检索结果-南通市图书馆

Satellite anomaly detection based on reconstruction discrepancy theory utilizing a new dual-branch reconstruction model

引用

Science China Technological Sciences 2024年第10期67卷 3294-3307页

作者： ZHAO HaoTian qiu shi LIU Ming CAO XiBin Research Center of Satellite Technology School of AstronauticsHarbin Institute of Technology

To enhance the accuracy of deep learning methods based on reconstruction discrepancy in satellite anomaly detection tasks, this study proposes a dual-branch reconstruction model(DBRM) and designs a comprehensive satellite anomaly detection framework around this model. Firstly, we introduce the temporal-channel mixer(TC-Mixer) module, which mainly comprises a self-attention layer for capturing long-range temporal dependencies in telemetry data, and two types of feed-forward networks(FFN) for extracting complex patterns in the temporal and channel dimension of telemetry data. This design endows the TC-Mixer module with robust capabilities for extracting complicated dependencies in telemetry data. Secondly, with the TC-Mixer module as the main component, we designed the DBRM. This model utilizes a shared latent representation layer, allowing the regeneration branch and forecasting branch of the DBRM to share most of the feature extraction network architecture. This approach significantly enhances the model's regression accuracy while reducing computational complexity. Thirdly, using the DBRM as the core network model, we devised a comprehensive satellite anomaly detection framework. This includes an anomaly criterion that considers the reconstruction discrepancy of both the regeneration and forecasting branches, the peak-over-threshold(POT) method for anomaly thresholding, and the MIC-based feature engineering method, etc. Finally, we conducted comparative experiments with several SOTA anomaly detection algorithms on two public and one private satellite anomaly detection datasets. The experimental results validate the effectiveness and superiority of our proposed method.

关键词： anomaly detection reconstruction discrepancy dual-branch reconstruction model (DBRM) satellite telemetry data time series

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Hyperspectral Image Based Interpretable Feature Clustering Algorithm

引用

Computers, Materials & Continua 2024年第5期79卷 2151-2168页

作者： Yaming Kang PeishunYe Yuxiu Bai shi qiu School of Information Engineering Yulin UniversityYulin719000China Key Laboratory of Spectral Imaging Technology CAS Xi’an Institute of Optics and Precision MechanicsChinese Academy of SciencesXi’an710119China

Hyperspectral imagery encompasses spectral and spatial dimensions,reflecting the material properties of *** application proves crucial in search and rescue,concealed target identification,and crop growth *** is an important method of hyperspectral *** vast data volume of hyperspectral imagery,coupled with redundant information,poses significant challenges in swiftly and accurately extracting features for subsequent *** current hyperspectral feature clustering methods,which are mostly studied from space or spectrum,do not have strong interpretability,resulting in poor comprehensibility of the ***,this research introduces a feature clustering algorithm for hyperspectral imagery from an interpretability *** commences with a simulated perception process,proposing an interpretable band selection algorithm to reduce data *** this,amulti-dimensional clustering algorithm,rooted in fuzzy and kernel clustering,is developed to highlight intra-class similarities and inter-class *** optimized P systemis then introduced to enhance computational *** system coordinates all cells within a mapping space to compute optimal cluster centers,facilitating parallel *** approach diminishes sensitivity to initial cluster centers and augments global search capabilities,thus preventing entrapment in local minima and enhancing clustering *** conducted on 300 datasets,comprising both real and simulated *** results show that the average accuracy(ACC)of the proposed algorithm is 0.86 and the combination measure(CM)is 0.81.

关键词： Hyperspectral fuzzy clustering tissue P system band selection interpretable

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Multilevel Attention Unet Segmentation Algorithmfor Lung Cancer Based on CT Images

引用

Computers, Materials & Continua 2024年第2期78卷 1569-1589页

作者： Huan Wang shi qiu Benyue Zhang Lixuan Xiao Xi’an Institute of Optics and Precision Mechanics Chinese Academy of SciencesXi’anChina School of Biomedical Engineering Fourth Military Medical UniversityXi’anChina University of Illinois at Urbana Champion ChampaignUSA

Lung cancer is a malady of the lungs that gravely jeopardizes human ***,early detection and treatment are paramount for the preservation of human *** computed tomography(CT)image sequences can explicitly delineate the pathological condition of the *** meet the imperative for accurate diagnosis by physicians,expeditious segmentation of the region harboring lung cancer is of utmost *** utilize computer-aided methods to emulate the diagnostic process in which physicians concentrate on lung cancer in a sequential manner,erect an interpretable model,and attain segmentation of lung *** specific advancements can be encapsulated as follows:1)Concentration on the lung parenchyma region:Based on 16-bit CT image capturing and the luminance characteristics of lung cancer,we proffer an intercept histogram algorithm.2)Focus on the specific locus of lung malignancy:Utilizing the spatial interrelation of lung cancer,we propose a memory-based Unet architecture and incorporate skip connections.3)Data Imbalance:In accordance with the prevalent situation of an overabundance of negative samples and a paucity of positive samples,we scrutinize the existing loss function and suggest a mixed loss *** results with pre-existing publicly available datasets and assembled datasets demonstrate that the segmentation efficacy,measured as Area Overlap Measure(AOM)is superior to 0.81,which markedly ameliorates in comparison with conventional algorithms,thereby facilitating physicians in diagnosis.

关键词： Lung cancer computed tomography computer-aided diagnosis Unet segmentation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Mural Anomaly Region Detection Algorithm Based on Hyperspectral Multiscale Residual Attention Network

引用

Computers, Materials and Continua 2024年第1期81卷 1809-1833页

作者： Guo, Bolin qiu, shi Zhang, Pengchang Tang, Xingjia Key Laboratory of Spectral Imaging Technology CAS Xi'an Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi'an 710119 China School of Optoelectronics University of Chinese Academy of Sciences Beijing 100408 China Institute of Culture and Heritage Northwest Polytechnic University Xi'an 710072 China

Mural paintings hold significant historical information and possess substantial artistic and cultural ***, murals are inevitably damaged by natural environmental factors such as wind and sunlight, as well as by human activities. For this reason, the study of damaged areas is crucial formural restoration. These damaged regions differ significantly from undamaged areas and can be considered abnormal targets. Traditional manual visual processing lacks strong characterization capabilities and is prone to omissions and false detections. Hyperspectral imaging can reflect the material properties more effectively than visual characterization methods. Thus, this study employs hyperspectral imaging to obtain mural information and proposes a mural anomaly detection algorithm based on a hyperspectral multi-scale residual attention network (HM-MRANet). The innovations of this paper include: (1) Constructing mural painting hyperspectral datasets. (2) Proposing a multi-scale residual spectral-spatial feature extraction module based on a 3D CNN (Convolutional Neural Networks) network to better capture multiscale information and improve performance on small-sample hyperspectral datasets. (3) Proposing the Enhanced Residual Attention Module (ERAM) to address the feature redundancy problem, enhance the network's feature discrimination ability, and further improve abnormal area detection accuracy. The experimental results show that theAUC(AreaUnderCurve), Specificity, andAccuracy of this paper's algorithmreach 85.42%, 88.84%, and 87.65%, respectively, on this dataset. These results represent improvements of 3.07%, 1.11% and 2.68% compared to the SSRN algorithm, demonstrating the effectiveness of this method for mural anomaly detection. © 2024 The Authors. Published by Tech Science Press.

关键词： Convolutional neural networks

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Colorectal Cancer Segmentation Algorithm Based on Deep Features from Enhanced CT Images

引用

Computers, Materials & Continua 2024年第8期80卷 2495-2510页

作者： shi qiu Hongbing Lu Jun Shu Ting Liang Tao Zhou School of Biomedical Engineering Fourth Military Medical UniversityXi’an710119China Department of Radiology Xijing HospitalFourth Military Medical UniversityXi’an710032China Department of Radiology The First Affiliated Hospital of Xi’an Jiaotong UniversityXi’an710061China School of Computer Science and Engineering North Minzu UniversityYinchuan750030China

Colorectal cancer,a malignant lesion of the intestines,significantly affects human health and life,emphasizing the necessity of early detection and *** segmentation of colorectal cancer regions directly impacts subsequent staging,treatment methods,and prognostic *** colonoscopy is an effective method for detecting colorectal cancer,its data collection approach can cause patient *** address this,current research utilizes Computed Tomography(CT)imaging;however,conventional CT images only capture transient states,lacking sufficient representational capability to precisely locate colorectal *** study utilizes enhanced CT images,constructing a deep feature network from the arterial,portal venous,and delay phases to simulate the physician’s diagnostic process and achieve accurate cancer *** innovations include:1)Utilizing portal venous phase CT images to introduce a context-aware multi-scale aggregation module for preliminary shape extraction of colorectal cancer.2)Building an image sequence based on arterial and delay phases,transforming the cancer segmentation issue into an anomaly detection problem,establishing a pixel-pairing strategy,and proposing a colorectal cancer segmentation algorithm using a Siamese *** with 84 clinical cases of colorectal cancer enhanced CT data demonstrated an Area Overlap Measure of 0.90,significantly better than Fully Convolutional Networks(FCNs)at *** research will explore the relationship between conventional and enhanced CT to further reduce segmentation time and improve accuracy.

关键词： Colorectal cancer enhanced CT multi-scale siamese network segmentation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Two-dimensional precise figuring of 500 mm-long X-ray mirror using one-dimensional ion beam system

引用

Advances in Manufacturing 2024年第1期12卷 177-184页

作者： qiu-shi Huang Han-Dan Huang Qiao-Yu Wu Jun Yu Zhong Zhang Zhan-Shan Wang MOE Key Laboratory of Advanced Micro-Structured Materials Institute of Precision Optical Engineering(IPOE)School of Physics Science and EngineeringTongji UniversityShanghai200092People’s Republic of China Shanghai Professional Technical Service Platform for Full-Spectrum and High-Performance Optical Thin Film Devices and Applications Tongji UniversityShanghai200092People’s Republic of China Shanghai Frontiers Science Center of Digital Optics Tongji UniversityShanghai200092People’s Republic of China

In this study,a new method was developed to realize two-dimensional(2D)figure correction of grazing-incidence X-ray mirrors using a one-dimensional(1D)ion-beam figuring system.A mask of holes was specifically designed to generate removal functions at different widths and extend the figuring capability over a wide ***,a long mirror could be *** this method,the surface height root-mean-square(RMS)error of the center area of 484 mm×16 mm was reduced from 11.49 nm to 2.01 nm,and the 1D meridional RMS error reached 1.0 *** proposed method exhibits high precision and cost effectiveness for production of long X-ray mirrors.

关键词： Long-size mirrors Ion beam figuring Two-dimensional figure correction Mask

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Rapid characterization of non-volatile phenolic compounds reveals the reliable chemical markers for authentication of traditional Chinese medicine Xiang-ru among confusing Elsholtzia species

引用

Chinese Journal of Natural Medicines 2024年第4期22卷 375-384页

作者： ZENG Zhen ZHANG Chen HU Jiadong WANG Feiyan WU Ziding WANG Jing ZHANG Jun YANG Shuda CHEN Junfeng LI Mingming TONG Qi qiu shi CHEN Wansheng The SATCM Key Laboratory for New Resources&Quality Evaluation of Chinese Medicine Institute of Chinese Materia MedicaShanghai University of Traditional Chinese MedicineShanghai 201203China Department of Pharmacy Second Affiliated Hospital of Navy Medical UniversityShanghai 200003China Kunming Plant Classification Biotechnology Co. Ltd.Kunming 650500China School of Pharmaceutical Sciences and Yunnan Key Laboratory of Pharmacology for Natural Products Kunming Medical UniversityKunming 650500China State Key Laboratory for Quality Ensurance and Sustainable Use of Dao-di Herbs Beijing100700China

The aerial parts of Mosla chinensis *** Mosla chinensis cv.'Jiangxiangru'(MCJ)are widely utilized in traditional Chinese medicine(TCM),known collectively as ***,due to clinical effectiveness concerns and frequent misidentification,the original plants have increasingly been substituted by various species within the genera Elsholtzia and *** challenge in distinguishing between these genera arises from their similar morphological and metabolic *** address this issue,our study introduced a rapid method for metabolic characterization,employing high-resolution mass spectrometry-based *** detailed biosynthetic and chemometric analyses,we pinpointed five phenolic compounds—salviaflaside,cynaroside,scutellarein-7-O-D-glucoside,rutin,and vicenin-2—among 203 identified compounds,as reliable chemical markers for distinguishing Xiang-ru from closely related Elsholtzia *** methodology holds promise for broad application in the analysis of plant aerial parts,especially in verifying the authenticity of aromatic traditional medicinal *** findings underscore the importance of non-volatile compounds as dependable chemical markers in the authentication process of aromatic traditional medicinal plants.

关键词： Genus Elsholtzia Genus Mosla Traditional Chinese medicine Xiang-ru Non-volatile phenolic compounds Liquid chromatography-mass spectrometry

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

效力体系视角下的法律行为成立理论构建

引用

当代法学 2024年第2期38卷 41-52页

作者：殷秋实中央财经大学法学院

现有的法律行为成立理论聚焦于成立与效力的区分、成立为事实判断和成立要件,并未关注不成立,未能明晰成立与不成立的效果与功能,导致理论的不自恰和法条解释基础的缺失。这些问题的解决需要在效力体系的视角下构建法律行为成立理论。... 详细信息

现有的法律行为成立理论聚焦于成立与效力的区分、成立为事实判断和成立要件,并未关注不成立,未能明晰成立与不成立的效果与功能,导致理论的不自恰和法条解释基础的缺失。这些问题的解决需要在效力体系的视角下构建法律行为成立理论。基于我国法的具体规定,在非决议的法律行为中,不成立具有和无效不同的效果,成立具有和有效不同的效果。不成立否定行为的存在及其意思自治意义,成立则意味着法律认可当事人行为具有意思自治上的重要性,是法律行为全部规范的适用前提。据此,成立是法律行为效力评价体系的一部分,并非事实判断,而是法律判断。重塑后的成立理论要求成立要件符合准入门槛低、由法律强制规定、不成立会导致无任何法律行为效力可能等标准。

关键词：法律行为不成立无效效力体系成立要件

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

内镜技术治疗肝胆管结石值得关注的几个问题

引用

中国实用外科杂志 2024年第3期44卷 267-270页

作者：冯秋实北京大学第一医院肝胆外科北京100034

在我国,肝胆管结石病是临床常见病,肝胆管结石的高残石率、高复发率、高再手术率迄今仍是胆道外科的难题。因为肝胆管结石病多合并肝胆管狭窄、反复发作的胆管炎,晚期发展至肝硬化门静脉高压症,且是发生胆管癌的重要因素,诊断和治疗均... 详细信息

在我国,肝胆管结石病是临床常见病,肝胆管结石的高残石率、高复发率、高再手术率迄今仍是胆道外科的难题。因为肝胆管结石病多合并肝胆管狭窄、反复发作的胆管炎,晚期发展至肝硬化门静脉高压症,且是发生胆管癌的重要因素,诊断和治疗均非常困难。虽然规则性肝段、肝叶切除是治疗肝胆管结石病的首选方法,近年来,肝胆管结石病微创治疗领域已取得一系列进展和突破,但仍有部分肝胆管结石难以通过手术完全去除。涉及腹腔镜、机器人手术系统、内镜等众多微创技术,其中内镜技术同样发挥了重要的作用,弥补了单纯手术治疗的不足,为不能手术肝切除或多次手术后、合并肝硬化的残留和(或)复发性结石病人的治疗带来更多的选择。内镜技术的广泛应用为肝胆管结石病的治疗注入了新的活力,使得肝胆管结石的治疗方案更为多元化。

关键词：肝胆管结石胆道镜经皮经肝胆道镜

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Time-resolved ultra-small-angle X-ray scattering beamline(BL10U1)at SSRF

引用

Nuclear Science and Techniques 2024年第2期35卷 6-19页

作者： Wen-Qiang Hua Chun-Ming Yang Ping Zhou Feng Tian Jin-You Lin Yu-Zhu Wang Xiao-Yun Li Xia-Ran Miao Chun-Xia Hong qiu-shi Huang Xin-Tong Zhao Yong-Feng Men Jie Wang Xing-Yu Gao Xiu-Hong Li Shanghai Synchrotron Radiation Facility Shanghai Advanced Research InstituteChinese Academy of SciencesShanghai 201204China Key Laboratory of Advanced Micro Structural Materials MOEInstitute of Precision Optical EngineeringSchool of Physics Science and EngineeringTongji UniversityShanghai 200092China State Key Laboratory of Polymer Physics and Chemistry Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchun 130022China

The construction of a new beamline,BL10U1,was completed at the Shanghai synchrotron radiation facility in *** multipurpose beamline was designed to provide X-ray scattering techniques such as ultra-small-angle X-ray scattering(USAXS),small-angle X-ray scattering(SAXS),wide-angle X-ray scattering,and microfocus SAXS(μSAXS)for a broad user *** realize fast time-resolved USAXS experiments,the beamline adopted an in-vacuum undulator with a total length of 1.6 m as the photon *** in-house cryogenic-cooled double multilayer monochromator was installed to deliver a photon flux of approximately 10^(13) photons/s at a photon energy of 10 *** three-year successful operation of this beamline demonstrated that the monochromator operated smoothly,as ***10U1 has three end stations in succession:USAXS end station,μSAXS end station,and end station for industrial *** minimum scattering vector q~0.0042 nm^(-1) at 10 keV can be achieved at the USAXS end station equipped with a 28 m-long and 1.8 m-diameter vacuum flight *** theμSAXS end station,a beam spot of less than 10×8μm was achieved for micro-SAXS *** contrast,in situ experimental instruments up to 5 m high and 8 m wide can be mounted at the industrial application end station,which offers industrial scientists the opportunity to use their large industrial ***10U1 opens up a new capability to investigate phenomena such as non-equilibrium and dynamic processes of materials with a wide length scale from angstroms to micrometers with millisecond time *** this paper,we also report beamline design considerations and commissioning results.

关键词： Synchrotron radiation Ultra-small-angle X-ray scattering Micro small-angle X-ray scattering USAXS Time resolved μSAXS

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：