检索结果-内蒙古大学图书馆

RBCA-ETS: enhancing extractive text summarization with contextual embedding and word-level attention

International Journal of Information technology (Singapore) 2025年第2期17卷 1127-1135页

作者： Gangundi, Ravindra Sridhar, Rajeswari Department of Computer Science and Engineering National Institute of Technology Tamil Nadu Tiruchirappalli 620015 India

The existing limitations in extractive text summarization encompass challenges related to preserving contextual features, limited feature extraction capabilities, and handling hierarchical and compositional aspects. To address these issues, the RoBERTa-BiLSTM-CNN-Attention Extractive Text Summarization, i.e., the RBCA-ETS model, is proposed in this work. RoBERTa word embedding is used to generate contextual embeddings. Parallelly connected CNN and BiLSTM layers extract textual features. CNN focuses more on local features, and BiLSTM captures long-range dependencies that extend across sentences. These two feature sets are concatenated and forwarded to the attention layer, highlighting the most relevant features. In the output layer, a fully connected layer receives the attention vector and calculates sentence scores for each sentence. This leads to the generation of the final summary. The RBCA-ETS model has demonstrated superior performance on the CNN-Daily Mail (CNN/DM) dataset compared to many state-of-the-art methods, and it has also outperformed existing state-of-the-art techniques when tested on the out-of-domain DUC 2002 dataset. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Attention BiLSTM CNN RoBERTa Text summarization

来源：评论

学校读者我要写书评

暂无评论

A systematic review of machine learning and deep learning techniques for anomaly detection in data mining

引用

International Journal of computers and Applications 2025年第2期47卷 169-187页

作者： Tahir, Mahjabeen Abdullah, Azizol Izura Udzir, Nur Azhar Kasmiran, Khairul Serdang Malaysia Serdang Malaysia Department of Computer Engineering Sir Syed University of Engineering & Technology Karachi Pakistan

The growing use of the internet has increased the threat of cyberattacks. Anomaly detection systems are vital for protecting networks by spotting irregular activities. Various studies investigated anomaly detection techniques without a systematic approach. So far, the existing reviews mainly concerned time series and data streaming methods almost neglected the growing interest in graph-based data mining techniques which are vital in social networks, finance, and IoT domains. Following PRISMA guidelines, this systematic review examines anomaly detection methods applied to time series, data streaming, and graph-based data from 2018 to 2023. A total of 34 papers were selected from four key databases ScienceDirect, Scopus, Web of Science, and IEEE. In addition, this review addressed several issues with existing techniques including low scalability, explainability, and interpretability for real-time anomaly detection systems. In modern applications where data structures are complex, and processing requirements are high these traditional techniques are insufficient for real-time data processing. Finally, our study demanded more advanced, complex methods to address these evolving challenges. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Data streams

来源：评论

学校读者我要写书评

暂无评论

A Stratified Seed Selection Algorithm for K-Means Clustering on Big Data

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1334-1344页

作者： Bajpai, Namita Paik, Jiaul H. Sarkar, Sudeshna Indian Institute of Technology Department of Artificial Intelligence Kharagpur721302 India Indian Institute of Technology Department of Computer Science Kharagpur721302 India

In k-means clustering, the selection of initial seeds significantly influences the quality of the resulting clusters. Moreover, clustering large-sized data introduces an additional challenge for seed selection. We propose a novel and scalable seed selection approach by jointly modeling the quality and diversity of the potential seeds through a principled probabilistic stochastic point process. To this end, we also propose a novel seed quality estimation approach on large data. Our approach quantifies the quality of a seed by measuring the divergence between the distribution of similarity between the closest neighbors and that of the randomly chosen neighbors from exhaustive stratified batches of samples. Unlike many existing scalable approaches, we do not rely on a small sample of the original data;instead, we use the entire data, thereby minimizing the chance of leaving out information about a potentially high-quality seed. The extensive evaluation on a set of benchmark data shows that it outperforms a number of strong, well-known, and recent algorithms measured by three standard metrics. © 2020 IEEE.

关键词： k-nearest neighbors

来源：评论

学校读者我要写书评

暂无评论

Securing FANET using federated learning through homomorphic matrix factorization

引用

International Journal of Information technology (Singapore) 2025年第1期17卷 17-36页

作者： Banerjee, Aiswaryya Mahato, Ganesh Kumar Chakraborty, Swarnendu Kumar Department of Computer Science and Engineering National Institute of Technology Arunachal Pradesh Jote 791113 India

As Flying Ad Hoc Networks (FANETs) continue to advance, ensuring robust security, privacy, and data reliability remains a significant challenge. This research presents a novel framework known as HE-FSMF-short for Homomorphic Encrypted Federated Secure Matrix Factorization-specifically designed to tackle these challenges. HE-FSMF integrates matrix factorization with federated learning and homomorphic encryption to enhance both security and efficiency in FANET environments. Matrix factorization, commonly used in recommendation systems, is adapted here to address the unique complexities of FANETs. By leveraging detailed feature extraction through the VGG-16 model, HE-FSMF ensures precise and secure data processing even in dynamic and high-mobility settings. The incorporation of homomorphic encryption protects data throughout cloud-based computations, maintaining privacy and integrity without compromising performance. Additionally, HE-FSMF features mechanisms to verify the accuracy and authenticity of results, which is crucial for establishing trust in distributed systems. This framework not only enhances learning efficiency and improves data transmission rates but also provides strong safeguards for sensitive information. HE-FSMF offers a robust solution for advancing FANET capabilities, making it a valuable tool for secure and efficient communication in the increasingly interconnected and rapidly evolving landscape of networked systems. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： FANET Federated learning Homomorphic encryption UAV

来源：评论

学校读者我要写书评

暂无评论

Method to avert vehicle collision based on driver’s attention lapse predicted using BCI

引用

Multimedia Tools and Applications 2025年 1-24页

作者： Mishra, Unnati Chauhan, Hitesh Maru, Madhuri Parikh, Saurin Computer Science and Engineering Department Institute of Technology Nirma University Sarkhej Gandhinagar Highway Near Gota Gujarat Ahmedabad382481 India

In this paper, a BCI-based machine learning method is proposed to predict the attention lapse of the driver. An EEG headset is used to capture brain activity from different regions of the human brain. The data is further pre-processed and various machine learning classifiers such as KNN, decision tree, and naive Bayes are trained using the data to classify the attention state of the driver as in-attention, attention lapse or attention regain. The KNN model is the best performer showing 97% accuracy, wherein the true positive rate (TPR) of 85.5% is measured to predict attention lapse and 82% to predict attention regain states. Besides this, a sensor-based model is also proposed to avert the vehicle’s collision by alerting the driver about the attention lapse. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

UETT4K Anti-UAV: A Large Scale 4K Benchmark Dataset for Vision-based Drone Detection in High-Resolution Imagery

引用

IEEE Access 2025年 13卷 73553-73568页

作者： Awan, Mughees Sarwar Zaidi, Syed Azhar Ali Mir, Junaid Dr. A. Q. Khan Institute of Computer Sciences and Information Technology Kahuta Pakistan University of Engineering and Technology Department of Electronics Engineering Taxila47080 Pakistan University of Engineering and Technology Department of Electrical Engineering Taxila47080 Pakistan

In recent years, incidents involving unmanned aerial vehicles (UAVs) have increased significantly, raising concerns over security and privacy, especially concerning civilian and military facilities. Vision-based approaches, especially those employing deep convolutional neural networks (DCNNs), show great promise in addressing the need for an accurate and cost-effective UAV detection system. However, DCNNs rely heavily on extensive and well-labeled datasets, which are essential for achieving high accuracy and effectiveness. For drone detection tasks, a dataset of high-resolution images is especially valuable, as it provides more contextual information for DCNNs, enabling more accurate drone detection. This work presents a new drone detection dataset composed of 4K resolution images named University of engineering and technology Taxila 4K Anti-UAV (UETT4K Anti-UAV). The dataset is created by obtaining real-world videos of different types of drones in diverse environmental and challenging conditions. A custom dataset of 33601 images, manually annotated with hand-labeled bounding boxes, is created from these *** used our dataset to train, validate, and test eight state-of-the-art YOLOv6v3 algorithm models. The test results and qualitative analysis guide selecting the most suitable model for drone detection applications. The proposed extensive 4K dataset offers a valuable resource for effectively training deep learning models to detect drones across diverse conditions accurately. © 2013 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Bi-SMOTE: a novel framework for handling imbalanced datasets using machine learning techniques

引用

International Journal of Information technology (Singapore) 2025年第1期17卷 431-445页

作者： Tigga, Onima Pal, Jaya Mustafi, Debjani Department of Computer Science & amp Engineering Birla Institute of Technology Jharkhand Mesra Ranchi India

Working with Imbalance data in real-world problems is not so easy due to the different cardinality of classes. Several machine learning Techniques have been used to overcome this kind of problem for 100% original data for classification. In this research work, the proposed Bi-SMOTE approach on the imbalanced Red wine and Glass datasets using machine learning techniques, Random Forest (RF), K Nearest Neighbor (KNN), Logistic Regression (LR), and Decision Tree (DT) have been used. Moreover, preprocessing steps are done by Binarization and standardization. The accuracy and F1-score are calculated of without SMOTE / with SMOTE / proposed Bi-SMOTE approaches with classifiers RF, KNN, LR, and DT for 95% & 100% of original datasets. Here the Bi-SMOTE approach gives better results up to 12%, and up to 22% for accuracy and up to 29% and up to 28% for F1-score for the Red wine and the Glass dataset respectively. Moreover, mean squared error (MSE) is continuously decreased in these machine learning techniques with original data with SMOTE and Bi-SMOTE. Thus, the proposed approach Bi-SMOTE yields the highest values in all performance measures, including accuracy, and F1-score for 95% data than 100% data. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Accuracy Binarization Class Imbalance Machine learning (ML) SMOTE (Synthetic minority over-sampling technique)

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Motor Imagery Classification using Wavelet Packet Decomposition and Complex Morlet Transform

引用

Multimedia Tools and Applications 2025年 1-24页

作者： Shirodkar, Vaishali Edla, Damodar Reddy Kumari, Annu Department of Computer Science and Engineering National Institute of Technology Goa Kottamoll Plateau Goa Cuncolim403703 India Information Technology Department Goa College of Engineering Farmagudi Goa Ponda403401 India

The area of brain-computer interface research is widely spreading as it has a diverse array of potential applications. Motor imagery classification is a boon to several people with motor impairment. Low accuracy and datasets with few trial recordings present challenges for this classification. This research offers a novel approach to these problems in electroencephalography signal classification for efficient control of neuroprosthetic devices. By using wavelet packet decomposition the proposed method divides the EEG signal into eight frequency bands. Each of these bands were then evaluated by a one-dimensional convolution neural network to find the most discriminative band. Only EEG signals filtered with these bands were used to generate time-frequency images called scalograms using complex Morlet transform. These scalograms were then classified using a two-dimensional convolution neural network optimized for spatial-temporal feature extraction and classification. To mitigate data scarcity, generative adversarial networks were used for effective data augmentation. Experimental evaluation on a benchmark dataset demonstrated substantial improvement: the two-dimensional convolution neural network achieved 93.63% accuracy, surpassing the 85% achieved by the one-dimensional convolution neural network baseline. Precision, recall, and F1-score metrics validated robust performance across motor imagery tasks. Comparative analysis with the latest methods underscored the proposed model’s superiority in accuracy and reliability. Using wavelet transformations, convolution neural network architectures, and generative adversarial network-driven data augmentation presented a promising framework for advancing brain-computer interface applications, particularly in enhancing neuroprosthetic device control. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

DeepFakeGuard: Safeguarding Digital Platforms Against Fake Profiles Using AI 4

DeepFakeGuard: Safeguarding Digital Platforms Against Fake P...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Swarna Sudha, M. Manjula, S. Bharathi, Indira Krishnasamy, Valarmathi Vijayalakshmi, K. Ramco Institute of Technology Department of Computer Science and Engineering Rajapalayam India School of Computer Science and Engineering Vellore Institute of Technology Chennai India PSR Engineering College Department of Electronics and Communication Engineering Sivakasi India

ISBN: (纸本)9798331523923

This research introduces DeepFakeGuard, a hybrid deep learning framework designed to detect fake profiles on social media platforms, addressing the growing threat of fraudulent accounts online. DeepFakeGuard integrates multiple data modalities, including textual, visual, behavioral, and network features, to accurately classify profiles as real or fake. Leveraging advanced deep learning models such as BERT for textual analysis, ResNet for image processing, and LSTM for modeling behavioral patterns, DeepFakeGuard provides a comprehensive and robust solution for identifying fake profiles across diverse platforms. The framework processes a rich set of profile characteristics, including account information, posting behavior, post sentiment, and network relationships, ensuring a multi-dimensional analysis of social media accounts. The hybrid architecture of DeepFakeGuard merges outputs from individual sub-models, which are then processed through dense layers for final classification using a sigmoid activation function. This multi-faceted approach significantly enhances detection accuracy, precision, and recall compared to traditional methods. The framework is highly scalable and adaptable to various social media platforms, offering a versatile tool for strengthening online security. With strong performance metrics, including high classification accuracy, DeepFakeGuard demonstrates its potential for real-world applications in mitigating the risks associated with fake profiles. By fostering secure and trustworthy social media environments, this research contributes to the ongoing fight against fraudulent accounts, paving the way for safer online interactions. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Swin Transformer and Momentum Contrast (MoCo) in Leukemia Diagnostics: A New Paradigm in Al-Driven Blood Cell CancerClassification

引用

IEEE Access 2025年 13卷 82441-82466页

作者： Jain, Eshika Kaushik, Pratham Kukreja, Vinay Ati, Modafar Hariharan, Shanmugasundaram Ahuja, Vandana Bhattacherjee, Abhishek Kaushal, Rajesh Kumar Chitkara University Centre for Research Impact and Outcome Chitkara University Institute of Engineering and Technology Punjab Rajpura140401 India Abu Dhabi University Computer Science and Information Technology College of Engineering Abu Dhabi United Arab Emirates Vardhaman College of Engineering Department of Artificial Intelligence and Data Science Shamshabad Telangana Hyderabad501218 India Swami Vivekanand Institute of Engineering and Technology Department of Computer Science & Engineering Punjab Ramnagar140601 India Lovely Professional University Department of Computer Science Engineering Punjab Phagwara144411 India

Acute Lymphoblastic Leukemia (ALL) is a rapidly progressing blood cancer requiring timely and accurate diagnosis for effective treatment. Automated image-based diagnostic models offer a potential solution but often lack robustness in clinical applications. This study aims to develop a robust, automated classification model for ALL subtypes using peripheral blood smear images, employing advanced feature extraction through the Swin Transformer framework. The proposed model utilizes the Swin Transformer architecture combined with Momentum Contrast (MoCo) for contrastive learning. Swin Transformer’s patch-based embedding and multi-level attention capture local and global cellular features, enhancing feature discrimination across ALL subtypes. MoCo further improves feature extraction by generating distinct embeddings, reducing overlap between cell types. The model achieved an overall classification accuracy of 92.5%, with a precision of 90.3%, recall of 91.1%, and F1-score of 90.7% across four classes (Benign, Malignant Early Pre-B, Malignant Pre-B, and Malignant Pro-B). Class-specific performance metrics indicate that Malignant Pre-B achieved the highest F1-score of 92.4%. The MoCo framework demonstrated a contrastive loss reduction from 0.5 to 0.097 for benign cells, significantly enhancing feature discrimination. Additionally, an ablation study showed that omitting the dynamic queue reduced accuracy by 5%, highlighting its importance for robust feature learning. This approach can be extended to other hematologic malignancies, with potential enhancements using more extensive datasets and integration with real-time diagnostic workflows in clinical settings to support precision medicine. © 2013 IEEE.

关键词： Diseases

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：