检索结果-内蒙古大学图书馆

9th International Conference on Business and Industrial Research, ICBIR 2024

作者： Mayatopani, Hendra Murad, Dina Fitria Yahaya, Nor Adnan School of Computing University Malaysia of Computer Science and Engineering Selangor Malaysia Pradita University Information System Tangerang Indonesia Binus Online Bina Nusantara University Information Systems Department Jakarta Indonesia

ISBN: (纸本)9798350383010

In today's digital age, recommendation systems have become an important tool in many sectors, including education. This study presents a comprehensive bibliometric analysis of the literature related to recommendation systems in an educational context. Using major scientific databases and bibliometric analysis tools, we evaluate publications from the last 5 years to identify research trends, collaboration patterns, and methodological developments. Our results show a significant increase in the number of publications and interest in this field, with a wide variety of research themes ranging from personalized learning to optimization of educational resources. The most dominant analytics techniques include collaborative filtering and content-based filtering, while hybrid and deep learning approaches show growing potential. In addition, we identified geographic and institutional concentrations of research, as well as a set of challenges such as data privacy and the need for adaptation to learner dynamics. This research underscores the importance of recommendation systems in improving tailored educational experiences and supporting data-driven academic decisions. We also offer insights for future research directions, including the need for interdisciplinary research and closer international collaboration. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Toward Privacy-Preserving Spatial Crowdsourcing: From Offline to Online

引用

IEEE Network 2024年第3期39卷 326-332页

作者： Hengzhi Wang Junjie Mai Lei Zhang Linfeng Shen Laizhong Cui Jiangchuan Liu College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computing Science Simon Fraser University Burnaby BC Canada

Recent years have seen Spatial Crowdsourcing (SC) becoming a promising paradigm of collecting large amounts of location-aware data for various network applications. Its strengths lie in leveraging the power of the crowd to gather data effectively at a low cost. However, during the interaction process between SC participants (e.g., workers and task requestors) and the SC platform, participants’ sensitive information is inevitably exposed, raising severe privacy concerns. Existing studies addressing these privacy concerns have mostly focused on offline SC settings, where the participants’ information is known and accessible in advance. Yet real-world SC participants can be highly dynamic with uncertain behaviors; hence, in practice, their information is largely unknown a priori. In this article, we closely examine the privacy challenges as well as the trade-off between privacy and efficiency in online SC settings. We develop a comprehensive online privacy-preserving SC framework and analyze the critical implementation issues.

关键词： Privacy Costs Crowdsourcing Real-time systems Protection Vehicle dynamics Data privacy

来源：评论

学校读者我要写书评

暂无评论

An Overview of Using External Beacons with UAV for Navigation, Localization, and Information Exchange 6

An Overview of Using External Beacons with UAV for Navigatio...

引用

6th International Conference on Control and Robotics, ICCR 2024

作者： Phadke, Abhishek Hadimlioglu, Alihan School of Engineering and Computing Christopher Newport University Newport NewsVA United States Texas A&M University-Corpus Christi Department of Computer Science Corpus ChristiTX United States

ISBN: (纸本)9798331518158

UAVs (Unoccupied Aerial Vehicles) work in high-risk environments where disruptions and failures impede their progress. A UAV must exhibit a degree of robustness to these disruptions in order to conduct operations satisfactorily. Like all current vehicular robots, UAVs rely on GNSS (Global Navigation Satellite System) and onboard sensor data to perform navigation, communication, and execute critical actuated behaviors. However, these UAVs may often travel to regions where signal availability is sparse, and incidents arise when critical information such as location and telemetry from primary onboard sensors, ground control, or satellites is unavailable. In such cases, external beacon networks are the solution to address this information scarcity. In critical situations, these beacons can sometimes be the only source of information for an agent that could prevent catastrophic agent or mission failure. This study provides a comprehensive overview of external beacons supporting UAV operations. A taxonomy of sensors, beacons, and marker systems is provided, and four primary categories of beacon systems are discussed. Potential limitations in applying the solution and critical factors for proper implementation are also explored. © 2024 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Hybrid Malware Variant Detection Model with Extreme Gradient Boosting and Artificial Neural Network Classifiers

引用

Computers, Materials & Continua 2023年第9期76卷 3483-3498页

作者： Asma A.Alhashmi Abdulbasit A.Darem Sultan M.Alanazi Abdullah M.Alashjaee Bader Aldughayfiq Fuad A.Ghaleb Shouki A.Ebad Majed A.Alanazi Department of Computer Science Northern Border UniversityArar9280Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Information Systems College of Computer Science and InformationJouf UniversitySakakaAljoufSaudi Arabia School of Computing University Teknologi Malaysia81310 UTM Johor BahruJohor81310Malaysia Department of Computer and Electronic Engineering Sana’a Community CollegeSana’a5695Yemen

In an era marked by escalating cybersecurity threats,our study addresses the challenge of malware variant detection,a significant concern for amultitude of sectors including petroleum and mining *** paper presents an innovative Application Programmable Interface(API)-based hybrid model designed to enhance the detection performance of malware *** model integrates eXtreme Gradient Boosting(XGBoost)and an Artificial Neural Network(ANN)classifier,offering a potent response to the sophisticated evasion and obfuscation techniques frequently deployed by malware *** model’s design capitalizes on the benefits of both static and dynamic analysis to extract API-based features,providing a holistic and comprehensive view of malware *** these features,we construct two XGBoost predictors,each of which contributes a valuable perspective on the malicious activities under *** outputs of these predictors,interpreted as malicious scores,are then fed into an ANN-based classifier,which processes this data to derive a final *** strength of the proposed model lies in its capacity to leverage behavioral and signature-based features,and most importantly,in its ability to extract and analyze the hidden relations between these two types of *** efficacy of our proposed APIbased hybrid model is evident in its performance *** outperformed other models in our tests,achieving an impressive accuracy of 95%and an F-measure of 93%.This significantly improved the detection performance of malware variants,underscoring the value and potential of our approach in the challenging field of cybersecurity.

关键词： API-based hybrid malware detection model static and dynamic analysis malware detection

来源：评论

学校读者我要写书评

暂无评论

Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes 38

Lips Are Lying: Spotting the Temporal Inconsistency between ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Liu, Weifeng She, Tianyi Liu, Jiawei Li, Boheng Yao, Dongyu Liang, Ziyou Wang, Run Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China Nanyang Technological University Singapore Carnegie Mellon University United States

In recent years, DeepFake technology has achieved unprecedented success in high-quality video synthesis, but these methods also pose potential and severe security threats to humanity. DeepFake can be bifurcated into entertainment applications like face swapping and illicit uses such as lip-syncing fraud. However, lip-forgery videos, which neither change identity nor have discernible visual artifacts, present a formidable challenge to existing DeepFake detection methods. Our preliminary experiments have shown that the effectiveness of the existing methods often drastically decrease or even fail when tackling lip-syncing videos. In this paper, for the first time, we propose a novel approach dedicated to lip-forgery identification that exploits the inconsistency between lip movements and audio signals. We also mimic human natural cognition by capturing subtle biological links between lips and head regions to boost accuracy. To better illustrate the effectiveness and advances of our proposed method, we create a high-quality LipSync dataset, AVLips, by employing the state-of-the-art lip generators. We hope this high-quality and diverse dataset could be well served the further research on this challenging and interesting field. Experimental results show that our approach gives an average accuracy of more than 95.3% in spotting lip-syncing videos, significantly outperforming the baselines. Extensive experiments demonstrate the capability to tackle deepfakes and the robustness in surviving diverse input transformations. Our method achieves an accuracy of up to 90.2% in real-world scenarios (e.g., WeChat video call) and shows its powerful capabilities in real scenario deployment. To facilitate the progress of this research community, we release all resources at https://***/AaronComo/LipFD. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of Omicron Caused Pneumonia from Radiology Images Using Convolution Neural Network(CNN)

引用

Computers, Materials & Continua 2023年第2期74卷 3743-3761页

作者： Arfat Ahmad Khan Malik Muhammad Ali Shahid Rab Nawaz Bashir Salman Iqbal Arshad Shehzad Ahmad Shahid Javeria Maqbool Chitapong Wechtaisong College of Computing Khon Kaen UniverityKhon Kaen40000Thailand Department of Computer Science COMSATS University IslamabadVehari61100Pakistan Department of Petroleum&Gas Engineering University of Engineering&Technology54890Pakistan Electrical Engineering Department SBASSELahore University of Management SciencesLahore54890Pakistan School of Telecommunication Engineering Suranaree University of TechnologyNakhon Ratchasima30000Thailand

COVID-19 disease caused by the SARS-CoV-2 virus has created social and economic disruption across *** ability of the COVID-19 virus to quickly mutate and transfer has created serious concerns across the *** is essential to detectCOVID-19 infection caused by different variants to take preventive measures *** existing method of detection of infections caused by COVID-19 and its variants is costly and *** impacts of theCOVID-19 pandemic in developing countries are very drastic due to the unavailability of medical facilities and infrastructure to handle the *** is the major symptom of COVID-19 *** radiology of the lungs in varies in the case of bacterial pneumonia as compared to COVID-19-caused *** pattern of pneumonia in lungs in radiology images can also be used to identify the cause associated with *** this paper,we propose the methodology of identifying the cause(either due to COVID-19 or other types of infections)of pneumonia from radiology ***,because different variants of COVID-19 lead to different patterns of pneumonia,the proposed methodology identifies pneumonia,the COVID-19 caused pneumonia,and Omicron caused pneumonia from the radiology *** fulfill the above-mentioned tasks,we have used three Convolution Neural Networks(CNNs)at each stage of the proposed *** results unveil that the proposed step-by-step solution enhances the accuracy of pneumonia detection along with finding its cause,despite having a limited dataset.

关键词： COVID-19 pneumonia radiology images omicron convolution neural network(CNN) microscopy

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Skin Disease Diagnosis: Deep Learning Solution 1

Next-Generation Skin Disease Diagnosis: Deep Learning Soluti...

引用

1st International Conference on Technological Innovations and Advance computing, TIACOMP 2024

作者： Bhatt, Chandradeep Saini, Nancy Rathi, Garima Mishra, Pawan Kumar Graphic Era Hill University Cse Department Dehradun India Uttaranchal University Uttaranchal School of Computing Sciences Dehradun India Graphic Era Deemed to Be University Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350392111

Skin conditions are more prevalent than other illnesses. Fungal infections, bacterial infections, allergens, viruses, and other agents can cause skin problems. The development of photonics and laser-based medical technologies has accelerated the speed and accuracy of the analysis of skin conditions. Conversely, the cost of this kind of analysis is yet extremely high. As a result, image processing technology aids in the early development of automated dermatology screening systems. The process of characterizing traits is essential to the categorization of skin conditions. Computer vision may be used in a variety of ways to detect skin conditions. Skin conditions are widespread in deserts and hot climates. This paper advances the study of skin disorder recognition. We suggested using image processing to identify skin conditions. With this technique, the type of disease will be determined by image analysis applied to a digital image of the affected skin part. The method will function with a colored image as input. Next, use pretrained CNN to extract features from the image by resizing it. Following that, multiclass SVM will be used to categorize the features. Ultimately, the user will see the results, which include the disease's type, severity, and spread. © 2024 IEEE.

关键词： Alexnet deep learning algorithm eczema skin diseases detection

来源：评论

学校读者我要写书评

暂无评论

U-Net-Attention-TBNet: A Cutting-Edge Solution for Accurate TB Lesion Segmentation and Classification 8

U-Net-Attention-TBNet: A Cutting-Edge Solution for Accurate ...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Karthikeyan, M. Saravana Raj, J. Relin Francis Parvathi, R. Anushya, S. Thanga Krishnan, R. Santhana Joshua, K. Paul Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai Avadi India SaveethaInstitute of Medical and Technical Sciences Saveetha School of Engineering Department of Electronics and Communication Engineering Chennai India Department of Smart Computing Vellore India Scad College of Engineering and Technology Department of Computer Science and Engineering Cheranmahadevi India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India

ISBN: (纸本)9798350376425

U-Net-Attention-TBNet is an innovative deep-learning model developed for precisely segmenting and classifying tuberculosis (TB) lesions in chest X-ray images. This Model combines the U-Net architecture with an advanced attention mechanism, enhancing feature extraction and boosting detection accuracy. Trained on the CheXpert dataset, U-Net-Attention-TBNet demonstrates superior performance compared to existing models, including DenseNet with U-Net, ResNet with U-Net, and VGGNet with U-Net. It achieves significantly higher accuracy, precision, recall, and F1 score, showcasing its effectiveness in distinguishing between primary TB lesions, secondary TB lesions, miliary TB lesions, and calcified granulomas. The attention mechanism refines the Model's ability to focus on pertinent features, leading to improved segmentation and reduced false positives. This progress represents a significant advancement in TB diagnosis, offering enhanced reliability and efficiency in medical imaging and contributing to better management of tuberculosis. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Simplifying Graph-Parallel Computation in Apache Spark with GraphX 8

Simplifying Graph-Parallel Computation in Apache Spark with ...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Vyakaranam, Lasya Raman, Ramakrishnan Shah, Harshal Mishra, Nilamadhab Meenakshi, R. Murugan, S. Pune Maharashtra Pune India Maharashtra Pune India Parul Institute of Engineering and Technology Parul University Faculty of Engineering and Technology Gujarat Vadodara India Vit Bhopal University School of Computing Science and Engineering Madhya Pradesh India Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350367904

Streamlining Apache graph-parallel computing the goal of integrating Spark with GraphX is to make processing massive amounts of graph data easier and faster. The goal is to streamline the process of creating and running graph algorithms by using GraphX, a Spark-based distributed graph processing platform. The eventual objective is to create a scalable platform that is easy to use for graph-structured data analysis and manipulation. Improving GraphX's performance, expanding its features, and integrating it with Spark's ecosystem are all part of this process. The expected result is a flexible and strong framework that lets data scientists and developers execute complicated graph analytics tasks with ease. This will pave the way for applications in many fields, including recommendation systems, social network analysis, and biological network analysis. Optimizing performance in graph-parallel computer situations, making the development process easier, and making it more scalable are the main goals. The graph structure visualization results in graph data revealing values in the range of 1.2 to 5.6 for a sample of five distinct vertex/edge types. The degree distribution histogram in the same dataset shows that, for five different frequencies, the numbers range from around 1.5 to 4.5. For the same dataset, the PageRank Convergence Plot shows values ranging from 0.4 to 0.9 for five distinct iterations/scores. © 2024 IEEE.

关键词： Apache Spark Big Data Graph Analytics Graph-Parallel Computation GraphX

来源：评论

学校读者我要写书评

暂无评论

A robust deep structured prediction model for petroleum reservoir characterization using pressure transient test data

引用

Petroleum Research 2022年第2期7卷 204-219页

作者： Rakesh Kumar Pandey Anil Kumar Ajay Mandal Department of Petroleum and Energy Studies School of Engineering and TechnologyDIT UniversityDehradun248009India Data Science Research Group School of ComputingDIT UniversityDehradun248009India Department of Petroleum Engineering Indian Institute of Technology(Indian School of Mines)Dhanbad826004India

A robust deep learning model consisting of long short-term memory and fully connected neural net-works has been proposed to automatically interpret homogeneous petroleum reservoirs having infinite,no flow,and constant pressure outer boundary *** pressure change data recorded during the well test operation along with its derivative is input into the model to perform the classification for identifying the reservoir model and,further,regression to estimate output *** noise was added to analytical models while generating the synthetic training *** hyperparameters were regulated to perform model optimization,resulting in a batch size of 64,Adam optimization algorithm,learning rate of 0.01,and 80:10:10 data split ratio as the best choices of *** perfor-mance accuracy also increased with an increase in the number of samples during *** classification and regression metrics have been used to evaluate the performance of the *** paper also demonstrates the prediction performance of the optimized model using simulated and actual oil well pressure drawdown test *** proposed model achieved minimum and maximum relative errors of 0.0019 and 0.0308,respectively,in estimating output for the simulated test cases and relative error of 0.0319 for the real test case.

关键词： Well test Reservoir characterization Automatic interpretation Prediction model Hyperparameter tuning Performance indicator

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：