Results 11 to 20 of about 17,258 (161)
对在轨卫星的运行状态进行监测、分析以及异常检测是卫星在轨运行管理的重要内容。预测卫星遥测参数序列的变化趋势,对卫星异常检测与处置、保障安全运行非常必要。针对目前对于周期性不明显且具有多种变化特征的遥测参数预测精确度不够的问题,本文引入对遥测参数的预测有辅助作用的因素作为协变量,提出了基于改进组合机器学习的预测模型。该模型使用全局模型和局部模型分别获取遥测参数序列的趋势特征和局部不规则波动特征,并采用改进的注意力机制捕获多维参数之间的关联关系,提高了预测精度。此模型可以提供点预测和区间预测的结果 ...
姜 改新, 刘 玉荣
doaj +1 more source
Our research allows us to understand the predictors of extinction risk in traditional Chinese medicinal (TCM) plant species with known threat status, and incorporate this knowledge to predict other TCM plants with unknown conservation status in China so as to improve the overall effectiveness of conservation strategies.
Yuhan Zheng +4 more
wiley +1 more source
Climate change drives shifts in suitable habitats for Eurasian lynx and its prey (hare, roe deer) in Mohe, Daxing'anling Mountains. Under RCP scenarios, moderate warming (RCP4.5) promotes substantial habitat expansion, while high‐emission conditions (RCP8.5) lead to strong expansion in the 2050s but slower gains and partial contraction by the 2070s ...
Binglian Liu +5 more
wiley +1 more source
Read the free Plain Language Summary for this article on the Journal blog. Abstract Decomposition is the transformation of dead organic matter into its inorganic constituents. In most biomes, decomposition rates can be accurately predicted with simple mathematical models, but these models have long under‐predicted decomposition in globally extensive ...
Heather L. Throop +8 more
wiley +1 more source
Jellyfish blooms restructure plankton dynamics and trophic linkages in coastal waters
Read the free Plain Language Summary for this article on the Journal blog. Abstract Jellyfish blooms are increasing globally in frequency and intensity, introducing complex ecological interactions, yet the mechanisms by which they alter ecosystem structure remain poorly characterized due to a lack of sustained field observations.
Pengpeng Wang +4 more
wiley +1 more source
摘要: 预测模型是用来预测个体发生目标事件概率或预测结局值的统计模型。预测模型结果可视化展现是开发预测模型全流程中必不可少的一部分。良好的预测模型展现形式不仅可以使预测结果具有更好的可读性、可解释性,也在很大程度上决定了其使用方式和便利性。本文将详细介绍各种预测模型的展现形式,并阐述各自的优缺点。随后结合脑血管病临床预测模型研究,通过研究示例逐一介绍不同展现形式在脑血管病研究中的应用。 Abstract: A prediction model is a statistical model ...
金奥铭,谷鸿秋
doaj +1 more source
Abstract DNA barcode‐based species identification has become pivotal in biodiversity research. Current barcoding‐based deep learning methods have advantages in species identification but exhibit significant limitations. By using COI barcoding alone, previous studies were unable to fully capture species identification features. Prior methods showed that
Bin Ye +4 more
wiley +1 more source
目的构建2型糖尿病发病风险预测模型。方法在体检人群中招募糖尿病患者53人,非糖尿病患者93人,体检的同时进行相应的基因检测,并填写健康体检自测问卷,收集全部数据采用XGBoost构建2型糖尿病预测模型。结果模型预测的准确率是86.6%,特征重要性评估结果显示,对模型贡献前三名的变量依次是血糖、甘油三酯和SLC30A8基因rs13266634-C位点的等位基因。结论 XGBoost糖尿病发病风险预测模型具有很强的预测能力。
张洪侠 +13 more
doaj
A link between increased temperature and avian body condition in a logged tropical forest
Abstract The combined effects of anthropogenic disturbances, such as logging and climate change, remain poorly understood; yet, they are the main threats to tropical biodiversity. Most tropical African countries lack long‐term climate data, so climate impacts on biodiversity cannot be assessed.
Moreen Uwimbabazi +7 more
wiley +1 more source
分析了利用神经网络进行时间序列预测的方法及其基本工作原理,并且利用神经 网络建立了土壤水分预测模型.试验结果表明:所建立的模型具有较好的预测效果;用神经网络建立土壤水分预测模型的方法是可行的.
刘洪斌, 武伟, 魏朝富
doaj +2 more sources

