检索结果-内蒙古大学图书馆

Detection of Misinformation Related to Pandemic Diseases using Machine Learning Techniques in Social Media Platforms

引用

EAI Endorsed Transactions on Pervasive Health and Technology 2024年 10卷

作者： Naeem, J. Gul, O.M. Parlak, I.B. Karpouzis, K. Salman, Y.B. Kadry, S.N. Department of Computer Engineering Bahcesehir University Istanbul Turkey Informatics Institute Istanbul Technical University Istanbul Turkey Department of Computer Engineering Galatasaray University Istanbul Turkey Panteion University of Social and Political Sciences Greece Department of Software Engineering Bahcesehir University Istanbul Turkey Department of Applied Data Science Noroff University College Kristiansand Norway Ajman University Ajman346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon MEU Research Unit Middle East University Amman11831 Jordan

INTRODUCTION: The advent of the COVID-19 pandemic has brought with it not only a global health crisis but also an infodemic characterized by the rampant spread of misinformation on social media platforms. OBJECTIVES: In response to the urgent need for effective misinformation detection, this study presents a comprehensive approach harnessing machine learning and deep learning techniques, culminating in ensemble methods, to combat the proliferation of COVID-19 misinformation on Facebook, Twitter, Instagram, and YouTube. METHODS: Drawing from a rich dataset comprising user comments on these platforms, encompassing diverse COVID-19-related discussions, our research applies Support Vector Machine (SVM), Decision tree, logistic regression, and neural networks to perform in depth analysis and classification of comments into two categories: positive and negative information. The innovation of our approach lies in the final phase, where we employ ensemble methods to consolidate the strengths of various machine learning and deep learning algorithms. This ensemble approach significantly improves the model’s overall accuracy and adaptability. RESULTS: Experimental results underscore the efficacy of our methodology, showcasing marked improvements in detection performance compared to individual models. After applying ensemble learning, we achieve an accuracy of 91% for Facebook data, 79% for Instagram data, 80% for Twitter data and 95% for YouTube data. CONCLUSION: Our system not only aids in curbing the dissemination of COVID-19 misinformation but also provides a robust framework for addressing misinformation across various contexts on social media platforms. © 2024 J. Naeem et al., licensed to EAI.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Analysis and Optimization of Garbage Removal System in Jiamusi City 2

Analysis and Optimization of Garbage Removal System in Jiamu...

引用

2020 2nd International Conference on Advances in Civil engineering, Energy Resources and Environment engineering, ACCESE 2020

作者： Jia, Xiaoqian Sun, Yanbin Wen, Bin Zhang, Yuehua Guan, Jinqiu Li, Lan College of Science Jiamusi University Jiamusi City Heilongjiang Province154007 China College of Big Data and Software Engineering Wuzhou University Wuzhou City Guangxi province543000 China

With the development of the social environment, the amount of urban domestic garbage has increased rapidly, and garbage removal has become particularly important, which severely affects social-environmental resources. At present, the level of waste disposal Jiamusi City, far behind the rate of discharge of garbage, removal of garbage, and recycling efficiency is not high. To reduce environmental damage and waste of resources, it is necessary to improve the efficiency of waste removal and recycling. This paper analyses the current situation of the garbage removal and transportation system in Jiamusi City, establishes a mathematical model to solve it in mat lab, and uses genetic algorithm and particle swarm optimization to obtain the optimal path for garbage transportation. Combined with example verification, the results of the two algorithms are obtained and compared respectively, and an algorithm suitable for optimizing the waste removal path is derived. © Published under licence by IOP Publishing Ltd.

关键词： Waste disposal

来源：评论

学校读者我要写书评

暂无评论

Screening of Phosphate-Resolving Bacteria in Rhizosphere of Cold Sunflower and Physiological and Biochemical Study 2

Screening of Phosphate-Resolving Bacteria in Rhizosphere of ...

引用

2020 2nd International Conference on Advances in Civil engineering, Energy Resources and Environment engineering, ACCESE 2020

作者： Ba, Huifen Jiang, Huimin Shen, Penglin Cao, Yajie Song, Yujun Li, Lan College of Science Jiamusi University Jiamusi City Heilongjiang Province154007 China College of Big Data and Software Engineering Wuzhou University Wuzhou City Guangxi Province543000 China

The purpose of the experiment is to obtain high-efficiency microbial phosphorus dephosphorization fertilizer, increase the soluble phosphorus content of the soil, and promote plant growth. The phosphorus detoxifying bacteria in sunflower rhizosphere were studied through dilution and coating plate method, molybdenum-antimony anti-spectrophotometry, plate culture, physiological and biochemical detection. 10 strains were isolated and purified to form bright rings, D/d value is between 1.10-4.35. The quantitative analysis of the pressure showed that BX2 had the best effect in dissolving phosphorus. The available phosphorus increment was 38.59μg/mL, BX7 had the lowest phosphorus dissolving effect, and the effective phosphorus increase was only 1.77μg/mL. These strains of BX2, BX3, BX5, BX9 and BX10 have excellent phosphorus-dissolving properties, providing necessary conditions for the subsequent development of microbial fertilizer. © Published under licence by IOP Publishing Ltd.

关键词： Phosphorus

来源：评论

学校读者我要写书评

暂无评论

An Autonomous Mobile Robot Path Planner using Spline Curves and Differential Evolution

An Autonomous Mobile Robot Path Planner using Spline Curves ...

引用

Latin America Congress on Computational Intelligence (LA-CCI)

作者： Elias José de Rezende Freitas Miri Weiss Cohen Frederico Gadelha Guimarães Graduate Program in Electrical Engineering Universidade Federal de Minas Gerais Av. Antônio Carlos 6627 Belo Horizonte MG Brazil Federal Institute of Minas Gerais IFMG Department of Software Engineering Braude College of Engineering Karmiel Israel Department of Electrical Engineering Machine Intelligence and Data Science Laboratory (MINDS) Universidade Federal de Minas Gerais UFMG Belo Horizonte MG Brazil

Robots that operate autonomously require a path planner that ensures the robot reaches the desired position in a safe manner. The robot will be able to achieve greater speeds along the path if the path is smooth, minimizing the effort of the controller. This work presents two new path planners, called DE-Spline and DE-NURBS. These planners provide a smooth path directly by the cost function optimization using the algorithm L-SHADE (Success-History based Adaptive of Differential Evolution using linear population size reduction algorithm) and two path’s parametrization: Ferguson cubic spline and NURBS. Additionally, it ensures that the robot reaches the target in the desired orientation. The planners are compared with a Vector Field-based planner, widely used in robot soccer. Based on the results, it has been found that both planners provide a smoother path along the shortest path, by accounting for the robot’s starting angle and its goal angle. Furthermore, DE-NURBS provides a greater degree of planning freedom than DESpline.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MIKE11 Model in Water Quality Research of Songhua River in Jiamusi City 2

MIKE11 Model in Water Quality Research of Songhua River in J...

引用

2020 2nd International Conference on Advances in Civil engineering, Energy Resources and Environment engineering, ACCESE 2020

作者： Chi, Jianan Sun, Yanbin Zhang, Yuehua Wang, Xue Cao, Yajie Li, Lan College of Science Jiamusi University Jiamusi City Heilongjiang Province154007 China College of Big Data and Software Engineering Wuzhou University Wuzhou City Guangxi Province543000 China

The monitoring data of chemical oxygen demand and NH3-N in the upper and lower sections of Jiamusi City in Songhua River were analyzed, and the law of water quality change in Songhua River in Jiamusi City was explored. Based on the simulation results of MIKE11 model for the water from the interval, the minimum ecological safety distance of the upper and lower reaches of Songhua River in Jiamusi city is predicted. Between the rainy season and the standard water period, the Jiamusi section meets the minimum ecological safety distance between Tangyuan County and there is no minimum safety distance during the dry season. The MIKE11 model has good adaptability to the diffusion simulation of pollutants in the upper and lower reaches of the Songhua River in Jiamusi and can be used as an evaluation basis for analyzing the impact of the water quality of the sewage outlet of the river. © Published under licence by IOP Publishing Ltd.

关键词： Water quality

来源：评论

学校读者我要写书评

暂无评论

Transfer learning architectures with fine-tuning for brain tumor classification using magnetic resonance imaging

引用

Healthcare Analytics 2023年 4卷 100270-100270页

作者： Islam, Md. Monirul Barua, Prema Rahman, Moshiur Ahammed, Tanvir Akter, Laboni Uddin, Jia Department of Software Engineering Daffodil International University Daffodil Smart City (DSC) Birulia Savar Dhaka 1216 Bangladesh Department of Computer Science and Engineering University of Information Technology and Sciences (UITS) Dhaka 1212 Bangladesh AI and Big Data Department Endicott College Woosong University South Korea

Deep learning methods in artificial intelligence are used for brain tumor diagnosis as they handle a huge amount of data. Compared to computerized tomography (CT), Ultrasound, and X-ray imaging, Magnetic Resonance Imaging (MRI) is effectively used for machine vision-based brain tumor diagnosis. However, due to the complex nature of the brain, brain tumor diagnosis is always challenging. This research aims to study the effectiveness of deep transfer learning architectures in brain tumor diagnosis. This paper applies four transfer learning architectures- InceptionV3, VGG19, DenseNet121, and MobileNet. We used a dataset with data from three benchmark databases of figshare, SARTAJ, and Br35H to validate the models. These databases have four classes: pituitary, no tumor, meningioma, and glioma. Image augmentation is applied to make the classes balanced. Experimental results demonstrate that the MobileNet outperforms competing methods by exhibiting an accuracy of 99.60%. © 2023 The Author(s)

关键词： Artificial intelligence Brain tumor Computerized tomography Deep learning Magnetic resonance imaging Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Detection with Graph Simplification and Enhanced Graph Representation Learning

arXiv

引用

arXiv 2023年

作者： Wen, Xin-Cheng Chen, Yupan Gao, Cuiyun Zhang, Hongyu Zhang, Jie M. Liao, Qing School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Big Data and Software Engineering Chongqing University China Department of Informatics King’s College London United Kingdom Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies China Peng Cheng Laboratory China

Prior studies have demonstrated the effectiveness of Deep Learning (DL) in automated software vulnerability detection. Graph Neural Networks (GNNs) have proven effective in learning the graph representations of source code and are commonly adopted by existing DL-based vulnerability detection methods. However, the existing methods are still limited by the fact that GNNs are essentially difficult to handle the connections between long-distance nodes in a code structure graph. Besides, they do not well exploit the multiple types of edges in a code structure graph (such as edges representing data flow and control flow). Consequently, despite achieving state-of-the-art performance, the existing GNN-based methods tend to fail to capture global information (i.e., long-range dependencies among nodes) of code graphs. To mitigate these issues, in this paper, we propose a novel vulnerability detection framework with grAph siMplification and enhanced graph rePresentation LEarning, named AMPLE. AMPLE mainly contains two parts: 1) graph simplification, which aims at reducing the distances between nodes by shrinking the node sizes of code structure graphs;2) enhanced graph representation learning, which involves one edge-aware graph convolutional network module for fusing heterogeneous edge information into node representations and one kernel-scaled representation module for well capturing the relations between distant graph nodes. Experiments on three public benchmark datasets show that AMPLE outperforms the state-of-the-art methods by 0.39%-35.32% and 7.64%-199.81% with respect to the accuracy and F1 score metrics, respectively. The results demonstrate the effectiveness of AMPLE in learning global information of code graphs for vulnerability detection. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Construction Cost Index Forecasting: A Multi-feature Fusion Approach

arXiv

引用

arXiv 2021年

作者： Zhan, Tianxiang He, Yuanpeng Xiao, Fuyuan College of Computer and Information Science College of Software Southwest University Chongqing400715 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology China

The construction cost index is an important indicator of the construction industry. Predicting CCI has important practical significance. This paper combines information fusion with machine learning, and proposes a multi-feature fusion (MFF) module for time series forecasting. Compared with the convolution module, the MFF module is a module that extracts certain features. Experiments have proved that the combination of MFF module and multi-layer perceptron has a relatively good prediction effect. The MFF neural network model has high prediction accuracy and efficient prediction efficiency. At the same time, MFF continues to improve the potential of prediction accuracy, which is a study of continuous attention. Copyright © 2021, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Automatic Repeat Request Design in AoI-Aware Broadcast With Heterogeneous Direct and Relay-Assisted Users

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Xueer Pan, Haoyuan Chan, Tse-Tin Li, Jianqiang Shenzhen University College of Computer Science and Software Engineering Shenzhen China The Education University of Hong Kong Department of Mathematics and Information Technology Hong Kong Shenzhen University National Engineering Laboratory for Big Data System Computing Technology The College of Computer Science and Software Engineering Shenzhen China

This paper investigates the design of automatic repeat request (ARQ) protocols in age of information (AoI)-aware broadcast systems with heterogeneous users, including both direct and relay-assisted users. In this setup, a direct user receives status updates directly via a single-hop link, while a relay-assisted user can receive status updates through either a direct single-hop link or a two-hop relay-assisted link. While ARQ is commonly used to ensure reliable transmission in error-prone wireless networks, previous studies suggest that ARQ does not improve the average AoI in single-hop networks. However, its impact on AoI in systems with relays, particularly those involving heterogeneous users, remains unclear. We address this gap by analyzing the average AoI under different ARQ strategies, introducing a transmission limit k ≥ 0 at the relay. Here, k = 0, k = 1, and k > 1 correspond to non-relay, non-ARQ-at-relay, and truncated-ARQ-at-relay strategies, respectively. Utilizing a unified Markov chain framework that models the transmission processes for each user type, we derive the theoretical average AoI. Our results show that the direct user benefits most from non-relay and non-ARQ strategies, similar to single-hop systems. In contrast, the relay-assisted user achieves optimal performance with truncated-ARQ-at-relay, leveraging both direct and relay-assisted links. For the overall system, applying a non-ARQ-at-relay approach strikes a balance in AoI between the direct and relay-assisted users, leading to a more stable and lower system-wide average AoI. © 2014 IEEE.

关键词： Mobile telecommunication systems

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attacks on Large Language Model-Based System and Mitigating Strategies: A Case Study on ChatGPT

引用

Security and Communication Networks 2023年第1期2023卷

作者： Liu, Bowen Xiao, Boao Jiang, Xutong Cen, Siyuan He, Xin Dou, Wanchun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen China School of Computer Science & Technology Nanjing University of Posts and Telecommunications Nanjing China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China

Machine learning algorithms are at the forefront of the development of advanced information systems. The rapid progress in machine learning technology has enabled cutting-edge large language models (LLMs), represented by GPT-3 and ChatGPT, to perform a wide range of NLP tasks with a stunning performance. However, research on adversarial machine learning highlights the need for these intelligent systems to be more robust. Adversarial machine learning aims to evaluate attack and defense mechanisms to prevent the malicious exploitation of these systems. In the case of ChatGPT, adversarial induction prompt can cause the model to generate toxic texts that could pose serious security risks or propagate false information. To address this challenge, we first analyze the effectiveness of inducing attacks on ChatGPT. Then, two effective mitigating mechanisms are proposed. The first is a training-free prefix prompt mechanism to detect and prevent the generation of toxic texts. The second is a RoBERTa-based mechanism that identifies manipulative or misleading input text via external detection models. The availability of this method is demonstrated through experiments. © 2023 Bowen Liu et al.

关键词： Machine learning

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：