检索结果-内蒙古大学图书馆

Fake News Detection Using ARO and LSTM Algorithms

SN computer science 2025年第1期6卷 1-11页

作者： Bhagat, Amit Dangi, Dharmendra Suman, Vaibhav Dixit, Dheeraj Kumar Sharma, Suvarna Department of Computer Applications MANIT Madhya Pradesh Bhopal India Department of Information Technology IIIT Madhya Pradesh Bhopal India Department of Computer Science & Engineering LNCT University Madhya Pradesh Bhopal India Department of Computer Science & Engineering MITS Madhya Pradesh Gwalior India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

There has been an exponential increase in social media content over the past few years due to the popularity of social media platforms. However, this has also resulted in the dissemination of intentionally false information, or fake news, which can have significant negative effects on society. As a result, detecting fake news has become an important issue that requires attention. Promoting trust in the global community is crucial to preventing the spread of false information in mass media. A study report suggests a reliable technique for identifying false news in order to remedy this. The author has thoughtfully chosen two distinct datasets: the Buzzfeed dataset, which is an assortment of news articles from Buzzfeed News, and the ISOT dataset, which is a collection of social media postings and articles from other sources. The author thoroughly analyzed a variety of content kinds and assessed the efficacy of various approaches and methods for processing and categorizing them using the datasets. The study found that these datasets have accuracy rates of 99% and 97.8% respectively. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： ARO algorithm Fake news detection LSTM Pre-processing

来源：评论

学校读者我要写书评

暂无评论

GIS and ML Integrated Techniques for Detection of Landslide-Prone Areas 2

GIS and ML Integrated Techniques for Detection of Landslide-...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Sul, Astha Patil, Sanjay Vellore Institute of Technology School of Computer Science and Engineering Vellore India Maharashtra Remote Sensing Applications Centre Maharashtra Pune India

ISBN: (纸本)9798350368413

Landslides are a common natural disaster that can result in substantial casualties. One of the region's most vulnerable to landslides in India is Western Ghats. The risk casualty is reduced with the use of the landslide susceptibility map (LSM) and prediction of landslide points. The aim of this research is to explore and compare the 4 ML algorithms (K-Nearest Neighbor (KNN), Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR)) for generating the most promising LSM. This study focuses on 12 Landslide conditioning factors (LCFs) such as Elevation, Slope, Lithology, LULC, Distance to Road, Topographic Wetness Index (TWI), Stream Power Index (SPI), Topographic Roughness Index (TRI), Drainage Networks, NDVI, Rainfall, Sediment Transport Index (STI). It has been found that the slope of the ground, the distance to the road, and the annual rainfall all have a significant impact on the occurrence of landslides. The models made using different approaches have been analysed and compared using the following metrics: prediction accuracy, precision, recall, F1-score, and True Skill Statistics (TSS). Overall accuracy for LR, SVM, KNN, RF are 82.30, 84.00, 82.50, 87.20 respectively. The findings of the study show that there are more landslide-prone locations in Bhor, Velhe, Ambegaon, and Junnar in Pune District, Maharashtra. © 2024 IEEE.

关键词： Landslides

来源：评论

学校读者我要写书评

暂无评论

Optimization of Speech Emotion Recognition Through Advanced Ensemble Learning Techniques 9

Optimization of Speech Emotion Recognition Through Advanced ...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Prathyakshini Prathwini Keerthana Department of Information Science and Engineering Nitte Karkala India Department of Master of Computer Applications Nitte Karkala India Nitte Karkala India

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377972

Recognition of emotion in speech (RES) is generating significant interest due to its promise to improve human-computer interaction through precise identification of emotions from speech signals. This work investigates how well deep learning methods advance RES accuracy. The study makes it possible to analyze a variety of speech patterns, emotional expressions, and demographic information all of which are crucial for developing trustworthy RES models. According to the study, CNNs demonstrated their ability to capture spatial characteristics from voice spectrogram representations with an amazing accuracy rate of 93%. RNNs performed exceptionally well at modeling temporal dependencies and capturing the sequential nature of speech, with an accuracy rate of 90%. Both models performed well, but some emotions such 'angry' and 'surprise' were more accurately detected than others, including 'disgust' and 'happy,' suggesting room for improvement. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Generalized Framework for Brain Tumor and Pneumonia Detection Using Streamlite Application 4

A Generalized Framework for Brain Tumor and Pneumonia Detect...

引用

4th International Conference for Emerging Technology, INCET 2023

作者： Kishore, S. Nair, Rekha R Mehra, Vishal Babu, Tina Dayananda Sagar University Department of Computer Applications School of Engineering Bengaluru India Dayananda Sagar University Department of Computer Science and Engineering School of Engineering Bengaluru India

ISBN: (纸本)9798350335750

One of the dangerous disease pneumonia, which can affect one or both lungs, is frequently brought on by viruses, fungi or bacteria. Radiotherapists with advanced training are required to evaluate chest X-rays used to diagnose pneumonia. Brain tumours are another fatal disease that can have a profound impact on a patient's quality of life and alter everything for them and their loved ones. Therefore, creating an automatic system for diagnosing pneumonia would help treat the disease quickly, especially in remote areas. The work proposes a general framework for MRI and CT images that can automatically detect diseases such as brain tumours and pneumonia with single framework using VGG16. The proposed work focusing on developing streamlit web application for deployment. The proposed work gained an accuracy of 97.87% compared to Inception, Xception and ResNet for brain tumor detection and 94.3% for Pnemonia detection model. The training and testing data are compared using a CNN-based classifier to determine the optimal outcome. © 2023 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

An Automated Machine Learning NLP Model for Enhancing the Translation of English Causative Sentences into Malayalam Language

An Automated Machine Learning NLP Model for Enhancing the Tr...

引用

2023 Annual International Conference on Emerging Research Areas: International Conference on Intelligent Systems, AICERA/ICIS 2023

作者： Tom, Rony Mathew, Juby Amal Jyothi College of Engineering Department of Computer Applications Kerala Kanjirappally India Amal Jyothi College of Engineering Department of Computer Science & Engineering Kerala Kanjirappally India

ISBN: (纸本)9798350303452

This research paper introduces an innovative Neural Machine Translation (NMT) model designed to accurately translate causative English sentences into Malayalam. The study comprehensively explores the various forms of causative sentences utilized in both English and Malayalam, focusing on syntactic and semantic differences. Additionally, it delves into the limitations of current translation models such as Google Translator in accurately translating causative constructs. To address these challenges and enhance translation accuracy, a collaborative effort with professional linguists in both languages led to the creation of a rich dataset. The dataset comprises a diverse collection of causative sentences, covering tense variations, singular and plural forms, noun and verb classes, as well as sentence forms involving non-human and animate-human subjects. This model integrates essential components including tokenization, Part of Speech (POS) tagging, tense identification, suffix identification and addition, and sentence reordering for improved translation. Comparative evaluations between the Google Translator and the newly developed system were conducted based on translation accuracy and fluency. The evaluation revealed that the novel NMT model consistently outperforms existing translation systems, demonstrating superior translation results. The findings underscore the effectiveness and potential of the proposed NMT model in advancing causal English to Malayalam translation, offering valuable insights for the improvement of machine translation systems. © 2023 IEEE.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Bubble Prediction in Stock Markets: Leveraging SVM and Technical Indicators for High Accuracy 3

Bubble Prediction in Stock Markets: Leveraging SVM and Techn...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Yuvaraj, S. Chenni Kumaran, J. Manogar, E. Doss, P.Lourdu Mahimai Gunasekaran, M. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering TamilNadu Chennai India B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Applications Chennai India

ISBN: (纸本)9798331509675

Predicting stock market bubbles is indispensable for risk control and refinement of trading strategies. Therefore, this study presents a Machine-Learning Framework to detect price bubble formations based on Support Vector Machine (SVM) and through important technical indicators. Among these are momentum indicators, such as the Relative Strength Index (RSI), and the Moving Average Convergence Divergence (MACD) histogram, which are complemented with volatility measures from Bollinger Bands and with normalized volume indicators, all to improve predictive accuracy. Recent historical stock data were fed to the model during training and testing, yielding exceptional accuracy: 98.54% on the test set and 98.95% on the training set. The performance evaluation was carried out based on Classification Reports, Confusion Matrices, Receiver Operating Characteristic (ROC) curve, and Precision-Recall metrics, thus confirming the performance efficiency of the developed framework. With this approach, bubbles' early detection allows traders and analysts a powerful tool to make informed decisions in risk mitigation or strategic enhancement. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Face Mask detection using Mask R-CNN to control the spread of Covid-19

Face Mask detection using Mask R-CNN to control the spread o...

引用

2023 IEEE International Conference on Recent Trends in Electronics and Communication, ICRTEC 2023

作者： Mohan, V.S. Abhay Gowda, G. Nair, Rekha R Kishore, S. Babu, Tina School of Engineering Dayananda Sagar University Department of Computer Applications Banglore India School of Engineering Dayananda Sagar University Department of Computer Science and Engineering Banglore India

ISBN: (纸本)9798350396195

Business executives are developing cutting-edge digital solutions as the virus outbreak spreads. A face mask detection system is one of them, and it can be used to spot people wearing them. Face mask identification software and applications have already been released by a few businesses, and others have promised to do the same for the service. The proposed work examines face mask detection accuracy using CNN networks. Mask wear is now required in many developed and developing countries worldwide when leaving the house or entering public spaces. It will be difficult to maintain touchless access control in buildings while recognising faces wearing masks on any surveillance systems. Masks covering faces has made face detection algorithms and performance difficult. The proposed work detect face mask labeled no mask or mask with detection accuracy. The work train the system to click images of a face and provide labeled data. The work is classified using Convolution Neural Network (CNN), a Deep learning technique, to classify the input image with the help of the classification algorithm MobileNetV2. The trained system shows whether a person in the video frame is wearing a mask or not. © 2023 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

mHAR: a novel convolutional recurrent model for recognizing motion-based human activity 12

mHAR: a novel convolutional recurrent model for recognizing ...

引用

12th International Young Scientists Conference in Computational science, YSC 2023

作者： Kumar, Prabhat Suresh, S. Department of Computer Science Institute of Science Banaras Hindu University Varanasi221 005 India Department of Computer Engineering & Applications GLA University Mathura281406 India Department of Computer Applications National Institute of Technology Kurukshetra136119 India

With sensors built into smartphones and wearable devices, Human Activity Recognition (HAR) makes it possible to identify regular activities. One of the challenges is to access the motion information from activity data and extract the features from this information. A general model trained without motion features may perform poorly while recognizing the contextual patterns in human activities. In this paper, we proposed the mHAR (motion HAR) model for recognizing static, gradual, and dynamic motion activity to address this challenge. We examine the impact of the proposed model against the general non-convolutional and convolutional recurrent networks in terms of accuracy rates and F1 score. As an experimental dataset, the publicly accessible WISDM was employed. Additionally, the findings of the experiments demonstrate that, in contrast to the unbalanced class problem, motion features play a significant role in activity recognition by achieving accuracy rates of 92.29% and an average F1 score of 83.33%. © 2023 The Authors. Published by Elsevier B.V.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Comparison of Faster RCNN and YOLO V3 for Video Anomaly Localization

Comparison of Faster RCNN and YOLO V3 for Video Anomaly Loca...

引用

2023 International Conference on Power, Instrumentation, Control and Computing, PICC 2023

作者： Anoopa, S. Salim, A. Nadera Beevi, S. College of Engineering Trivandrum Dept. of Computer Science and Engineering Kerala India Government Engineering College Thrissur Dept. of Computer Science and Engineering Kerala India Tkm College of Engineering and Technology Dept. of Computer Applications Kerala India

ISBN: (纸本)9798350334463

Video Anomaly Localization techniques are interesting and emerging tasks in computer vision that is used to locate the position of an anomalous object with bounding boxes. Convolutional neural network-based object localization methods have been developed which detect and classify objects with high precision and accuracy. Many algorithms have been developed for object detection and localization with excellent outcomes. These algorithms are fast RCNN, faster RCNN, and YOLO. In this paper, a comprehensive analysis of faster RCNN and YOLO V3 algorithms for anomaly localization is performed based on the parameters FPS, mAP, Precision, Recall and F1 Score. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Recent Developments in Botnet Detection Tools and Techniques for IoT Security: A Review 2

Recent Developments in Botnet Detection Tools and Techniques...

引用

2nd IEEE International Conference on Advancements and Key Challenges in Green Energy and Computing, AKGEC 2024

作者： Jain, Ruchi Nihalani, Neelu UIT-RGPV Department of Computer Science & Engineering M.P. Bhopal India UIT-RGPV Department of Computer Applications M.P. Bhopal India

ISBN: (纸本)9798350390179

The Internet of Things (IoT) embodies a paradigm shift in technology, connecting a diverse array of devices to enhance operational efficiency and user convenience across industries, educational settings, and urban infrastructures. This paper provides an in-depth examination of IoT's evolution, showcasing its profound impact on transforming traditional practices through interconnected smart systems. Despite its numerous advantages, the widespread adoption of IoT introduces significant challenges in cyber security and privacy. Recent high-profile cyber-attacks have underscored vulnerabilities inherent in IoT networks. This study delves into the growing threat of IoT botnets, sophisticated networks of compromised devices exploited by malicious actors for largescale attacks. It explores cutting-edge detection methodologies, including advanced deep learning models and architectural frameworks such as IoT-BDA, designed to proactively identify and mitigate these emerging threats. By critically analyzing current methodologies and technological innovations, this research aims to bolster awareness and develop robust strategies to safeguard IoT ecosystems. Ultimately, these efforts seek to establish a secure foundation that fosters continuous innovation and sustainable development within the IoT landscape. © 2024 IEEE.

关键词： Bot (Internet)

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：