检索结果-内蒙古大学图书馆

computer vision-based six layered ConvNeural network to recognize sign language for both numeral and alphabet signs

Biomimetic Intelligence & Robotics 2024年第1期4卷 45-58页

作者： Muhammad Aminur Rahaman Kabiratun Ummi Oyshe Prothoma Khan Chowdhury Tanoy Debnath Anichur Rahman Md.Saikat Islam Khan Department of Computer Science and Engineering Green University of BangladeshDhakaBangladesh Department of Computer Science and Engineering National Institute of Textile Engineering and Research(NITER)Constituent Institute of Dhaka UniversityDhakaBangladesh Department of Computer Science and Engineering Mawlana Bhashani Science and Technology UniversityTangailBangladesh

People who have trouble communicating verbally are often dependent on sign language,which can be difficult for most people to understand,making interaction with them a difficult *** Sign Language Recognition(SLR)system takes an input expression from a hearing or speaking-impaired person and outputs it in the form of text or voice to a normal *** existing study related to the Sign Language Recognition system has some drawbacks,such as a lack of large datasets and datasets with a range of backgrounds,skin tones,and *** research efficiently focuses on Sign Language Recognition to overcome previous *** importantly,we use our proposed Convolutional Neural Network(CNN)model,“ConvNeural”,in order to train our ***,we develop our own datasets,“BdSL_OPSA22_STATIC1”and“BdSL_OPSA22_STATIC2”,both of which have ambiguous backgrounds.“BdSL_OPSA22_STATIC1”and“BdSL_OPSA22_STATIC2”both include images of Bangla characters and numerals,a total of 24,615 and 8437 images,***“ConvNeural”model outperforms the pre-trained models with accuracy of 98.38%for“BdSL_OPSA22_STATIC1”and 92.78%for“BdSL_OPSA22_STATIC2”.For“BdSL_OPSA22_STATIC1”dataset,we get precision,recall,F1-score,sensitivity and specificity of 96%,95%,95%,99.31%,and 95.78%***,in case of“BdSL_OPSA22_STATIC2”dataset,we achieve precision,recall,F1-score,sensitivity and specificity of 90%,88%,88%,100%,and 100%respectively.

关键词： Conv NeuralSign language CNN Static Feature extraction Convolution2D Fully connected layer Dropout

来源：评论

学校读者我要写书评

暂无评论

How far are we to GPT-4V?Closing the gap to commercial multimodal models with open-source suites

引用

science China(Information sciences) 2024年第12期67卷 5-22页

作者： Zhe CHEN Weiyun WANG Hao TIAN Shenglong YE Zhangwei GAO Erfei CUI Wenwen TONG Kongzhi HU Jiapeng LUO Zheng MA Ji MA Jiaqi WANG Xiaoyi DONG Hang YAN Hewei GUO Conghui HE Botian SHI Zhenjiang JIN Chao XU Bin WANG Xingjian WEI Wei LI Wenjian ZHANG Bo ZHANG Pinlong CAI Licheng WEN Xiangchao YAN Min DOU Lewei LU Xizhou ZHU Tong LU Dahua LIN Yu QIAO Jifeng DAI Wenhai WANG State Key Laboratory for Novel Software Technology Nanjing University Shanghai AI Laboratory School of Computer Science Fudan University SenseTime Research Department of Information Engineering The Chinese University of Hong Kong Department of Electronic Engineering Tsinghua University

In this paper, we introduce InternVL 1.5, an open-source multimodal large language model(MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. We introduce three simple improvements.(1) Strong vision encoder: we explored a continuous learning strategy for the large-scale vision foundation model — InternViT-6B, boosting its visual understanding capabilities, and making it can be transferred and reused in different LLMs.(2) Dynamic high-resolution: we divide images into tiles ranging from 1 to 40 of 448×448 pixels according to the aspect ratio and resolution of the input images, which supports up to 4K resolution input.(3) High-quality bilingual dataset: we carefully collected a high-quality bilingual dataset that covers common scenes, document images,and annotated them with English and Chinese question-answer pairs, significantly enhancing performance in optical character recognition(OCR) and Chinese-related tasks. We evaluate InternVL 1.5 through a series of benchmarks and comparative studies. Compared to both open-source and proprietary commercial models, InternVL 1.5 shows competitive performance, achieving state-of-the-art results in 8 of 18 multimodal benchmarks. Code and models are available at https://***/OpenGVLab/InternVL.

关键词： multimodal model open-source vision encoder dynamic resolution bilingual dataset

来源：评论

学校读者我要写书评

暂无评论

An aspect-based sentiment analysis model for Arabic game reviews based on hybrid transformers models

引用

Neural Computing and Applications 2025年 1-23页

作者： Hammad, Mahmoud AbuEnnab, Noor Al-Refai, Mohammed IT Department Ajman University Ajman United Arab Emirates Software Engineering Department Jordan University of Science and Technology Irbid Jordan Computer Science Department Jordan University of Science and Technology Irbid Jordan

Aspect-based sentiment analysis (ABSA) is a natural language processing (NLP) technique to determine the various sentiments of a customer in a single comment regarding different aspects. The increasing online data content generated by interested customers and reviewers motivated researchers and data scientists to conduct ABSA. ABSA has become increasingly popular in recent years due to its versatility in e-commerce, social media, and customer feedback analysis. However, ABSA faces several significant challenges, including determining the aspects and their sentiment polarities (positive, negative, or neutral) in a given text. Moreover, ABSA faces particular challenges in non-English languages such as Arabic due to the lack of resources and mature models. Typically, ABSA tackles one or more of the ABSA research tasks: (T1) aspect term extraction, (T2) aspect term polarity, (T3) aspect category identification, and (T4) aspect category polarity. To identify the aspects and their corresponding sentiment polarities in a given text, accurate and efficient NLP techniques are required. Despite growing interest in Arabic ABSA, the lack of annotated datasets and pre-trained models has hindered its development. In this research, we have collected a dataset of Arabic game reviews and annotated them using three annotators, and then we trained an ABSA deep learning model based on the BERT pre-trained model combined with zero-shot learning (ZSL) to tackle all the four aforementioned tasks. Our best performing model achieved a high accuracy on all four tasks with an accuracy of 91.61% on T1, 90.99% on T2, 79.08% on T3, and 88.17% on T4. Finally, we compared our model’s accuracy with the state-of-the-art Arabic-based ABSA models on different datasets. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

A Novel Certificateless Signature-based Access Control Scheme for Named In-network Computing Service

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第1期52卷 38-45页

作者： Li, Wanji Liu, Qiangbin Zhu, Yi School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China School of Computer Science and Communication Engineering the Dean of Department of Communication Engineering Jiangsu University Zhenjiang China

Named in-network computing service (NICS) is a potential computing paradigm emerged recently. Benefitted from the characteristics of named addressing and routing, NICS can be flexibly deployed on NDN router side and provide nearby computing service to Internet users. But the NICS feature of dynamic deployment also causes serious security risk of access control. How to independently check out the subscription relationship between requester and requested computing service on NICS side become a challenge. To solve this problem, we propose a novel certificateless signature-based access control scheme (CS-ACS) in this paper. In CS-ACS, the entire user public-private key pairs consist of two parts, user side and source server side. Where, the user public-private key pairs (server side) are generated according to the user ID, service subscription relationship and subscription expiration time. Based on this special design, when authorized user signs the interest packet of invoking specific service using its private key, the NICS can verify the signature then check out whether the requester is a valid subscriber and the subscription is expired or not. Simulation results show that, comparing with fundamental solutions, CS-ACS can avoid extra secret key storage cost on NICS side and markedly shorten authentication delay. © (2025), (International Association of Engineers). All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

REAL-TIME GLUCOSE MONITORING SYSTEM AND DIETARY RECOMMENDATIONS FOR DIABETES MELLITUS USING FOG COMPUTING

引用

Telecommunications and Radio engineering (English translation of Elektrosvyaz and Radiotekhnika) 2025年第5期84卷 55-67页

作者： Sathish, N. Elangovan, D. Nagalakshmi, R. Suresh, G. Chitra, Devi D. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Information Technology Saveetha Engineering College Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Artificial Intelligence and Data Science Kings Engineering College Sriperumbudur India Department of Computer Science And Engineering S.A. Engineering College Chennai India

This systematic review gave special attention to diabetes and the advancements in food and nutrition needed to prevent or manage diabetes in all its forms. There are two main forms of diabetes mellitus: Type 1 (T1D) and Type 2 (T2D). The loss of beta cells brought on by an autoimmune reaction causes the pancreas to be unable to produce enough insulin, which leads to Type 1 diabetes. A deficiency of insulin could arise as the illness worsens. The most frequent cause is a combination of excessive body weight and inadequate exercise. Currently, 90–95% of patients have Type 2 diabetes mellitus (T2DM). Age-specific normal blood sugar ranges exist and knowing them is crucial for determining a target blood sugar level that is both healthy and appropriate. The main takeaway is that diet regimens ought to be tailored to the patient’s requirements and should account for their capacity for change. Carbohydrates are the nutrients that have the biggest impact on the rise in blood glucose. In this paper, we have proposed a novel method for glucose monitoring and diet recommendations for diabetic patients using fog computing. A paradigm known as fog computing makes use of the benefits that come from using both cloud and edge devices to support modern computing systems by offering high-quality services, cutting latency, facilitating mobility, supporting multi-tenancy, and many other features. © 2025 by Begell House, Inc.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

An active learning framework for adversarial training of deep neural networks

引用

Neural Computing and Applications 2025年第9期37卷 6849-6876页

作者： Ghosh, Susmita Chatterjee, Abhiroop Fiondella, Lance Department of Computer Science and Engineering Jadavpur University Kolkata India Department of Electrical and Computer Engineering University of Massachusetts Dartmouth United States

This article introduces a novel approach to bolster the robustness of Deep Neural Network (DNN) models against adversarial attacks named "Targeted Adversarial Resilience Learning (TARL)". The initial evaluation of a baseline DNN model reveals a significant accuracy decline when subjected to adversarial examples generated through techniques like FGSM, PGD, Carlini Wagner, and DeepFool attacks. To address this vulnerability, the article proposes an active learning framework, wherein the model iteratively identifies and learns from the most uncertain and misclassified instances. The key components of this approach include uncertainty estimation score in predicting the class of the input sample, selecting challenging samples based on this uncertainty score, labeling these challenging examples and augmenting them into the training set, and thereafter retraining the model with the expanded training set. The iterative active learning process, governed by parameters such as the number of iterations and batch size, demonstrates the potential to systematically enhance the resilience of DNN against adversarial threats. The proposed methodology has been investigated on several popular datasets such as the SARS-CoV-2 CT scan, MNIST, CIFAR-10, and Caltech-101, and demonstrated to be effective. Experiments illustrate that the learning framework improves the adversarial accuracies from 17.4% to 98.71% for the SARS-CoV-2 dataset, from 8.4% to 99.89% for the MNIST dataset, 1.6% to 78.84% for the CIFAR-10, and 12% to 92.92% for Caltech-101. Further, comparative analysis with several state-of-the-art methods suggests that the proposed framework offers superior defense against various attack methods and offers promising defensive mechanisms to deep neural networks. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

3D AIR-UNet: attention–inception–residual-based U-Net for brain tumor segmentation from multimodal MRI

引用

Neural Computing and Applications 2025年 1-22页

作者： Sharma, Vani Kumar, Mohit Yadav, Arun Kumar Department of Computer Science & Engineering NIT Hamirpur Hamirpur India

Brain tumors are ranked highly among the leading causes of cancer-related fatalities. Precise segmentation and quantitative assessment of brain tumors are crucial for effective diagnosis and treatment planning. However, manual segmentation is often laborious, challenging, and prone to errors, necessitating the creation of a fully automated brain tumor segmentation approach. This article introduces "3D AIR-UNet," an end-to-end architecture aiming to automate the segmentation of brain tumors from MRI data. The presented model employs an encoder–decoder architecture, with carefully constructed inception–residual units replacing the usual convolution layers used in UNet. The inception–residual block combines the advantages of inception modules and residual connections to provide a powerful feature extraction mechanism. It captures extensive multi-scale information by combining different filter sizes. This block’s design is effective at handling complex 3D data patterns, making it a vital component of sophisticated neural network architecture. Moreover, an attention mechanism further boosts the capability of the model to differentiate between tumor and non-tumor regions, leading to improved localization and contextual understanding. Additionally, skip connections are employed between the encoder and decoder at each level to speed up the training process. The proposed 3D AIR-UNet architecture demonstrated encouraging outcomes, attaining dice scores of 0.9218 for the whole tumor, 0.9019 for the tumor core, and 0.8788 for the enhancing tumor when evaluated on the BraTS 2020 dataset. Comparative analysis with contemporary methods suggests that 3D AIR-UNet notably enhances the segmentation accuracy of brain tumor subregions. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Penetration Testing Operating Systems: Exploiting Vulnerabilities

Penetration Testing Operating Systems: Exploiting Vulnerabil...

引用

2024 IEEE International Conference on Communications, Computing, Cybersecurity and Informatics, CCCI 2024

作者： Gardner, Evan Singh, Gurmeet Qu, Weihao Software Engineering Monmouth University Department of Computer Science United States

ISBN: (纸本)9798350349832

The safeguarding of critical data stored on devices such as phones, computers, and tablets against unauthorized access has emerged as a central concern in modern society. Along with the increasing reliance on these devices for both productivity and personal affairs, the protection of the vast collections of sensitive information becomes crucial. Information safety against unauthorized access is a critical area in cybersecurity which is addressed through the discipline of penetration testing. This practice involves security researchers simulating adversarial attacks to evaluate the defenses of various technological systems, including web applications, operating systems, and networks, with the goal of protecting sensitive data from malicious actors. This research specifically focuses on the study of penetration testing operating systems without requiring login credentials, employing techniques such as command combinations in languages like BASH within the terminal to gain access to administrative accounts. Our further studies explore the performance of emulating keystrokes when these command combinations are used in conjunction with penetration testing devices, such as a USB Rubber Ducky, focusing on optimizing speed and efficiency. This research uncovers significant security vulnerabilities that, if exploited, could result in severe consequences not only for individual devices but also for entire networks and critical infrastructures, including core businesses, healthcare systems, schools, and government agencies. By identifying and mitigating these vulnerabilities, we contribute to strengthening security protocols, such as implementing system administration enhancements that prevent unauthorized access to the root terminal. In this way, our work bolsters efforts to protect digital systems against evolving cyber threats, ensuring the safety and integrity of both individual and collective digital operations. © 2024 IEEE.

关键词： Critical infrastructures

来源：评论

学校读者我要写书评

暂无评论

COVID-19 emergency decision-making using q-rung linear diophantine fuzzy set,differential evolutionary and evidential reasoning techniques

引用

Applied Mathematics(A Journal of Chinese Universities) 2025年第1期40卷 182-206页

作者： G Punnam Chander Sujit Das Department of Computer science and Engineering National Institute of TechnologyWarangal 506004India

In this paper,a robust and consistent COVID-19 emergency decision-making approach is proposed based on q-rung linear diophantine fuzzy set(q-RLDFS),differential evolutionary(DE)optimization principles,and evidential reasoning(ER)*** proposed approach uses q-RLDFS in order to represent the evaluating values of the alternatives corresponding to the *** optimization is used to obtain the optimal weights of the attributes,and ER methodology is used to compute the aggregated q-rung linear diophantine fuzzy values(q-RLDFVs)of each *** the score values of alternatives are computed based on the aggregated *** alternative with the maximum score value is selected as a better *** applicability of the proposed approach has been illustrated in COVID-19 emergency decision-making system and sustainable energy planning ***,we have validated the proposed approach with a numerical ***,a comparative study is provided with the existing models,where the proposed approach is found to be robust to perform better and consistent in uncertain environments.

关键词： COVID-19 q-rung linear diophantine fuzzy set differential evolutionary evidential reasoning decision-making

来源：评论

学校读者我要写书评

暂无评论

Controllable multi-domain semantic artwork synthesis

引用

Computational Visual Media 2024年第2期10卷 355-373页

作者： Yuantian Huang Satoshi Iizuka Edgar Simo-Serra Kazuhiro Fukui Department of Computer Science University of TsukubaTsukuba 305-8577Japan Department of Computer Science and Engineering Waseda UniversityTokyo 169-8050Japan

We present a novel framework for the multidomain synthesis of artworks from semantic *** of the main limitations of this challenging task is the lack of publicly available segmentation datasets for art *** address this problem,we propose a dataset called ArtSem that contains 40,000 images of artwork from four different domains,with their corresponding semantic label *** first extracted semantic maps from landscape photography and used a conditional generative adversarial network(GAN)-based approach for generating high-quality artwork from semantic maps without requiring paired training ***,we propose an artwork-synthesis model using domain-dependent variational encoders for high-quality multi-domain ***,the model was improved and complemented with a simple but effective normalization method based on jointly normalizing semantics and style,which we call spatially style-adaptive normalization(SSTAN).Compared to the previous methods,which only take semantic layout as the input,our model jointly learns style and semantic information representation,improving the generation quality of artistic *** results indicate that our model learned to separate the domains in the latent ***,we can perform fine-grained control of the synthesized artwork by identifying hyperplanes that separate the different ***,by combining the proposed dataset and approach,we generated user-controllable artworks of higher quality than that of existing approaches,as corroborated by quantitative metrics and a user study.

关键词： semantic artwork synthesis generative adversarial network(GAN) datasets non-photorealistic rendering

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：