检索结果-内蒙古大学图书馆

Three-stage polyp segmentation network based on reverse attention feature purification with Pyramid Vision transformer

引用

Computers in Biology and Medicine 2024年 179卷 108930页

作者： Meng, Lingbing Li, Yuting Duan, Weiwei School of Computer and Software Engineering Anhui Institute of Information Technology China

Colorectal polyps serve as potential precursors of colorectal cancer and automating polyp segmentation aids physicians in accurately identifying potential polyp regions, thereby reducing misdiagnoses and missed diagnoses. However, existing models often fall short in accurately segmenting polyps due to the high degree of similarity between polyp regions and surrounding tissue in terms of color, texture, and shape. To address this challenge, this study proposes a novel three-stage polyp segmentation network, named Reverse Attention Feature Purification with Pyramid Vision Transformer (RAFPNet), which adopts an iterative feedback UNet architecture to refine polyp saliency maps for precise segmentation. Initially, a Multi-Scale Feature Aggregation (MSFA) module is introduced to generate preliminary polyp saliency maps. Subsequently, a Reverse Attention Feature Purification (RAFP) module is devised to effectively suppress low-level surrounding tissue features while enhancing high-level semantic polyp information based on the preliminary saliency maps. Finally, the UNet architecture is leveraged to further refine the feature maps in a coarse-to-fine approach. Extensive experiments conducted on five widely used polyp segmentation datasets and three video polyp segmentation datasets demonstrate the superior performance of RAFPNet over state-of-the-art models across multiple evaluation metrics. © 2024 Elsevier Ltd

关键词： Purification

来源：评论

学校读者我要写书评

暂无评论

An Approach for Performance Calculation of AVS/RS in Multi-floor Workshop 3rd

An Approach for Performance Calculation of AVS/RS in Multi-f...

引用

3rd International Conference on Smart Manufacturing, Industrial and Logistics engineering, SMILE 2023 and the 7th Asian Conference of Management Science and Applications, ACMSA 2023

作者： Liu, Xiaopeng Wu, Cuiying Zhang, Baolin Xi, An Chen, Xuanrui Ministry of Industry and Information Technology Key Laboratory of Industrial Software Engineering Application Technology China Electronic Product Reliability and Environmental Testing Research Institute Guangzhou510619 China School of Computer and Information Engineering Hanshan Normal University Guangdong Chaozhou521041 China

ISBN: (纸本)9789819701933

Warehouse management is an important part of the production process. As a result of the development of technology, more and more companies tend to use automated logistics technologies such as AVS/RS to handle the internal logistics of the production system. Especially in multi-floor workshops, the production process on each floor are connected with each other through AVS/RS. It is becoming more and more important to study the integration process of AVS/RS and multi-floor workshop production process. In this paper, an integrated queuing network model of multi-floor workshop and AVS/RS was established, and a calculation method of system performance index was proposed. The accuracy and efficiency of the proposed method are demonstrated by comparing the results with simulations from numerical experiments. The work of this article can provide a basis for the design of autonomous vehicle storage and retrieve systems in multi-floor workshop, and the calculation method can be used as the support of WMS technology base. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving System Design for Digital Presence Protection

引用

Computers, Materials & Continua 2023年第5期75卷 3091-3110页

作者： Eric Yocam Ahmad Alomari Amjad Gawanmeh Wathiq Mansoor Department of Computer and Cyber Sciences The Beacom CollegeDakota State UniversitySouth DakotaUSA Department of Software Engineering and Information Technology Ecole de Technologie Superieure(ETS)MontrealCanada College of Engineering and IT University of DubaiDubaiUnited Arab Emirates

A person’s privacy has become a growing concern,given the nature of an expansive reliance on real-time video activities with video capture,stream,and *** paper presents an innovative system design based on a privacy-preserving *** proposed system design is implemented by employing an enhanced capability that overcomes today’s single parameterbased access control protection mechanism for digital privacy *** enhanced capability combines multiple access control parameters:facial expression,resource,environment,location,and *** proposed system design demonstrated that a person’s facial expressions combined with a set of access control rules can achieve a person’s privacy-preserving *** findings resulted in different facial expressions successfully triggering a person’s face to be blurred and a person’s privacy when using a real-time video conferencing service captured from a webcam or virtual webcam.A comparison analysis of capabilities between existing designs and the proposed system design shows enhancement of the capabilities of the proposed system.A series of experiments exercising the enhanced,real-time multi-parameterbased system was shown as a viable path forward for preserving a person’s privacy while using a webcam or virtual webcam to capture,stream,and store videos.

关键词： Attribute-based access control authentication authorization biometrics facial recognition identity privacy machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Sampling Fourier Single-Pixel Imaging Method Based on Discrete Coefficients 28

An Adaptive Sampling Fourier Single-Pixel Imaging Method Bas...

引用

28th International Conference on Automation and Computing, ICAC 2023

作者： Chen, Guangyao Xu, Yuanping Zhou, Jiliu Xu, Zhijie Zhang, Chaolong Kong, Chao Li, Tukun Gai, Qiuyan School of Software Engineering Chengdu University of Information Technology Chengdu China School of Computing and Engineering University of Huddersfield Queensgate Huddersfield United Kingdom

ISBN: (纸本)9798350335859

Fourier Single-Pixel Imaging (FSPI) can directly obtain the Fourier spectrum of a target scene and reconstruct it. However, the existing FSPI spectrum sampling methods are mostly constrained within a prior range, which makes it challenging to balance the image details and noise suppression under limited samples and short reconstruction time. One of the crucial issues in the practical application of SPI technology is how to enhance its imaging speed while ensuring the quality of the imaging. Therefore, this study proposed an adaptive sampling FSPI method based on discrete coefficients. This method utilizes the characteristic of energy concentration in the Fourier spectrum to plan circular and rectangular sampling paths in the frequency domain. Measurements are taken along the planned sampling paths, and the mean and standard deviation of each segment are calculated to obtain the discrete coefficients. When the discrete coefficient exceeds the threshold, the sampling stops automatically. Then, the target image is reconstructed by performing the inverse Fourier transform on the acquired spectrum. The method proposed in this article has significantly improved the imaging efficiency of SPI. © 2023 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Feature Model Configuration Reuse Scheme for Self-Adaptive Systems

引用

Computers, Materials & Continua 2022年第4期71卷 1249-1262页

作者： Sumaya Alkubaisi Said Ghoul Oguz Ata Electrical and Computer Engineering Department Altinbas UniversityIstanbul34218Turkey Faculty of Information Technology Research Laboratory on Bio-Inspired Software EngineeringPhiladelphia UniversityAmman26160Jordan

Most large-scale systems including self-adaptive systems utilize feature models(FMs)to represent their complex architectures and benefit from the reuse of commonalities and variability ***-adaptive systems(SASs)are capable of reconfiguring themselves during the run time to satisfy the scenarios of the requisite ***,reconfiguration of SASs corresponding to each adaptation of the system requires significant computational time and *** process of configuration reuse can be a better alternative to some contexts to reduce computational time,effort and ***,systems’complexity can be reduced while the development process of systems by reusing elements or *** are considered one of the new ways of reuse process that are able to introduce new opportunities for the reuse process beyond the conventional system *** current FM-based modelling techniques represent,manage,and reuse elementary features to model SASs concepts,modeling and reusing configurations have not yet been *** this context,this study presents an extension to FMs by introducing and managing configuration features and their reuse *** results demonstrate that reusing configuration features reduces the effort and time required by a reconfiguration process during the run time to meet the required scenario according to the current context.

关键词： Self-adaptive system feature model system reuse configuration management variability modeling

来源：评论

学校读者我要写书评

暂无评论

Mandalika Modeling Topic on Social Media Using Latent Dirichlet Allocation

Mandalika Modeling Topic on Social Media Using Latent Dirich...

引用

2023 International Conference on Computer Science, information technology and engineering, ICCoSITE 2023

作者： Hardita, Veny Cahya Hammad, Rifqi Amrullah, Ahmad Zuli STMIK Palangkaraya Informatics Engineering Palangkaraya Indonesia Bumigora University Software Engineering Mataram Indonesia Bumigora University Information Technology Mataram Indonesia

ISBN: (纸本)9798350320954

The Mandalika Circuit is one of the tourist attractions on the island of Lombok. The circuit is used for MotoGP events which can provide a positive trend for Lombok tourism. Many people provide information and comments on social media, especially Twitter, related to the Mandalika Circuit. The information and comments can be either positive or negative. This information can be used by certain parties to become a reference in improving the quality of services related to the Mandalika Circuit. information and comments are obtained from Twitter with a total of 1,300 tweets. In analyzing the information and comments related to the mandibular circuit, this study used the Latent Dirichlet Allocation (LDA) method. LDA is used to find out topics that often appear. The topics are then tested for coherence. Based on the LDA, it was found that the topics that most frequently appeared were circuits, mandalika and others with a coherence value of 0.473. This study succeeded in displaying the visualization of the results of the topic modeling into the visualization of wordcloud and pyLDAvis the results of word distribution on topics related to the Mandalika Circuit. This can make it easier to understand and analyze trending topics. © 2023 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Data-to-text Generation with Data Control and Multi-loss Fusion 2

Data-to-text Generation with Data Control and Multi-loss Fus...

引用

2nd International Conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2023

作者： Luo, Weier Yue, Xi Zhong, Chaotie Chengdu University of Information Technology Chengdu610225 China Sichuan Province Engineering Technology Research Center of Support Software of Informatization Application China

ISBN: (纸本)9798400707544

The goal of data-to-text generation is to generate fluent and fidelity natural language based on input data. At present, most models focus on data planning. Generating text according to the planning can effectively improve the fidelity to the generated text, but they lack attention to the fluency of the generated text, resulting in poor readability of the generated text. In order to address this issue, we propose a data-to-text generation model based on a pre-training language model. A control module is cleverly designed inside the language model to improve the fidelity to generated text. In training stage, multiple loss functions are cleverly designed to optimize the fluency and fidelity of generated text. Finally, the experimental results of RotoWire datasets show that the strong prior knowledge based on the Generative Pre-Training 2.0 (GPT2) can effectively improve the fluency of the generated text, and the proposed model in this paper can generate and control the fluency and fidelity of the generated text simultaneously. © 2023 Copyright held by the owner/author(s).

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Towards Edge Computing for 6G Internet of Everything: Challenges and Opportunities 1

Towards Edge Computing for 6G Internet of Everything: Challe...

引用

1st International Conference in Advanced Innovation on Smart City, ICAISC 2023

作者： Alawadhi, Abdulwadood Almogahed, Abdullah Azrag, Etidal Universiti Utara Malaysia School of Computing Kedah Malaysia Taiz University Faculty of Engineering and Information Technology Department of Software Engineering Taiz Yemen

ISBN: (纸本)9781665472753

The Internet of Everything (IoE)-based smart services are becoming more prominent as a result of the growing demands placed on wireless networks. Despite 5G having the ability to serve a wide range of IoE-based applications, they are unable to fully satisfy the needs of the newest intelligent systems. Therefore, 6G is the next generation for the IoT, IoE, and cellular networks, which aim to significantly improve smart services quality, such as maximum throughput and reduced latency. The number of internet-connected smart devices grows exponentially on a daily basis, resulting in Big Data. Several other cloud-based implementations use data centers as centralized servers for handling data collected by edge devices. This model places ever-increasing demands on computational infrastructure and communication, with unavoidable consequences for Experience and Quality-of-Service. By attempting to obtain cloud abilities closer to end users, edge computing is a novel technology which enables the development for 6G by attempting to overcome typical cloud weaknesses such as high latency and a lack of security. The purpose of this paper is to discuss challenges and opportunities in edge computing technology in 6G IoE. © 2023 IEEE.

关键词： Internet of Everything

来源：评论

学校读者我要写书评

暂无评论

Deployment of Polar Codes for Mission-Critical Machine-Type Communication Over Wireless Networks

引用

Computers, Materials & Continua 2022年第4期71卷 573-592页

作者： Najib Ahmed Mohammed Ali Mohammed Mansoor Rodina Binti Ahmad Saaidal Razalli Bin Azzuhri Department of Software Engineering Faculty of Computer Science and Information TechnologyUniversity of Malaya50603Kuala Lumpur Malaysia 2Department of Computer System&TechnologyFaculty of Computer Science and Information TechnologyUniversity of Malaya50603Kuala LumpurMalaysia

Mission critical Machine-type Communication(mcMTC),also referred to as Ultra-reliable Low Latency Communication(URLLC),has become a research *** is primarily characterized by communication that provides ultra-high reliability and very low latency to concurrently transmit short commands to a massive number of connected *** the reduction in physical(PHY)layer overhead and improvement in channel coding techniques are pivotal in reducing latency and improving reliability,the current wireless standards dedicated to support mcMTC rely heavily on adopting the bottom layers of general-purpose wireless standards and customizing only the upper *** mcMTC has a significant technical impact on the design of all layers of the communication protocol *** this paper,an innovative bottom-up approach has been proposed for mcMTC applications through PHY layer targeted at improving the transmission reliability by implementing ultra-reliable channel coding scheme in the PHY layer of IEEE 802.11a standard bearing in mind short packet transmission *** achieve this aim,we analyzed and compared the channel coding performance of convolutional codes(CCs),low-density parity-check(LDPC)codes,and polar codes in wireless network on the condition of short data packet *** Viterbi decoding algorithm(VA),logarithmic belief propagation(Log-BP)algorithm,and cyclic redundancy check(CRC)successive cancellation list(SCL)(CRC-SCL)decoding algorithm were adopted to CC,LDPC codes,and polar codes,***,a new PHY layer for mcMTC has been *** reliability of the proposed approach has been validated by simulation in terms of Bit error rate(BER)and packet error rate(PER)***-to-noise ratio(SNR).The simulation results demonstrate that the reliability of IEEE 802.11a standard has been significantly improved to be at PER=10−5 or even better with the implementation of polar *** results also show that the general-purpose wireless net

关键词： Machine-type communication mission-critical applications MTC URLLC M2M wireless networks polar codes

来源：评论

学校读者我要写书评

暂无评论

An Improved SMOTE Algorithm for Enhancing Classification Performance in Imbalanced Adolescent Mental Health Datasets

An Improved SMOTE Algorithm for Enhancing Classification Per...

引用

2023 International Conference on Computer Applications technology, CCAT 2023

作者： Pan, Bin Zhang, HaiQing Li, DaiWei Yu, Xi Cai, Bo Deng, JunYu Chengdu University of Information Technology School of Software Engineering Chengdu China Chengdu University Stirling College Chengdu China

ISBN: (纸本)9798350301540

In order to address the performance bias in modeling on imbalanced datasets of adolescent mental health issues, as well as the issues introduced by existing oversampling methods that do not fully consider sample distribution and may introduce noise, a novel improved SMOTE algorithm called HD-SMOTE is proposed. This algorithm utilizes the concept of natural neighbors and the principle of information entropy to obtain the natural neighbor density of minority class samples and the density of sample boundaries, and then weights the two densities to obtain adaptive mixed density weights. Finally, these weights are used for adaptive synthetic oversampling. Experimental comparisons were conducted on six publicly available imbalanced datasets against four other classical algorithms. The results demonstrate that the proposed algorithm exhibits significant improvements in terms of AUC, F1, and G-mean. Furthermore, the combination of HD-SMOTE with the CatBoost algorithm shows strong performance in identifying adolescent mental health issues compared to two other ensemble learning methods, highlighting its practical value. © 2023 IEEE.

关键词： Learning systems

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：