检索结果-内蒙古大学图书馆

Outage Prediction and Improvement in 6G for UAV Swarm Relays Using Machine Learning

Progress In Electromagnetics Research B 2024年 107卷 33-45页

作者： Khalil, Hisham Ali, Gauhar Rahman, Saeed Ur Asim, Muhammad Affendi, Mohammed El Department of Intelligent Systems Faculty of Information Technology University of Lahore Pakistan EIAS Data Science and Block chain Lab College of Computer and Information Sciences Prince Sultan University Riyadh11586 Saudi Arabia School of Electronic Engineering Xidian University Xi’an China

The issue of signal outages in sub-THz frequency communication for future 6G networks is addressed by this research. A machine learning method is proposed, employing Random Forest and K-Means algorithms to predict the optimal frequency band and outage probabilities for UAV relays. Both space and frequency diversity are explored to enhance signal strength, and metasurface-carrying UAVs are introduced with a 16 × 16 mm2 design. This design significantly reduces the predicted outage probability from 0.1% to 0.0178%. Finally, triangular and hexagonal UAV swarm formations with metasurfaces are investigated, demonstrating improved performance through heatmap results. © (2024), (Electromagnetics Academy). All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Wind Power Fault Detection Based on Vertical Federated Learning 14

Wind Power Fault Detection Based on Vertical Federated Learn...

引用

14th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Hangzhou 2023

作者： Yang, Dike Long, Zhuo Ma, Xiaoguang Xu, Bin College of Computer Science and Engineering Northeastern University Shenyang China School of Electrical and Information Engineering Changsha University of Science and Technology Changsha China College of Information and Engineering Northeastern University Shenyang China

ISBN: (纸本)9798350301359

Wind power generation is one of the most widely used distributed renewable energy sources. The diagnosis and monitoring of wind power system is one of the important means to ensure its power supply reliability. Since wind power monitoring data is an important production data for enterprises, how to realize distributed diagnosis of wind power system under the premise of ensuring data security is a difficult problem that needs to be solved. To solve the above problems, this paper proposes a new vertical Federated learning method to achieve distributed fault diagnosis of wind power systems on the premise of ensuring data privacy and security. The method was verified through testing of EDP, NERL and other real-time wind power data, and the highest diagnostic accuracy reached more than 99%, showing its great potential to be used in this field. © 2023 IEEE.

关键词： fault diagnosis vertical federated learning Wind Power

来源：评论

学校读者我要写书评

暂无评论

SELECTING FEATURES BY UTILIZING INTUITIONISTIC FUZZY ENTROPY METHOD

Decision Making: Applications in Management and Engineering

引用

Decision Making: Applications in Management and engineering 2023年第1期6卷 111-133页

作者： Pandey, Kiran Mishra, Arunodaya Raj Rani, Pratibha Ali, Jabil Chakrabortty, Ripon Department of Computer Science and Engineering Technocrats Institute of Technology Madhya Pradesh Bhopal India Department of Mathematics Government College Raigaon Madhya Pradesh Satna India Department of Engineering Mathematics Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India School of Engineering and Technology Department of Computer Science and Engineering Sharda University Uttar Pradesh Greater Noida India Capability Systems Centre School of Engineering and Information Technology UNSW Canberra Australia

Feature selection is the most significant pre-processing activity, which intends to reduce the data dimensionality for enhancing the machine learning process. The evaluation of feature selection must consider classification, performance, efficiency, stability, and many factors. Nowadays, uncertainty is commonly occurred in the feature selection process due to time limitations, imprecise information, and the subjectivity of human minds. Moreover, the theory of intuitionistic fuzzy set has been proven as an extremely valuable tool to tackle the uncertainty and ambiguity that arises in many practical situations. Thus, this study introduces a novel feature selection framework using intuitionistic fuzzy entropy. In this regard, new entropy for IFS is proposed first and then compared with some of the previously developed entropy measures. As entropy is a measure of uncertainty present in data (features), features with higher entropy values are filtered out, and the remaining features having lower entropy values have been used to classify the data. To verify the effectiveness of the proposed entropy-based feature selection, some experiments are done with ten standard benchmark datasets by employing a support vector machine, K-nearest neighbor, and Naïve Bias classifiers. The outcomes of the study validate that the proposed entropy-based filter feature selection is more feasible and impressive than existing filter-based feature selection methods. © 2023 by the authors.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

ICDAC: Intelligent Contracts Driven Access Control Model for IoT Device Communication

引用

SN computer science 2024年第8期5卷 1054页

作者： Rajesh, S.M. Prabha, R. Department of Information Science and Engineering Dr. Ambedkar Institute of Technology Affiliated to Visvesvaraya Technological University Karnataka Bangalore India Department of Computer Science and Engineering Dr. Ambedkar Institute of Technology Affiliated to Visvesvaraya Technological University Karnataka Bangalore India

In the Internet of Things (IoT) epoch, the seamless communication of smart devices through autonomous collaboration demands real-time IoT networks to possess a high level of intelligence. However, the resource-constrained nature of IoT limits the adoption of traditional intuitive access control models for communication in dynamic, complex, and large-scale applications. The frequent changes in the IoT environment urge creating a secured autonomous dynamic access control system for device-to-device communication to secure device-sensitive data and detect abnormal access behaviors to ensure the smart infrastructure is free from cyberattacks. Smart Home infrastructure with various sensors and validation systems is used as the target application in the proposed system. Addressing the challenges, the novel design of an intelligent access control model to protect the privacy of device information and data is presented by integrating Artificial Intelligence and Blockchain. The attribute-based access policies are designed to create synthetic datasets by encompassing the if-then rule. Smart Home devices and transaction data are secured under the hashed storage structure IPFS. The Deep Learning-based ResNet model is employed in the design of intelligent contracts, and its execution is focused on the required device only. The authentic and immutable nature of the blockchain enforces the end-to-end security of the proposed system with an enhanced accuracy of 96.8% in access decisions to accommodate the Smart Home Infrastructure. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： ABAC Blockchain D2D Intelligent contracts IPFS ResNet Smart home

来源：评论

学校读者我要写书评

暂无评论

H2/H∞ Robust Observed-State Feedback Control Based on Slack LMI-LQR for LCL-Filtered Inverters

引用

IEEE Transactions on Industrial Electronics 2023年第5期70卷 4785-4798页

作者： Tran, Thuy Vi Kim, Kyeong-Hwa Lai, Jih-Sheng Seoul National University of Science and Technology Department of Electrical and Information Engineering Research Center for Electrical and Information Technology Seoul01811 Korea Republic of Virginia Polytechnic Institute and State University Future Energy Electronics Center Department of Electrical and Computer Engineering BlacksburgVA24061 United States

A robust controller for an LCL-filtered grid-connected inverter (GCI) is presented in this article in the context of the system model uncertainties and nonideal grid environment. Under the occurrence of exogenous inputs from parameter drifts affecting the controller and observer, the H2/H∞ approach of the linear quadratic regulator control is developed to obtain the state-feedback gain and observer gain with the system stability guarantee by means of Lyapunov stability theory. Furthermore, the use of slack-linear matrix inequalities to handle parameter-dependent Lyapunov functions in synthesizing the robust controller can achieve a less conservative condition than the conventional quadratic stability. System robustness and stability are assessed through the closed-loop pole map and the discrete-time frequency analysis approaches. Hardware experiments are conducted for the LCL-filtered GCI to validate the feasibility and effectiveness of the proposed control method. Fair comparisons with the conventional schemes are also performed to highlight the superior performance of the proposed scheme. © 1982-2012 IEEE.

关键词： Stability criteria

来源：评论

学校读者我要写书评

暂无评论

An Efficient Convolutional Multi-Scale Vision Transformer for Image Classification 2

An Efficient Convolutional Multi-Scale Vision Transformer fo...

引用

2nd International Conference on Image Processing, computer Vision and Machine Learning, ICICML 2023

作者： Zhang, Ji Chen, Zhihao Ge, Yiyuan Yu, Mingxin Beijing Information Science and Technology University School of Instrument Science and Opto-Electronics Engineering Beijing China Beijing Information Science and Technology University Computer School Beijing China Jilin University Department of Software Engineering Changchun China

ISBN: (纸本)9798350331417

This paper introduces an innovative and efficient multi-scale Vision Transformer (ViT) for the task of image classification. The proposed model leverages the inherent power of transformer architecture and combines it with the concept of multi-scale processing generally used in convolutional neural networks (CNNs). The work aims to address the limitations of conventional ViTs which typically operate at a single scale, hence overlooking the hierarchical structure in visual data. The multi-scale ViT enhances classification performance by processing image features at different scales, effectively capturing both low-level and high-level semantic information. Extensive experimental results demonstrate the superior performance of the proposed model over standard ViTs and other state-of-the-art image classification methods, signifying the effectiveness of the multi-scale approach. This research opens new avenues for incorporating scale-variance in transformer-based models for improved performance in vision tasks. © 2023 IEEE.

关键词： Classification Convolutional neural networks Multi-scale Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuned Large Language Model for Banking 12th

Fine-Tuned Large Language Model for Banking

引用

12th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2024

作者： Limkar, Suresh Nale, Soham Darade, Shreyash Chaudhari, Ashwin Taras, Atharva Department of Computer Science and Engineering Central University of Jammu Jammu and Kashmir Jammu India Department of Artificial Intelligence and Data Science AISSMS Institute of Information Technology Pune India

ISBN: (纸本)9789819601387

A new, improved computer program made specifically for banking helps in solving problems like inadequate guidance and makes it convenient for people who cannot visit banks for some reason. This helps people answer questions faster and makes it easier for bank workers. Making the program better involved picking the right model and making a special set of data. After making these improvements, the llama2_sharded model is really good at answering banking questions, doing better than others by 2.67%. This shows how important it is to give programs lots of practice with different information, proven by reaching a low error rate after many tries. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Banking

来源：评论

学校读者我要写书评

暂无评论

Big Mart Sales using Hybrid Learning Framework with Data Analysis 2

Big Mart Sales using Hybrid Learning Framework with Data Ana...

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Phani Praveen, S. Chaitanya, Polavarapu Mohan, A. Shariff, Vahiduddin Ramesh, Janjhyam Venkata Naga Sunkavalli, Jayaprakash Computer Science and Engineering Prasad V Potluri Siddhartha Institute of Technology Kanuru Vijayawada India Computer Science and Engineering Sir C R Reddy College of Engineering Eluru India Computer Science and Engineering Chaitanya Bharathi Institute of Technology Hyderabad India Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur India Information Technology Velagapudi Ramakrishna Siddhartha Engineering College Vijayawada India

ISBN: (纸本)9798350340235

The retail industry has undergone a rapid transformation in recent years, owing to technological advancements and the availability of massive amounts of data. In this context, predictive analytics is critical in assisting retailers in making informed decisions, optimising operations, and increasing profitability. This study employs a hybrid learning framework combining machine learning and traditional statistical methods to predict sales in the Big Mart retail chain. The first stage of the proposed approach entails a thorough data analysis in which this study examines historical sales data, product attributes, store demographics, and other relevant variables to gain insights into sales patterns and correlations. Exploratory data analysis and feature engineering are used to prepare the data for model development. The new algorithm analyses customer data and provides insights to help businesses make better business decisions. Using this technology, Big Mart hopes to increase sales and improve customer satisfaction. Big Mart used the Ensemble algorithm in this paper, a type of artificial intelligence that can learn from data and make predictions based on that data. The ensemble algorithm is a hybrid algorithm that combines the two algorithms used to find Big Mart sales, such as Random Forest (RF) and S upport Vector Machine (S VM). The algorithm is trained using historical customer data, such as purchase history, demographic information, and other variables that may influence purchasing behavior. The dataset is obtained from Kaggle to evaluate the model's performance. The algorithm can use this data to identify patterns and trends in customer behaviour, which can be used to forecast future sales. © 2023 IEEE.

关键词： Machine Learning Random Forest (RF) Support Vector Machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

Level-Line Guided Edge Drawing for Robust Line Segment Detection 48

Level-Line Guided Edge Drawing for Robust Line Segment Detec...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Lin, Xinyu Zhou, Yingjie Liu, Yipeng Zhu, Ce University of Electronic Science and Technology of China School of Information and Communication Engineering China Sichuan University College of Computer Science China

ISBN: (纸本)9781728163277

Line segment detection plays a cornerstone role in computer vision tasks. Among numerous detection methods that have been recently proposed, the ones based on edge drawing attract increasing attention owing to their excellent detection efficiency. However, the existing methods are not robust enough due to the inadequate usage of image gradients for edge drawing and line segment fitting. Based on the observation that the line segments should locate on the edge points with both consistent coordinates and level-line information, i.e., the unit vector perpendicular to the gradient orientation, this paper proposes a level-line guided edge drawing for robust line segment detection (GEDRLSD). The level-line information provides potential directions for edge tracking, which could be served as a guideline for accurate edge drawing. Additionally, the level-line information is fused in line segment fitting to improve the robustness. Numerical experiments show the superiority of the proposed GEDRLSD1 algorithm compared with state-of-the-art methods. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Integration of Clinical and Imaging Data for Enhancing Oral Cancer Detection Using Deep Learning

Integration of Clinical and Imaging Data for Enhancing Oral ...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Shakila, M. Dhasaratham, M. Saranya, N. Naga Thotapalli, Aruna Telrandhe, S.V. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India Tkr College of Engineering and Technology Department of Information Technology Hyderabad India Saveetha College of Liberal Arts & Science Simats Department of Computer Applications Chennai India Cvr College of Engineering Department of Information Technology Telangana Hyderabad India Guru Nanak Institute of Engineering & Technology Department of Etc Nagpur India

ISBN: (纸本)9798350360660

This study aims at unlocking the integration of clinical and imaging data using the deep learning model for enhancing the diagnosis of oral cancer cases. Therefore, for image analysis, in this paper proposed to major on CNNs while for clinical data, our Research used RNNs and hence came up with a unique architecture. The proposed model was trained on the patients' records and Histopathological Images Database from 5000 patients. As for the overall measure of accuracy of all of the constructed classifiers applying our integrated model the result was 94 %. Specificity achieved for the system was 7% while sensitivity was 93% for the oral cancer. 2%, sensitivity of 69.1%. This is an improvement of the previous methods that required either imaging or clinical data to obtain accuracy approximated at 85-90 percent. As a unique effectiveness factor of increasing the accuracy of oral cancer diagnosis, it is proposed to use an integration of clinical and imaging data through deep learning, which can also result in inclusion of the diagnosis at the early stages of the disease, thereby enhancing the prognosis of the illness. © 2024 IEEE.

关键词： Lung cancer

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：