检索结果-南通市图书馆

Comparative Analysis of ARIMA and LSTM Model-Based Anomaly Detection for Unannotated Structural Health Monitoring Data in an Immersed Tunnel

引用

Computer Modeling in Engineering & Sciences 2024年第5期139卷 1797-1827页

作者： qing Ai Hao Tian Hui Wang qing lang Xingchun Huang Xinghong Jiang Qiang Jing School of Naval Architecture Ocean and Civil EngineeringShanghai Jiao Tong UniversityShanghai200240China Key Laboratory of Road and Bridge Detection and Maintenance Technology of Zhejiang Province Hangzhou311305China Zhejiang Scientific Research Institute of Transport Hangzhou310023China State Key Laboratory of Coal Mine Dynamics and Control Chongqing UniversityChongqing400044China Hong Kong-Zhuhai-Macao Bridge Authority Zhuhai519060China

Structural Health Monitoring(SHM)systems have become a crucial tool for the operational management of long tunnels.For immersed tunnels exposed to both traffic loads and the effects of the marine environment,efficiently identifying abnormal conditions from the extensive unannotated SHM data presents a significant challenge.This study proposed amodel-based approach for anomaly detection and conducted validation and comparative analysis of two distinct temporal predictive models using SHM data from a real immersed tunnel.Firstly,a dynamic predictive model-based anomaly detectionmethod is proposed,which utilizes a rolling time window for modeling to achieve dynamic prediction.Leveraging the assumption of temporal data similarity,an interval prediction value deviation was employed to determine the abnormality of the data.Subsequently,dynamic predictive models were constructed based on the Autoregressive Integrated Moving Average(ARIMA)and Long Short-Term Memory(LSTM)models.The hyperparameters of these models were optimized and selected using monitoring data from the immersed tunnel,yielding viable static and dynamic predictive models.Finally,the models were applied within the same segment of SHM data,to validate the effectiveness of the anomaly detection approach based on dynamic predictive modeling.A detailed comparative analysis discusses the discrepancies in temporal anomaly detection between the ARIMA-and LSTM-based models.The results demonstrated that the dynamic predictive modelbased anomaly detection approach was effective for dealing with unannotated SHM data.In a comparison between ARIMA and LSTM,it was found that ARIMA demonstrated higher modeling efficiency,rendering it suitable for short-term predictions.In contrast,the LSTM model exhibited greater capacity to capture long-term performance trends and enhanced early warning capabilities,thereby resulting in superior overall performance.

关键词： Anomaly detection dynamic predictive model structural health monitoring immersed tunnel LSTM ARIMA

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

Progress in the design and quality control of placeboes for clinical trials of traditional Chinese medicine

引用

Journal of Integrative Medicine 2022年第3期20卷 204-212页

作者： Ning Guo Fei Wu Mei Wu Yuan Wang qing lang Xiao Lin Yi Feng College of Chinese Materia Medica Shanghai University of Traditional Chinese MedicineShanghai 201203China Engineering Research Center of Modern Preparation Technology of TCM of Ministry of Education Shanghai University of Traditional Chinese MedicineShanghai 201203China Department of Traditional Chinese Medicine Beicai Community Health Service Center of Pudong New DistrictShanghai 201204China

In recent years,new preparations of traditional Chinese medicines(TCMs)have been developed,increasing the need for their clinical trials.Using placeboes rather than control drugs is increasingly popular in clinical trials of TCMs,as the therapeutic effects of the tested TCMs can be more properly judged.The basic attributes of TCM placeboes include similarity,safety,applicability and controllability.In particular,it is necessary to have similarities in appearance,color,smell and taste between the tested TCMs and placeboes.This is quite difficult for some TCMs due to their distinctive smell and taste.On the other hand,according to the TCM theory on homology of medicine and food,many foods also have certain bioactivities,potentially further complicating the selection of materials for TCM placeboes.In this review,firstly,studies on the special smell and taste of TCMs were introduced.Then,the preparation quality evaluation processes for TCM placeboes were summarized and discussed,based on the relevant literature published in recent years and the research results from our own lab.This review will facilitate the further research and development of TCM placeboes.

关键词： Traditional Chinese medicines Placebo Critical quality attributes Clinical trial Similarity

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

航空发动机滑油泵调压特性研究

引用

液压气动与密封 2024年第7期44卷 100-103页

作者：张浪清中国航发南方工业有限公司湖南株洲412000

根据某航空发动机滑油系统滑油泵出口流量无法调节的问题,采用AMESim建立了滑油泵调压特性分析模型,分析了不同弹簧刚度下滑油泵的调压特性,结果显示通过合理匹配弹簧刚度和预紧力,不同刚度的弹簧均可以满足系统调压的需求,且趋势为大... 详细信息

根据某航空发动机滑油系统滑油泵出口流量无法调节的问题,采用AMESim建立了滑油泵调压特性分析模型,分析了不同弹簧刚度下滑油泵的调压特性,结果显示通过合理匹配弹簧刚度和预紧力,不同刚度的弹簧均可以满足系统调压的需求,且趋势为大刚度弹簧需要较小的预紧力,小刚度弹簧需要较大的弹簧预紧力。通过增加弹簧调节空间和减小弹簧刚度的措施解决了滑油泵出口流量无法调节的问题。对不同弹簧刚度的滑油泵进行了高空性分析,结果显示不同刚度的弹簧在高空性表现具有较高的相似性,小刚度的弹簧具有更好的高空性能。

关键词：调压特性弹簧刚度 AMESim仿真高空性

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

Domain Adaptation for Synthesis of Hazy Images

Domain Adaptation for Synthesis of Hazy Images

引用

作者： Haoying Sun Yutong Zheng qing lang School of Information Engineering Minzu University of China

Most existing image dehazing methods based learning are less able to perform well to real hazy images.An important reason is that they are trained on synthetic hazy images whose distribution is different from real hazy images.To relieve this issue, this paper proposes a new hazy scene generation model based on domain adaptation, which uses a variational autoencoder to encode the synthetic hazy image pairs and the real hazy images into the latent space to adapt.The synthetic hazy image pairs guide the model to learn the mapping of clear images to hazy images, the real hazy images are used to adapt the synthetic hazy images’ latent space to real hazy images through generative adversarial loss, so as to make the generative hazy images’ distribution as close to the real hazy images’ distribution as possible.By comparing the results of the model with traditional physical scattering models and Adobe Lightroom CC software, the hazy images generated in this paper is more realistic.Our end-to-end domain adaptation model is also very convenient to synthesize hazy images without depth map.Using traditional method to dehaze the synthetic hazy images generated by this paper, both SSIM and PSNR have been improved, proved that the effectiveness of our method.The non-reference haze density evaluation algorithm and other quantitative evaluation also illustrate the advantages of our method in synthetic hazy images.

关键词： Haze Scene Domain Adaptation Generative Adversarial Net Variational Autoencoder Deep Learning

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Domain Adaptation for Synthesis of Hazy Images

引用

Journal of Computer and Communications 2021年第10期9卷 142-151页

作者： Haoying Sun Yutong Zheng qing lang School of Information Engineering Minzu University of China Beijing China

Most existing image dehazing methods based learning are less able to perform well to real hazy images. An important reason is that they are trained on synthetic hazy images whose distribution is different from real hazy images. To relieve this issue, this paper proposes a new hazy scene generation model based on domain adaptation, which uses a variational autoencoder to encode the synthetic hazy image pairs and the real hazy images into the latent space to adapt. The synthetic hazy image pairs guide the model to learn the mapping of clear images to hazy images, the real hazy images are used to adapt the synthetic hazy images’ latent space to real hazy images through generative adversarial loss, so as to make the generative hazy images’ distribution as close to the real hazy images’ distribution as possible. By comparing the results of the model with traditional physical scattering models and Adobe Lightroom CC software, the hazy images generated in this paper is more realistic. Our end-to-end domain adaptation model is also very convenient to synthesize hazy images without depth map. Using traditional method to dehaze the synthetic hazy images generated by this paper, both SSIM and PSNR have been improved, proved that the effectiveness of our method. The non-reference haze density evaluation algorithm and other quantitative evaluation also illustrate the advantages of our method in synthetic hazy images.

关键词： Haze Scene Domain Adaptation Generative Adversarial Net Variational Autoencoder Deep Learning

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

大模型在社会治理应用中的偏见性检测方法

引用

中国电子科学研究院学报 2024年第1期19卷 69-75页

作者：林晖郭庆浪王迎雪黄虎中国电子科学研究院北京100041 广东省公共服务供给智能计算重点实验室深圳518055 社会安全风险感知与防控大数据应用国家工程研究中心北京100041 北京大学深圳研究生院广东深圳518055

随着人工智能技术的快速发展,大模型的分析、生成、推理能力在社会治理应用中的许多领域都得到了广泛应用。例如,互联网舆情分析等。然而,由于大模型的训练数据主要源于开源世界,其中的大量文本数据可能包含各种偏见和歧视,这可能在应... 详细信息

随着人工智能技术的快速发展,大模型的分析、生成、推理能力在社会治理应用中的许多领域都得到了广泛应用。例如,互联网舆情分析等。然而,由于大模型的训练数据主要源于开源世界,其中的大量文本数据可能包含各种偏见和歧视,这可能在应用大模型进行社会治理时产生偏见。本研究对大型语言模型(如GPT-3.5、LLaMa)的政治偏见进行了深入探讨。尽管大模型的训练机构坚称其公正,但研究文献表明,大模型在回应特定争议性话题时,常常展示出偏见,这可能导致社会治理的问题。本研究提出了一种偏见性检测方法,要求多个大模型扮演支持或反对特定目标(如政策、人物、话题等)的角色进行问题和答案的设计,并使用额外的大模型进行测试,通过比较这些答案和特定角色生成的答案,以推断接受测试的模型是否存在政治偏见。为降低对生成文本随机性的担忧,对同一问题进行了多次收集答案,每轮都对问题顺序进行随机化处理。实验结果显示,不同的大型语言模型在处理争议话题时都表现出显著的偏见性。这些结果引起了深刻关注,即大模型的直接应用可能会扩大甚至放大争议性信息。本研究的发现,对政策制定者、媒体、政治和学术利益相关者具有重要启示作用。

关键词：大模型偏见性检测社会治理

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

引用

疑难病杂志 2024年第7期23卷 834-839页

作者：彭昱锦杨琴廖德超严英郎清四川省达州市中心医院肝病科 635000

目的探讨乙型肝炎病毒相关慢加急性肝衰竭(HBV-ACLF)患者血清C-X-C基序趋化因子配体(CXCL)1、CXCL16与肝衰竭分期及短期预后的关系。方法选取2018年1月—2023年6月达州市中心医院肝病科收治的HBV-ACLF患者170例纳入病例组,再根据肝衰竭... 详细信息

目的探讨乙型肝炎病毒相关慢加急性肝衰竭(HBV-ACLF)患者血清C-X-C基序趋化因子配体(CXCL)1、CXCL16与肝衰竭分期及短期预后的关系。方法选取2018年1月—2023年6月达州市中心医院肝病科收治的HBV-ACLF患者170例纳入病例组,再根据肝衰竭分期分为早期亚组(71例)、中期亚组(54例)、晚期亚组(45例),根据患者90 d预后分为死亡亚组(60例)和存活亚组(110例),另选取同期健康体检者100例纳入健康对照组。采用酶联免疫吸附法检测血清CXCL1、CXCL16水平;单因素及多因素Logistic回归分析HBV-ACLF患者死亡的影响因素;受试者工作特征(ROC)曲线评估血清CXCL1、CXCL16和终末期肝病模型(MELD)评分对HBV-ACLF患者死亡的预测效能。结果与健康对照组比较,病例组患者血清CXCL1、CXCL16水平显著升高(t/P=30.816/<0.001,29.811/<0.001);早期亚组、中期亚组、晚期亚组血清CXCL1、CXCL16水平依次升高(F/P=317.656/<0.001,211.391/<0.001);与存活亚组比较,死亡亚组患者血清CXCL1、CXCL16水平显著升高(t/P=7.775/<0.001,7.137/<0.001);肝衰竭分期晚期和MELD评分高、CXCL1升高、CXCL16升高为HBV-ACLF患者死亡的独立危险因素[OR(95%CI)=5.069(1.322~19.441)、1.548(1.174~2.042)、1.914(1.162~3.153)、3.423(1.468~7.980)];血清CXCL1、CXCL16联合MELD评分预测HBV-ACLF患者死亡的ROC曲线下面积为0.927,大于血清CXCL1、CXCL16和MELD评分单独预测的0.786、0.781、0.784(Z=4.594、4.261、4.288,P均<0.001)。结论HBV-ACLF患者血清CXCL1、CXCL16水平升高,与肝衰竭分期及短期不良预后有关,在MELD评分基础上联合血清CXCL1、CXCL16对HBV-ACLF患者短期预后进行预测具有较高的价值。

关键词：乙型肝炎病毒相关慢加急性肝衰竭 C-X-C基序趋化因子配体肝衰竭分期预后

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

城市工业遗址公园的生态敏感性分析

引用

西北林学院学报 2024年第4期39卷 261-266页

作者：钱锋陈旭王大庆单晴朗喻振宇孟昭阳路梓欣王婧璇王丽薇贺玉瑶刘慧民东北农业大学园艺园林学院黑龙江哈尔滨150030 黑龙江农垦经济研究所黑龙江哈尔滨150030 海口经济学院海南海口571127 北京林业大学园林学院北京100083

生态敏感性分析可表明场地内不同区域抗干扰能力,可为区域内景观开发设计与场地利用提供数据支持与理论参考,对改善区域周边环境、提高地方生态系统稳定性有着重大意义。以大庆林源工业遗址公园为研究对象,使用GIS软件以及运用层次分析... 详细信息

生态敏感性分析可表明场地内不同区域抗干扰能力,可为区域内景观开发设计与场地利用提供数据支持与理论参考,对改善区域周边环境、提高地方生态系统稳定性有着重大意义。以大庆林源工业遗址公园为研究对象,使用GIS软件以及运用层次分析法、加权叠加法等方法,经一致性检验确定规划中生态敏感性影响因子及其权重,并进行生态敏感性综合分析。结果表明,高程、坡向、潜在水网为规划中生态敏感性影响因子,各因子所占权重分别为0.210 9、0.084 1、0.704 9;规划范围里高敏感范围占比18.84%,低敏感区域占比62.32%,不敏感区域占比18.84%:研究区生态敏感性相对适中,适宜进行一定程度的景观设计与开发。

关键词：城市工业遗址公园生态敏感性分析地理信息系统(GIS) 低敏感大庆市

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

Variable projection algorithms with sparse constraint for separable nonlinear models

引用

Control Theory and Technology 2024年第1期22卷 135-146页

作者： Hui-lang Xu Guang-Yong Chen Si-qing Cheng Min Gan Jing Chen College of Computer and Data Science Fuzhou UniversityFuzhou350116FujianChina Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhou350116FujianChina Key Laboratory of Intelligent Metro of Universities in Fujian Fuzhou UniversityFuzhou350116FujianChina Engineering Research Center of Big Data Intelligence Ministry of EducationFuzhou UniversityFuzhou350116FujianChina School of Science Jiangnan UniversityWuxi214122JiangsuChina

Separable nonlinear models are widely used in various fields such as time series analysis, system modeling, and machine learning, due to their flexible structures and ability to capture nonlinear behavior of data. However, identifying the parameters of these models is challenging, especially when sparse models with better interpretability are desired by practitioners. Previous theoretical and practical studies have shown that variable projection (VP) is an efficient method for identifying separable nonlinear models, but these are based on \(L_2\) penalty of model parameters, which cannot be directly extended to deal with sparse constraint. Based on the exploration of the structural characteristics of separable models, this paper proposes gradient-based and trust-region-based variable projection algorithms, which mainly solve two key problems: how to eliminate linear parameters under sparse constraint;and how to deal with the coupling relationship between linear and nonlinear parameters in the model. Finally, numerical experiments on synthetic data and real time series data are conducted to verify the effectiveness of the proposed algorithms.

关键词： Variable projection(VP) Non-smooth constraint Separable nonlinear models

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

Stress Concentration Effect in Interface Between Conductor and Epoxy Resin in Coaxial Components of Power Equipment

引用

CSEE Journal of Power and Energy Systems 2024年第1期10卷 412-420页

作者： Chuang Wang Kang Lei qing Sun Hui Li Jiawei Zhang lang Zhao Zongren Peng School of Electrical Engineering Xi’an University of TechnologyXi’an 710054China Xi’an Power Supply Company State Grid Shaanxi Electric Power CompanyXi’an 710032China State Key Laboratory of Electrical Insulation and Power Equipment Xi’an Jiaotong UniversityXi’an 710049China

The spacer used in gas insulated switchgear(GIS)plays a vital role in its safe operation.The mismatch of mechanical properties between conductor and insulating material in spacers results in stress concentration at the interface between them.During a hydrostatic test,mechanical damages are often initiated from the interface.In this paper,the stress between aluminum conductors and epoxy resin is studied by using a simplified coaxial structure specimen.The measurement system and finite element simulation are used to explore the generation of stress and strain during curing and shrinkage.The real-time measurement of strain at the interface shows that the residual strain in the entire process is primarily generated during the cooling stage.Consequently,the temperature and stress/strain distribution at the interface during the cooling stage are further studied,and combined with experiments and simulations.The consistency between the finite element simulation and the experimental measurement results verifies the validity of the simulation method used.The results show that the maximum of the first principal stress generated during the cooling stage of the production process is concentrated on the upper and lower edges of the interface which is critical to the impact of the production quality of the spacer.

关键词： Epoxy resin GIS interface stress/strain distribution

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

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：