Results 41 to 50 of about 14,820 (116)

Mistimed surveys lead to underestimated migratory bird impacts from wind farms

open access: yesJournal of Applied Ecology, Volume 63, Issue 4, April 2026.
Current guidance and approaches to surveying migratory birds at windfarm developments in Australia are insufficient. Evidence‐based alignment with seasonal presence is needed to improve biodiversity assessment standards, ensuring renewable energy expansion proceeds in a way that better safeguards migratory species and supports global biodiversity and ...
Xu Shi   +7 more
wiley   +1 more source

基于可解释机器学习模型的电信行业客户流失预测研究

open access: yesDianxin kexue
在电信行业中,客户流失的准确预测对于相关企业维持市场竞争力和增加收益至关重要。为此提出一个结合CatBoost算法和SHAP(shapley additive explanations)模型的客户流失预测框架,旨在提高预测的准确性,同时增强模型的可解释性。利用新疆某通信公司的实际营业数据,通过数据预处理及特征工程,构建预测模型,选取5种主要关键性能指标评估模型性能。实验结果显示,所提出模型在选取的评价指标上均优于当前主流机器学习预测模型。最后引入SHAP框架增强模型可解释性,揭示影响客户流失的关键因素 ...
王圣节, 张庆红
doaj   +1 more source

Multi‐barcoding‐based species identification using a hierarchical attention network with staged curriculum learning

open access: yesMethods in Ecology and Evolution, Volume 17, Issue 4, Page 1143-1160, April 2026.
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

Informing spatial conservation prioritization with species’ traits

open access: yesConservation Biology, Volume 40, Issue 2, April 2026.
Abstract New Guinea, the most botanically diverse island on the planet, is the location for one of the boldest conservation initiatives. The Manokwari Declaration aims to achieve 70% conservation designation for the Bird's Head Peninsula. This is 40% higher than the 2022 Global Biodiversity Framework target.
Liam A. Trethowan   +27 more
wiley   +1 more source

考虑纤维截面形状的木棉毡流阻率的分析模型

open access: yesZhendong Ceshi yu Zhenduan
针对现有模型不适用于木棉纤维材料流阻率预测的问题,测试了不同体密度的木棉毡。首先,使用已有的预测模型计算了木棉毡的流阻率;其次,通过对测试值拟合,给出了适用于木棉毡流阻率预测的经验模型;最后,考虑不同体密度下木棉纤维的截面形状与排布,基于Tarnow模型和哈根‑泊肃叶流动假设,通过推导微单元中的平均速度和摩擦力,给出了纤维圆形截面和扁平截面下木棉毡流阻率的分析模型,并使用压扁率对模型进行了修正。结果表明:与测试值对比,已有模型的木棉毡流阻率预测精度较低;修正模型适用于介于两种截面之间的过渡状态 ...
doaj   +1 more source

基于遗传神经网络对运行线路绝缘子污秽度的预测

open access: yesDianci bileiqi, 2018
为了实现对输电线路上绝缘子污秽度的预测,提出一种基于遗传算法优化BP神经网络的绝缘子污秽度预测模型。鉴于BP算法在训练神经网络模型时其收敛速度慢、动态特性不够理想等不足,故本文提出利用遗传算法来提高预测的精度。本文不仅以风力、温度、降水量和相对湿度等气象因素作为输入量,同时也综合考虑空气质量指数(AQI)中PM2.5、PM10等环境因素指标作为输入量,以绝缘子盐密(ESDD)和灰密(NSDD)的预测值作为输出量,建立绝缘子污秽度的预测模型。结果表明:优化后的预测模型相较于BP神经网络模型预测更加准确。
王自立   +6 more
doaj  

Machine Learning Model for an App‐Based Tool to Assist With the Diagnosis of Canine Atopic Dermatitis

open access: yesVeterinary Dermatology, Volume 37, Issue 2, Page 236-246, April 2026.
Canine atopic dermatitis (cAD) is a chronic condition requiring life‐long management. Accurate diagnosis can be challenging, with no reliable diagnostic test. This study aimed to generate a simple diagnostic model for cAD. This model is a relevant prototype for an app‐based tool to support general practitioners in the diagnosis of cAD alongside ...
Xavier Langon   +2 more
wiley   +1 more source

F10.7指数与Ap指数短期预报检验

open access: yesKongjian kexue xuebao
国家空间天气监测预警中心(NCSW)从2004年7月1日开始对用户提供空间天气预报服务, 其中包括未来24, 48 h和72 h的F10.7指数和Ap指数预报. 本文对2005-2022年NCSW的F10.7指数和Ap指数的预报结果进行了检验. 通过检验发现, NCSW预报的未来24, 48 h和72 h的F10.7指数平均比实测值偏小; 未来24 h的Ap指数平均比实测值偏大, 未来48 h和72 h的Ap指数平均比实测值偏小.
陈 安芹   +5 more
doaj   +1 more source

基于广义回归神经网络的油纸绝缘变压器的寿命预测

open access: yesGaoya dianqi, 2015
文中基于广义回归神经网络(GRNN)技术挖掘数据变化规律,构建了GRNN神经网络预测模型,运用该模型对油纸绝缘变压器进行寿命预测。将变压器绝缘纸老化过程中生成的特征产物如糠醛、CO2和CO的质量分数,以及相关时间参量作为模型输入。将所采集的多组油纸绝缘变压器的测试样本作为基础数据,运用该模型对相应的变压器进行寿命预测。结果表明,模型寿命预测的输出值与实际值基本一致,从而验证了模型的合理性,这对监测绝缘材料老化状态的进一步研究具有现实意义。
林喆, 兰生, 张宇航
doaj  

Forecasting the costs of residential construction based on support vector machine and least squares-support vector machine(基于SVM和LS-SVM的住宅工程造价预测研究)

open access: yesZhejiang Daxue xuebao. Lixue ban, 2016
为在方案设计初期与工程造价相关信息很少的条件下,准确快速地预测住宅工程造价,在分析既往相关理论和方法优劣的基础上,选取支持向量机构建住宅工程造价预测模型,并通过主成分分析对原始数据进行降噪处理.选取住宅工程造价预测指标集与样本,对输入指标的数据进行主成分分析,消除指标相关性的同时对原始数据降维,将处理后的数据分别导入到“标准支持向量机”和“最小二乘支持向量机”模型中进行训练和预测,并对预测结果进行对比分析,选取较为合理的预测模型,通过参数寻优进一步优化预测效果.所构建预测模型的相对误差均控制在±7%以内,
QINZhongfu(秦中伏)   +3 more
doaj   +1 more source

Home - About - Disclaimer - Privacy