Results 41 to 50 of about 15,391 (164)
Dianxin 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
Veterinary Dermatology, EarlyView.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
Guangtongxin yanjiu, 2007 文章研究了利用Bass模型预测我国互联网用户数的方法。首先对Bass模型进行了描述,然后通过已有数据确定了Bass模型参数,最后利用该模型预测了我国互联网用户数并进行了误差分析。从预测结果中可以大致看出我国互联网用户达到饱和的时间,为今后带宽的预测打下了基础。文章最后给出了Bass模型的适用范围与参数确定方法,同时也提出了几种改善预测精度的方案。
陈晶晶, 毛谦, 刘国辉
doaj
World Water Policy, Volume 12, Issue 1, February 2026.ABSTRACT Urban expansion significantly impacts flood risk, particularly in rapidly growing areas where impervious surfaces exacerbate surface runoff. This study examines spatial patterns of urban growth and their effects on flood exposure in Mecklenburg County, North Carolina, from 2011 to 2021.
Pegah Madadi, Azad Sadeghi
wiley +1 more source
Zhejiang 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
基于加权基因共表达网络分析和机器学习的瘢痕疙瘩列线图预测模型 [PDF]
, 2023 Zhengyu Li, Baohua Tian, Haixia Liang
openalex +1 more source
Genetic origins and climate‐induced erosion in economically important Asian walnuts
Conservation Biology, Volume 40, Issue 1, February 2026.Abstract The global climate is undergoing unprecedented changes, posing significant threats to species persistence. However, the spatiotemporal impacts on genetic diversity remain poorly understood, hindering species conservation and management. Walnuts, generally referred to as Juglans regia and J. sigillata, are economically vital in Asia, but little
Peng‐Zhen Fan +17 more
wiley +1 more source
Conservation Biology, Volume 40, Issue 1, February 2026.Abstract As the global protected area (PA) network expands to meet international targets, it is important to assess whether traditional reliance on public land will suffice for projected PA growth or whether other tenures, such as Indigenous or pastoral lands, may increasingly contribute.
Emmeline Norris +2 more
wiley +1 more source
Dianci 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
Conservation Biology, Volume 40, Issue 1, February 2026.The graphical abstract highlights the research collaboration with fishers through interviews to record fishers' knowledge and participatory monitoring, to provide data on small‐scale fisheries in three clear water rivers (Trombetas, Tapajos and Tocantins).
Renato A. M. Silvano +10 more
wiley +1 more source