检索结果-内蒙古大学图书馆

Regularized Total Least Squares Broad Learning System for Regression

Journal of Computers (Taiwan) 2025年第1期36卷 89-112页

作者： Xiong, Ke-Jia Yang, Guan-Ci Zhou, Tao Xie, Zhen-Qiang State Key Laboratory of Public Big Data Guizhou University Guizhou Province Guiyang City550025 China Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guizhou Province Guiyang City550025 China National Engineering Research Center of Big Data Application to The Improvement of Governance Capacity Guizhou Province Guiyang City550000 China

The Broad Learning System (BLS) has been extensively developed and applied across various fields due to its significant advantages, including high efficiency, strong generality, and scalability. However, in practical applications where both inputs and outputs are contaminated by noise, traditional BLS demonstrates suboptimal performance in handling sample data. This study introduces a novel regularized total least squares broad learning system (RTLS-BLS) designed to enhance the robustness of BLS when noisy values are present in both the input and the output of the training set. Initially, the k-support norm is integrated into the BLS-based autoencoder (BLS-AE), embedded within BLS, to extract robust features from the original input data. The BLS-AE equipped with the k-support norm effectively addresses or mitigates issues related to overly sparse (based on L1-norm) or overly dense (based on L2-norm) regularization of extracted features. Subsequently, regularized total least squares (RTLS) are employed to assess the output weights of BLS, further enhancing its robustness. Moreover, simultaneous perturbation measures for the coefficient matrix and the output are provided. Experimental results from two function approximation tasks, eight benchmark regression tasks, and two network interface flow datasets demonstrate that the proposed RTLS-BLS achieves significantly robust performance under noisy conditions compared to other methods. © 2025 Codon Publications. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

The Mass Assembly History for Galaxies with MaNGA

引用

research in Astronomy and Astrophysics 2024年第3期24卷 58-69页

作者： Xue Ge Hong-Tao Wang Cheng-Long Lei Yun-Jun Guo Yi-Long Jiang Xiao-Xiao Cao School of Physics and Information Engineering Jiangsu Second Normal University Jiangsu Province Engineering Research Center of Basic Education Big Data Application Jiangsu Second Normal University Key Laboratory of Modern Astronomy and Astrophysics Nanjing UniversityMinistry of Education School of Science Langfang Normal University

How galaxies assemble masses through their own star formation or interaction with the external environment is still an important topic in the field of galaxy formation and *** use Value Added Catalogs with galaxy features that are spatially and temporally resolved from Sloan Digital Sky Survey data Release 17 to investigate the mass growth histories of early-type galaxies(ETGs)and late-type galaxies(LTGs).We find that the mass growth of ETGs is earlier than that of LTGs for massive galaxies(M_(*)>10^(10)M_⊙),while low-mass(M_(*)≤10^(10)M_⊙)ETGs have statistically similar mass assembly histories as low-mass *** stellar metallicity of all massive galaxies shows a negative gradient and basically does not change with ***,in low-mass galaxies,the stellar metallicity gradient of elliptical galaxies is negative,and the stellar metallicity gradient of lenticular and spiral galaxies evolves from positive to *** are not all in a high-density environment,but exhibit mass *** the tidal strength increases,the star formation rate of low-mass ETGs rapidly *** results support a picture where massive galaxies exhibit inside-out quenching mode,while low-mass galaxies show outside-in quenching *** effects play an important role in regulating the mass assembly histories of low-mass ETGs.

关键词： Galaxy evolution-galaxies star formation-Galaxy formation

来源：评论

学校读者我要写书评

暂无评论

application of U-Net and Optimized Clustering in Medical Image Segmentation:A Review

引用

Computer Modeling in engineering & Sciences 2023年第9期136卷 2173-2219页

作者： Jiaqi Shao Shuwen Chen Jin Zhou Huisheng Zhu Ziyi Wang Mackenzie Brown School of Physics and Information Engineering Jiangsu Second Normal UniversityNanjing211200China State Key Laboratory of Millimeter Waves Southeast UniversityNanjing210096China Jiangsu Province Engineering Research Center of Basic Education Big Data Application Nanjing211200China School of Data Science Perdana UniversitySerdangSelangor43400Malaysia

As a mainstream research direction in the field of image segmentation,medical image segmentation plays a key role in the quantification of lesions,three-dimensional reconstruction,region of interest extraction and so *** with natural images,medical images have a variety of ***,the emphasis of information which is conveyed by images of different modes is quite *** it is time-consuming and inefficient to manually segment medical images only by professional and experienced ***,large quantities of automated medical image segmentation methods have been ***,until now,researchers have not developed a universal method for all types of medical image *** paper reviews the literature on segmentation techniques that have produced major breakthroughs in recent *** the large quantities of medical image segmentation methods,this paper mainly discusses two categories of medical image segmentation *** is the improved strategies based on traditional clustering *** other is the research progress of the improved image segmentation network structure model based on *** power of technology proves that the performance of the deep learning-based method is significantly better than that of the traditional *** paper discussed both advantages and disadvantages of different algorithms and detailed how these methods can be used for the segmentation of lesions or other organs and tissues,as well as possible technical trends for future work.

关键词： Medical image segmentation clustering algorithm U-Net

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Image Segmentation Models in COVID-19 Diagnosis 1

引用

29th International Conference on Computational and Experimental engineering and Sciences, ICCES 2023

作者： Xu, Sheng Chen, Shuwen Chen, Mike School of Physics and Information Engineering Jiangsu Second Normal University Nanjing211200 China Jiangsu Province Engineering Research Center of Basic Education Big Data Application Nanjing211200 China

ISBN: (数字)9783031449475

ISBN: (纸本)9783031449468

With Omicron sweeping the world, it has brought huge pressure on the healthcare system, and quick diagnosis of pneumonia caused by COVID-19 using chest computed tomography (CT) scans plays a key role in saving lives. Image processing techniques have been widely used to analyze CT scans and other medical images, which also facilitate the diagnosis and treatment of Coronavirus disease. This article introduces several image segmentation models that are used to facilitate the diagnosis of COVID-19 and applies several recently proposed deep learning (DL) models to the task, including UNEt TRansformers (UNETR++) and Dual Attention-guided Efficient Transformer (DAE-Former). We compare the performance of these models and provide a thorough analysis of different methods. The experimental results show that for the task of segmenting COVID-19 lesion areas, both Transformer-based models obtained better performance in terms of the value of mIoU compared with U-Net, a CNN-based model, while U-Net obtained higher accuracy. The DAE-Former model has superior anti-noise ability to UNETR++, whereas UNETR++ is more robust in terms of domain transfer. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Detection Based on 6-Layered Explainable Customized Convolutional Neural Network

引用

Computer Modeling in engineering & Sciences 2023年第9期136卷 2595-2616页

作者： Jiaji Wang Shuwen Chen Yu Cao Huisheng Zhu Dimas Lima School of Physics and Information Engineering Jiangsu Second Normal UniversityNanjing211200China State Key Laboratory of Millimeter Waves Southeast UniversityNanjing210096China Jiangsu Province Engineering Research Center of Basic Education Big Data Application Nanjing211200China Department of Electrical Engineering Federal University of Santa CatarinaFlorianópolis88040-900Brazil

This paper presents a 6-layer customized convolutional neural network model(6L-CNN)to rapidly screen out patients with COVID-19 infection in chest CT *** model can effectively detect whether the target CT image contains images of pneumonia *** this method,6L-CNN was trained as a binary classifier using the dataset containing CT images of the lung with and without pneumonia as a *** results show that the model improves the accuracy of screening out COVID-19 *** to othermethods,the performance is *** addition,the method can be extended to other similar clinical conditions.

关键词： COVID-19 custom convolutional neural network medical images

来源：评论

学校读者我要写书评

暂无评论

Optimization Scheme of Active Reconfigurable Intelligent Surface Assisted Internet of Vehicles System

Optimization Scheme of Active Reconfigurable Intelligent Sur...

引用

2024 International Workshop on Automation, Control, and Communication engineering, IWACCE 2024

作者： Xu, Zhuoran Ni, Yiyang Sun, Wenxue Liu, Yaxuan Mo, Zhaoying Zhao, Haitao Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and Telecommunications Nanjing210003 China Jiangsu Province Engineering Research Center of Basic Education Big Data Application Jiangsu Second Normal University Nanjing210013 China

ISBN: (数字)9781510685420

ISBN: (纸本)9781510685413

In recent years, the Integrated Satellite Aerial Terrestrial (I-SAT) network has emerged as an innovative and comprehensive communication system and has gained wide attention. However, in the face of a complex external environment, it will still be affected by other factors. This paper considers the integration of Unmanned Aerial Vehicle (UAV) with Reconfigurable Intelligent Surfaces (RIS) and introduces a novel sub-connected active RIS architecture under the energy consumption constraints of the system. Firstly, a joint RIS phase shift, amplification, and UAV trajectory optimization algorithm is proposed to achieve a high achievable sum rate. Secondly, a Deep Deterministic Policy Gradient (DDPG) algorithm is utilized to solve the optimization problem and converge in a continuous action space. Finally, simulation results confirm that the proposed approach significantly enhances the system performance compared to the other schemes. © 2024 SPIE. 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

Performance Analysis for Configured Active RIS-Aided Communication Systems

Performance Analysis for Configured Active RIS-Aided Communi...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Li, Longze Zhao, Haitao Ni, Yiyang Xu, Zhuoran Xun, Wei Xu, Bangning Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Wireless Communications Nanjing210003 China Jiangsu Second Normal University Nanjing Jiangsu Province Engineering Research Center of Basic Education Big Data Application 210003 China

ISBN: (纸本)9798350345384

The reconfigurable intelligent surface (RIS) is a crucial wireless channel control technology in 6G systems. Unlike traditional passive RIS (PRIS), active RIS (ARIS) can overcome the "multiplicative fading"effect. However, the configuration of the reflecting elements can significantly impact the system performance. In this paper, we focus on the ARIS equipped with uniform planar array (UPA) reflecting elements. We provide the ergodic achievable rate (EAR) for both unconfigured and configured ARIS system with closed-form. The effects of reflecting element area on the signal-to-noise ratio (SNR) are investigated, and a model selection scheme is proposed to determine whether to use ARIS or PRIS. Moreover, we analyze the average received power (ARP) and amplification power in ARIS. Based on the results of the analysis, a joint reflecting element area and quantity optimization scheme is proposed to improve system performance. The simulation results verify the accuracy of the analysis and highlight the superiority of the ARIS-assisted communication system. © 2023 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Survey of COVID-19 Diagnosis Based on Deep Learning from X-ray Images and CT-Scan Images 29th

A Survey of COVID-19 Diagnosis Based on Deep Learning from X...

引用

29th International Conference on Computational and Experimental engineering and Sciences, ICCES 2023

作者： Wang, Jiaji Chen, Shuwen Zhu, Huisheng School of Physics and Information Engineering Jiangsu Second Normal University Nanjing211200 China Jiangsu Province Engineering Research Center of Basic Education Big Data Application Nanjing211200 China State Key Laboratory of Millimeter Waves Southeast University Nanjing210096 China

ISBN: (纸本)9783031449468

The Coronavirus pandemic has been going on for three years. Undoubtedly, it caused huge damage to people, physically and mentally. The earlier the doctor diagnoses, the sooner the patient will recover In this paper, we review the more advanced applications of deep learning in COVID-19 diagnosis. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Advance of Thyroid Nodule Ultrasound Diagnosis Based on Deep Learning 29th

Advance of Thyroid Nodule Ultrasound Diagnosis Based on Deep...

引用

29th International Conference on Computational and Experimental engineering and Sciences, ICCES 2023

作者： Wan, Huiling Chen, Shuwen Ni, Yiyang Qi, Shaojia Qu, Hui School of Physics and Information Engineering Jiangsu Second Normal University Nanjing211200 China State Key Laboratory of Millimeter Waves Southeast University Nanjing210096 China Jiangsu Province Engineering Research Center of Basic Education Big Data Application Nanjing211200 China

ISBN: (纸本)9783031449468

The incidence of thyroid nodules is increasing rapidly worldwide. In order to reduce the burden on doctors and improve the accuracy of diagnosis, ultrasound imaging plays an important role in the diagnosis and follow-up of thyroid nodules. In recent years, artificial intelligence (AI) technology based on machine learning and deep learning has improved significantly. With the help of medical imaging screening tools, physicians can make clinical decisions about thyroid nodules more efficiently and provide the best protection for patients as early as possible. This paper mainly discusses the research progress of computer vision and related algorithms in ultrasonic imaging of thyroid nodules in recent years from the aspects of image preprocessing, detection and segmentation of focal areas, feature extraction, and identification of benign/malignant nodules. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Signage Detection Based on Adaptive SIFT 1

引用

11th International Conference on Frontiers of Intelligent Computing: Theory and applications, FICTA 2023

作者： Wang, Jiaji Chen, Shuwen Shao, Jiaqi Qu, Hui Wang, Ziyi School of Physics and Information Engineering Jiangsu Second Normal University Nanjing211200 China Jiangsu Province Engineering Research Center of Basic Education Big Data Application Nanjing211200 China State Key Laboratory of Millimeter Waves Southeast University Nanjing210096 China

ISBN: (数字)9789819967063

ISBN: (纸本)9789819967056

In navigation and wayfinding applications, signage is crucial for finding destinations. This paper proposes a new method for detecting signage, with the aim of helping blind individuals navigate unfamiliar indoor environments. To enhance the accuracy of signage detection and eliminate interference, the proposed method initially obtains the attended areas through a saliency map. The signage is then identified in these attended areas using SIFT algorithm-based adaptive threshold. This innovative approach is capable of detecting and recognizing multiple signs. Finally, audio facilitates the detection and recognition of results transferred to the users. Our experimental results, based on indoor signage datasets we collected, demonstrate the efficiency of our proposed method. On average, it takes 0.104 s to process the data. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer programming

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：