检索结果-南通市图书馆

Predicting Hurricane Evacuation Decisions with Interpretable Machine Learning Methods

International Journal of Disaster Risk Science 2024年第1期15卷 134-148页

作者： Yuran sun Shih‑Kai Huang Xilei zhao Department of Civil and Coastal Engineering University of FloridaGainesvilleFL 32611USA Department of Emergency Management and Public Administration Jacksonville State UniversityJacksonvilleAL 36265USA

Facing the escalating effects of climate change,it is critical to improve the prediction and understanding of the hurricane evacuation decisions made by households in order to enhance emergency management.Current studies in this area often have relied on psychology-driven linear models,which frequently exhibited limitations in practice.The present study proposed a novel interpretable machine learning approach to predict household-level evacuation decisions by leveraging easily accessible demographic and resource-related predictors,compared to existing models that mainly rely on psychological factors.An enhanced logistic regression model(that is,an interpretable machine learning approach) was developed for accurate predictions by automatically accounting for nonlinearities and interactions(that is,univariate and bivariate threshold effects).Specifically,nonlinearity and interaction detection were enabled by low-depth decision trees,which offer transparent model structure and robustness.A survey dataset collected in the aftermath of Hurricanes Katrina and Rita,two of the most intense tropical storms of the last two decades,was employed to test the new methodology.The findings show that,when predicting the households’ evacuation decisions,the enhanced logistic regression model outperformed previous linear models in terms of both model fit and predictive capability.This outcome suggests that our proposed methodology could provide a new tool and framework for emergency management authorities to improve the prediction of evacuation traffic demands in a timely and accurate manner.

关键词： Artifcial Intelligence(AI) Decision-making modeling Hurricane evacuation Interpretable machine learning Nonlinearity and interaction detection

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

QAR Data Imputation Using Generative Adversarial Network with Self-Attention Mechanism

引用

Big Data Mining and Analytics 2024年第1期7卷 12-28页

作者： Jingqi zhao Chuitian Rong Xin Dang Huabo sun School of Computer Science and Technology Tiangong UniversityTianjin 300387China Institute of Aviation Safety China Academy of Civil Aviation Science and TechnologyBeijing 100028China

Quick Access Recorder(QAR),an important device for storing data from various flight parameters,contains a large amount of valuable data and comprehensively records the real state of the airline flight.However,the recorded data have certain missing values due to factors,such as weather and equipment anomalies.These missing values seriously affect the analysis of QAR data by aeronautical engineers,such as airline flight scenario reproduction and airline flight safety status assessment.Therefore,imputing missing values in the QAR data,which can further guarantee the flight safety of airlines,is crucial.QAR data also have multivariate,multiprocess,and temporal features.Therefore,we innovatively propose the imputation models A-AEGAN("A"denotes attention mechanism,"AE"denotes autoencoder,and"GAN"denotes generative adversarial network)and SA-AEGAN("SA"denotes self-attentive mechanism)for missing values of QAR data,which can be effectively applied to QAR data.Specifically,we apply an innovative generative adversarial network to impute missing values from QAR data.The improved gated recurrent unit is then introduced as the neural unit of GAN,which can successfully capture the temporal relationships in QAR data.In addition,we modify the basic structure of GAN by using an autoencoder as the generator and a recurrent neural network as the discriminator.The missing values in the QAR data are imputed by using the adversarial relationship between generator and discriminator.We introduce an attention mechanism in the autoencoder to further improve the capability of the proposed model to capture the features of QAR data.Attention mechanisms can maintain the correlation among QAR data and improve the capability of the model to impute missing data.Furthermore,we improve the proposed model by integrating a self-attention mechanism to further capture the relationship between different parameters within the QAR data.Experimental results on real datasets demonstrate that the model can reasonably impute the missing values in QAR data wi

关键词： multivariate time series data imputation self-attention Generative Adversarial Network(GAN)

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

Predicting the Mechanical Properties of Polyurethane Elastomers Using Machine Learning

引用

Chinese Journal of Polymer Science 2023年第3期41卷 422-431,I0009页

作者： Fang Ding Lun-Yang Liu Ting-Li Liu Yun-Qi Li Jun-Peng Li zhao-Yan sun State Key Laboratory of Polymer Physics and Chemistry Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchun 130022China School of Applied Chemistry and Engineering University of Science and Technology of ChinaHefei 230026China Department of Polymer Materials and Engineering College of Materials and MetallurgyGuizhou UniversityGuiyang 550025China State Key Laboratory of Advanced Technologies for Comprehensive Utilization of Platinum Metals Sino-Platinum Metals Co.Ltd.Ltdunming 650106China

Bridging the gap between the computation of mechanical properties and the chemical structure of elastomers is a long-standing challenge.To fill the gap,we create a raw dataset and build predictive models for Young’s modulus,tensile strength,and elongation at break of polyurethane elastomers(PUEs).We then construct a benchmark dataset with 50.4%samples remained from the raw dataset which suffers from the intrinsic diversity problem,through a newly proposed recursive data elimination protocol.The coefficients of determination(R^(2)s)from predictions are improved from 0.73-0.78 to 0.85-0.91 based on the raw and the benchmark datasets.The fitting of stress-strain curves using the machine learning model shows a slightly better performance than that for one of the well-performed constitutive models(e.g.,the Khiêm-Itskov model).It confirmed that the black-box machine learning models are feasible to bridge the gap between the mechanical properties of PUEs and multiple factors for their chemical structures,composition,processing,and measurement settings.While accurate prediction for these curves is still a challenge.We release the raw dataset and the most representative benchmark dataset so far to call for more attention to tackle the longstanding gap problem.

关键词： Mechanical properties Stress-strain curves Polyurethane elastomers Machine learning Benchmark dataset

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

Protein neddylation and its role in health and diseases

引用

Signal Transduction and Targeted Therapy 2024年第5期9卷 1869-1904页

作者： Shizhen Zhang Qing Yu Zhijian Li Yongchao zhao Yi sun Department of Breast Surgery the Second Affiliated HospitalZhejiang University School of MedicineHangzhou 310029China Cancer Institute(Key Laboratory of Cancer Prevention and Intervention China National Ministry of Education)the Second Affiliated HospitalZhejiang University School of MedicineHangzhou 310029China Institute of Translational Medicine Zhejiang University School of MedicineHangzhou 310029China Department of Thyroid Surgery Zhejiang Cancer HospitalInstitute of Basic Medicine and Cancer(IBMC)Chinese Academy of SciencesHangzhou 310022China Key Laboratory of Head&Neck Cancer Translational Research of Zhejiang Province Hangzhou 310022China Department of Hepatobiliary and Pancreatic Surgery Zhejiang University School of MedicineHangzhou 310029China Zhejiang Provincial Key Laboratory of Pancreatic Disease The First Affiliated HospitalZhejiang University School of MedicineHangzhou 310029China Zhejiang University Cancer Center Hangzhou 310029China Leading Innovative and Entrepreneur Team Introduction Program of Zhejiang Hangzhou 310024China Research Center for Life Science and Human Health Binjiang Institute of Zhejiang UniversityHangzhou 310053China

NEDD8(Neural precursor cell expressed developmentally downregulated protein 8)is an ubiquitin-like protein that is covalently attached to a lysine residue of a protein substrate through a process known as neddylation,catalyzed by the enzyme cascade,namely NEDD8 activating enzyme(E1),NEDD8 conjugating enzyme(E2),and NEDD8 ligase(E3).The substrates of neddylation are categorized into cullins and non-cullin proteins.Neddylation of cullins activates CRLs(cullin RING ligases),the largest family of E3 ligases,whereas neddylation of non-cullin substrates alters their stability and activity,as well as subcellular localization.Significantly,the neddylation pathway and/or many neddylation substrates are abnormally activated or over-expressed in various human diseases,such as metabolic disorders,liver dysfunction,neurodegenerative disorders,and cancers,among others.Thus,targeting neddylation becomes an attractive strategy for the treatment of these diseases.In this review,we first provide a general introduction on the neddylation cascade,its biochemical process and regulation,and the crystal structures of neddylation enzymes in complex with cullin substrates;then discuss how neddylation governs various key biological processes via the modification of cullins and non-cullin substrates.We further review the literature data on dysregulated neddylation in several human diseases,particularly cancer,followed by an outline of current efforts in the discovery of small molecule inhibitors of neddylation as a promising therapeutic approach.Finally,few perspectives were proposed for extensive future investigations.

关键词： NEDD8 attached attractive

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

Hernandezine promotes cancer cell apoptosis and disrupts the lysosomal acidic environment and cathepsin D maturation

引用

Chinese Journal of Natural Medicines 2024年第5期22卷 387-401页

作者： FENG Qianwen sun Lu Muhammad Jibran Sualeh zhao Qingli zhao Songji CUI Zhengguo INADERA Hidekuni Department of Public Health Graduate School of Medicine and Pharmaceutical SciencesUniversity of ToyamaToyama 930-8501Japan Department of Pediatric Cardiology Heart CenterGuangzhou Women and Children’s Medical CenterGuangzhou Medical UniversityGuangzhou 510000China Department of Basic Medical Sciences College of MedicineUniversity of SharjahSharjah 57545United Arab Emirates Department of Radiology Graduate School of Medicine and Pharmaceutical SciencesUniversity of ToyamaToyama 930-8501Japan Advanced Clinical Research Center Fukushima Global Medical Science CenterFukushima Medical UniversityFukushima CityFukushima 960-8074Japan Department of Environmental Health School of Medical SciencesUniversity of FukuiFukui 910-8580Japan

Hernandezine(Her),a bisbenzylisoquinoline alkaloid extracted from Thalictrum flavum,is recognized for its range of biological activities inherent to this herbal medicine.Despite its notable properties,the anti-cancer effects of Her have remained largely unexplored.In this study,we elucidated that Her significantly induced cytotoxicity in cancer cells through the activation of apoptosis and necroptosis mechanisms.Furthermore,Her triggered autophagosome formation by activating the AMPK and ATG5 conjugation systems,leading to LC3 lipidation.Our findings revealed that Her caused damage to the mitochondrial membrane,with the damaged mitochondria undergoing mitophagy,as evidenced by the elevated expression of mitophagy markers.Conversely,Her disrupted autophagic flux,demonstrated by the upregulation of p62 and accumulation of autolysosomes,as observed in the RFP-GFP-LC3 reporter assay.Initially,we determined that Her did not prevent the fusion of autophagosomes and lysosomes.However,it inhibited the maturation of cathepsin D and increased lysosomal pH,indicating an impairment of lysosomal function.The use of the early-stage autophagy inhibitor,3-methyladenine(3-MA),did not suppress LC3II,suggesting that Her also induces noncanonical autophagy in autophagosome formation.The application of Bafilomycin A1,an inhibitor of noncanonical autophagy,diminished the recruitment of ATG16L1 and the accumulation of LC3II by Her,thereby augmenting Her-induced cell death.These observations imply that while autophagy initially plays a protective role,the disruption of the autophagic process by Her promotes programmed cell death.This study provides the first evidence of Her’s dual role in inducing apoptosis and necroptosis while also initiating and subsequently impairing autophagy to promote apoptotic cell death.These insights contribute to a deeper understanding of the mechanisms underlying programmed cell death,offering potential avenues for enhancing cancer prevention and therapeutic strategies.

关键词： Hernandezine Apoptosis Mitophagy Autophagic flux Lysosome Noncanonical autophagy

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

一锅法合成抗氧剂412S生产工艺研究

引用

广州化工 2024年第1期52卷 205-206,243页

作者：孙召韩海峰梁霄袁永霞江苏极易新材料有限公司研发部江苏徐州221700

抗氧剂412S是一种含多个硫原子、耐热、耐水解性优异的塑料抗氧。本文以正十二硫醇、丙烯酸甲酯、季戊四醇为主要原料,在催化剂催化下正十二硫醇与丙烯酸甲酯发生加成反应生成中间体3-十二烷基硫基丙酸甲酯;再加入季戊四醇与中间体发生... 详细信息

抗氧剂412S是一种含多个硫原子、耐热、耐水解性优异的塑料抗氧。本文以正十二硫醇、丙烯酸甲酯、季戊四醇为主要原料,在催化剂催化下正十二硫醇与丙烯酸甲酯发生加成反应生成中间体3-十二烷基硫基丙酸甲酯;再加入季戊四醇与中间体发生酯交换反应生成抗氧剂412S,收率82%。本方法实现一锅法合成抗氧剂412S,有效的减少实验操作,节约反应时间,节省人力和物力,为优化现有生产工艺提供一种方法。

关键词：抗氧剂412S 正十二硫醇丙烯酸甲酯一锅法酯交换

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

Hydroxyl radical production by abiotic oxidation of pyrite under estuarine conditions:The effects of aging,seawater anions and illumination

引用

Journal of Environmental Sciences 2024年第1期135卷 715-727页

作者： Ruixue Liu Yinshun Dai Yucheng Feng Shiwen sun Xiaodong Zhang Chunjiang An Shan zhao Shandong Key Laboratory of Water Pollution Control and Resource Reuse School of Environmental Science and EngineeringShandong UniversityQingdao 266237China Department of Building Civil and Environmental EngineeringConcordia UniversityMontrealQC H3G 1M8Canada

Pyrite is widely distributed in estuarine sediments as an inexpensive natural Fenton-like reagent,however,the mechanism on the hydroxyl radical(HO^(·))production by pyrite under estuarine environmental conditions is still poorly understood.The batch experiments were performed to investigate the effects of estuarine conditions including aging(in air,in water),seawater anions(Cl^(-),Br^(-)and HCO_(3)^(-))and light on the HO^(·)production by pyrite oxidation.The one-electron transfer dominated the process from O_(2) to HO^(·)induced by oxidation of pyrite.The Fe(oxyhydr)oxide coatings on the surface of pyrite aged in air and water consumed hydrogen peroxide while mediating the electron transfer,and the combined effect of the two resulted in a suppression of HO^(·)production in the early stage of aging and a promotion of HO^(·)production in the later stage of aging.Corrosion of the surface oxide layers by aggressive anions was the main reason for the inhibition of HO^(·)production by Cl^(-)and Br^(-),and the generation of Cl^(·)and Br^(·)may also play a role in the scavenging of HO^(·).HCO_(3)^(-)increased the average rate of HO^(·)production through surface-CO_(2) complexes formed by adsorption on the surface of pyrite.The significant enhancement of HO^(·)production under light was attributed to the formation of photoelectrons induced by photochemical reactions on pyrite and its surface oxide layers.These findings provide new insights into the environmental chemical behavior of pyrite in the estuary and enrich the understanding of natural remediation of estuarine environments.

关键词： Hydroxyl radical Pyrite oxidation Aging Anions Irradiation

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

基于双斜坡法的光纤应变快速测量方法

引用

科学技术与工程 2024年第16期24卷 6749-6756页

作者：董艳唯王浩孙昭张春晖李琳李苏雅陈永辉国网天津市电力公司电力科学研究院天津300384 华北电力大学电子与通信工程系保定071003

为了提高基于布里渊散射的光纤应变测量的实时性,将仅根据两个工作点布里渊增益计算布里渊频移的双斜坡法用于光纤应变测量。介绍双斜坡法的基本原理,基于仿真布里渊谱研究左右两侧工作点选择对布里渊频移计算准确性的影响规律,确定最... 详细信息

为了提高基于布里渊散射的光纤应变测量的实时性,将仅根据两个工作点布里渊增益计算布里渊频移的双斜坡法用于光纤应变测量。介绍双斜坡法的基本原理,基于仿真布里渊谱研究左右两侧工作点选择对布里渊频移计算准确性的影响规律,确定最佳的工作点。基于确定的最佳工作点和不同信噪比的布里渊谱,研究信噪比(signal-to-noise ratio, SNR)对双斜坡法和最小二乘拟合法准确性的影响规律。结果表明:双斜坡法的两个工作点围绕光纤沿线布里渊频移的均值对称时误差最小;随两个工作点频率之差的增加布里渊频移误差先减小后增大。相似准确性下双斜坡法的布里渊谱测量时间仅为最小二乘拟合法的约1/30,布里渊频移的计算时间仅约为后者的1/480。

关键词：布里渊散射分布式光纤传感双斜坡法快速应变测量

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

基于深度学习建立颈椎病MR诊断模型研究

引用

放射学实践 2024年第6期39卷 779-787页

作者：朱逸峰李雨师孙兆男张耀峰李家轮张晓东王可欣王霄英北京大学第一医院医学影像科北京100034 大连医科大学附属第二医院放射科辽宁116027 北京赛迈特锐医学科技有限公司北京100011 首都医科大学北京100069

目的:探索利用深度学习方法在建立颈椎病MR诊断模型的可行性。方法:回顾性搜集本院2020年10月-2023年3月诊断为颈椎病患者的MR图像514例,使用已有颈椎分割模型在轴面T 2WI上分别预测硬膜囊、脊髓、椎间盘、后纵韧带和黄韧带,在矢状面T ... 详细信息

目的:探索利用深度学习方法在建立颈椎病MR诊断模型的可行性。方法:回顾性搜集本院2020年10月-2023年3月诊断为颈椎病患者的MR图像514例,使用已有颈椎分割模型在轴面T 2WI上分别预测硬膜囊、脊髓、椎间盘、后纵韧带和黄韧带,在矢状面T 1WI和T 2WI上预测颈椎椎体和椎间盘。由一位低年资放射科医生(阅片经验2年)修改标注,另一位高年资放射科医生(阅片经验≥15年)对低年资医师的标注进行复核。按照颈椎病的不同诊断要点分别进行3D或2D深度学习分类模型训练,包括①颈椎椎体增生模型;②颈椎椎体滑脱模型;③颈椎间盘突出分类模型;④后纵韧带增厚模型;⑤黄韧带增厚模型。将模型输出结果导入R软件进行混淆矩阵分析及ROC曲线绘制,采用正确率、灵敏度、特异度、阳性预测值、阴性预测值以及ROC曲线下面积等评价5种模型的分类效能。结果:5种分类模型中诊断效能最好的是颈椎间盘突出分类模型,正确率0.90,灵敏度0.95,特异度0.85,ROC曲线下面积0.982。颈椎椎体增生和滑脱的正确率分别为0.81和0.80,灵敏度为0.74和0.76,特异度为0.84和1.00,ROC曲线下面积分别为0.855和0.905。后纵韧带和黄韧带增厚的模型正确率分别为0.82和0.77,灵敏度为0.78和0.84,特异度为0.86和0.70,ROC曲线下面积分别为0.902和0.929。结论:本部分研究采用深度学习方法建立了颈椎病MR的自动分类诊断模型,对颈椎椎体增生、滑脱、椎间盘突出、后纵韧带及黄韧带增厚进行了分类模型训练,证明深度学习方法可以用于颈椎病MR的辅助诊断,为未来进一步探索建立颈椎病MR自动诊断模型及结构化报告的植入奠定了基础。

关键词：磁共振成像颈椎病深度学习

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

Effects of simulated gut pH environment on bacterial composition and pheromone production of Dendroctonus valens

引用

Insect Science 2024年第1期31卷 225-235页

作者： Qingjie Cao Yu zhao Tuuli-Marjaana Koski Huiping Li Jianghua sun College of Forestry Hebei Agricultural UniversityBaodingHebei ProvinceChina State Key Laboratory of Integrated Management of Pest Insects and Rodents Institute of ZoologyChinese Academy of SciencesBeijingChina College of Life Science/Hebei Basic Science Center for Biotic Interactions Institute of Life Science and Green DevelopmentHebei UniversityBaodingHebei ProvinceChina

Bark beetles are an economically and ecologically important insect group,with aggregation behavior and thus host colonization success depends on pheromone-mediated communication.For some species,such as the major invasive forest pest in China,red turpentine beetle(Dendroctonus valens),gut microbiota participates in pheromone production by converting tree monoterpenes into pheromone products.However,how variation in gut microenvironment,such as pH,affects the gut microbial composition,and consequently pheromone production,is unknown.In this study,we fed wild caught D.valens with 3 different pH media(main host diet with natural pH of 4.7;a mildly acidic diet with pH 6 mimicking the beetle gut pH;and highly acidic diet with pH 4),and measured their effects on the gut pH,bacterial community and production of the main aggregation and anti-aggregation pheromone(verbenone).We further tested the verbenone production capacity of 2 gut bacterial isolates in different pH environments(pH 6 and 4).Compared to natural state or main host diet,feeding on less acidic diet(pH 6)diluted the acidity of the gut,whereas feeding on highly acidic diet(pH 4)enhanced it.Both changes in gut pH reduced the abundance of dominant bacterial genera,resulting in decreased verbenone production.Similarly,the highest pheromone conversion rate of the bacterial isolates was observed in pH mimicking the acidity in beetle gut.Taken together,these results indicate that changes in gut pH can affect gut microbiota composition and pheromone production,and may therefore have the potential to affect host colonization behavior.

关键词： Dendroctonus valens gut bacteria gut pH verbenone

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：