检索结果-内蒙古大学图书馆

4th International Conference on Computing and Communications Technologies, ICCCT 2021

作者： Ponmalar, A. Rajkumar, K. Hariharan, U. Kalaiselvi, V.K.G. Deeba, S. Sri Sai Ram Institute of Technology Department of Information Technology Tamilnadu Chennai India Faculty of Engineering and Technology Department of Computer Science and Engineering Karnataka Bengaluru India Chandigarh University Apex Institute of Technology Department of Computer Science and Engineering Punjab Mohali India Sri Manakula Vinayagar Engineering College Department of Computer Science and Engineering Puducherry India

ISBN: (纸本)9781665414470

Content-based text classification system can automatically categories the text document into predefined limited classes. But the e-mail document classification is a challenging process in the modern internet environment. The e-mail documents are lightly signified in a great dimensional features space, creating a learning process, and the generalization (abstraction) process is problematic. Spam is unsolicited mail, the bulk of spam mails sent by the spammers who use vast e-mail programs to cover their characteristics and send the spam mails every day with no money. The spam mail directs various effects, including exposing unwanted images, decreasing company productivity, blocking Internet Service Providers' (ISP) networks, etc. Additionally, the spam mail contains an infection, which is gotten ready for some fake movement. Newline PSO is mighty in taking care of multivariable issues, where factors take on genuine qualities that are taken as new lines an independent method to arrange the datasets and contemplate the PSO-based Classifier for Multiclass Data Sets. Spam has become the foundation of decisions utilized by digital crooks to spread vindictive payloads, for example, infections and Trojans. Community-oriented spam recognition methods can manage the enormous scope of electronic communication information subsidized through numerous causes, and special issues needing exposure to electronic communication information. Distance-protecting hash standard arrangements utilized to save the security of electronic communication information while empowering mails orders to detect spam recognition. PSO, a Big Data security safeguarding synergistic spam identification stage based on top of a standard Map Reduce office. Without PSO feature selection, the training accuracy would be less. With the help of the best dataset fit, the classification result will be high. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Experimental Protocol for Biological Experiments on Petri Dishes

Experimental Protocol for Biological Experiments on Petri Di...

引用

International Conference on Measurement

作者： Marek Bajtoš Ladislav Janoušek Roman Radil Lucia Čarnecká Kristína Paulecová Department of Electromagnetic and Biomedical Engineering Faculty of Electrical Engineering and Information Technology University of Zilina Zilina Slovakia Department of Electrical Computer and Energy Engineering University of Colorado Boulder Boulder Colorado USA

In this paper, the experimental protocol for the further exposition of low-frequency magnetic fields on biological cells is established. Experiments for one-week mass controlling of Petri dishes with YPD agar and Saccharomyces cerevisiae inoculum are performed. Firstly, four groups of samples are prepared to find out the proper volume of inoculum with the lowest standard deviation between the samples. Secondly, the dedicated volume of inoculum is used for another set of experiments for comparison with YPD agar plates without the yeast cells. The statistical evaluation of two groups of data is determined.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning for Fetal Health Classification

引用

computer Systems Science & engineering 2023年第10期47卷 823-842页

作者： Mesfer Al Duhayyim Sidra Abbas Abdullah Al Hejaili Natalia Kryvinska Ahmad Almadhor Huma Mughal Department of Computer Science College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz University Al-Kharj16273Saudi Arabia Department of Computer Science COMSATS UniversityIslamabad53000Pakistan Faculty of Computers&Information Technology Computer Science DepartmentUniversity of TabukTabuk71491Saudi Arabia Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySakaka72388Saudi Arabia Information Systems Department Faculty of Management Comenius University in BratislavaOdbojárov 1082005 Bratislava 25Slovakia Department of Computer Science Kinnaird College for WomenLahore54000Pakistan

Cardiotocography(CTG)represents the fetus’s health inside the womb during ***,assessment of its readings can be a highly subjective process depending on the expertise of the *** signals from fetal monitors acquire parameters(i.e.,fetal heart rate,contractions,acceleration).Objective:This paper aims to classify the CTG readings containing imbalanced healthy,suspected,and pathological fetus ***:We perform two sets of ***,we employ five classifiers:Random Forest(RF),Adaptive Boosting(AdaBoost),Categorical Boosting(CatBoost),Extreme Gradient Boosting(XGBoost),and Light Gradient Boosting Machine(LGBM)without over-sampling to classify CTG readings into three categories:healthy,suspected,and ***,we employ an ensemble of the above-described classifiers with the *** use a random over-sampling technique to balance CTG records to train the ensemble *** use 3602 CTG readings to train the ensemble classifiers and 1201 records to evaluate *** outcomes of these classifiers are then fed into the soft voting classifier to obtain the most accurate ***:Each classifier evaluates accuracy,Precision,Recall,F1-scores,and Area Under the Receiver Operating Curve(AUROC)*** reveal that the XGBoost,LGBM,and CatBoost classifiers yielded 99%***:Using ensemble classifiers over a balanced CTG dataset improves the detection accuracy compared to the previous studies and our first experiment.A soft voting classifier then eliminates the weakness of one individual classifier to yield superior performance of the overall model.

关键词： Fetal health cardiotocography(CTG) ensemble learning adaptive boosting(AdaBoost) voting classifier

来源：评论

学校读者我要写书评

暂无评论

SYNCHRONIZATION BY NOISE FOR TRAVELING PULSES

arXiv

引用

arXiv 2025年

作者： Kuehn, Christian van Winden, Joris Technical University of Munich School of Computation Information and Technology Department of Mathematics Boltzmannstrasse 3 Garching85748 Germany Delft University of Technology Faculty of Electrical Engineering Mathematics and Computer Science Mekelweg 4 Delft2628 CD Netherlands

We consider synchronization by noise for stochastic partial differential equations which support traveling pulse solutions, such as the FitzHugh–Nagumo equation. We show that any two pulse-like solutions which start from different positions but are forced by the same realization of a multiplicative noise, converge to each other in probability on a time scale σ−2 t exp(σ−2), where σ is the noise amplitude. The noise is assumed to be Gaussian, white in time, colored and periodic in space, and non-degenerate only in the lowest Fourier mode. The proof uses the method of phase reduction, which allows one to describe the dynamics of the stochastic pulse only in terms of its position. The position is shown to synchronize building upon existing results, and the validity of the phase reduction allows us to transfer the synchronization back to the full *** Codes 60H15, 37H15, 37L30, 37L10 Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

FOGO - an Optimized Fog and Edge Computing Method for VANETs

FOGO - an Optimized Fog and Edge Computing Method for VANETs

引用

Proceedings of the International Convention MIPRO

作者： Renato Ćorluka Ivona Matoš Davor Damjanović Josip Balen Faculty of Electrical Engineering Computer Science and Information Technology Osijek Josip Juraj Strossmayer University of Osijek Kneza Trpimira 2b Osijek

Vehicular Ad-hoc Networks (VANETs) have many specific issues and challenges due to a heterogeneous and highly dynamic environment, and therefore traditional solutions need to be improved and adopted in order to satisfy the networking and processing requirements. Fog and edge computing principles enable VANETs to achieve a more realistic and dependable architecture by using several layers for information processing. In this paper, the developed FOGO method is improved and customized for VANETs. The proposed solution is using an enhanced infrastructure in which additional mobile fog nodes are added to the network together with the existing stationary nodes. Small and medium sized messages are processed by mobile fog nodes, which then disseminate the results across the network. Roadside units (RSUs) are fixed, highly-capable devices positioned throughout the network to assist the processing of increasing volumes of data. Additionally, the cloud is taken into account, but only when processing large amounts of data. Along with the presented method flowcharts, operating algorithms, and message structure, the proposed system architecture is described. Furthermore, potential use cases are suggested together with the metrics for the system performance evaluation. The LuST scenario was used to evaluate the proposed architecture and the results showed improved message processing efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Off-Shelf Deep Learning Architectures as Feature Extractor in CT COVID-19 Classification

Off-Shelf Deep Learning Architectures as Feature Extractor i...

引用

Emerging Trends in Computing and engineering Applications (ETCEA), International Conference on

作者： Haythem El-Messiry College of Engineering and Technology University of Science and Technology of Fujairah Fujairah UAE Departement of Computer Science Faculty of Computer and Information Science Ainsham university

ISBN: (纸本)9781665477109

Recently the chest imaging plays an important role in COVID-19 diagnosis compared to laboratory diagnosis such as RT-PCR. This paper investigates a robust algorithm to detect infected COVID-19 patients using computed tomography scans. The proposed algorithm utilizes a deep learning approach through applying an off shelf pretrained neural network to extract a feature map matrix from the first layer of convolutional neural network, which preserve the basic features related to geometry structures. Later the trained features are classified using a machine learning classifier as support vector machine algorithm to classify the tested images into two classes infected against not infected. The investigated algorithm was trained and tested using two open-source datasets. The results were experimented using five general pretrained off shelf CNN architectures, the performance of the pretrained algorithm was measured and evaluated for the extracted image features with popular five pretrained CNN and classification accuracy 90%.

关键词： COVID-19 Support vector machines Deep learning Machine learning algorithms Sensitivity Computational modeling Computed tomography

来源：评论

学校读者我要写书评

暂无评论

Co-Design of Phase Shifters and Antenna Elements For Series-Fed Arrays with Improved Performance (Invited)

Co-Design of Phase Shifters and Antenna Elements For Series-...

引用

IEEE Asia-Pacific Conference on Antennas and Propagation (APCAP)

作者： Yun-Peng Lyu Lei Zhu College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications Nanjing China Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macau SAR China

In this talk, we present the co-design of phase shifters and antenna elements for series-fed arrays (SFA) to improve the performance, including the wider return loss bandwidth, lower sidelobe level (SLL), smaller gain variation, and larger achievable radiation range. We find the return loss and current distribution bandwidths of series-fed network (SFN) in SFA are dominated by its the input reactance slope. The ratio of phase shifter’s impedance Z 0 and antenna element’s impedance Z L plays an important role in it. When the optimal Z 0 /Z L makes the input reactance slope equal to zero at the center frequency, the bandwidth of SFN can be highly extended by 2~4 times compared with non-optimal solutions. Herein, four classical types of SFNs are investigated and synthesized. The closed-form optimal formulas for these SFNs are further deduced under the specified element number N and current distributions I 1 , I 2 , … and I N . By virtue of the proposed co-design method, the designed SFA exhibits enhanced impedance and radiation bandwidths as predicted.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Digital Mirror technology for Securing IoT-Enabled Smart Infrastructures

AI-Driven Digital Mirror Technology for Securing IoT-Enabled...

引用

Integrated Intelligence and Communication Systems (ICIICS), International Conference on

作者： Jyoti Chaudhary Upma Jain Sudarshan N Vasudeva Pai Kamal Sutaria Natrayan L Department of Computer Engineering The Technological Institute of Textile and Sciences Bhiwani India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Department of Mechanical Engineering The National Institute of Engineering Mysuru India Department of Information Science and Engineering NMAM Institute of Technology (NITTE Deemed to be University) Karkala India Faculty of Engineering and Technology Parul institute of Engineering and Technology Vadodara India Department of Mechanical Engineering Saveetha School of Engineering Chennai India

ISBN: (数字)9798331504960

ISBN: (纸本)9798331504977

The expansion of the Internet of Things (IoT) is driven by the proliferation of interconnected wireless gadgets, made possible by ever-improving computer and Internet infrastructure. The IoT is an extensive system of interconnected sensors and gateways. In the course of their constant environmental interaction, IoT devices produce a wealth of data resources, including images, audio, video, digital signals, and more. Connectivity to the Internet allows all Internet of Things (IoT) equipment and apps to exchange data and resources more effectively. The proposed AI-Driven Digital Mirror technology effectively enhances the security of IoT-enabled smart infrastructures by integrating real-time monitoring, anomaly detection, and adaptive response mechanisms. By employing advanced AI algorithms such as Graph Neural Networks (GNNs) and Reinforcement Learning (RL), the technology mirrors IoT environments digitally, enabling dynamic modeling and threat assessment. The system demonstrated a significant improvement in threat detection accuracy, achieving a precision rate of 95.6% and a recall rate of 93.2% during simulations. Additionally, the adaptive response mechanism reduced the average response time to security breaches by 40%, ensuring minimal disruption to infrastructure operations. Comparative analysis with traditional security solutions highlighted the system's superiority in mitigating complex, multi-layered attacks, and its scalability makes it suitable for various smart infrastructure applications, including smart cities, industrial automation, and intelligent transportation systems. The results underscore the potential of AI-Driven Digital Mirror technology in securing IoT ecosystems against evolving cyber threats while maintaining operational efficiency and resilience.

关键词： Access control Analytical models Adaptation models Scalability Heuristic algorithms Biological system modeling Predictive models Threat assessment Internet of Things Mirrors

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Metaverse Tools Based on Privacy Model Using Fuzzy MCDM Approach 1

引用

3rd International Multi-Disciplinary Conference - Theme: Integrated Sciences and Technologies, IMDC-IST 2024

作者： Husin, Nor Azura Abdulsaeed, Ali A. Muhsen, Yousif Raad Zaidan, Ali Shakir Alnoor, Alhamzah Al-mawla, Zahraa Raad Department of Computer Science Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang Malaysia Civil Department College of Engineering Wasit University Kut Iraq School of Management Universiti Sains Malaysia Pulau Pinang11800 Malaysia Management Technical College Southern Technical University Basrah Iraq Department of Education University of Al-Mustansiriyah Baghdad10001 Iraq

ISBN: (数字)9783031517167

ISBN: (纸本)9783031517150

The issue of uncertainty in decision modelling for control engineering tools that support industrial cyber-physical metaverse smart manufacturing systems (ICPMSMSs) can be classified as a multi-criteria decision-making challenge for three primary reasons. Firstly, there are multiple components in the industry cyber-physical system (ICPS) that need to be taken into account. Secondly, these components vary in terms of their importance. Lastly, there is a variation in the available data. Despite substantial efforts, neither of the control engineering tools developed for ICPMSMSs has been capable of completely satisfying all ICPS aspects. As a result, choosing the best possible tool to support ICPMSMSs is a difficult process. Even though studies have evaluated control engineering tools, there are still unresolved issues regarding information ambiguity and uncertainty. In order to overcome these issues, this research improves the fuzzy weighted with zero inconsistency (FWZIC) method by adding Hexagonal Fuzzy Numbers to the process of assigning weights to the ICPS’s multiple components. Subsequently, the established Hexagonal-FWZIC method will be combined with the additive ratio assessments (ARAS) method to handle the rank in modelling control engineering tools. According to the results of the Hexagonal-FWZIC analysis, cybersecurity is the most influential factor, while the digital twin component has the least. The ARAS findings indicate that, of the ten tools studied, tools_1, tool_3, and tool_4 are the best three tools. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Identifying Relevant Features of CSE-CIC-IDS2018 Dataset for the Development of an Intrusion Detection System

arXiv

引用

arXiv 2023年

作者： Göcs, László Johanyák, Zsolt Csaba Department of Information Technology John von Neumann University GAMF Faculty of Engineering and Computer Science Izsáki út 10 Kecskemét Hungary

Intrusion detection systems (IDSs) are essential elements of IT systems. Their key component is a classification module that continuously evaluates some features of the network traffic and identifies possible threats. Its efficiency is greatly affected by the right selection of the features to be monitored. Therefore, the identification of a minimal set of features that are necessary to safely distinguish malicious traffic from benign traffic is indispensable in the course of the development of an IDS. This paper presents the preprocessing and feature selection workflow as well as its results in the case of the CSE-CIC-IDS2018 on AWS dataset, focusing on five attack types. To identify the relevant features, six feature selection methods were applied, and the final ranking of the features was elaborated based on their average score. Next, several subsets of the features were formed based on different ranking threshold values, and each subset was tried with five classification algorithms to determine the optimal feature set for each attack type. During the evaluation, four widely used metrics were taken into *** Codes 68T05 © 2023, CC BY.

关键词： Python

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：