检索结果-内蒙古大学图书馆

Efficient and accurate numerical-projection of electromagnetic multipoles for scattering objects

Frontiers of Optoelectronics 2023年第4期16卷 215-226页

作者： Wenfei Guo Zizhe Cai Zhongfei Xiong Weijin Chen Yuntian Chen School of Optical and Electronic Information Huazhong University of Science and TechnologyWuhan 430074China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117576Singapore Wuhan National Laboratory of Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China Optics Valley Laboratory Wuhan 430074China

In this paper,we develop an efcient and accurate procedure of electromagnetic multipole decomposition by using the Lebedev and Gaussian quadrature methods to perform the numerical ***,we briefy review the principles of multipole decomposition,highlighting two numerical projection methods including surface and volume ***,we discuss the Lebedev and Gaussian quadrature methods,provide a detailed recipe to select the quadrature points and the corresponding weighting factor,and illustrate the integration accuracy and numerical efciency(that is,with very few sampling points)using a unit sphere surface and regular *** the demonstrations of an isotropic dielectric nanosphere,a symmetric scatterer,and an anisotropic nanosphere,we perform multipole decomposition and validate our numerical projection *** obtained results from our procedure are all consistent with those from Mie theory,symmetry constraints,and fnite element simulations.

关键词： Multipole decomposition Numerical quadrature Light scattering

来源：评论

学校读者我要写书评

暂无评论

Prediction of Customer Retention Rate Employing Machine Learning Techniques 1

Prediction of Customer Retention Rate Employing Machine Lear...

引用

1st International Conference on Informatics, ICI 2022

作者： Sharma, Achintya Gupta, Deepak Nayak, Nikhil Singh, Deepti Verma, Ankita Jaypee Institute of Information Technology Department of Computer Science Engineering & Information Technology Uttar Pradesh 62 Noida India

ISBN: (纸本)9781665437219

In the recent decade, telecom sector is subjected to major revolution in the terms of subscribers' count and the technological content. Owing to institutional and policy reforms that have liberalized the sector, there is a significant rise in competition among telecom companies. With companies experiencing an ever-increasing rate of customer churn rate, and as it is costlier to acquire a new customer than to retain an existing one, customer retention has become one of the prime focus of companies. Enterprises and managers are focusing on improving customer retention rate now more than ever. With the large amount of customer data at our disposal, machine learning algorithms are apt for the efficient analysis of such data. This study compares the accuracy of traditional data mining techniques viz Logistic Regression, Support Vector Machine (SVM), Decision Tree, XGBoost, Random Forest, Light Gradient Boosting, Gradient Descent Boosting and Cat Boost in predicting customer churn and then proposes an algorithm based on the above techniques that aims to find the major causes for customer churn from one company to another and the ways in which enterprises can improve customer retention. The reduced set of relevant features are selected by employing our proposed algorithm. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Smart Healthcare Monitoring System: Integrating IoT, Deep Learning, and XGBoost for Real-Time Patient Diagnosis 21

Smart Healthcare Monitoring System: Integrating IoT, Deep Le...

引用

21st OITS International Conference on information technology, OCIT 2023

作者： Paulraj, Kruthika Soms, Nisha David Samuel Azariya, S. Sathya Priya, S. Jeba Emilyn, J. Sureshkumar, Vidhushavarshini Sona College of Technology Department of Information Technology Tamil Nadu Salem India KPR Institute of Engineering and Technology Department of Computer Science Tamil Nadu Coimbatore India M. Kumarasamy College of Engineering Department of Artificial Intelligence and Data Science Tamil Nadu Karur India SRMIST Department of Computer Science Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350358230

Integrating the Internet of Things (IoT), Deep Learning (DL), and the XGBoost algorithm has paved the way for transformative advancements in healthcare. This paper presents a pioneering study on a "Smart Healthcare Monitoring System"that harnesses the synergy of these technologies for real-Time patient diagnosis. With the escalating demand for accurate and swift medical assessments, our work addresses the crucial need for timely and precise diagnosis. The proposed system amalgamates IoT-enabled wearable devices and sensors to capture comprehensive patient data. A hybrid approach is employed to leverage this data, comprising a Deep Learning model for intricate pattern recognition and the XGBoost algorithm for rapid decision-making. Nonetheless, challenges such as data security and model interpretability are acknowledged, highlighting avenues for future research. This paper underscores the transformative potential of the IoT-Deep Learning-XGBoost integration, offering a robust foundation for further innovation in intelligent healthcare systems. As healthcare delivery evolves, our work underscores the promise of this interdisciplinary fusion in revolutionizing patient diagnosis and care. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Optimizing Image Recognition Model through Transfer Learning and Robust Feature Extraction in Neural Networks 2

Optimizing Image Recognition Model through Transfer Learning...

引用

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Ramesh, G. Agoramoorthy, Moorthy Ahamed Ali, S. Sujatha, D. Michael Raj, T.F. K.L.N.College of Engineering Department of Information Technology Sivagangai Tamilnadu Pottapalayam India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India Easwari Engineering College Computer Science and Engineering Chennai Ramapuram India St. Peters College of Engineering and Technology Department of Computer Science and Engineering Chennai Avadi India Sclas Simats Department of Computer Applications Tamilnadu Chennai India

ISBN: (纸本)9798350369960

These advances in image identification's technology have created massive changes, mainly in the health care facilities plus self-directed systems. Transfer learning strategies coupled with robust feature extraction techniques are used in the model to promote efficiency in the imaging system. A technique of fine-tuning the weights used for recognition tasks on pre-trained convolutional neural network architectures is proposed. State of art feature extraction pipeline composed with edge detection, texture analysis and spatial frequency analysis to enrich network capacity of distinguishing intricate visual textures and patterns. This combination of techniques helps in faster model training with top class prediction results on mixed image datasets. After rigorous testing on various benchmark datasets, including CIFAR-10 and ImageNet, considerable enhancement in recognition performance beyond baselines was observed. Additionally, the proposed approach is resilient to changes in image quality, illumination, and occlusions. The proposed framework enhances the existing model efficiency, flexibility, and robustness for application in real-time image identification. This approach opens new capabilities for the medical imagery, self-navigation cars, and object recognize mechanisms whose image classification must be exact. © 2023 IEEE.

关键词： Feature Extraction Image Recognition Neural Network Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Prediction of Kidney Disease Utilizing a Hybrid Deep Learning Methodology 2

Prediction of Kidney Disease Utilizing a Hybrid Deep Learnin...

引用

2nd International Conference on computer, Communication and Control, IC4 2024

作者： Nallarasan, V. Ponnusamy, Vijayakumar Lakshminarayanan, R. Sona, K. Vigneshwari, S. Vinoth, R. Srm Institute of Science and Technology School of Computing Department of Networking and Communications Chengalpattu Kattankulathur India Srm Institute of Science and Technology Department of Electronics and Communications Chengalpattu Kattankulathur India Sri Ramakrishna Engineering College Department of Computer Science and Engineering India V.S.B College of Engineering Technical Campus India Gojan School of Business and Technology Department of Information Technology RedhillsTamilnadu Chennai600052 India

ISBN: (纸本)9798350387933

The kidney is an essential organ inside the human body, playing a crucial role in several physiological processes. One of its primary roles is the filtration of waste products and surplus fluids from the bloodstream, facilitating their subsequent elimination via urine production. In order to mitigate potential life-threatening complications, it is essential to identify and investigate chronic renal illnesses. The suggested method takes into account the limitations of early prediction and robust decision-making oscillations due to the presence of False Positive Rates in Kidney CT Images. The suggested system incorporates a hybrid method that combines machine learning and deep learning techniques. A prognostic method is developed by using the kidney dataset collected from TCIA, which involves the analysis of patients' past health information. The suggested system incorporates a hybrid approach of random forest regression and multinomial regression algorithms to identify the Explorer data analysis technique for the chronic kidney disease dataset. The secondary approach involves using a computer tomography image dataset obtained from the TCIA public data set. This dataset is processed using a deep convolutional neural network (DCNN) architecture that has many layers of deep convolution filters. The purpose of this architecture is to accurately detect and classify kidney abnormalities within the images. The integration of main and secondary outcomes is used to determine the presence or absence of renal disease in a patient. In this study, we examine a unique methodology known as Hybrid Deep K-Net (H-DKN). The accuracy reached by HDKN is reported to be 97%. Furthermore, we compare this approach with many state-of-the-art methods that have been established on the current platform. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Enhanced DDoS Attack Detection in Cyber-Physical Systems Within Supply Chain 4.0 Using Optimized TSO-DBN Deep Learning Technique

Enhanced DDoS Attack Detection in Cyber-Physical Systems Wit...

引用

2024 IEEE International Women in engineering (WIE) Conference on Electrical and computer engineering, WIECON-ECE 2024

作者： Divyashree, H.S. Kalluri, Venkata Saiteja Shenu, S. Kavitha, S. Bhuvanesh, A. Keerthanadevi, R. Brindavan College of Engineering Department of Information Science and Engineering Bengaluru India Salesforce Developer the Cleaver Brooks Company Inc GA United States Gregorian Institute of Technology Department of Electrical and Electronics Engineering Kottayam India Sri Eshwar College of Engineering Department of English Coimbatore India Psn College of Engineering and Technology Department of Electrical and Electronics Engineering Tirunelveli India Psn College of Engineering and Technology Department of Computer Science and Engineering Tirunelveli India

ISBN: (纸本)9798331535476

It is critical to implement strong detection methods in the developing field of Supply Chain Risk Management 4.0, as cyber-physical systems (CPS) are becoming more vulnerable to Distributed Denial of Service (DDoS) attacks. The authors of this paper present a state-of-the-art approach to detecting distributed denial of service attacks (DDoS) by combining several artificial intelligence (AI) and data processing methods. The first step is Z-score normalization for pre-processing, which involves standardizing the data to make sure that feature scaling is consistent. In order to reduce dimensionality while keeping considerable variation, feature extraction is performed using Principal Component Analysis (PCA). To take the model to the next level, we optimize the feature subset to improve detection performance using Tunicate Swarm Optimization (TSO), which is employed for feature selection. The selected characteristics are then used by a Deep Belief Network (DBN), a model of Deep Learning (DL), to classify anomalies. The DBN uses learnt patterns to differentiate between normal and attack situations. Accuracy, precision, recall, and F1-score are some of the performance indicators used to evaluate the detection system and make sure the model is functional. More than that, the research compares the effects of several feature selection algorithms on the DDoS detection system's overall performance to determine which one is the most effective. In the ever-changing landscape of Supply Chain Risk Management 4.0, this all-encompassing method boosts cyber-physical system resistance to attacks with a 99% success rate and increases DDoS attack detection accuracy and dependability. © 2024 IEEE.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Hyper-Convergence Storage Framework for EcoCloud Correlates

引用

computers, Materials & Continua 2022年第1期70卷 1573-1584页

作者： Nadia Tabassum Tahir Alyas Muhammad Hamid Muhammad Saleem Saadia Malik Department of Computer Science Virtual University of PakistanLahore54000Pakistan Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan Department of Statistics and Computer Science University of Veterinary and Animal SciencesLahore54000Pakistan Department of Industrial Engineering Faculty of EngineeringRabighKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology-RabighKing Abdulaziz UniversityJeddah21589Saudi Arabia

Cloud computing is an emerging domain that is capturing global users from all walks of life—the corporate sector,government sector,and social arena as *** cloud providers have offered multiple services and facilities to this audience and the number of providers is increasing very *** enormous pace is generating the requirement of a comprehensive ecosystem that shall provide a seamless and customized user environment not only to enhance the user experience but also to improve security,availability,accessibility,and *** technology is providing robust solutions to many of our problems,the cloud platform is one of *** is worth mentioning that these solutions are also amplifying the complexity and need of sustenance of these rapid *** with cloud computing,new entrants as cloud service providers,resellers,tech-support,hardware manufacturers,and software developers appear on a daily *** actors playing their role in the growth and sustenance of the cloud *** objective is to use convergence for cloud services,software-defined networks,network function virtualization for infrastructure,cognition for pattern development,and knowledge *** order to gear up these processes,machine learning to induce intelligence to maintain ecosystem growth,to monitor performance,and to become able to make decisions for the sustenance of the *** may be programmed to“superficially”imitate most business applications and create large numbers using lightweight workload generators that merely stress the *** today’s current IT environment,when many enterprises use the cloud to service some of their application demands,a different performance testing technique that assesses more than the storage is *** and storage are merged into a single building block with HCI(Hyper-converged infrastructure),resulting in a huge pool of compute and storage resources when clustered with other building ***

关键词： Virtual cloud software define network network function virtualization hyper-convergence virtualization

来源：评论

学校读者我要写书评

暂无评论

Novel Deep Learning Network Architectures for Time Series Forecasting

Novel Deep Learning Network Architectures for Time Series Fo...

引用

2023 IEEE International Conference on Paradigm Shift in information Technologies with Innovative Applications in Global Scenario, ICPSITIAGS 2023

作者： Katariya, Jitendra Kumar Yadav, Dhananjay Gayathri, C. Kolekar, Vikas K. Daivagna, Umesh M. Pushparajesh, V. Vivekananda Global University Department of Computer Science & Application Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology UP India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Atlas SkillTech University Department of UGDX Maharastra Mumbai India Faculty of Engineering and Technology Department of Electrical and Electronics Engineering Karnataka Bangalore India

ISBN: (纸本)9798350329773

This paper presents novel deep-learning network architectures for time series forecasting. First, a singular deep gaining knowledge of network architecture is proposed and tested for the usage of the Google tendencies dataset as a benchmark. The proposed structure combines 1-dimensional convolution neural networks, recurrent neural networks, and long-term cells to seize and study lengthy-term styles in the time series information. The structure is compared to current deep getting-to-know architectures and is shown to outperform them in phrases of accuracy. Moreover, the proposed structure is applied to a secondary time collection dataset, the COVID-19 confirmed infection dataset, to attain compelling effects. Eventually, an open-source implementation of the proposed architecture is made available for use in addition to research. © 2023 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

RVTN: Recommender system for vehicle routing in transportation network 7

RVTN: Recommender system for vehicle routing in transportati...

引用

7th International Conference on Parallel, Distributed and Grid Computing, PDGC 2022

作者： Tandon, Righa Verma, Ajay Gupta, P.K. Chitkara University Institute of Engineering and Technology Chitkara University Department of Computer Science and Engineering Punjab India Jaypee University of Information Technology Department of Computer Science and Engineering Solan India

ISBN: (纸本)9781665454018

The recommender system predicts the future paths based on the vehicle interactions in a vehicular environment. As the data is ubiquitous, we have a number of options available to make a selection for finding the path in the vehicular network. This is the scenario where the recommender system plays its role by narrowing the available options and make the selection process easy and effective. In this paper, we have proposed a sequential recommender system that considers the vehicle's interactions along with the paths in sequential order and map the sequences dynamically in which the weight-age is given to current preferences and recent choices as explored by the vehicle of the network. A detailed comparison of the proposed sequential recommender system with the commonly used matrix factorization model has also provided. The proposed recommender system is based on sequential dependencies and responds equally well to the vehicle routing problem. The obtained results using vehicle routing dataset reveals that the proposed recommender system is much faster with higher Mean reciprocal rank (MRR) value. © 2022 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Detection of Anomaly in Internet of Things using Gated Recurrent Unit with Artificial Bee Colony 1

Detection of Anomaly in Internet of Things using Gated Recur...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Karthik, M. Ganesh Divya, N. Sree Shnaeen, Amaar Haamid Alagarraja, K. Praveena, S. Gitam University Department of Computer Science and Engineering Bengaluru India Mahatma Gandhi Institute of Technology Department of Information Technology Hyderabad India The Islamic University of Al Diwaniyah College of Technical Engineering Department of Computers Techniques Engineering Al Diwaniyah Iraq New Prince Shri Bhavani College of Engineering and Technology Department of Mechanical Engineering Chennai India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Electronics and Communication Engineering Mamallapuram India

ISBN: (纸本)9798331529246

Now a days, development in Internet of Things (IoT) networking generates large attack surface for cybercriminals, that impact the industry has resulted with exponential increase in cyber-attacks. To develop a robust anomaly detection system, a Gated Recurrent Unit Anomaly Detection (GRUAD) is proposed in this research. Initially, the data is collected from the Toyama IoT Network Traffic Dataset (TON-IoT) dataset which includes samples of packet capture data (PCAP files) and network logs (text files). Then, the collected data is pre-processed using data cleaning technique which removes noisy and irrelevant data, then label encoding and data normalization assist to transform data into a suitable format while data splitting. Further, features are selected using Mutual information (MI) in which features with high mutual information with the target variable are selected. Then, Pearson Coefficient Correlation (PCC) identifies features with strong linear correlations. At the end, K-Best selects the top-ranked features. Finally, the Multistep-Prediction is performed using GRUAD by hyperparameter tuning the Artificial Bee Colony (ABC). The proposed model gained better results in terms of precision with value 98.54%, f1 score of 98.74%, Accuracy of 98.62%, recall of 98.77% comparing with existing method Logistic Regression (LR) respectively. © 2025 IEEE.

关键词： Logistic regression

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：