检索结果-内蒙古大学图书馆

Fake news detection on social media using Adaptive Optimization based Deep Learning Approach

Multimedia Tools and applications 2025年第9期84卷 6091-6111页

作者： Steni Mol, T.S. Sreeja, P.S. Department of Computer Science Hindustan Institute of Technology and Science Chennai India Department of Computer Applications Vellore Institute of Technology Chennai India

Various content-sharing platforms and social media are developed in recent times so that it is highly possible to spread fake news and misinformation. This kind of news may cause chaos and panic among people. The automatic and accurate detection of fake news is a complex task. To consider this issue, an automatic and effective fake news detection approach is implemented. The proposed methodology is named Adaptive Adam Adadelta Optimizer-based Deep Bi-directional Long Short Term Memory (Bi-LSTM), in which Adaptive Adam AO is the merging of Adadelta Optimizer (AO), Adaptive concept, and Adam Optimization. The Bidirectional Encoder Representations from Transformers (BERT) is used for the tokenization and then, feature mining is done. Also, the dimensionality of the features is reduced by Singular Value Decomposition (SVD) and Moving Principal Component Analysis (MPCA). From them, the top-N feature selection is performed using Joint Quantum Entropy. Finally, for fake news detection, Adaptive Adam AO trained Deep Bi-LSTM is used, which obtained maximum specificity, sensitivity, and accuracy of 0.928, 0.945, and 0.938. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Video captioning – a survey

引用

Multimedia Tools and applications 2025年第2期84卷 947-978页

作者： Vaishnavi, J. Narmatha, V. Department of Computer Applications SRM Institute of Science and Technology Trichy India Department of Computer and Information Science Annamalai University Annamalai Nagar Tamilnadu 608002 India

The explosion of the novel phenomenon of the combination of computer vision and Natural language processing is playing a vital role in converting the ordinary world into a more technological pool. Natural language processing and computer vision are the vanguard of Artificial intelligence with the enormous potential currently ruling more fields. The trending Accelerated research of the NLP and CV combo are cancer screening, surgical simulation, visual properties description, visual retrieval, visual description, etc. Video captioning is a task of localizing the event and various features are extracted from the particular event and then the description of the entire event is performed with Natural languages using various techniques. The task of video captioning has some evolution of various techniques from Traditional methods to Deep learning. Currently, Deep learning techniques are ruling the field. Several models are being proposed for the better enhancement of the video captioning task with the default Encoder-Decoder framework and some models with the variance of Attention mechanism and Transfer learning etc., The Attainment of every technique and the accuracy of the generated results are highly dependent on the nature of the problem, diversity, performance of chosen dataset and construction of the technique with various layers, and the amount of data split for train, validate, and test. This survey discusses the captioning types, real-time applications of video captioning, evolution of various methods in video captioning, advanced techniques, different datasets, metrics that are used to evaluate the results, and analysis of the results of the existing models for video captioning. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Robust Image Forgery Localization Using Hybrid CNN-Transformer Synergy Based Framework

引用

computers, Materials & Continua 2025年第3期82卷 4691-4708页

作者： Sachin Sharma Brajesh Kumar Singh Hitendra Garg Department of Computer Science Abdul Kalam Technical UniversityLucknow226031India Department of Computer Engineering & Applications GLA UniversityMathura281406India Department of Computer Science Raja Balwant Singh Engineering Technical CampusAgra283105India

Image tampering detection and localization have emerged as a critical domain in combating the pervasive issue of image manipulation due to the advancement of the large-scale availability of sophisticated image editing *** manual forgery localization is often reliant on forensic *** recent times,machine learning(ML)and deep learning(DL)have shown promising results in automating image forgery ***,the ML-based method relies on hand-crafted ***,the DL method automatically extracts shallow spatial features to enhance the ***,DL-based methods lack the global co-relation of the features due to this performance degradation noticed in several *** the proposed study,we designed FLTNet(forgery localization transformer network)with a CNN(convolution neural network)encoder and transformer-based *** encoder extracts local high-dimensional features,and the transformer provides the global co-relation of the *** the decoder,we have exclusively utilized a CNN to upsample the features that generate tampered mask ***,we evaluated visual and quantitative performance on three standard datasets and comparison with six state-of-the-art *** IoU values of the proposed method on CASIA V1,CASIA V2,and CoMoFoD datasets are 0.77,0.82,and 0.84,*** addition,the F1-scores of these three datasets are 0.80,0.84,and 0.86,***,the visual results of the proposed method are clean and contain rich information,which can be used for real-time forgery *** code used in the study can be accessed through URL:https://***/ajit2k5/Forgery-Localization(accessed on 21 January 2025).

关键词： Image tampering convolution neural network(CNN) hybrid transformer localization

来源：评论

学校读者我要写书评

暂无评论

Predictive VM placement algorithm for resource optimization: leveraging deep learning forecasting and resource relationship modeling

引用

International Journal of computers and applications 2025年第4期47卷 398-411页

作者： Garg, Rajni Arora, Indu Gupta, Anu Department of Computer Science Lala Lajpat Rai Govt. College Moga India Department of Computer Science Mehr Chand Mahajan DAV College for Women Chandigarh India Department of Computer Science and Applications Panjab University Chandigarh India

The growing demand for cloud computing has made it imperative to optimize the utilization of cloud resources. Resource optimization can be improved through Virtual Machine (VM) Placement. In order to effectively optimize placement of VMs, it becomes necessary to anticipate future resource demand. However, accurate resource forecasting is a major challenge due to the dynamic nature of cloud applications. Furthermore, if VMs are placed on the same server, it can lead to resource contention, especially when they compete for the same resources. This contention can adversely affect VMs performance and potentially increase cost for users, as well as energy consumption by the infrastructure. This work proposes a model named Predictive Disparity-based Virtual Machine Placement (PDVMP) which aims to enhance VM placement decision. The model integrates forecasting techniques grounded in Deep Learning for estimating the future resource needs of VMs. This estimation is incorporated in VM placement decision in order to ensure long-term sustainability of the VM on the destination server. Moreover, the model used in the current research work balances resource optimization and execution performance by packing multiple VMs that exhibit complementary resource demand on a same physical server. The performance of PDVMP model is tested against benchmark placement policies using real workload traces of bitBrains datacenter. The results show that the proposed approach improves resource utilization while reducing both performance bottlenecks and energy consumption. The experimentation shows an improvement in Energy Performance Metric ranging from 49.3% to 62.97%. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Bismuth alloys

来源：评论

学校读者我要写书评

暂无评论

Seizure Prediction on EEG Signals using Feature Augmentation based Multi Model Ensemble

引用

Recent Patents on Engineering 2025年第1期19卷 41-49页

作者： Anandaraj, A. Alphonse, P.J.A. Department of Computer Science and Engineering Sri Eshwar College of Engineering Coimbatore India Department of Computer Applications National Institute of Technology Tamilnadu Tiruchirappalli India

Background: Epilepsy is a neurological disorder that leads to seizures. This occurs due to excessive electrical discharge by the brain cells. An effective seizure prediction model can aid in improving the lifestyle of epilepsy patients. After analyzing various patents related to seizure prediction, it is observed that monitoring electroencephalography (EEG) signals of epileptic patients is an important task for the early diagnosis of seizures. Objective: The main objective of this paper is to assist epileptic patients to enhance their way of living by predicting the seizure in advance. Methods: This paper builds a feature augmentation-based multi-model ensemble-based architecture for seizure prediction. The proposed technique is divided into 2 broad categories;feature augmentation and ensemble modeling. The feature augmentation process builds temporal features while the multi-model ensemble has been designed to handle the high complexity levels of the EEG data. The first phase of the multi-model ensemble has been designed with heterogeneous classifier models. The second phase is based on the prediction results obtained from the first phase. Experiments were performed using the seizure prediction dataset from the University Hospital of Bonn. Results: Comparison indicates 98.7% accuracy, with improvement of 5% from the existing model. High prediction levels indicate that the model is highly capable of providing accurate seizure predictions, hence ensuring its applicability in real time. Conclusion: The result of this paper has been compared with existing methods of predicting seizures and it indicated that the proposed model has better enhancement in the accuracy levels. © 2025 Bentham science Publishers.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Classifying the state of knowledge-based question answering: patterns, progress, and prospects

引用

International Journal of computers and applications 2025年第1期47卷 93-105页

作者： Sharma, Sumit Jain, Sarika Tiwari, Mukesh Kumar lal, Sohan Department of Computer Science and Engineering Quantum University Roorkee Uttarakhand Roorkee India Department of Computer Applications National Institute of Technology Haryana Kurukshetra India

In response to inquiries posed in natural languages, question-answering systems (QASs) produce responses. The capabilities of early QASs are limited because they were designed for certain domains. The current generation of QASs focuses on the types of inquiries that users typically enquire, the features of the data sources that are used, and the formats in which the right responses are produced. Many QASs have been developed since the 1960s when research on the subject first started. There are several cutting-edge frameworks for answering questions that can be used to categorize the QA system according to a number of criteria. The necessity for an extensive survey on QASs comes naturally in order to determine the future focus of research in this field. In this study, QASs are analyzed by the number of criteria used to categorize question-answering (QA) and provide the dimension using a variety of standards to cover all the QAS. We describe the current state of research in each QAS area and make recommendations for its future direction. Based on the dimension criteria outlined in the research methodology, research studies are chosen for additional review and comparison. Constructed some criteria to classify the QASs, we provide the classification and go over the benefits and drawbacks of each class's QAS, as well as the problems with the corresponding study. Results are detailed summarized and compared. As a result of this study, a general architecture of frameworks for QA over knowledge base (KB) is drawn in addition to the comparative analysis of systems, serving as a reference for academics working on related topics. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Model to Predict Students’ Sentiments in Higher Educational Institutions

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2025年第1期19卷 46-61页

作者： Ananthi, Claral Mary T. Department of Computer Applications Faculty of Science and Humanities SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chengalpattu India

Sentiment analysis has been widely used in various fields of social media, education, and business. Specifically, in the education domain, the usage of sentiment analysis is difficult due to the huge amount of information, the nature of language, and processing the diverse perceptions of students. Deep learning emerges as an advanced concept in the realm of machine learning that learns features automatically from raw text data, making them well-suited for sentiment analysis tasks. In recent years, deep learning has been used in analyzing the sentiments. Deep learning architectures have surpassed other machine learning paradigms for performing sentiment analysis. The ability to analyze automatically the students’ sentiments enables HEI to process huge amounts of unstructured data quickly, efficiently, and cost-effectively. The paper aims to predict the sentiments of students’ reviews posted in VLE regarding online learning that enables the educators to optimize their teaching methods for the best results. This study paper explores the usage of CNN, LSTM, and hybrid CNN-LSTM for the prediction of sentiments. The proposed hybrid CNN-LSTM architecture achieves superior performance compared to other baseline algorithms with respect to accuracy, precision, recall, and F1 score. According to outcomes, the recommended technique achieves remarkable accuracy of 97%. The findings facilitate the progress of a more efficient deep learning sentiment prediction system that gives valuable insights from a huge volume of students’ textual data. © 2025 by the authors of this article.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Tuberculosis mycobacterium segmentation using deeply connected membership tweaked fuzzy segmentation network

引用

Multimedia Tools and applications 2025年第10期84卷 6899-6929页

作者： Shiny, A. Amala Sivagami, B. Department of Computer Applications S.T. Hindu College Nagercoil India Affiliated to Manonmaniam Sundaranar University Tirunelveli India Department of Computer Science & Applications S.T. Hindu College Nagercoil India

Tuberculosis (TB) is a contagious disease that spreads through the air when an infected person coughs, sneezes, or talks. TB is a bacterial infection caused by Mycobacterium tuberculosis (MTB). Nowadays, TB diagnosis is mainly influenced by the segmentation of MTB objects in Ziehl-Neelsen (ZN)-stained microscopy images. There are a number of segmentation algorithms that have been extensively examined in the literature, and these are still prone to issues like less accuracy due to over and under segmentation as well as unclear edges in bacterium objects. Hence, this paper presents a novel MTB segmentation method entitled ‘TB Mycobacterium Segmentation using Deeply connected Membership tweaked Fuzzy Segmentation Network (TBMS-DMFSN)’. This method takes the ZN-stained MTB color microscopic image as input and generates the segmented result. The own contribution of this paper is the FCM-based Mycobacterium segmentation algorithm called ‘Deeply connected Membership modified Fuzzy Segmentation Network (DMFSN),’ which is a deeply connected fuzzy network. The DMFSN network uses a back-propagated fuzzy network to separate the Mycobacterium objects. The proposed TBMS-DMFSN method incorporates eight optimum feature images from four different color spaces, lightness enhancement, and Gamma correction algorithms. Experimental evaluation is constructed with the help of both online and real-time clinical databases. The proposed TBMS-DMFSN approach has overall average segmentation accuracy (SA) of 95.26%, whereas the second-best method has a segmentation accuracy of 93.03%. As a result, the proposed approach raises the SA values by up to 2.226%. The achieved results reflect that the proposed method produces higher accuracy compared to state-of-the-art methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Secure Healthcare Monitoring System for Disease Diagnosis in the IoT Environment

引用

Multimedia Tools and applications 2025年第7期84卷 3767-3792页

作者： Verma, Ankit Gupta, Amit Kumar Kumar, Vipin Rajak, Akash Kumar, Sushil Panda, Rabi Narayan Department of Computer Applications KIET Group of Institutions Delhi-NCR Ghaziabad India Computer Science & Engineering KIET Group of Institutions Ghaziabad Delhi-NCR India

People who lead hectic lives daily suffer from a variety of illnesses, including diabetes, high blood pressure, hypertension, etc. For someone to survive, they must become aware of these illnesses promptly. The Internet of Things (IoT) and cloud computing are the two critical prerequisites for digital healthcare. In the present research, the attacked data are detected and removed using the security module to enhance the security of the healthcare system. However, an accurate prediction mechanism is needed for the early diagnosis of the diseases. To predict the sickness and its severity more accurately, a unique Dragon Fly-based Generalised Approximate Reasoning Intelligence Control (DF-GARIC) is devised in this article. This system was primarily responsible for preprocessing the cloud medical records entered into the system. Additionally, the regression algorithm extracts the relevant features. Based on the retrieved features, the dragonfly function is used to classify the disease and estimate its severity. Subsequently, a warning is given to the providers for the abnormal condition via SMS or e-mail. The system validated a higher accuracy level of 99.8% from the MATLAB execution. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Title-Based Topic Modeling on E-learning Web Content Titles Using BERTopic Model 5th

Title-Based Topic Modeling on E-learning Web Content Titles ...

引用

5th International Conference on Computing and Network Communications, CoCoNet 2023

作者： Lalitha, T.B. Sreeja, P.S. Department of Computer Applications Hindustan Institute of Technology and Science Chennai India Department of Computer Applications Vellore Institute of Technology Chennai India

ISBN: (纸本)9789819747108

In today’s information-rich digital age, the volume of web content available to users has become overwhelming, making it challenging for individuals to find relevant and personalized content. Recommendation systems have emerged as a transformative solution, catering to individual users by offering customized suggestions aligned with their unique interests. This research explores a novel approach that utilizes topic modeling techniques on web content titles for recommendation purposes. Topic modeling, a subfield of natural language processing (NLP) is utilized to automatically identify latent topics within a large corpus of text. The proposed work begins by collecting a diverse dataset of web content titles across the domains. It employs a combination of other state-of-the-art topic modeling algorithms like BERTopic modeling and statistical model to uncover the underlying topics in the titles. By leveraging this approach on web content titles, aim to extract meaningful themes and categorize the content efficiently. Then preprocess the data to remove irrelevant information, ensuring that the subsequent topic modeling process yields accurate and meaningful results. This approach not only expedites the recommendation process but also conserves computational resource. Once the topics are identified, associate them with appropriate metadata, such as user preferences, and content types. This step forms the foundation of our content-based recommendation approach. Then maps the user’s interests to the most relevant topics, enabling us to present a tailored list of web content titles. By recommending content based on underlying themes rather than just keywords, this approach surpasses traditional methods, ensuring more accurate and diverse suggestions for users. The results demonstrate the system’s ability to provide highly personalized recommendations, enhancing user satisfaction and engagement. By delving into the semantic structure of content rather than relying solely on

关键词： Modeling languages

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：