检索结果-内蒙古大学图书馆

10th IEEE Smart World Congress, SWC 2024

作者： Qiu, Wen Shao, Xun Zhao, Wei Masui, Hiroshi Kitami Institute of Technology Information and Communication Engineering Hokkaido Japan Toyohashi University of Technology Department of Electrical and Electronic Information Engineering Toyohashi Japan Anhui University of Technology School of Computer Science and Technology Anhui China Kitami Institute of Technology Information Processing Center Hokkaido Japan

ISBN: (纸本)9798331520861

With the swift advancement of automotive technology, the need for efficient allocation of resources in V2V (vehicle-to-vehicle) communications has grown significantly. However, the dynamic nature of channels in vehicular networks introduces considerable uncertainty in resource allocation. This research presents a novel approach to addressing these challenges by utilizing multi-agent deep reinforcement learning (MADRL). By leveraging shared resource blocks (RBs) for V2V and vehicle-to-infrastructure (V2I) communications, our approach minimizes interference with V2I links and ensures optimal V2V performance. Unlike traditional methods that select actions sequentially, our approach treats every V2V link as an agent and simultaneously determines all agents' actions to improve coordination and efficiency. To accelerate the training of the multi-agent critic network, we integrate an embedding module to simplify and compress the network input dimensions. Through the use of our embedding multi-agent proximal policy optimization (E-MAPPO) algorithm, the agents collaboratively optimize their transmission strategies to efficiently share spectrum with V2I links. Simulation results show that our method greatly minimizes interference with V2I links while meeting the stringent latency and reliability requirements of V 2 V communications, surpassing baseline approaches. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Sorting the Digital Stream: Big data-driven Insights into Email Classification for Spam and Ham Detection

Sorting the Digital Stream: Big Data-driven Insights into Em...

引用

2023 IEEE International Conference on Big data, Bigdata 2023

作者： Shah, Syed Attique Arputham, Emil Anthony Ahmed, Awais Farah, Mohamed Ben Shah, Attal Aziz, Abdul Birmingham City University STEAMhouse School of Computing and Digital Technology BirminghamB47RQ United Kingdom University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan China Faculty of Ict Buitems Department of Computer Engineering Quetta Pakistan Universidad de Zaragoza Aragon Institute of Engineering Research Zaragoza50018 Spain

ISBN: (纸本)9798350324457

In contemporary email communication, the ever- expanding volume of digital correspondence has ushered in an era where big data plays a pivotal role in addressing the challenge of distinguishing between legitimate (ham) and unsolicited (spam) emails. The primary objective of this paper is the meticulous identification and establishment of criteria for the discrimination between ham and spam emails. To achieve this, the study harnesses data from three distinct datasets, aiming to identify common attributes shared across all emails, irrespective of their classification, while concurrently devising methodologies for precise spam detection. Central to this endeavor is the evaluation of the effectiveness of feature selection techniques, specifically Chi-Square and Pearson Correlation, in elevating the accuracy of email classification. The investigation extends to assessing how the combination of these feature selection techniques with the broader machine learning framework can be optimized. This optimization entails the application of diverse preprocessing techniques to the datasets, all designed to amplify the precision of email classification. Furthermore, this research scrutinizes the performance evaluation metrics employed in the assessment of email classifiers. By conducting comprehensive experiments, the study identifies optimal classifiers based on rigorous evaluation metrics. This contributes valuable insights to the toolkit of techniques for proficient email classification within the realm of big data analysis. © 2023 IEEE.

关键词： Artificial Neural Network Classification data Pre-processing Decision Tree Email Spam Detection Feature Selection Machine Learning Naive Bayes

来源：评论

学校读者我要写书评

暂无评论

Unleashing The Power Of 6g Assisted Wireless Communication Network To Define A New Routing Strategy To Preserve Communication Energy 10

Unleashing The Power Of 6g Assisted Wireless Communication N...

引用

10th International Conference on Electrical Energy Systems, ICEES 2024

作者： Avinash, S. Sujatha, S. Poornima, D. Vedhashree, S.K. Saravanan, V. Malathi, P. St. Josephs College of Engineering Department of MBA Tamil Nadu Chennai India Sri Sairam College of Engineering Department of EEE Anekal Karnataka Bangalore India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India M.Kumarasamy College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Nano Electronics Materials and Sensors Tamilnadu Chennai India SIMATS Saveetha College of Liberal Arts and Sciences Department of Data Analytics Tamil Nadu Chennai India

ISBN: (纸本)9798350353778

The incorporation of cutting-edge technology into intelligent power grid management becomes a top priority as the globe keeps searching for effective and environmentally friendly energy solutions. The arrival of 6G wireless networks is expected to completely transform the methods used to track, manage, and enhance energy grids. An effort to provide high data speeds has already been made with the deployment of commercial fifth-generation (5G) wireless communications networks. The advent of IoT applications and the proliferation of smart devices will put a heavy strain on 5G wireless networks since they need extremely dependable and lowlatency connection. So, the massive continuous data traffic boom is probably going to be too much for 5G networks to handle. Research into enhancing current wireless networks in preparation for the 6G cellular systems, the next generation of mobile communication, has been spurred by this. This paper introduces the Neural 6G Wireless Routing Protocol (N6GWRP), a new routing protocol that supports intelligent communication. To evaluate the effectiveness of the suggested approach, it is cross-validated with the Multiple-Access Routing Protocol (MARP), a traditional routing model. Users should not experience any disruptions when mobile power and data transmission systems interact. Another major obstacle is connecting the vast array of devices and people with varying degrees of processing power in a way that is both sustainable and environmentally conscious. This study delves into the smart solution to the aforesaid difficulties and examines how 6G wireless networks might improve smart energy grid resilience and dependability through seamless interaction with other sophisticated technologies like blockchain. A more environmentally friendly and smart vision regarding electrical grid administration is possible thanks to the extensive study that strives to illuminate the revolutionary significance of 6G wireless technologies. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Human-Spa: An Online Platform Based on Spatial Transcriptome data for Diseases of Human Systems

Human-Spa: An Online Platform Based on Spatial Transcriptome...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Su, Yunyun Cui, Feifei Yan, Shiyu Zou, Quan Cao, Chen Zhang, Zilong Hainan University School of Computer Science and Technology Haikou China Hainan University School of Life Sciences Haikou China University of Electronic Science and Technology of China Institute of Fundamental and Frontier Sciences Chengdu China Nanjing Medical University School of Biomedical Engineering and Informatics Nanjing China

ISBN: (纸本)9798350337488

Spatial transcriptomics has become a major method for high-throughput analysis of gene expression at the current level of cells, which can directly study gene expression changes in disease cells, reveal the occurrence and development mechanism of diseases, identify potential therapeutic targets related to diseases, and provide new clues for disease diagnosis and treatment. Although there have been major breakthroughs in the analysis and acquisition of transcriptome data, there are still many challenges in how to effectively manage, share and utilize these valuable data resources in the study of human systemic diseases. To solve this problem, we are committed to building a spatial transcriptome database website related to human systemic diseases, aiming to provide reliable datasets related to multiple diseases, and provide certain data information and analysis results to accelerate the progress of human systemic diseases research. This paper will introduce the construction process of the database website in detail, and discuss its application prospects in disease research, with the aim of promoting further development and innovation in the field of human health. Here, Human-spa mainly includes 12 Human systems, 38 disease types, 55 datasets, and Human-Spa provides a very friendly web interface for visualization and dataset parsing. In conclusion, the construction of Human-Spa will provide a powerful tool and resource platform for Human disease research. Human-Spa is available for free at http://***/ © 2023 IEEE.

关键词： data analysis database website diseases of human system spatial transcriptome

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model based on Deep Learning and Cross-attention for Short-term Wind Power Prediction 5

A Hybrid Model based on Deep Learning and Cross-attention fo...

引用

5th International Conference on Renewable Energy and Power engineering, REPE 2022

作者： Zhang, Yiqin Peng, Cheng School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200000 China School of Computing University of Electronic Science and Technology of China Zhongshan Institute Zhongshan China

ISBN: (数字)9781665482066

ISBN: (纸本)9781665482066

New energy is a substitute for traditional energy in the coming decades, but its stability is poor. Power generation forecasting is an effective way to mitigate its negative effects. This paper proposed a wind power generation prediction model algorithm independent of meteorological data and propose a new way to build the cross-attention mechanism and perform a better result. We introduce a three-year wind farm dataset and apply out model to it, which facilitate feasibility analysis. © 2022 IEEE.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

RailPC: A large-scale railway point cloud semantic segmentation dataset

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1548-1560页

作者： Tengping Jiang Shiwei Li Qinyu Zhang Guangshuai Wang Zequn Zhang Fankun Zeng Peng An Xin Jin Shan Liu Yongjun Wang Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing Normal UniversityNanjingChina Technology Innovation Center for Integrated Applications in Remote Sensing and Navigation Ministry of Natural ResourcesNanjingChina Eastern Institute of Technology(EIT) NingboChina Tianjin Key Laboratory of Rail Transit Navigation Positioning and Spatio-temporal Big Data Technology TianjinChina College of Computer Science and Engineering Northwest Normal UniversityLanzhouChina Mckelvey School of Engineering Washington University in St.LouisSt.LouisMissouriUSA School of Electronic and Information Engineering Ningbo University of TechnologyNingboChina

Semantic segmentation in the context of 3D point clouds for the railway environment holds a significant economic value,but its development is severely hindered by the lack of suitable and specific ***,the models trained on existing urban road point cloud datasets demonstrate poor generalisation on railway data due to a large domain gap caused by non-overlapping special/rare categories,for example,rail track,track bed *** harness the potential of supervised learning methods in the domain of 3D railway semantic segmentation,we introduce RailPC,a new point cloud *** provides a large-scale dataset with rich annotations for semantic segmentation in the railway ***,RailPC contains twice the number of annotated points compared to the largest available mobile laser scanning(MLS)point cloud dataset and is the first railway-specific 3D dataset for semantic *** covers a total of nearly 25 km railway in two different scenes(urban and mountain),with 3 billion points that are finely labelled as 16 most typical classes with respect to railway,and the data acquisition process is completed in China by MLS *** extensive experimentation,we evaluate the performance of advanced scene understanding methods on the annotated dataset and present a synthetic analysis of semantic segmentation *** on our findings,we establish some critical challenges towards railway-scale point cloud semantic *** dataset is available at https://***/NNU-GISA/GISA-RailPC,and we will continuously update it based on community feedback.

关键词： data benchmark MLS point clouds railway scene semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Research on coking diagnosis based on semi-supervised Bayesian T-distribution mixed model 4

Research on coking diagnosis based on semi-supervised Bayesi...

引用

4rth International Conference on Applied Mathematics, Modelling, and Intelligent Computing, CAMMIC 2024

作者： Yang, Hanmei Cui, Delong Li, Qirui Peng, Zhiping Zuo, Jinglong School of Information and Control Engineering Jilin Institute of Chemical Technology Jilin132022 China School of Electronic and Information Engineering Guangdong University of Petrochemical Technology Maoming525000 China School of Computer Science Guangdong University of Petrochemical Technology Maoming525000 China Jiangmen Polytechnic College Jiangmen529090 China

ISBN: (纸本)9781510681637

In the process of ethylene production, the operating data of ethylene cracking furnace not only has the problems of time variability, non-gauss, strong noise, and outlier influence but also the collected data is incomplete, presenting the problem of scarce data with labels and abundant data without labels. To solve the above problems, this paper proposes a soft measurement model based on a semi-supervised Bayesian T-distribution mixture for the coking diagnosis of ethylene cracking furnaces. The model adopts a semi-supervised structure to solve the problem of the small number of data labels, adopts a T-distribution model to ensure the robustness of the model to strong noise and outliers under the Bayesian framework, and solves the solid variation of process data through the mixed model—complexity, non-Gaussian, and nonlinear problems. Finally, the experiment was carried out on the coking data of an ethylene cracking furnace in a petrochemical plant to verify the feasibility and prediction accuracy of the model under the condition of limited label data, and also to verify the robustness of the model to outliers. © 2024 SPIE.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Towards Fair Federated Learning via Unbiased Feature Aggregation

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： He, Zeqing Wang, Zhibo Dong, Xiaowei Sun, Peng Ren, Ju Ren, Kui Zhejiang University State Key Laboratory of Blockchain and Data Security China Institute of Blockchain and Data Security Hangzhou310027 China Wuhan University School of Cyber Science and Engineering Wuhan430072 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Tsinghua University Department of Computer Science and Technology Beijing100084 China Zhongguancun Laboratory Beijing100094 China

Federated learning (FL) is a distributed machine learning framework that enables multiple clients to collaboratively train models without raw data exchange. Prior studies on FL mainly focus on optimizing learning performance, enhancing privacy preservation, and improving attack resilience. However, little work studies how to mitigate the unfairness of federated trained models while unfair models would make discriminatory decisions toward certain groups or populations (e.g., favoring males over females), leading to serious ethical concerns. Thus, it is crucial to mitigate model unfairness in FL, yet challenging as this requires centralized access to each data point's fairness-sensitive information (e.g., race, gender), which is prohibited in FL. In this work, we propose a novel fair FL framework FedUFA, where the server can aggregate clients' learned knowledge in an unbiased manner, to obtain fair and high-usability federated trained models. Specifically, to unearth the bias in clients' local data and account for potentially heterogeneous local models, we propose a knowledge distillation-based FL scheme, where clients' knowledge of learned features on a public dataset is amalgamated to the server for aggregation. We train an unbiased feature mapper at the server to remove fairness-sensitive latent features and extract fair representations from clients' submitted raw features. In particular, we design an adversarial training method to train the mapper, which involves a predictor aiming to maximize the prediction accuracy on the FL task and a discriminator intending to help identify fairness-sensitive features. Extensive experiments on real-world datasets demonstrate the effectiveness of FedUFA. © 2025 IEEE. All rights reserved,

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An Exploratory data Analysis and Visualizations of Underprivileged Communities Diabetes dataset for Public Good

An Exploratory Data Analysis and Visualizations of Underpriv...

引用

IEEE WIC ACM International Conference on Web Intelligence (WI)

作者： Majdi Owda Amani Yousef Owda Maria Fasli Faculty of Data Science UNESCO Chair in Data Science for Sustainable Development Arab American University Ramallah West Bank Palestine Deprtment of Natural Engineering and Technology Sciences Faculty of Graduate Studies Arab American University Ramallah West Bank Palestine University of Essex School of Computer Science and Electronic Engineering Institute for Analytics and Data Science Colchester UK

Exploratory data analysis and visualization are essential tools for discovering patterns, highlighting anomalies, and discovering insights from datasets. In addition, visualizations tend to provide information in a way that is more accessible for the audience to understand and comprehend. Underprivileged communities will need an easier way to comprehend issues, challenges, and threats such as avoiding diseases. The use of exploratory data analysis and visualizations of diabetes datasets can be used as a means to make this topic easier to understand for underprivileged communities. A methodology has been developed to explore a dataset collection of diabetes patients. The dataset was obtained from the Palestinian community medical center (first-hand dataset), then the dataset was prepared and cleaned, and all rows with missing values or wrong values were dropped and removed, then an exploratory data analysis with a large number of data visualizations was produced, and last, a sample of the produced visualizations have been used to conduct a social acceptance experiment to educate an underprivileged population in the Palestinian community about the risks of diabetes. The result of the experiment was excellent and very promising in which participants understood the contents in a much easier way and provided very positive feedback on utilizing visualizations of diabetes datasets for public awareness and good.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transmission Line Routing Based on Multi-Source Geographic Information and Improved Grey Wolf Algorithm 5

Transmission Line Routing Based on Multi-Source Geographic I...

引用

5th International Conference on Machine Learning and computer Application, ICMLCA 2024

作者： Yang, Shu Xia, Yudong Zhu, Lankang Chen, Hao Cui, Li Pan, Wenwu Li, Ali He, Liang Jiaxing Hengchuang Electric Power Design and Research Institute Co. Ltd Jiaxing Hengchuang Jiaxing China School of Computer Science and Technology Xinjiang University Urumqi China Tsinghua University Center for Information Science and Technology Department of Electronic Engineering and Beijing National Research Beijing China

ISBN: (纸本)9798331530334

The design and selection of transmission lines are crucial for the security, economy and reliability of power systems. Traditional planning methods mainly rely on field visits and empirical judgment of grid researchers and have many limitations. This paper proposes a transmission line path planning method using multi-source geographic information and the improved grey wolf algorithm to reduce some costs. We utilize the geographic information system (GIS) for data processing and apply triangular fuzzy number hierarchical analysis to assess cost weights. By incorporating crossover and mutation operators, we enhance the grey wolf algorithm for optimized path planning. A local area in Jiaxing City, Zhejiang Province, is used for case study, which demonstrates that our method reduces costs compared to traditional grey wolf optimization to a certain extent. The results indicate that our approach offers a more reasonable path planning solution. © 2024 IEEE.

关键词： Power transmission lines

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：