检索结果-内蒙古大学图书馆

2023 Congress in Computer science, Computer Engineering, and Applied Computing, CSCE 2023

作者： Ojeda, Daniel Champion, Anissa Huang, Ching-Yu Kwak, Daehan Kean University Department of Computer Science and Technology UnionNJ United States

ISBN: (纸本)9798350327595

The COVID-19 pandemic has had a great impact on the world, with the United States experiencing a disproportionately high burden in terms of infections and deaths compared to other nations. The virus has disrupted daily life across the country and highlighted longstanding health inequalities. Therefore, this study aims to analyze the correlation between total COVID-19 cases and deaths with various demographic variables such as median age, education level, race, ethnicity, income, unemployment rate, disability status, and insurance coverage. The goal is to identify groups of people who are disproportionately affected by the COVID-19 virus and the factors that contribute to this inequality. To achieve this, the study collects data from all 50 states in the United States, using authoritative sources such as the U.S. Census Bureau and the Bureau of Labor. Then, ETL process (Extract, Transform, and Load) is performed to obtain clean and refined datasets and compile them into a final table for correlation analysis. With the help of this study, public health officials and policymakers could initiate the development of targeted interventions to ensure that everybody has the same opportunity to achieve good health, regardless of their demographic, economic, and social status. © 2023 ieee.

关键词： Correlation Analysis Covid-19 data Mining data visualization Health Disparities

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Intelligent Management Accounting Platform 6

Research on the Application of Intelligent Management Accoun...

引用

6th International Conference on Big data and Artificial Intelligence, BDAI 2023

作者： Wen, Yong Guangdong University of Science and Technology Department of Finance Dongguan China Nueva Ecija University of Science and Technology Graduate School Cabanatuan Philippines

ISBN: (纸本)9798350303667

5G technology, RPA technology, intelligent recognition technology, machine learning technology, business intelligence and other technologies have led to the birth of intelligent management accounting. The intelligent management accounting platform highly integrates business intelligence, artificial intelligence, and management accounting, forming a new management accounting model. This article constructs an intelligent management accounting platform, explores the architecture of the intelligent management accounting platform, analyzes the processing process of the intelligent management accounting platform, summarizes the main functions of the intelligent management accounting platform, and takes Guangdong JL Company as an example to introduce the application of the company's intelligent management accounting platform. Practice has proven that the intelligent management accounting platform has achieved automation, visualization, and intelligence in management accounting, improved management decision-making efficiency, and provided support for enterprise risk prevention. © 2023 ieee.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Interactive Visual Cluster Analysis by Contrastive Dimensionality Reduction

引用

ieee Transactions on visualization and Computer Graphics 2023年第1期29卷 734-744页

作者： Xia, Jiazhi Huang, Linquan Lin, Weixing Zhao, Xin Wu, Jing Chen, Yang Zhao, Ying Chen, Wei School of Computer Science and Engineering Central South University China Cardiff University United Kingdom State Key Lab of CAD&CG Zhejiang University China Laboratory of Art and Archaeology Image Zhejiang University Ministry of Education China

We propose a contrastive dimensionality reduction approach (CDR) for interactive visual cluster analysis. Although dimensionality reduction of high-dimensional data is widely used in visual cluster analysis in conjunction with scatterplots, there are several limitations on effective visual cluster analysis. First, it is non-trivial for an embedding to present clear visual cluster separation when keeping neighborhood structures. Second, as cluster analysis is a subjective task, user steering is required. However, it is also non-trivial to enable interactions in dimensionality reduction. To tackle these problems, we introduce contrastive learning into dimensionality reduction for high-quality embedding. We then redefine the gradient of the loss function to the negative pairs to enhance the visual cluster separation of embedding results. Based on the contrastive learning scheme, we employ link-based interactions to steer embeddings. After that, we implement a prototype visual interface that integrates the proposed algorithms and a set of visualizations. Quantitative experiments demonstrate that CDR outperforms existing techniques in terms of preserving correct neighborhood structures and improving visual cluster separation. The ablation experiment demonstrates the effectiveness of gradient redefinition. The user study verifies that CDR outperforms t-SNE and UMAP in the task of cluster identification. We also showcase two use cases on real-world datasets to present the effectiveness of link-based interactions. © 2022 ieee.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Off-Road Path-Planning Based on Large Scale OpenStreetMap and DSM data 9

Off-Road Path-Planning Based on Large Scale OpenStreetMap an...

引用

9th International Conference on Big data and Information Analytics, BigDIA 2023

作者： Ren, Shaoxuan Zhang, Maojun Liu, Yan Wang, Jingyi Zhou, Wen National University of Defense Technology College of Systems and Engineering Changsha China Hangzhou Dianzi University School of Computer Science and Technology Changsha China

ISBN: (纸本)9798350330076

In order to plan collision-free and shortest routes for vehicles in large-scale off-road scenarios, it is necessary to have a sufficient understanding and utilization of scene information. This paper proposes an off-road path planning method based on large scale OpenStreetMap (OSM) and Digital Surface Model (DSM). Our method comprehensively utilizes the terrain information from OpenStreetMap, slope information from DSM to analysis the traversability of the scene. We conduct experiments with a 2.5 km ∗ 3.5 km area surrounding the Federal Institute of Technology in Lausanne, Switzerland. In order to more intuitively display the results of path planning in the terrain, we conducted a three-dimensional visualization of the results. The experimental results verify the effectiveness of the method and the collision-free and the shortest routes can be planned in the large scale off-road scenarios. © 2023 ieee.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

RSNet: Relation Separation Network for Few-Shot Similar Class Recognition

引用

ieee TRANSACTIONS ON MULTIMEDIA 2023年 25卷 3894-3904页

作者： Guo, Kehua Shen, Changchun Hu, Bin Hu, Min Kui, Xiaoyan Cent South Univ Sch Comp Sci & Engn Changsha 410083 Peoples R China

Although deep learning methods have drastically improved the performance on visual recognition tasks in which large inter-class variances exist, similar-class recognition continues to pose significant challenges, mainly due to the close resemblance between similar classes. The challenge is further compounded in the case of few-shot learning because only a very small amount of training data is available;accordingly, a certain performance degradation has been observed when some few-shot methods are applied for classification tasks. To address the aforementioned issue, we propose a novel Relation Separation Network (RSNet) in this paper, aiming to boost few-shot learning by improving similar-class recognition performance. We assume that image features consist of commonand private features, where thecommonfeatures capture the basic attributes shared among similar classes and their private counterparts capture the unique attributes of each class. Our RSNet learns to decouple the common and private features of an image. As a result, the feature representation of an image is composed of two weakly associated but easily aligned components, and better classification performance is achieved by giving more attention to subtle features. Experimental results on the publicly available datasets miniImageNet, CUB, and CIFAR-FS show that the proposedmodel outperforms existing state-of-the-artmethods. Specifically, compared to PT+MAP, RSNet improves the accuracy of classification on the CUB dataset by approximately 5% and that of similar-class classification by more than 10%.

关键词： Feature extraction Task analysis Training Estimation Degradation visualization Training data Few-shot learning image classification similar class recognition feature separation

来源：评论

学校读者我要写书评

暂无评论

Deep Temporal State Perception Toward Artificial Cyber-Physical Systems

引用

ieee INTERNET OF THINGS JOURNAL 2023年第21期10卷 18782-18789页

作者： Jin, Yan Wang, Shaokun Liu, Fan Fan, Hongyun Hu, Yupeng Li, Xueqing Liu, Shijun Shandong Univ Sch Software Jinan 250101 Peoples R China Shandong Univ Sch Qilu Transportat Jinan 250101 Peoples R China Xi An Jiao Tong Univ Coll Software Engn Xian 710049 Peoples R China Natl Univ Singapore Sch Comp Singapore 250061 Singapore

Cyber-physical systems (CPS), as the cornerstone of smart city, has been attracting great interest from academia and industry. It aims to monitor/control physical components via communication and computation while ensuring effectiveness, intelligence, and security. The related research has pointed that the state perception on physical device is the prerequisite for boosting overall CPS performance. Toward this end, we present an effective deep temporal perception network to achieve classification-based state detection. Namely, we first design a multifeature encoding network for multiview time-series representation. Concretely, on the one hand, we utilize two piecewise aggregate representation strategies to obtain the key temporal trends;on the other hand, we adopt a temporal symbolic representation strategy to capture the necessary contextual semantic correlations. Thereafter, we develop a comprehensive representation enhancement module to improve feature comprehension capability and thus boosting the overall performance and interpretability. Corresponding comparison experiments, ablation studies, and data visualization analyses on benchmark data sets have verified the effectiveness of our model.

关键词： Time series analysis Internet of Things data mining Encoding Market research Robot kinematics Monitoring Cyber-physical systems (CPS) data mining temporal representation learning time-series classification

来源：评论

学校读者我要写书评

暂无评论

The Technical Importance of Accurate Diagnosis Using AI and ML Algorithms in the Field of Radioloy: A Medical Application

The Technical Importance of Accurate Diagnosis Using AI and ...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Mehrotra, Shashi Agarhari, Abishek Malik, Suraj Yuvaraj, K. Jeevananthan, P. Mehta, Pradnya Ccsit Tmu India Invertis University Department of Computer Science & Engineering Uttar Pradesh Bareilly243123 India School of Engineering and Technology Iimt University Meerut India Karpagam Academy of Higher Education Department of Computer Science Coimbatore641021 India Karpagam College of Engineering Department of Electrical and Electronics Engineering Coimbatore641032 India Engineering Vishwakarma Institute of Information Technology Pune India

ISBN: (纸本)9798350357769

Due to the accessibility of sizable databases, significant advancements in processing power, and novel approaches to deep learning, excitement in applications of AI-such as those involving imaging-is high and increasing quickly on a global scale. There are numerous possibilities and hurdles for the visualization group aside from the invention of fresh Methodologies per se, such as the creation of a widespread designations, improved methods for sharing image data, and guidelines for vindicating application use across different imaging social media channels and patient groups. By reporting malicious or favorable cases for honest review, intelligence services may aid pharmacists in prioritizing their to-do lists. They are additionally capable of helping extract brain mri data from photos that cannot be seen visually, done more easily the diagnostic as well as prognostlc value of data sets. There have been prophecies that doctors will become obsolete due to AI. This problem has been exaggerated, and doctors are considerably more likely to effectively integrate AI techniques into about their operations. The current shortages of technological know-how and even processing capacity will be handled in time, and internet connectivity options too can help. AI in radiography will be successful if it adds value through improvements in patient results, quicker response times, greater diagnosis confidence, and doctors' satisfaction with their lives at employment. A fresh and innovative collection of approaches for studying picture data are provided by AI. These novel avenues will be investigated by specialists, who will probably take the lead in AI's uses to medicine. © 2023 ieee.

关键词： Accuracy Artificial Intelligence Clinical diagnosis databases Deep learning Diagnosis confidence Diagnostic Doctors Imaging Internet connectivity Machine Learning medical uses Patient outcomes Radiology Technological know-how visualization

来源：评论

学校读者我要写书评

暂无评论

Universal Attack Against Automatic Modulation Classification DNNs Under Frequency and data Constraints

引用

ieee INTERNET OF THINGS JOURNAL 2023年第14期10卷 12938-12950页

作者： Wang, Chao Wei, Xianglin Fan, Jianhua Hu, Yongyang Yu, Long Tian, Qing Nanjing Univ Informat Sci & Technol Sch Comp & Software Nanjing 210044 Peoples R China Natl Univ Def Technol Res Inst 63 Nanjing 210007 Peoples R China

In spite of unique advantages like higher recognition accuracy and better generalization capability, automatic modulation classification (AMC)-oriented deep neural networks (ADNNs) are still vulnerable to adversarial examples (AEs). Recent results revealed that an attacker can easily fool ADNNs through adding a small and imperceptible perturbation to the original signal. Among different AE generation methods, universal adversarial perturbation (UAP) has unique characteristics, including input agnostic and shift invariance. However, applying UAP directly to RF signals faces three main challenges, i.e., perturbation neutralization, high perceptibility, and dependency of original signals. In this backdrop, a novel UAP under frequency and data constraints (UAP-FD) attack is put forward for solving these problems in this article. First, an individual perturbation is filtered based on the representation visualization algorithm to counter the neutralization problem in perturbation integration. Second, the high-frequency components in the integrated UAP is eliminated through signal decomposition and reconstruction for promoting the imperceptibility. Third, a proxy signal generation method is proposed to help UAP-FD adapt to data-free black-box settings. A series of experiments is conducted to evaluate the aggressiveness and imperceptibility of UAP-FD attack in different settings on a public data set. Results show that, compared with the existing proposal, UAP-FD has a 40% higher fooling rate, and it can reduce the accuracy of the ADNN model from 83% to 9% while maintaining a good imperceptibility and shift-invariance property. In addition, UAP-FD is applied to real-world captured signals over the transmission channel;and it can reduce the model accuracy from 98.3% to 12.5%.

关键词： Adversarial attacks automatic modulation classification (AMC) deep learning wireless security

来源：评论

学校读者我要写书评

暂无评论

DLT Based Smart Medical Ecosystem

DLT Based Smart Medical Ecosystem

引用

2023 ieee International Conference on Network, Multimedia and Information Technology, NMITCON 2023

作者： Puri, Vikram Kataria, Aman Rani, Sita Pareek, Piyush Kumar Duy Tan University Center of Visualization and Simulation Da Nang Viet Nam Amity Institute of Defence Technology Amity University Uttar Pradesh Noida India Guru Nanak Dev Engineering College Department of Computer Science and Engineering Ludhiana India Nitte Meenakshi Institute of Technology Dept. of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798350300826

The healthcare system has become more reliant on the data collection capabilities of fast evolving IoT devices. Patient healthcare records (PHR) now contain additional information as a result. However, securing identities and guaranteeing data security have emerged as critical challenges in the healthcare system. When it comes to regulating PHR, many of the centralized and decentralized methods now in use struggle difficulties such as single point of failure, high transaction fees, slow throughput, and excessive latency. To address these concerns, a distributed ledger technology (DLT)-based framework named IOTA rather than a blockchain-based platform such as Ethereum or Polygon is proposed. The proposed framework considered the example of a hospital with several patients on the same and various floors. Furthermore, the suggested approach employs a real-time experimental setup for calculating the time and power consumption of the devices. © 2023 ieee.

关键词： Distributed ledger

来源：评论

学校读者我要写书评

暂无评论

IoT Driven Smart Greenhouse: A Cost-Effective and User-Centric Automation Solution For Agriculture 17

IoT Driven Smart Greenhouse: A Cost-Effective and User-Centr...

引用

17th ieee International Conference on Advanced Networks and Telecommunications Systems, ANTS 2023

作者： Toke, Ishtiaque Ahmed Faisal Rahman, Mahir Mohammad Monir, Md Fahad Ahmed, Tarem Rabbani, Khondkar Ayaz Independent University Department of Computer Science and Engineering Bangladesh Independent University Department of Environmental Science and Management Bangladesh

ISBN: (纸本)9798350307672

Current smart greenhouse systems face challenges with regard to energy efficiency, cost-effectiveness, and the design of user-friendly interfaces. Wide-scale adoption of these systems requires simple and accessible solutions. These issues highlight the need for more straightforward simple and accessible solutions. Our study introduces an automated, user-friendly, affordable and power-optimized greenhouse management system using open-source technologies to tackle current efficiency and accessibility challenges. The system, powered by a solar-charged battery, uses a Node-RED designed interface, Raspberry Pi 3B for data parsing and storage, and an Arduino 2560 for micro-processing. With a custom automation algorithm and a remote control feature, the system provides real-time data visualization and enhanced usability. Particularly suited to Bangladesh's agricultural needs, it addresses local conditions such as climate and rural electricity scarcity. © 2023 ieee.

关键词： Solar energy

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：