检索结果-内蒙古大学图书馆

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

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

LooP: A Low-Overhead Path Reconstruction for Large-Scale IoTs

引用

IEEE Transactions on Network science and engineering 2025年第3期12卷 1623-1634页

作者： Fu, Luwei Zhao, Zhiwei Liu, Zhuoliu Min, Geyong University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China University of Exeter Department of Computer Science ExeterEX4 4QF United Kingdom

Internet of Things (IoT) plays a vital role in various smart applications due to its cost-efficiency and good scalability. For safety and management of a large-scale IoT with many gateways, packet-level path reconstruction which exactly reveals the transmission path of each packet is desired. However, the existing path reconstruction schemes rely on correlation between diverse packets, which results in either considerable overhead or poor accuracy. It is particularly difficult to reconstruct the paths by affordable overhead under the intensive deployment, constrained resource, and weak correlation of IoT devices. To this end, we propose a Low-overhead Path reconstruction (LooP) for large-scale IoT. The proposed scheme exploits the nature of incremental update that each node only identifies the changes of its one-hop topology for diverse gateways. The gateway nodes then iteratively recover the complete path of each received packet according to the reported changes and historical information. It removes much redundant overhead (e.g., the common paths information) while guaranteeing the accurate reconstruction in a large scale and dynamic topology network. We analyze the information entropy of LooP and several existing schemes to theoretically prove the superiority of our proposal. The experimental results also demonstrate LooP can achieve 98% reconstruction accuracy on average and at least 3x gain-cost-ratio of the sub-optimal rival. © 2013 IEEE.

关键词： Gateways (computer networks)

来源：评论

学校读者我要写书评

暂无评论

Improved dynamic threshold based fuzzy logic to detect and classify diabetic retinopathy

引用

Multimedia Tools and Applications 2025年第6期84卷 3117-3135页

作者： Bhimavarapu, Usharani Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India

Diabetic retinopathy (DR) is a leading cause of vision impairment and blindness globally, with its severity classified into non-proliferative and proliferative stages. Effective detection and segmentation of multiple lesions are crucial for accurate diagnosis and management. This study presents a novel fuzzy logic-based model for the segmentation of multi-lesion diabetic retinopathy, which addresses the complexities associated with varying severity levels. The proposed multi-phase approach employs a comprehensive fuzzy inference system to enhance the detection and classification of diverse lesions related to diabetic retinopathy. Evaluated using three benchmark datasets—Messidor-2, Eyepacs, and IDRiD—proposed model achieved an accuracy of 99.57% on the Messidor-2 dataset and consistently high precision, recall, and F1-scores exceeding 99% across all datasets. Comparative analyses reveal that the proposed model significantly outperforms existing approaches, with an accuracy increase of 2.45% in multi-lesion segmentation metrics. Additionally, statistical validation demonstrates the robustness of our findings, with p-values less than 0.001. This study emphasizes the potential of fuzzy logic in enhancing diagnostic capabilities for diabetic retinopathy through precise lesion segmentation, ultimately aiding in improved patient outcomes. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

Web information extraction and fake news detection in twitter using optimized hybrid bi-gated deep learning network

引用

Multimedia Tools and Applications 2025年第11期84卷 9471-9504页

作者： Jadhav, Dhanaraj Singh, Jaibir Department of Computer Science and Engineering Om Parkash Jogender Singh University Rajasthan Churu331303 India

In today's scenario, extracting information from websites is a challenging problem because of the increasing amount of information shared on the Internet. Recently, there has been an increase in the popularity of using social media platforms like Twitter, Facebook, Instagram, etc., where everyone can share information very easily. However, malicious users were also increasing on social media, so they shared fake news to mislead the users. Most recently, fake news has spread widely on Twitter. Thus, to solve this problem, this paper proposes an effective deep learning mechanism based on an optimized deep attention (EDLM-ODA) network for detecting fake news on Twitter. First, the input data is converted into a CSV file in JSON format and then pre-processed using tokenization, special character removal, punctuation removal, lowercase, stemming, and spelling correction. The term frequency-inverse average document frequency (TF-IADF), n-gram level vectorizer, character level vectorizer, and hashing vectorizer are feature extractors to extract substantial features. Further, the extracted features are fed into the dual attention based convolutional bi-gated reptile optimal network (DA_CBiG_RepNet) model to classify real and fake news. In the DA_CBiG_RepNet model, the extended reptile optimization algorithm (EROA) is applied to minimize the loss function. The proposed EDLM-ODA network is implemented using the Python platform, and the performance is evaluated in terms of various evaluation metrics using the PHEME, Liar, and FakeNewsNet datasets. Further, the performance of the EDLM-ODA network is compared with prevailing methods. As a result, the implemented outcomes proved that the EDLM-ODA network had attained a better accuracy of 99%, 99.12%, and 99.2% than the prevailing methods using PHEME, Liar, and FakeNewsNet datasets. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Wi-Fi-enabled Vision via Spatially-variant Pose Estimation based on Convolutional Transformer Network

引用

IEEE Access 2025年 13卷 84855-84869页

作者： Lee, Hyeon-Ju Buu, Seok-Jun Gyeongsang National University Department of Computer Science and Engineering Gyeongsangnam-do Jinju52828 Korea Republic of

Wi-Fi-enabled vision offers a transformative paradigm for non-optical pose estimation, particularly in occluded or privacy-sensitive environments where traditional visual systems falter. Despite its promise, extracting reliable pose information from Wi-Fi Channel State Information (CSI) remains a formidable challenge due to spatial variability in torso localization, cross-view discrepancies, and inherent signal perturbations caused by multipath propagation and environmental noise. To address these challenges, we propose a Convolutional Transformer Network, an architecture that integrates convolutional layers for localized spatial feature extraction and transformer layers for global temporal dependency modeling. This integrative design effectively captures the spatiotemporal dynamics of CSI signals, enabling robust pose estimation under cross-view and spatially-variant conditions. When evaluated on the benchmark WIDAR 3.0 datasets, the proposed model outperforms the structural and sequential learning baseline CNN-GRU by 1.72% in accuracy. It outperforms sequential models (RNN, GRU, LSTM) and image models (CNN, ViT) across all key metrics, demonstrating robust spatial-temporal modeling capabilities. These results highlight its advancement in non-optical pose estimation and practical applicability in real-world scenarios. © 2013 IEEE.

关键词： Feature Selection

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

Behavioral insights into compression: a study of Move-to-Front-or-Middle deterministic online algorithm through sequence classification and characterization

引用

International Journal of Information Technology (Singapore) 2025年第1期17卷 189-203页

作者： Baisakh Mohapatra, Hitesh Guru, Abhishek Department of Computer Science and Engineering Sambalpur University Institute of Information Technology Sambalpur India Computer Science and Engineering GMR Institute of Technology Andhra Pradesh Rajam India School of Computer Engineering KIIT Deemed to Be University Bhubanseswar India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India

Since the list update problem was applied to data compression as an effective encoding technique, numerous deterministic algorithms have been studied and analyzed. A powerful strategy, Move-to-Front (MTF), involves moving an accessed item to the front of the list immediately. Theoretical analysis has demonstrated MTF’s potential, showing it to be 2-competitive through competitive analysis. This success has inspired researchers to develop various intriguing MTF variants and assess their performance both theoretically and experimentally. One such variant, Move-to-Front-or-Middle (MFM), has been experimentally shown that MFM performed better than the classic MTF on Calgary and Cantebury Datasets. However, the experimental performance alone does not provide sufficient insight into the internal behavior of the algorithm or explain why its performance surpasses MTF on certain datasets. Therefore, in this paper, we conduct a detailed behavioral study of MFM through sequence classification and characterization to gain deeper understanding of the algorithm and aims to reconcile the disparity between theoretical and experimental outcomes. This paper also by classifying and characterizing MFM’s performance across various request sequences, considering both the presence and absence of locality of reference. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Competitive analysis Deterministic list update algorithm List update problem Sequence classification

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

Medicare fraud detection: a comparative study on the effectiveness of one-class and binary classification models

引用

International Journal of computers and Applications 2025年第3期47卷 323-328页

作者： Leevy, Joffrey L. Hancock, John Khoshgoftaar, Taghi M. Department of Electrical Engineering and Computer Science Florida Atlantic University Boca RatonFL United States

Research into Medicare fraud detection that utilizes machine learning methodologies is of great national interest due to the significant fiscal ramifications of this type of fraud. Our big data analysis pertains to three Medicare datasets: Part B, Part D, and DMEPOS. In this paper, One-Class Classification (OCC) and binary classification approaches are evaluated with six different classifiers. We note that when a practitioner is faced with a high cost or unreasonable wait associated with acquiring a second label for binary classification, OCC may intuitively seem like the better alternative. The evaluative metrics used in our study are Area Under the Receiver Operating Characteristic Curve (AUC) and Area Under the Precision-Recall Curve (AUPRC). As a result of our investigation, binary classification was found to be more effective than OCC in detecting Medicare fraud. Additionally, we determined that gradient-boosting algorithms, specifically CatBoost and XGBoost, yield the most robust performance. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Investigating mobility patterns through crowd-sourced activity data

Advances in Transportation Studies

引用

Advances in Transportation Studies 2025年 65卷 253-270页

作者： Castiglione, M. Cipriani, E. Gemma, A. Nigro, M. Department of Civil Computer Science Aeronautical Technologies Engineering Roma Tre University Rome00146 Italy

Investigating trip purposes represents an important phase of travel demand modeling which allows to correctly infer mobility patterns and to better understand travel behavior. Until now, researchers collected information on the motivation for carrying out a trip mainly through travel surveys. However, traditional methods of acquiring this type of information are challenging and expensive to implement;therefore, they are typically performed infrequently and with low sampling rates. These two occurrences do not always allow for adequate representation of the heterogeneity of trip purposes. This paper aims to investigate trip purposes through the joint processing of GPS-based data, such as Floating Car Data (FCD), and aggregated activity data available through open-source platforms, such as Google Popular Times (GPT), which provide information on the daily distribution of visits in a certain activity venue as well as the average visit duration based on aggregated data obtained from users who share their mobile phones geotraces. Through the application of clustering techniques on a FCD dataset containing trips carried out between September and November 2020 in the EUR district of Rome, Italy, we classify the trips as Home-Work trips and Not Home-Work trips, obtaining a total of 96 Origin-Destination matrices (one for every 15 minute time interval). Not Home-Work trips are further examined, exploiting 6 patterns obtained through the clustering of GPT activity data, and classified according to the arrival time at destination and the duration of their stopover. The obtained Origin-Destination matrices have been compared to values found in literature in terms of spatial and temporal flexibility to validate the results. © 2025, Aracne Editrice. All rights reserved.

关键词： Spatio-temporal data

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：