检索结果-内蒙古大学图书馆

Discovery Latency Analysis of Ultra-Dense Internet-of-Things Networks

IEEE Access 2025年 13卷 79929-79939页

作者： Fatihah, Siti Nur Dewa, Gilang Raka Rayuda Kim, Jindae Sohn, Illsoo Seoul National University of Science and Technology Department of Computer Science and Engineering Seoul01811 Korea Republic of

This paper presents a comprehensive performance analysis and optimization of ultra-dense Internet-of-Things (IoT) networks. While the high density of Bluetooth Low Energy (BLE) devices in IoT networks improves wireless coverage and enhances connectivity, these coexisting devices can also lead to increased interference and collisions, degrading device discovery performance and increasing the network's overall latency. In this work, we provide a mathematical analysis of the discovery latency in densely deployed BLE networks. Our mathematical model constructs a Markov chain model that implements the impacts of packet collisions and duplication on discovery latency. Based on a thorough performance analysis, we propose a novel duplication-avoidance protocol in which BLE devices cooperatively adjust advertising and minimize the network's overall discovery latency. Our simulation results shows that the proposed novel duplication-avoidance protocol consistently reduces latency compared to the standard discovery protocol in densely deployed BLE networks, with relative improvements ranging from 7.63% to 8.16%. © 2013 IEEE.

关键词： Bluetooth

来源：评论

学校读者我要写书评

暂无评论

Dual-Channel Multiplex Graph Neural Networks for Recommendation

引用

IEEE Transactions on Knowledge and Data engineering 2025年第6期37卷 3327-3341页

作者： Li, Xiang Fu, Chaofan Zhao, Zhongying Zheng, Guangjie Huang, Chao Yu, Yanwei Dong, Junyu Ocean University of China Faculty of Information Science and Engineering Qingdao266005 China Shandong University of Science and Technology College of Computer Science and Engineering Qingdao266590 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China The University of Hong Kong Department of Computer Science Hong Kong

Effective recommender systems play a crucial role in accurately capturing user and item attributes that mirror individual preferences. Some existing recommendation techniques have started to shift their focus towards modeling various types of interactive relations between users and items in real-world recommendation scenarios, such as clicks, marking favorites, and purchases on online shopping platforms. Nevertheless, these approaches still grapple with two significant challenges: (1) Insufficient modeling and exploitation of the impact of various behavior patterns formed by multiplex relations between users and items on representation learning, and (2) ignoring the effect of different relations within behavior patterns on the target relation in recommender system scenarios. In this work, we introduce a novel recommendation framework, Dual-Channel Multiplex Graph Neural Network (DCMGNN), which addresses the aforementioned challenges. It incorporates an explicit behavior pattern representation learner to capture the behavior patterns composed of multiplex user-item interactive relations, and includes a relation chain representation learner and a relation chain-aware encoder to discover the impact of various auxiliary relations on the target relation, the dependencies between different relations, and mine the appropriate order of relations in a behavior pattern. Extensive experiments on three real-world datasets demonstrate that our DCMGNN surpasses various state-of-the-art recommendation methods. It outperforms the best baselines by 10.06% and 12.15% on average across all datasets in terms of Recall@10 and NDCG@10 respectively. The source code of our paper is available at https://***/lx970414/TKDE-DCMGNN. © 1989-2012 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Rumor detection from online social media through feature selection and machine learning

引用

Multimedia Tools and Applications 2025年 1-25页

作者： Gurrapu, Neelima Baydeti, Nagaraju Department of Computer Science and Engineering National Institute of Technology Nagaland Nagaland Chumukedima797 103 India

Recently, Rumor Spreading over Online Social Media is found as one of the serious issue, which causes severe damage to society, organization and individuals. To control the rumor spread, rumor detection is found as one of the probable solution and gained huge interest in the research community. However, most of the past methods characterize the rumormonger behavior based on their own profiles and completely neglected the reputation features. A hybrid method for rumor identification by combining the user reputation feature with other features like user features, meta-content based features and linguistic features is proposed. The major novelty lies at the representation of users through their interaction with his/her followers in different communities. The own profile based features can be evaded easily but the reputation of follows cannot be evaded easily. Totally 44 features are used to characterize each tweet and trained through different classifiers. Four classifiers namely K-Nearest Neighbour (KNN), Support Vector Machine (SVM), Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) are used to train the system and the performance is analyzed through two standard datasets namely Zubiaga and Kwon. The obtained results show that the proposed method can recognize rumor with higher F1-score. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Binary Error-Correcting Codes With Minimal Noiseless Feedback

引用

IEEE Transactions on Information Theory 2025年第5期71卷 3424-3446页

作者： Gupta, Meghal Guruswami, Venkatesan Yun Zhang, Rachel Department of Electrical and Computer Engineering BerkeleyCA94720 United States Massachusetts Institute of Technology Department of Electrical Engineering and Computer Science CambridgeMA02139 United States

In the setting of error-correcting codes with feedback, Alice wishes to communicate a k-bit message x to Bob by sending a sequence of bits over a channel while noiselessly receiving feedback from Bob. It has been long known (Berlekamp, 1964) that in this model, Bob can still correctly determine x even if ≈ 1/3 of Alice’s bits are flipped adversarially. This improves upon the classical setting without feedback, where recovery is not possible for error fractions exceeding 1/4 . In the corresponding setting of erasures rather than bit flips, feedback improves the error resilience from 1/2 -Ε to 1 - Ε for any Ε > 0 . The original feedback setting assumes that after transmitting each bit, Alice knows (via feedback) what bit Bob received. In this work, our focus in on the limited feedback model, where Bob is only allowed to send a few bits at a small number of pre-designated points in the protocol. For any desired Ε > 0 , we construct a coding scheme that tolerates a 1/3 -Ε fraction of bit flips (respectively a 1 −Ε fraction of erasures) relying only on OΕ (log k) bits of feedback from Bob sent in a fixed OΕ (1) number of rounds. We complement this with a matching lower bound showing that Ω (log k) bits of feedback are necessary to recover from an error fraction exceeding 1/4 (respectively 1/2 for erasures), and for schemes resilient to a 1/3 -Ε fraction of bit flips (respectively a 1 −Ε fraction of erasures), the number of rounds must grow as Ε → 0 © 1963-2012 IEEE.

关键词： Binary codes

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Deep Learning Approach for Optimizing Fashion Product Recommendations

引用

SN computer science 2025年第4期6卷 1-13页

作者： Buradagunta, Suvarna Balakrishna, Sivadi Department of Computer Science and Engineering Vignan’s Foundation for Science Technology and Research Guntur India Department of Advanced Computer Science and Engineering Vignan’s Foundation for Science Technology and Research Guntur India

Online shopping platforms are experiencing rapid growth, necessitating effective product recommendation systems to enhance customer satisfaction by recommending visually similar products. Traditional statistical techniques often result in less accurate recommendations. This study encompasses two primary tasks: Query Product Classification and Product Recommendation Retrieval. The initial job employs a Deep Neural Network, which takes high-level feature representations derived from the Xception and VGG16 for the query image. The features are further analyzed to forecast the category of the product. The second step is retrieving analogous products by calculating cosine similarity, facilitating the identification of visually comparable items within the product database. By leveraging diverse feature representations, the proposed approach improves the precision and relevance of recommendations. Experimental evaluations on fashion product images and Shoe datasets demonstrate significant performance improvements over existing models, achieving accuracies of 91.76%, and 82.23% respectively. These results underscore the capability of the system to provide superior recommendations in online fashion shopping scenarios, emphasizing its effectiveness in improving customer experience. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Content-based recommendation Image based recommendation system Pretrained models Recommendation systems VGG-16 Visual product recommendation Xception

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer and Brain Connectivity Patterns for Estimating Cognitive States

引用

IEEE Access 2025年 13卷 74602-74612页

作者： Chakladar, Debashis Das Luleå University of Technology Department of Computer Science Electrical and Space Engineering Luleå971 87 Sweden

The transformer model is excellent at handling time series signals (such as electroencephalography: EEG) because it can extract information from long-term dependencies effectively. This work combines binarization of EEG connectivity features, cognitive state classification using the vision transformer (ViT), and identifying graphical connectivity patterns for each cognitive state of the mental arithmetic task. The common spatial pattern (CSP) filter coefficient-based channel selection method selects the optimum EEG channels from the input channel set. Then, the Singular Value Decomposition (SVD) method is applied to prepare the binarized connectivity feature matrices, eliminating noisy connections between the optimum channels. The binarized functional-effective connectivity features are passed to the ViT model for cognitive state classification. The ViT model achieves the maximum classification accuracy of 94.86% with the phase-based connectivity feature. The proposed model improves classification accuracy by 6.15% compared to the state-of-the-art studies. This study also suggests a robust brain connectivity network to build a graphical connectivity pattern for each cognitive state. My findings of the EEG-based graphical patterns will bring further understanding of the scalp-level EEG channel patterns among different brain regions for other cognitive tasks. © 2013 IEEE.

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

A multi-level DDoS defense mechanism in container based cloud environment

引用

Cluster Computing 2025年第5期28卷 1-19页

作者： Kumar, Anmol Agarwal, Mayank Department of Computer Science and Engineering Indian Institute of Technology Patna Bihta Bihar Patna801103 India

DDoS attacks target the victim’s service availability. In this paper, we propose a multi-level DDoS defense mechanism that combines two approaches: bandwidth limitation and resource isolation. We consider requests coming from the same source IP that exceed a threshold value as suspicious and treat other requests as genuine. To achieve this goal, we serve suspicious and legitimate user requests in separate containers. We also apply the bandwidth limitation to incoming traffic from containers that serve suspicious requests, ensuring that the victim container does not create a resource contention problem. We chose three different strategies to test our proposed mechanisms: the 50-25-75 strategy, the 100-50-150 strategy, and the 150-75-225 strategy. The experimental results demonstrate that the proposed approach, when subjected to DDoS attacks, reduces the failure rate of genuine requests and maintains response times that are comparable to those under normal network conditions. When there is a DDoS attack, the proposed defense system can make the target service available 87% of the time with the 50-25-75 strategy, 70% of the time with the 100-50-150 strategy, and 85% of the time with the 150-75-225 strategy, in contrast to a single-level DDoS defense system. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Feature Reconstruction Attacks and Countermeasures of DNN Training in Vertical Federated Learning

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 2659-2669页

作者： Ye, Peng Jiang, Zhifeng Wang, Wei Li, Bo Li, Baochun Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong University of Toronto Department of Electrical and Computer Engineering TorontoM5S 1A1 Canada

Federated learning (FL) has increasingly been deployed, in its vertical form, among organizations to facilitate secure collaborative training. In vertical FL (VFL), participants hold disjoint features of the same set of sample instances. The one with labels - the active party, initiates training and interacts with other participants - the passive parties. It remains largely unknown whether and how an active party can extract private feature data owned by passive parties, especially when training deep neural network (DNN) models. This work examines the feature security problem of DNN training in VFL. We consider a DNN model partitioned between active and passive parties, where the passive party holds a subset of the input layer with some features of binary values. Though proved to be NP-hard. we demonstrate that, unless the feature dimension is exceedingly large, it remains feasible, both theoretically and practically, to launch a reconstruction attack with an efficient search-based algorithm that prevails over current feature protection. We propose a novel feature protection scheme by perturbing intermediate results and fabricated input features, which effectively misleads reconstruction attacks towards pre-specified random values. The evaluation shows it sustains feature reconstruction attack in various VFL applications with negligible impact on model performance. © 2004-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Marine Life Ecosystem Analysis Based on Climate Change Detection Using Deep Learning Algorithms

引用

Remote Sensing in Earth Systems sciences 2025年第2期8卷 545-554页

作者： Rebecca, B. Sandhya, A. Pokkuluri, Kiran Sree Kanishka, Gunipati Shaik, Khasimbee Krishna, B. Murali Department of Computer Science and Engineering Marri Laxman Reddy Institute of Technology and Management Telangana Dundigal 500043 India Department of CSE SRM Institute of Science and Technology Chennai Ramapuram India Department of Computer Science and Engineering Shri Vishnu Engineering College for Women Andhra Pradesh Bhimavaram India Computer Science and Engineering (Cyber Security) Madanapalle Institute of Technology & Science Madanapalle India Department of Computer Science and Engineering Aditya University Andhra Pradesh Surampalem India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

The surrounding environmental and climatic conditions have a significant impact on the utilisation of ecosystem services for recreational purposes. Climate change poses a threat to future natural leisure opportunities because of this reliance. The way society functions is being challenged by climate change and significant adaptation will probably be needed to deal with future changes in weather patterns. Machine learning (ML) methods have advanced to the point that they are now being offered as a tool to support climate studies, in addition to being the source of advances in other fields of study. This research proposes a novel technique in marine life ecosystem–based climate change detection using deep learning model. Input is collected as climate change detection–based marine life ecosystem and processed for noise removal with normalisation. Then this data has been segmented and classified using watershed semantic fuzzy component analysis with quantile shrinkage convolutional regression model. The experimental analysis has been carried out in terms of training accuracy, specificity, recall, AUC and NSE. Suggested technique achieved training accuracy 98%, specificity 96%, NSE 45%, recall 95% and AUC 97%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Climate change detection Convolutional regression Deep learning Fuzzy component analysis Marine life ecosystem

来源：评论

学校读者我要写书评

暂无评论

Thoracic-net: Explainable artificial intelligence (XAI) based few shots learning feature fusion technique for multi-classifying thoracic diseases using medical imaging

引用

Multimedia Tools and Applications 2025年第9期84卷 5397-5433页

作者： Bhosale, Yogesh H. Patnaik, K. Sridhar Zanwar, S.R. Singh, Saket Kr. Singh, Vandana Shinde, U.B. Department of Computer Science & Engineering Birla Institute of Technology Ranchi Mesra India India India India

Background & Need: The early detection of thoracic diseases and COVID-19 (coronavirus disease) significantly limits propagation and increases therapeutic outcomes. This article focuses on swiftly distinguishing COVID-19 patients with 10 chronic thoracic illnesses from healthy examples. The death rates of COVID-19-confirmed patients are rising due to chronic thoracic illnesses. Method: To identify thoracic illnesses (Consolidation, Tuberculosis, Edema, Fibrosis, Hernia, Mass, Nodule, Plural-thickening, Pneumonia, Healthy) from X-ray images with COVID-19, we provide an ensemble-feature-fusion (FFT) deep learning (DL) model. 14,400 chest X-ray images (CXRI) of COVID-19 and other thoracic illnesses were obtained from five public sources and applied UNet-based data augmentation. High-quality images were intended to be provided under the CXR standard. To provide model parameters and feature extractors, four deep convolutional neural networks (CNNs) with a proprietary CapsNet as the backbone were employed. To generate the ensemble-fusion classifiers, we suggested five additional USweA (Unified Stacking weighted Averaging)-based comparative ensemble models as an alternative to depending solely on the findings of the single base model. Additionally, USweA enhanced the models' performance and reduced the base error-rate. USweA models were knowledgeable of the principles of multiple DL evaluations on distinct labels. Results: The results demonstrated that the feature-fusion strategy performed better than the standalone DL models in terms of overall classification effectiveness. According to study results, Thoracic-Net significantly improves COVID-19 context recognition for thoracic infections. It achieves superior results to existing CNNs, with a 99.75% accuracy, 97.89% precision, 98.69% recall, 98.27% F1-score, shallow 28 CXR zero-one loss, 99.27% ROC-AUC-score, 1.45% error rate, 0.9838 MCC, (0.98001, 0.99076) 95% CI, and 5.708 s to test individual CXR. This suggested USweA m

关键词： COVID-19

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：