者： T. Sai Lalith Prasad K. B. Manikandan J. Vinoj Research Scholar Department of Computer Science and Engineering Vignan's Foundation for Science and Technology & Research (Deemed to be University) Guntur Andhra Pradesh India Assistant Professor Department of Artificial Intelligence and Data Science Vignan Institute of Technology and Science Telangana India Assistant Professor Department of CSE Vignan's Foundation for Science Technology and Research (Deemed to be University) Guntur Andhra Pradesh India

ISBN: (数字)9798331532420

ISBN: (纸本)9798331532437

This research investigates the challenges posed by adversarial perturbations to the robustness and reliability of Natural Language Processing (NLP) models. The study focuses on three key paradigms for enhancing the resilience of NLP systems: meta-learning, reinforcement learning, and self-supervised learning. A comprehensive evaluation of these strategies is conducted, analyzing their strengths and weaknesses in mitigating adversarial attacks. The study provides insights into the most promising approaches for enhancing the robustness of NLP models and offers directions for future research in this critical area. By advancing the resilience of NLP systems, this research contributes to the development of more robust and trustworthy AI applications across various domains, including healthcare, finance, and security.

关键词： Training Surveys Renewable energy sources Scalability Self-supervised learning Natural language processing Robustness Security Artificial intelligence Resilience

来源：评论

学校读者我要写书评

暂无评论

Secure Localization Based Authentication (SLA) Strategy for Data Integrity in WNS

引用

computers, Materials & Continua 2021年第6期67卷 4005-4018页

作者： V.Manikandan M.Sivaram Amin Salih Mohammed V.Porkodi K.Shankar Assistant Professor Research Research CenterLebanese French UniversityErbil44001Iraq Vice President Lebanese French UniversityErbil44001Iraq Department of Information Technology College of Engineering and Computer ScienceLebanese French UniversityErbil44001Iraq Department of Computer Applications Alagappa UniversityKaraikudi630003India

Wireless Sensor Networks(WSN)has been extensively utilized as a communication model in Internet of Things(IoT).As well,to offer service,numerous IoT based applications need effective transmission over unstable *** ensure reliability,prevailing investigations exploit multiple candidate forwarders over geographic opportunistic routing in ***,these models are affected by crucial denial of service(DoS)attacks,where huge amount of invalid data are delivered intentionally to the receivers to disturb the functionality of ***,secure localization based authentication(SLA)is presented to fight against DoS attack,and to fulfil the need of reliability and *** examining state information,SLA projects a trust model to enhance efficacy of data ***,of the prevailing opportunistic protocols,SLA guarantees data integrity by modelling a trust based authentication,providing protection against DoS attackers and diminishing computational ***,this model acts as a verification strategy to accelerate?attackers and to handle *** strategy helps SLA in eliminating duplicate transmission and by continuous verification that results from conventional opportunistic *** is performed in a MATLAB environment that offers authentic and reliable delivery by consuming approximately 50%of the cost in contrast to other *** anticipated model shows better trade off in comparison to the prevailing ones.

关键词： Wireless sensor networks opportunistic routing secure localization based authentication denial of service computational cost

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning DenseNet121 for Effective Waste Categorization: Insights into Automated Sorting Systems

Fine-Tuning DenseNet121 for Effective Waste Categorization: ...

引用

Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA), International Conference on

作者： Vishnu Kant Amit Kumar Mishra K. Chandhar Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Computer Science and Engineering Graphic Era Hill University Dehradun Adjunct Professor Graphic Era Deemed to be University Dehradun Uttarakhand School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

ISBN: (数字)9798331517953

ISBN: (纸本)9798331517960

The rapid expansion of industrialization and urbanization has resulted in a notable increase in garbage generation, so effective waste management systems become ever more important. Automated solutions are especially important as conventional garbage sorting techniques are labour-intensive and prone to human error. This work investigates the application of convolutional neural network architecture DenseNet121 to categorize waste into six groups: cardboard, glass, metal, paper, plastic, and rubbish. We seek to maximize classification accuracy by using DenseNet121's dense connection and thereby minimize model parameters. We trained DenseNet121 for the task using a dataset taken from Kaggle and obtained an accuracy of 88%. The outcomes show the possibilities of the model in automating waste classification, so supporting sustainable cities, resource economy, environmental preservation, responsible manufacturing and consumption habits, and enhanced recycling procedures. We then address the design, training approach, and performance criteria, stressing the advantages and difficulties of including such systems in major waste management projects.

关键词： Waste management Training Accuracy Computational modeling Urban areas Metals Feature extraction Recycling Sorting Resilience

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：