检索结果-内蒙古大学图书馆

Continuous Arabic Sign Language Recognition Models

Sensors 2025年第9期25卷 2916-2916页

作者： Algethami, Nahlah Farhud, Raghad Alghamdi, Manal Almutairi, Huda Sorani, Maha Aleisa, Noura Computer Science Department College of Computing and Informatics Saudi Electronic University Riyadh11673 Saudi Arabia Information Technology Department College of Computing and Informatics Saudi Electronic University Riyadh11673 Saudi Arabia

A significant communication gap persists between the deaf and hearing communities, often leaving deaf individuals isolated and marginalised. This challenge is especially pronounced for Arabic-speaking individuals, given the lack of publicly available Arabic Sign Language datasets and dedicated recognition systems. This study is the first to use the Temporal Convolutional Network (TCN) model for Arabic Sign Language (ArSL) recognition. We created a custom dataset of the 30 most common sentences in ArSL. We improved recognition performance by enhancing a Recurrent Neural Network (RNN) incorporating a Bidirectional Long Short-Term Memory (BiLSTM) model. Our approach achieved outstanding accuracy results compared to baseline RNN-BiLSTM models. This study contributes to developing recognition systems that could bridge communication barriers for the hearing-impaired community. Through a comparative analysis, we assessed the performance of the TCN and the enhanced RNN architecture in capturing the temporal dependencies and semantic nuances unique to Arabic Sign Language. The models are trained and evaluated using the created dataset of Arabic sign gestures based on recognition accuracy, processing speed, and robustness to variations in signing styles. This research provides insights into the strengths and limitations of TCNs and the enhanced RNN-BiLSTM by investigating their applicability in sign language recognition scenarios. The results indicate that the TCN model achieved an accuracy of 99.5%, while the original RNN-BiLSTM model initially achieved a 96% accuracy but improved to 99% after enhancement. While the accuracy gap between the two models was small, the TCN model demonstrated significant advantages in terms of computational efficiency, requiring fewer resources and achieving faster inference times. These factors make TCNs more practical for real-time sign language recognition applications. © 2025 by the authors.

关键词： Continuous speech recognition

来源：评论

学校读者我要写书评

暂无评论

Masked Facial Expression Recognition with Attention Mechanism based on Mini_Xception Network 24

Masked Facial Expression Recognition with Attention Mechanis...

引用

Proceedings of the 2024 International Conference on Image Processing, Multimedia Technology and Maching Learning

作者： Zhiping Zhang Shuzlina Abdul-Rahman Norlina Mohd Sabri School of Computing Sciences College of Computing Informatics and Media Universiti Teknologi MARA Selangor Malaysia College of Computer and Mathematics Xinyu University Xinyu Jiangxi China School of Computing Sciences College of Computing Informatics and Media Universiti Teknologi MARA Selangor Malaysia Universiti Teknologi MARA Cawangan Terengganu Kuala Terengganu Malaysia

ISBN: (纸本)9798400713880

Facial expression recognition is of crucial importance in a variety of applications, including human-computer interaction and health monitoring. However, when there is occlusion, especially when the mouth region is occluded, conventional FER methods often suffer from significant performance degradation. To address this challenge, a novel FER model, Mini-Xception+CBAM, is proposed. This combines a lightweight network architecture with an attention mechanism to enhance performance in occlusion scenarios. The proposed approach utilises the Mini-Xception architecture and integrates a Convolutional Block Attention Module (CBAM) to enable the model to dynamically focus on key facial regions, such as the eyes and eyebrows, which are less likely to be occluded. Extensive experimentation on the FER2013, SMFER2013, and MFER2013 datasets demonstrates that the proposed model outperforms numerous state-of-the-art baseline models, including Mini-Xception, MobileNetV2, ResNet-18, and Vision Transformer, achieving The model achieved 90.4% accuracy on the FER2013, 89.2% on the SMFER2013, and 91.5% on the MFER2013, along with higher precision, recall, and F1 score. Furthermore, the model has been designed to be efficient, with a parameter count of 0.68M and a floating point operations count of 30.1M, making it ideal for deployment on devices with limited resources.

关键词： Expression recognition

来源：评论

学校读者我要写书评

暂无评论

A Multi-Modal Assessment Framework for Comparison of Specialized Deep Learning and General-Purpose Large Language Models

引用

IEEE Transactions on Big Data 2025年第3期11卷 1001-1012页

作者： Nadeem, Mohammad Sohail, Shahab Saquib Madsen, Dag Oivind Alzahrani, Ahmed Abrahim Ser, Javier Del Muhammad, Khan Aligarh Muslim University Department of Computer Science Aligarh India VIT Bhopal University School of Computing Science and Engineering Bhopal-Indore Highway Kothrikalan Madhya Pradesh Sehore466114 India University of South-Eastern Norway Norway King Saud University Computer Science Department Community College Riyadh11437 Saudi Arabia TECNALIA Derio48160 Spain Department of Communications Engineering Bilbao48013 Spain Department of Applied Artificial Intelligence School of Convergence College of Computing and Informatics Seoul03063 Korea Republic of

Recent years have witnessed tremendous advancements in Al tools (e.g., ChatGPT, GPT 4, and Bard), driven by the growing power, reasoning, and efficiency of Large Language Models (LLMs). LLMs have been shown to excel in tasks ranging from poem writing and coding to essay generation and puzzle solving. Despite their proficiency in general queries, specialized tasks such as metaphor understanding and fake news detection often require finely tuned models, posing a comparison challenge with specialized Deep Learning (DL). We propose an assessment framework to compare task-specific intelligence with general-purpose LLMs on suicide and depression tendency identification. For this purpose, we trained two DL models on a suicide and depression detection dataset, followed by testing their performance on a test set. Afterward, the same test dataset is used to evaluate the performance of four LLMs (GPT 3.5, GPT 4, Google Bard, and MS Bing) using four classification metrics. The BERT-based DL model performed the best among all, with a testing accuracy of 94.61%, while GPT 4 was the runner-up with accuracy 92.5%. Results demonstrate that LLMs do not outperform the specialized DL models but are able to achieve comparable performance, making them a decent option for downstream tasks without specialized training. However, LLMs outperformed specialized models on the reduced dataset. © 2015 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Groundbreaking taxonomy of metaverse characteristics

引用

Artificial Intelligence Review 2025年第8期58卷 1-50页

作者： Sadeghi-Niaraki, Abolghasem Rahimi, Fatema Azlan, Nur Alya Emanuelle Binti Song, Houbing Ali, Farman Choi, Soo-Mi Department of Computer Science and Engineering and Convergence Engineering for Intelligent Drone XR Research Center Sejong University Seoul Korea Republic of BaltimoreMD21250 United States Department of Applied AI School of Convergence College of Computing and Informatics Sungkyunkwan University Seoul03063 Korea Republic of

The Metaverse, a dynamic and immersive virtual realm, has captured the imagination of researchers and enthusiasts worldwide. This survey paper aims to introduce a groundbreaking taxonomy for the characteristics of the Metaverse offering a structured and adaptable framework that extends beyond existing categorizations by incorporating dynamic transformations. Unlike prior taxonomies, which often focus on fixed attributes, our approach emphasizes the dynamic evolution of Metaverse characteristics. Through an extensive review of published literature, this study explores key technological, social, economic, and ethical dimensions of the Metaverse. It introduces a process-oriented classification based on 23 distinct characteristics, including immersification, spatiotemporalification, interactification, persistentification, presentification, personification, unification, imaginification, economification, uncertaintification, and credification. By mapping these evolving aspects, we provide a structured and future-proof foundation for understanding the Metaverse’s continuous development. This survey establishes a new standard for comprehensiveness and innovation, shedding light on the diverse facets that have been explored in literature. Through this novel taxonomy, we provide a detailed map of the current landscape and offer insights that pave the way for future research and development in this burgeoning digital frontier. © The Author(s) 2025.

关键词： Comprehensive analysis Futuristic exploration Metaverse characteristics Paradigm-shifting taxonomy Revolutionary categorization

来源：评论

学校读者我要写书评

暂无评论

Impact of Backdoor Attacks on Face Classification Models through Training Data Poisoning

Impact of Backdoor Attacks on Face Classification Models thr...

引用

computing and Information Technology (ICCIT-1441), 2020 International Conference on

作者： Mohammed Kutbi Department of Computer Science College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

In this work, we highlight the critical importance of data integrity in training machine learning (ML) models and emphasizes the potential risks associated with outsourcing ML development, data collection, or labeling. Our study investigates the vulnerability of face classification models to backdoor attacks through training data poisoning. We demonstrate that even with a very low presence of poisoned data, it is possible to infect ML models while maintaining high accuracy on normal testing data. The experiments show that backdoor attacks can be as subtle as adding a small occlusion, like a bandage on a face, making it difficult for security personnel to detect in physical spaces. The findings underscore the importance of employing robust validation techniques to maintain reliable and secure models, particularly when using pre-trained models or outsourced data services.

关键词： Training Training data Machine learning Data models Outsourcing Security Reliability Personnel Faces Testing

来源：评论

学校读者我要写书评

暂无评论

Classification of lung cancer severity using gene expression data based on deep learning

引用

BMC Medical informatics and Decision Making 2025年第1期25卷 1-19页

作者： Nassif, Ali Bou Abujabal, Nour Ayman Omar, Aya Alchikh Department of Computer Engineering College of Computing and Informatics University of Sharjah P.O Box: 27272 Sharjah United Arab Emirates

Lung cancer is one of the most prevalent diseases affecting people and is a main factor in the rising death rate. Recently, Machine Learning (ML) and Deep Learning (DL) techniques have been utilized to detect and classify various types of cancer, including lung cancer. In this research, a DL model, specifically a Convolutional Neural Network (CNN), is proposed to classify lung cancer stages for two types of lung cancer (LUAD and LUSC) using a gene dataset. Evaluating and validating the performance of the proposed model required addressing some common challenges in gene datasets, such as class imbalance and overfitting, due to the low number of samples and the high number of features. These issues were mitigated by deeply analyzing the gene dataset and lung cancer stages from a medical perspective, along with extensive research and experiments. As a result, the optimized CNN model using F-test feature selection method, achieved high classification accuracies of approximately 93.94% for LUAD and 88.42% for LUSC. © The Author(s) 2025.

关键词： Classification Deep learning Feature selection Gene expression LUAD Lung cancer LUSC

来源：评论

学校读者我要写书评

暂无评论

Empowering the adoption of blockchain-based cryptocurrency as a payment method: A user-friendly educational approach

IET Blockchain

引用

IET Blockchain 2025年第1期5卷

作者： Alrehaili, Ahmed White, Martin Beloff, Natalia University of Sussex School of Engineering and Informatics Informatics Brighton United Kingdom Islamic University of Madinah College of Computing and Information Systems Computer Science Department Medina Saudi Arabia

Organizations are adopting technological innovations to transform payment systems due to challenges with traditional methods, such as slow speed and high fees. These challenges have prompted a shift towards blockchain-based cryptocurrencies. However, cryptocurrency adoption for payments remains limited, especially in Saudi Arabia. This study adapts the technology acceptance model to explore cryptocurrency adoption through the blockchain-based cryptocurrency as a payment method in Saudi Arabia (BCAP-SA) model. Factors within the model are assessed using an experimental vignette-task methodology and surveys. A key component is an educational package, offering comprehensive materials to explain blockchain technology. The findings confirm the reliability of surveys. Most model factors are statistically significant in influencing users’ intention to use cryptocurrency. The study finds that perceived ease of use, perceived usefulness, and perceived trust significantly impact participants’ intentions. Additionally, low transaction fees and age are the most influential factors on the technology acceptance model's core constructs. Statistical analysis indicates that decentralization and anonymity were insignificant and thus excluded from the revised BCAP-SA model. These findings highlight the potential to enhance cryptocurrency adoption in Saudi Arabia. The study's insights can guide strategies to promote wider cryptocurrency usage in the region. © 2025 The Author(s). IET Blockchain published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

关键词： blockchain platforms blockchains cryptocurrencies models and analysis

来源：评论

学校读者我要写书评

暂无评论

Face image authentication scheme based on MTCNN and SLT

引用

Multimedia Tools and Applications 2025年 1-43页

作者： Thabit, Rasha Al-Askari, Mohanad A. Mohammed, Dunya Zeki Anaam, Elham Abdulwahab Mahmood, Zainab H. Jabbar, Dina Jamal Salih, Zahraa Aqeel Information System Department College of Computer Sciences and Information Technology University of Al-Anbar Al-Anbar Iraq Computer Engineering Department College of Engineering Al-Iraqia University Baghdad Iraq Electronic and Communications Engineering Department College of Engineering Gilgamesh University Baghdad Iraq Faculty of Computing and Informatics Multimedia University Selangor Cyberjaya Malaysia Department of Cybersecurity Engineering College of Information Engineering Al-Nahrain University Baghdad Iraq Electrical Engineering Technical Collage Middle Technical University Baghdad Iraq Department of Business Administration Alamaal University College Baghdad Iraq

DeepFakes and face image manipulation methods have been widely distributed in the last few years and several techniques have been presented to check the authenticity of the face image and detect manipulation if exists. Most of the available manipulation detection techniques have been successfully applied to reveal one type of manipulation under specific conditions, however, many limitations and challenges can be encountered in this field. To overcome some limitations and challenges, this paper presents a new face image authentication (FIA) scheme based on Multi-Task Cascaded Conventional Neural Networks (MTCNN) and watermarking in Slantlet transform (SLT) domain. The proposed FIA scheme has three main algorithms that are face detection and selection, embedding, and extraction algorithms. Different block sizes have been used to divide the image into non-overlapping blocks followed by classifying them into two groups that are blocks from face area (FA) and blocks from the remaining area (RA) of the image. In the embedding algorithms, the authentication information is generated from FA blocks and embedded in the RA blocks. In the extraction algorithms, the embedded information is extracted from RA blocks and compared with the calculated data from FA blocks to reveal manipulations and localize the manipulated blocks if exist. Extensive experiments have been conducted to evaluate the performance of the proposed FIA scheme for different face images. The experimental work included tests for payload, capacity, visual quality, time complexity, and localization of manipulations. The results proved the efficiency of the proposed scheme in detecting and localizing different face image manipulations such as attributes attacks, retouching attacks, expression swap, face swap, and morphing attacks. The proposed scheme overcomes many limitations and it is 100% accurate in localizing the tampered blocks which makes it a better candidate for practical applications. © The Author(s), un

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Modeling uncertainties associated with decision-making algorithms based on similarity measures of possibility belief interval-valued fuzzy hypersoft setting

引用

Neutrosophic Sets and Systems 2025年 77卷 282-309页

作者： Romdhini, Mamika Ujianita Al-Sharqi, Faisal Al-Obaidi, R.H. Rodzi, Zahari Md. Department of Mathematics Faculty of Mathematics and Natural Science University of Mataram Mataram83125 Indonesia Department of Mathematics Faculty of Education for Pure Sciences University of Anbar Ramadi55431 Iraq Fuel and Energy Techniques Engineering Department College of Engineering and Technologies Al-mustaqbal University Babylon51001 Iraq College of Computing Informatics and Mathematics UiTM Cawangan Negeri Sembilan Kampus Seremban Negeri Sembilan 72000 Malaysia

Hypersoft sets (HSSs) were initiated as an extension of soft sets (SSs) to address real-life scenarios involving multiple disjoint sets with different traits. One such extension is the interval-valued fuzzy hypersoft set (IVFHSS), which has proven effective in decision-making (DM). However, the IVFHSS model lacks a mechanism to incorporate the degree of acceptance of DM opinions, which is crucial for accurate decision-making. To overcome this limitation, our work aims to develop a novel hyperstructure called a possibility interval-valued fuzzy hypersoft set (PIVFHS-set). We begin by introducing essential operations and their properties, such as PIVFHS-subset, PIVFHS-null set, PIVFHS-absolute set, and complement of a PIVFHS-set. These concepts are illustrated through numerical examples to demonstrate their practical applications. Next, we delve into set-theoretic operations of PIVFHS sets, including union, intersection, AND, OR, and relevant laws. These operations are further elucidated through numerical examples, matrix representations, and graphical illustrations. Additionally, we present two algorithms based on AND and OR operations, providing step-by-step explanations and showcasing their effectiveness through illustrative examples. Furthermore, we introduce a similarity measure to facilitate pattern recognition in PIVFHS-sets, aiding users in recruitment processes. Alongside an analytical study of the advantages and disadvantages of this model, we provide suggestions for future research based on the identified limitations. © 2025, University of New Mexico. All rights reserved.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Multi-granularity feature intersection learning for visible-infrared person re-identification

引用

Complex and Intelligent Systems 2025年第7期11卷 1-14页

作者： Chan, Sixian Wang, Jie Cui, Jiaao Hu, Jie Li, Zhuorong Mao, Jiafa College of Computer Science and Technology Zhejiang University of Technology Hangzhou 310023 China Key Laboratory of Intelligent Informatics for Safety & Emergency of Zhejiang Province Wenzhou University Wenzhou 325035 China School of Computer and Computing Science Hangzhou City University Hangzhou 310015 China

This paper proposes a multi-granularity feature intersection network (MGFINet) for visible-infrared person re-identification (VI-ReID). VI-ReID aims to retrieve images of the same pedestrian from different spectral cameras. The key challenge is to extract pedestrian descriptions with both inter-class discriminability and intra-class similarity. Previous methods ignore the potential loss of details during representation extraction and the presence of data bias in the metric function, limiting further improvements in retrieval performance. Meanwhile, the discrepancy regarding how to calculate the loss for representation learning and metric learning also affects the model’s training. To address the above issues, MGFINet consists of three components: a hierarchical part pooling method (HPP), a hierarchical part restriction method (HPC), and a feature intersection (FI) loss. HPP adopts a hierarchical framework to extract multi-granularity pedestrian representations, and it performs an inter-layer fusion operation to exploit the high-resolution information from shallow layers and the semantic representability from deep layers. Meanwhile, HPP employs part pooling with different step sizes to capture pedestrian details in each layer. Next, HPC spreads the identity loss across all layers to reduce the distance for gradient backpropagation and further optimize fine-grained features in shallow layers. Besides, FI loss combines representation and metric learning by incorporating hyperparameters of classifiers into metric learning, mitigating data bias and reducing the gap between the two learning processes. Finally, extensive experiments evaluated on two public datasets, SYSU-MM01 and RegDB demonstrate the effectiveness of the proposed method. © The Author(s) 2025.

关键词： Metric learning Multi-granularity Representation learning VI-ReID

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：