检索结果-内蒙古大学图书馆

Advance Computing and Innovative Technologies in Engineering (ICACITE), International Conference on

作者： Aadithyan G Kassem Al-Attabi Hayder Shareef Dibyahash Bordoloi Sahar R. Abdul Kadeem Osama Nazim Saadoun Ahmed Qusay Jawad Department of computer applications Hindustan institute of technology and science Department of computers Techniques engineering College of technical engineering The Islamic university Najaf Iraq Al-Farahidi university Baghdad Iraq Dept of CSE Graphic Era Hill University Graphic Era Deemed to be University Dehradun Uttarakhand College of Engineering National University of Science and Technology Dhi Qar Iraq Law Department Al-kunooze University College Basra Iraq Department of Electrical Engineering Technologies Kut University College Wasit Iraq

ISBN: (数字)9798350360165

ISBN: (纸本)9798350360172

Most databases on healthcare have the problem of missing data. The most common method for handling missing data is imputation. The basic idea of imputation is to replace each missing value with a sensible guess, and then to carry on the analysis as if the missing data has never occurred. However, objective predictions with imputed datasets can only be generated if the missing mechanism is fully independent of the present or missing data. This guarantee is often broken in the construction of healthcare datasets due to bias in respondent responses or unintentional errors. The algorithm, therefore, offers an integrated approach to feature selection and missing value imputation to enhance the classification accuracy. The dataset D, of size M, is thus divided into training (D_tr) and test (D_te) sets. The operations are first conducted on the complete data subset D_complete, resulting in a subset reduced to D_complete’ based on the feature selection algorithm. Similarly, incomplete samples of D_tr are reduced to D_incomplete’. Missing values of D incomplete’ are imputed through a learning model trained on D_complete’, after which the same operations are conducted for the test set D_te. Experiments on five UCI datasets show that, even in the presence of reduced-class instances, the feature selection significantly enhances the classification accuracy as compared to the baseline imputation models at different missing rates. Moreover, DT tends to be oversensitive in selecting the features, while GA and IG behave similarly, suggesting that one needs ad-hoc feature selection methodologies to attain improved imputation and classification performances.

关键词： Training Accuracy Databases Medical services Feature extraction Prediction algorithms Imputation

来源：评论

学校读者我要写书评

暂无评论

Adversarial laws of large numbers and optimal regret in online classification

arXiv

引用

arXiv 2021年

作者： Alon, Noga Moran, Shay Ben-Eliezer, Omri Naor, Moni Dagan, Yuval Yogev, Eylon Department of Mathematics Princeton University PrincetonNJ United States Schools of Mathematics and Computer Science Tel Aviv University Tel Aviv Israel Center for Mathematical Sciences and Applications Harvard University MA United States Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology CambridgeMA United States Department of Mathematics Technion Israel Department of Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot Israel Department of Computer Science Boston University Department of Computer Science Tel Aviv University Israel

Laws of large numbers guarantee that given a large enough sample from some population, the measure of any fixed sub-population is well-estimated by its frequency in the sample. We study laws of large numbers in sampling processes that can affect the environment they are acting upon and interact with it. Specifically, we consider the sequential sampling model proposed by Ben-Eliezer and Yogev (2020), and characterize the classes which admit a uniform law of large numbers in this model: these are exactly the classes that are online learnable. Our characterization may be interpreted as an online analogue to the equivalence between learnability and uniform convergence in statistical (PAC) learning. The sample-complexity bounds we obtain are tight for many parameter regimes, and as an application, we determine the optimal regret bounds in online learning, stated in terms of Littlestone’s dimension, thus resolving the main open question from Ben-David, Pál, and Shalev-Shwartz (2009), which was also posed by Rakhlin, Sridharan, and Tewari (2015). Copyright © 2021, The Authors. All rights reserved.

关键词： Environmental regulations

来源：评论

学校读者我要写书评

暂无评论

A nonconservative kinetic model under the action of an external force field for modeling the medical treatment of autoimmune response

arXiv

引用

arXiv 2023年

作者： Menale, Marco Travaglini, Romina Department of Mathematics and Applications "R. Caccioppoli" University of Naples "Federico II" Via Cintia Monte S. Angelo NapoliI-80126 Italy INDAM National Institute for Advanced Mathematics Department of Mathematical Physical and Computer Science University of Parma Parco Area delle Scienze 53/A ParmaI-43124 Italy

In this paper, we develop a nonconservative kinetic framework to be applied to the study of immune system dysregulation. From the modeling viewpoint, the model regards a system composed of stochastically interacting agents, under the action of an eternal force field. According to the application perspectives of this paper, the external force field has a specific analytical shape. In this case, some analytical results are proved, i.e. existence, uniqueness, positivity, and boundedness of solution of the related Cauchy problem, at least locally in time. Then, the model is refined to be implemented for the study of treatment strategies in case of autoimmune response. Specifically, we distinguish the autonomous case from the nonautonomous one, representing the absence or delivery of drugs, respectively. The former allows us to gain some stability results. Whereas, the latter is qualitatively studied. Numerical simulations are provided for both schemes. © 2023, CC BY-NC-ND.

关键词： Kinetic theory

来源：评论

学校读者我要写书评

暂无评论

Optimizing Advertising Campaigns through Advanced Deep Learning-Driven Audience Segmentation for Enhanced Targeting and Engagement 3

Optimizing Advertising Campaigns through Advanced Deep Learn...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Nikhil, Gunda Anil, P.S. Obaid, Saif Sehgal, Archana Kuppuraj, T. Saravanan K, Aanandha Digital Connect Hyderabad India Gnanam School of Business Department of Management Mary's junction Sengipatti TamilNadu Thanjavur India College of technical engineering The Islamic University Department of computers Techniques engineering Najaf Iraq Lovely Professional University Punjab Phagwara India Karpagam Academy of Higher Education Department of Computer Applications Coimbatore India Veltech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Ece Chennai India

ISBN: (纸本)9798331542375

The present work discusses the utilization of deep learning techniques for precise dividing the audience for advertising in order to increase efficiency and effectiveness of campaigns. Hence, the paper employs a diverse dataset of consumers' demographic data, purchase history, social media activity, and reviews and design a hybrid deep learning model using CNN, RNN-LSTM, and attention mechanisms. In all the assessment measurements of accuracy, precision, recall, and Fl-score, this model offers better results compared with the old-shoot segmentation methods. The performance analysis depicts great enhancements in CTR, conversion rate, as well as ROAS all of which highlight a superior engagement of the ads. Indeed, the outcome points to the effectiveness of deep learning in digital marketing that can provide clients with more efficient advertising tools. Nonetheless, the issues regarding computational capabilities and ethical concerns pose viable and useful innovations and solutions, thus contributing to the progression of deep learning theories in audience segmentation and advertising. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Solution of fractional order random ordinary differential equations using variational iteration method

引用

AIP Conference Proceedings 2024年第1期3097卷

作者： Sahar A. Mohammed Fadhel S. Fadhel Kasim A. Hussain Department of Mathematics College of Science Mustansiriyah University Baghdad Iraq Department of Mathematics and Computer Applications College of Science Al-Nahrain University Jadriya Baghdad-Iraq

The variational iteration approach is introduced in this article to solve linear and nonlinear fractional order random ordinary differential equations., in which it is possible sometimes, especially for linear problems to find the exact solution in a few iterations using this method or finding the approximate solution of the problem, which is most cases very accurate. This technique provides of evaluating a sequence of functions, which is proved to be converge to the exact solution of the problem under consideration. The variational iteration method is a powerful method used to solve a large class of linear and nonlinear problems involving also fractional order random ordinary differential equations, more easily and accurately, and thus it has been widely used in engineering and physical problems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Approximate solution of fractional order random ordinary differential equations using homotopy perturbation method

引用

AIP Conference Proceedings 2024年第1期3097卷

In this paper, the homotopy perturbation method will be applied to find the approximate solution of fractional order random ordinary differential equations, in which the fractional order derivatives and integrals are defined using Caputo and Riemann-Liouville definitions of fractional derivatives and integrals, respectively. Also, the convergence of the approximated solution is stated and proved in this work. The work is verified for three different examples, which are simulated for different generations of Brownian motion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HRED, an active queue management algorithm for TCP congestion control

引用

Recent Patents on computer science 2019年第3期12卷 212-217页

作者： Hamadneh, Nabhan Obiedat, Mamoon Qawasmeh, Ahmad Bsoul, Mohammad Computer Science and Applications Department Hashemite University P.O. Box 21233 Zarqa Jordan

Background: Active Queue Management (AQM) is a TCP congestion avoidance approach that predicts congestion before sources overwhelm the buffers of routers. Random Early Detection (RED) is an AQM strategy that keeps history of queue dynamics by estimating an average queue size parameter avg and drops packets when this average exceeds preset thresholds. The parameter configuration in RED is problematic and the performance of the whole network could be reduced due to wrong setup of these parameters. Drop probability is another parameter calculated by RED to tune the drop rate with the aggressiveness of arriving packets. Objective: In this article, we propose an enhancement to the drop probability calculation to increase the performance of RED. Methods: This article studies the drop rate when the average queue size is at the midpoint between the minimum and maximum thresholds. The proposal suggests a nonlinear adjustment for the drop rate in this area. Hence, we call this strategy as the Half-Way RED (HRED). Results: Our strategy is tested using the NS2 simulator and compared with some queue management strategies including RED, TD and Gentle-RED. The calculated parameters are: throughput, link utilization and packet drop rate. Conclusion: Each performance parameter has been plotted in a separate figure;then the robustness of each strategy has been evaluated against these parameters. The results suggest that this function has enhanced the performance of RED-like strategies in controlling congestion. HRED has outperformed the strategies included in this article in terms of throughput, link utilization and packet loss rate. © 2019 Bentham science Publishers.

关键词： Transmission control protocol

来源：评论

学校读者我要写书评

暂无评论

Radio Resource Management for Hybrid Satellite-Terrestrial Network 3

Radio Resource Management for Hybrid Satellite-Terrestrial N...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Revathy, S. Maharishi, Intekhab Alam Minhas, Deepak Tripathy, Jogeswar Soni, Ishika Vinay Kumar, S.B. Sathyabama Institute of Science and Technology Department of Information Technology Tamil Nadu Chennai India School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India Department of Computer Applications Odisha Bhubaneswar India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh Baddi174103 India Kamataka Bangalore India

ISBN: (纸本)9798331542375

Hybrid satellite-terrestrial networks demand proficient coordination of Radio Resource Management (RRM). Together, these networks offer the best of both satellite and terrestrial communicative technologies for fast and widespread connectivity. However, it is a difficult task to manage the limited radio resources involved in this very heterogeneous environment. The main goal of RRM in hybrid satellite-terrestrial networks is to provide efficient resource utilization and quality of service support for different applications. They touch on areas such as interference management, spectrum sharing, handover between satellite links, and offloading to terrestrial networks. In order to make RRM more efficient, the following techniques are used during resource allocation: adaptive modulation and coding (AMC), dynamic scheduling, and power control. Such techniques exploit network topology, propagation conditions, and user location to increase spectral efficiency and reduce interference. © 2025 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Improving Energy Efficiency using Colliding Bodies Optimization based Routing Protocol for Wireless Sensor Networks

Improving Energy Efficiency using Colliding Bodies Optimizat...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： P. Prabakaran R. Shalini N Hariharan S. Marieswari Kallakunta Ravi Kumar Maturi Gayatri Lakshmi Apoorva Department of Computer Applications School of Computing Sciences Vels Institute of Science Technology and Advanced Studies Chennai Department of BCA & IT School of Computing Sciences Vels Institute of Science Technology and Advanced Studies Chennai Science and Humanities – EEE R.M.K. College of Engineering and Technology Thiruvallur India Biomedical Engineering P. S. R. Engineering College Department of ECE Koneru Lakshmaiah Education Foundation Vaddeswaram ECE Department Amrita School of Engineering

Wireless sensor network (WSN) contains millions of small, low-power gadgets with a lack of resources are memory and battery power. Such gadgets were deployed in a dispersed manner and were often utilized to monitor and sense applications. Owing to constraints and limited resources of WSNs, routing can be a great difficulty. Routing in WSN was the process of choosing the optimal path for data to travel from a source node to a destination node. The goal of routing in WSN offer dependable and effective transmission while minimizing network overhead and energy consumption. This study designs an Energy Efficient Colliding Bodies Optimization based Routing Protocol (EECBO-RP) for WSN. The end goal of the EECBO-RP algorithm lies in the optimal election of routes to a destination. For achieving reasonable results for the minimization of energy exploitation, the EECBO-RP system derives the fitness function using the following variables: residual energy, distance to BS, and node degree. The EECBO-RP technique chooses the relay nodes so that a way that the overall efficiency of the WSN gets maximized. The simulation values of the EECBO-RP system are tested under several dimensions and the outcomes pointed out the betterment of the EECBO-RP technique.

关键词： Wireless sensor networks Renewable energy sources Voting Routing Minimization Routing protocols Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Data Acquisition Model for Precision Agriculture using IoT, Engineering Nanomaterials and Artificial Intelligence

A Hybrid Data Acquisition Model for Precision Agriculture us...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： K.Sankara Moorthy Ms. Peddinti Neeraia P. Pavitra R. Arivumalar K. Veeranjaneyulu S.Mohana Murali College of Management SRM Institute of Science and Technology Kattankulathur Department of Computer Applications School of Computing Mohan Babu University Tirupati Department of Basic science and humanities Dadi Institute of Engineering and Technology visakhapatnam Anakapalli Sri Sairam Engineering College West Tambaram Chennai-44 CVR College of Engineering Rangareddy Telangana Dept of commerce Govt Degree College Andhra Pradesh India

Two key ideas for wireless sensor network (WSN) optimization in precision farming serve as the guidelines for this study. According to its definition, a wireless sensor network is a collection of sensor nodes that link to one another and/or with a node outside of their coverage area via wireless communication. These nodes frequently have one or more sensors for evaluating internal or external elements as well as environmental characteristics. A CPU then controls the sensors, compiling, storing, processing, and, if requested, transmitting the data. In some systems, the sensor nodes' processing power is constrained to make them more energy-efficient. In this application, the sensor nodes transfer the collected data to a remote node with more powerful processing capabilities and greater storage in specified time intervals or condition-based events storage. Because of its ability to monitor processes at a small scale, nanotechnology is regarded as a leading technology for controlling agriculture. So, it paves the way for crucial advantages such as improving food quality and quantity, lowering the input needed for agricultural production, fully utilizing soil nutrients, etc. The availability of natural resources, detecting the right nutrients from the soil for crop-specific production, and crop cultivation are issues in these models. In order to boost crop yield by assessing the nutrients in the soil, various nano-sensors are used in this research study. The type of crop that can be employed for cultivation or irrigation depends on the accuracy of acquisition and detection. Real-time nanosensors are used to collect the soil constituents that are necessary for crop productivity. In comparison to state-of-the-art models, simulation results utilizing a deep learning detector based on input obtained from nanosensors, which demonstrate increased productivity

关键词： Productivity Wireless sensor networks Protocols Nanosensors Crops Process control Soil

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：