检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3579-3594页

作者： Chakraborty, Prabuddha Bhunia, Swarup University of Maine Department of Electrical & Computer Engineering OronoME04469 United States University of Florida Department of Electrical & Computer Engineering GainesvilleFL32603 United States

Edge computing devices in Internet-of-Things (IoT) systems are being widely used in diverse application domains including industrial automation, surveillance, and smart housing. These applications typically employ a large array of sensors, store a high volume of data, and search within the stored data for specific patterns using machine intelligence. Due to this heavy reliance on data in these applications, optimizing the memory performance in edge devices has become an important research focus. In this work, we note (based on some preliminary quantitative studies) that the memory requirements of such application-specific systems tend to differ drastically from traditional general-purpose computing systems. Inspired by these findings and also through drawing inspiration from the human brain (which excels at being highly adaptive), we design a digital memory framework that can continually adapt to the specific needs of different edge devices. This adaption is made possible through a continual reinforcement-based learning methodology, and it aims at creating a digital memory framework that is always self-aware of the data it hold and queries being made. Through a methodical implementation of the framework, we demonstrate its effectiveness for different use-cases, settings, and hyperparameters in comparison with traditional content-addressable memory. © 2020 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Performance *** Comparative Analysis of Multimodal Bilinear Pooling Fusion Approaches for Deep Learning-Based Visual Arabic-Question Answering Systems

引用

computer Modeling in engineering & sciences 2025年第4期143卷 373-411页

作者： Sarah M.Kamel Mai A.Fadel Lamiaa Elrefaei Shimaa I.Hassan Electrical Engineering Department Faculty of Engineering at ShoubraBenha UniversityCairo11629Egypt Computer Science Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer and Systems Engineering Faculty of Engineering and TechnologyBadr University in Cairo(BUC)Cairo11829Egypt Communication Systems Engineering Department Faculty of EngineeringBenha National UniversityObour11846QalyubiaEgypt

Visual question answering(VQA)is a multimodal task,involving a deep understanding of the image scene and the question’s meaning and capturing the relevant correlations between both modalities to infer the appropriate *** this paper,we propose a VQA system intended to answer yes/no questions about real-world images,in *** support a robust VQA system,we work in two directions:(1)Using deep neural networks to semantically represent the given image and question in a fine-grainedmanner,namely ResNet-152 and Gated Recurrent Units(GRU).(2)Studying the role of the utilizedmultimodal bilinear pooling fusion technique in the *** the model complexity and the overall model *** fusion techniques could significantly increase the model complexity,which seriously limits their applicability for VQA *** far,there is no evidence of how efficient these multimodal bilinear pooling fusion techniques are for VQA systems dedicated to yes/no ***,a comparative analysis is conducted between eight bilinear pooling fusion techniques,in terms of their ability to reduce themodel complexity and improve themodel performance in this case of VQA *** indicate that these multimodal bilinear pooling fusion techniques have improved the VQA model’s performance,until reaching the best performance of 89.25%.Further,experiments have proven that the number of answers in the developed VQA system is a critical factor that *** the effectiveness of these multimodal bilinear pooling techniques in achieving their main objective of reducing the model *** Multimodal Local Perception Bilinear Pooling(MLPB)technique has shown the best balance between the model complexity and its performance,for VQA systems designed to answer yes/no questions.

关键词： Arabic-VQA deep learning-based VQA deep multimodal information fusion multimodal representation learning VQA of yes/no questions VQA model complexity VQA model performance performance-complexity trade-off

来源：评论

学校读者我要写书评

暂无评论

Developing a Secure Framework Using Feature Selection and Attack Detection Technique

引用

computers, Materials & Continua 2023年第2期74卷 4183-4201页

作者： Mahima Dahiya Nitin Nitin Department of Electrical Engineering and Computer Science College of Engineering and Applied ScienceUniversity of Cincinnati2600 Clifton AveCincinnatiOH 45221USA

Intrusion detection is critical to guaranteeing the safety of the data in the *** though,since Internet commerce has grown at a breakneck pace,network traffic kinds are rising daily,and network behavior characteristics are becoming increasingly complicated,posing significant hurdles to intrusion *** challenges in terms of false positives,false negatives,low detection accuracy,high running time,adversarial attacks,uncertain attacks,*** to insecure Intrusion Detection System(IDS).To offset the existing challenge,the work has developed a secure Data Mining Intrusion detection system(DataMIDS)framework using Functional Perturbation(FP)feature selection and Bengio Nesterov Momentum-based Tuned Generative Adversarial Network(BNM-tGAN)attack detection *** data mining-based framework provides shallow learning of features and emphasizes feature engineering as well as ***,the IDS data are analyzed for missing values based on the Marginal Likelihood Fisher Information Matrix technique(MLFIMT)that identifies the relationship among the missing values and attack *** on the analysis,the missing values are classified as Missing Completely at Random(MCAR),Missing at random(MAR),Missing Not at Random(MNAR),and handled according to the ***,categorical features are handled followed by feature scaling using Absolute Median Division based Robust Scalar(AMDRS)and the Handling of the imbalanced *** selection of relevant features is initiated using FP that uses‘3’Feature Selection(FS)techniques i.e.,Inverse Chi Square based Flamingo Search(ICS-FSO)wrapper method,Hyperparameter Tuned Threshold based Decision Tree(HpTT-DT)embedded method,and Xavier Normal Distribution based Relief(XavND-Relief)filter ***,the selected features are trained and tested for detecting attacks using *** Experimental analysis demonstrates that the introduced DataMIDS framework produces an accurate diagnosis about the

关键词： Cyber security data mining intrusion detection system(DataMIDS) marginal likelihood fisher information matrix(MLFIM) absolute median deviation based robust scalar(AMD-RS) functional perturbation(FP) inverse chi square based flamingo search optimization(ICS-FSO) hyperparameter tuned threshold based decision tree(HpTT-DT) Xavier normal distribution based relief(XavND-relief) and Bengio Nesterov momentum-based tuned generative adversarial network(BNM-tGAN)

来源：评论

学校读者我要写书评

暂无评论

Low-profile,low sidelobe array antenna with ultrawide beam coverage for UAV communication

引用

Chinese Journal of Aeronautics 2025年第1期38卷 444-454页

作者： Mei LI Zhiliang SHANG Lin PU Ming-Chun TANG Lei ZHU School of Microelectronics and Communication Engineering Chongqing UniversityChongqing 400044China Department of Electrical and Computer Engineering University of MacaoMacao SAR 999078China

This paper presents a design method to implement an antenna array characterized by ultra-wide beam coverage,low profile,and low Sidelobe Level(SLL)for the application of Unmanned Aerial Vehicle(UAV)air-to-ground *** array consists of ten broadside-radiating,ultrawide-beamwidth elements that are cascaded by a central-symmetry series-fed network with tapered currents following Dolph-Chebyshev distribution to provide low ***,an innovative design of end-fire Huygens source antenna that is compatible with metal ground is presented.A low-profile,half-mode Microstrip Patch Antenna(MPA)is utilized to serve as the magnetic dipole and a monopole is utilized to serves as the electric dipole,constructing the compact,end-fire,grounded Huygens source ***,two opposite-oriented end-fire Huygens source antennas are seamlessly integrated into a single antenna element in the form of monopole-loaded MPA to accomplish the ultrawide,broadside-radiating *** consideration has been applied into the design of series-fed network as well as antenna element to compensate the adverse coupling effects between elements on the radiation *** indicates an ultrawide Half-Power Beamwidth(HPBW)of 161°and a low SLL of-25 dB with a high gain of 12 d Bi under a single-layer *** concurrent ultrawide beamwidth and low SLL make it particularly attractive for applications of UAV air-to-ground communication.

关键词： Array antenna Broad beam Fan beam Low sidelobe level Chebyshev synthesis UAV communication

来源：评论

学校读者我要写书评

暂无评论

Enhancing Arabic Cyberbullying Detection with End-to-End Transformer Model

引用

computer Modeling in engineering & sciences 2024年第11期141卷 1651-1671页

作者： Mohamed A.Mahdi Suliman Mohamed Fati Mohamed A.G.Hazber Shahanawaj Ahamad Sawsan A.Saad Information and Computer Science Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Information Systems Department College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Software Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Computer Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia

Cyberbullying,a critical concern for digital safety,necessitates effective linguistic analysis tools that can navigate the complexities of language use in online *** tackle this challenge,our study introduces a new approach employing Bidirectional Encoder Representations from the Transformers(BERT)base model(cased),originally pretrained in *** model is uniquely adapted to recognize the intricate nuances of Arabic online communication,a key aspect often overlooked in conventional cyberbullying detection *** model is an end-to-end solution that has been fine-tuned on a diverse dataset of Arabic social media(SM)tweets showing a notable increase in detection accuracy and sensitivity compared to existing *** results on a diverse Arabic dataset collected from the‘X platform’demonstrate a notable increase in detection accuracy and sensitivity compared to existing methods.E-BERT shows a substantial improvement in performance,evidenced by an accuracy of 98.45%,precision of 99.17%,recall of 99.10%,and an F1 score of 99.14%.The proposed E-BERT not only addresses a critical gap in cyberbullying detection in Arabic online forums but also sets a precedent for applying cross-lingual pretrained models in regional language applications,offering a scalable and effective framework for enhancing online safety across Arabic-speaking communities.

关键词： Cyberbullying offensive detection Bidirectional Encoder Representations from the Transformers(BERT) continuous bag of words Social Media natural language processing

来源：评论

学校读者我要写书评

暂无评论

A verifiable multi-secret image sharing scheme based on DNA encryption

引用

Multimedia Tools and Applications 2025年第4期84卷 1967-1983页

作者： Chattopadhyay, Arup Kumar Saha, Sanchita Nag, Amitava Singh, Jyoti Prakash Department of Computer Science and Engineering Central Institute of Technology Kokrajhar Kokrajhar India Department of Computer Science and Engineering National Institute of Technology Patna Bihar Patna India

A multi-secret image sharing (MSIS) scheme facilitates the secure distribution of multiple images among a group of participants. Several MSIS schemes have been proposed with a (n, n) structure that encodes secret input images into n share images. This encoding ensures that if a subset of participants collude, no information about the secret images can be revealed. The secret images can only be recovered if all participants cooperate. Most of these schemes are built using basic Boolean operations, primarily XOR operations. MSIS schemes that rely on Boolean logic offer various benefits compared to other methods, such as the ability to recover data without any loss, no increase in pixel size, and efficient computation. This article presents a verifiable MSIS scheme that relies on a secure two-variable one-way function and a secure hash function. The scheme allows for independent verification of both the dealer and the participants to detect any cheating attempts. The proposed scheme utilizes the Deoxyribonucleic acid (DNA) encryption technique to leverage the inherent benefits of DNA computing, such as enhanced security, fast computation, minimal storage needs, and low power usage. The share images produced by the proposed scheme exhibit an average entropy of 7.99, indicating that the generated 8-bit share images are completely random. Additionally, the correlation coefficient is approximately 0.005, suggesting that neighboring pixels in the images are not related to each other. The proposed scheme can detect any instance of cheating, whether it is done by the dealer or by a participant. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

Optimizing Image Retrieval in Cloud Servers with TN-AGW: A Secure and Efficient Approach

引用

Journal of The Institution of Engineers (India): Series B 2025年第2期106卷 459-473页

作者： Ponnuviji, N.P. Nirmala, G. Kokila, M. L. Sworna Priyadharshini, S. Indra Department of Computer Science and Engineering RMK College of Engineering and Technology Puduvoyal Thiruvallur India Department of Computer Science and Engineering RMD Engineering College Chennai India Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nādu Kattankulathur Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

The increasing use of cloud-based image storage and retrieval systems has made ensuring security and efficiency crucial. The security enhancement of image retrieval and image archival in cloud computing has received considerable attention in transmitting data and ensuring data confidentiality among cloud servers and users. Various traditional image retrieval techniques regarding security have developed in recent years but they do not apply to large-scale environments. This paper introduces a new approach called Triple network-based adaptive grey wolf (TN-AGW) to address these challenges. The TN-AGW framework combines the adaptability of the Grey Wolf Optimization (GWO) algorithm with the resilience of Triple Network (TN) to enhance image retrieval in cloud servers while maintaining robust security measures. By using adaptive mechanisms, TN-AGW dynamically adjusts its parameters to improve the efficiency of image retrieval processes, reducing latency and utilization of resources. However, the image retrieval process is efficiently performed by a triple network and the parameters employed in the network are optimized by Adaptive Grey Wolf (AGW) optimization. Imputation of missing values, Min–Max normalization, and Z-score standardization processes are used to preprocess the images. The image extraction process is undertaken by a modified convolutional neural network (MCNN) approach. Moreover, input images are taken from datasets such as the Landsat 8 dataset and the Moderate Resolution Imaging Spectroradiometer (MODIS) dataset is employed for image retrieval. Further, the performance such as accuracy, precision, recall, specificity, F1-score, and false alarm rate (FAR) is evaluated, the value of accuracy reaches 98.1%, the precision of 97.2%, recall of 96.1%, and specificity of 917.2% respectively. Also, the convergence speed is enhanced in this TN-AGW approach. Therefore, the proposed TN-AGW approach achieves greater efficiency in image retrieving than other existing

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Robotic FDM for free-form fabrication: evaluating adaptive non-planar slicing with different contour methods

引用

Rapid Prototyping Journal 2025年第11期31卷 160-178页

作者： Furlan, Valentina Insero, Federico Giberti, Hermes Department of Electrical Computer and Biomedical Engineering Università di Pavia Pavia Italy

Purpose: This study aims to investigate and compare three nonplanar (NP) slicing algorithms. The algorithms aim to control the layer thickness variation (LTV), which is a common issue in supportless fabrication of free-form parts. The comparison underlines the differences between theoretical and real scenarios, resulting in guidelines for toolpath generation of complex objects. Design/methodology/approach: The algorithm comparison uses a representative complex geometry, i.e. the quarter of torus. It presents an increasing overhang and constant curvature. It is represented using a parametric definition in the first two algorithms and by triangular meshes as the real scenario. The algorithms work on the contouring stage, whereas a B-spline approach is used to build the inner side of layers. Constant layer thickness (LT) is imposed, and an adaptive approach is adopted to avoid over-extrusion. Three algorithms are validated with a robotized fused deposition modeling system. LTs are measured on cross-sectioned samples and compared with the theoretical cases. Findings: The results show that two algorithms can provide an LTV of about 0% on the contour. Nevertheless, the theoretical results on the inner side are divergent from the previous evidence, moving on to higher LTV (approximately 90%). The need for an adaptive approach is demonstrated, resulting in an LTV reduction (approximately 30%). Printed parts present the same trends of theoretical results confirming the algorithms’ capabilities. Originality/value: The work shows, for the first time, a comparison between NP slicing techniques. The LTV problem in hollow and filled components is analyzed through theoretical and experimental evidence. The results are promising for supportless fabrication of free-form parts. © 2025, Valentina Furlan, Federico Insero and Hermes Giberti.

关键词： Fabrication

来源：评论

学校读者我要写书评

暂无评论

Consensus-relevance kNN and covariate shift mitigation

引用

MACHINE LEARNING 2024年第1期113卷 325-353页

作者： Kalpakis, Konstantinos Computer Science and Electrical Engineering Department University of Maryland Baltimore County 1000 Hilltop Circle Baltimore MD 21250 USA

Classification and regression algorithms based on k-nearest neighbors (kNN) are often ranked among the top-10 Machine learning algorithms, due to their performance, flexibility, interpretability, non-parametric nature, and computational efficiency. Nevertheless, in existing kNN algorithms, the kNN radius, which plays a major role in the quality of kNN estimates, is independent of any weights associated with the training samples in a kNN-neighborhood. This omission, besides limiting the performance and flexibility of kNN, causes difficulties in correcting for covariate shift (e.g., selection bias) in the training data, taking advantage of unlabeled data, domain adaptation and transfer learning. We propose a new weighted kNN algorithm that, given training samples, each associated with two weights, called consensus and relevance (which may depend on the query on hand as well), and a request for an estimate of the posterior at a query, works as follows. First, it determines the kNN neighborhood as the training samples within the kth relevance-weighted order statistic of the distances of the training samples from the query. Second, it uses the training samples in this neighborhood to produce the desired estimate of the posterior (output label or value) via consensus-weighted aggregation as in existing kNN rules. Furthermore, we show that kNN algorithms are affected by covariate shift, and that the commonly used sample reweighing technique does not correct covariate shift in existing kNN algorithms. We then show how to mitigate covariate shift in kNN decision rules by using instead our proposed consensus-relevance kNN algorithm with relevance weights determined by the amount of covariate shift (e.g., the ratio of sample probability densities before and after the shift). Finally, we provide experimental results, using 197 real datasets, demonstrating that the proposed approach is slightly better (in terms of F-1 score) on average than competing benchmark approaches for mit

关键词： Nearest neighbors Selection bias Covariate shift Density estimation kNN learners

来源：评论

学校读者我要写书评

暂无评论

xCViT:Improved Vision Transformer Network with Fusion of CNN and Xception for Skin Disease Recognition with Explainable AI

引用

computers, Materials & Continua 2025年第4期83卷 1367-1398页

作者： Armughan Ali Hooria Shahbaz Robertas Damaševicius Department of Electrical Engineering Wah Engineering CollegeUniversity of WahWah Cantt47040Pakistan Department of Computer Science HITEC UniversityTaxila47080Pakistan Department of Applied Informatics Vytautas Magnus UniversityKaunas44309Lithuania

Skin cancer is the most prevalent cancer globally,primarily due to extensive exposure to Ultraviolet(UV)*** identification of skin cancer enhances the likelihood of effective treatment,as delays may lead to severe tumor *** study proposes a novel hybrid deep learning strategy to address the complex issue of skin cancer diagnosis,with an architecture that integrates a Vision Transformer,a bespoke convolutional neural network(CNN),and an Xception *** were evaluated using two benchmark datasets,HAM10000 and Skin Cancer *** the HAM10000,the model achieves a precision of 95.46%,an accuracy of 96.74%,a recall of 96.27%,specificity of 96.00%and an F1-Score of 95.86%.It obtains an accuracy of 93.19%,a precision of 93.25%,a recall of 92.80%,a specificity of 92.89%and an F1-Score of 93.19%on the Skin Cancer ISIC *** findings demonstrate that the model that was proposed is robust and trustworthy when it comes to the classification of skin *** addition,the utilization of Explainable AI techniques,such as Grad-CAM visualizations,assists in highlighting the most significant lesion areas that have an impact on the decisions that are made by the model.

关键词： Skin lesions vision transformer CNN Xception deep learning network fusion explainable AI Grad-CAM skin cancer detection

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：