Results 31 to 40 of about 16,016 (204)

A study on time series prediction model based on CRBM algorithm(基于CRBM算法的时间序列预测模型研究)

open access: yesZhejiang Daxue xuebao. Lixue ban, 2016
针对受限玻尔兹曼机(restricted Boltzmann machines,RBM)算法对时序数据预测存在抽取抽象特征向量能力较差和梯度下降能力有限的问题,基于CRBM(conditional restricted Boltzmann machines)算法以及信念网络(deep belief network,DBN)模型,构建了 一种非线性的CRBM-DBN深度学习模型,并采用高斯分布处理输入特征值和对比散度抽样,用于预测时序数据.实验以浙江省近岸海域赤潮时序数据作为输入特征值 ...
ZHOUXiaoli(周晓莉)   +4 more
doaj   +1 more source

Exploring the Direct and Indirect Relations of E‐Book Narration and Bilingual Parent–Child Talk to Children's Learning Outcomes in EFL Shared Reading

open access: yesInternational Journal of Applied Linguistics, EarlyView.
ABSTRACT E‐books, powered by multimedia and interactive features, are widely used to support young children's language and literacy development. This study examines the relations of e‐book narration and bilingual parent–child talk to children's learning during shared reading. Data from 121 English learners in China and their parents were analyzed using
Dandan Yang   +3 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

基于太阳10.7 cm射电流量的全日面耀斑预报方法

open access: yesKongjian kexue xuebao, 2023
太阳耀斑是一种重要的太阳爆发活动现象,表现为近乎全波段的电磁辐射增强。统计表明,太阳活动水平越高,太阳爆发越频繁,耀斑爆发的概率越大。利用1975-2007年10.7 cm流量与耀斑爆发的统计关系,建立了一种可行的全日面爆发耀斑概率的预报方法,能够实现C,M,X三种级别的耀斑在全日面爆发的概率预报。通过2008-2016年的观测数据,对模型进行了预报性能的评估,得到模型对C,M,X级耀斑发生概率的预报误差均较小,Brier评分误差分别为0.113,0.087,0.012;模型的预报性能均比平均模型有提高,
雷 蕾   +3 more
doaj   +1 more source

Informal Digital Learning of English (IDLE) as Form‐Focused and Meaning‐Focused Activities: Refining its Measurement and Examining its Predictive Role in L2 Achievement and Confidence

open access: yesInternational Journal of Applied Linguistics, EarlyView.
ABSTRACT Acknowledging the limitations of existing measurement instruments in adequately capturing the distinct cognitive processes (e.g., form‐focused vs. meaning‐focused) involved in informal digital learning of English (IDLE), this paper asserts a pressing need to develop and validate robust instruments that measure form‐focused and meaning‐focused ...
Minlin Zou   +3 more
wiley   +1 more source

基于连续型贝叶斯概率估计器预测原子核质量

open access: yesHe jishu
近年来,机器学习方法被广泛应用于对原子核质量的预测中。基于连续型贝叶斯概率(Continuous Bayesian Probability,CBP)估计器,结合贝叶斯模型平均(Bayesian Model Averaging,BMA)改进了理论模型对核质量的描述。在CBP方法中,核质量理论值与实验值的差异被视为连续变量,通过核密度估计(Kernel Density Estimation,KDE)生成其先验和似然概率密度函数,并以贝叶斯定理确定后验概率密度函数。在全局优化和外推分析中 ...
谭 凯中, 高 琬晴, 刘 健
doaj   +1 more source

Exploring AI Literacy and AI‐Induced Emotions among Chinese University English Language Teachers: The Partial Least Square Structural Equation Modeling (PLS‐SEM) Approach

open access: yesInternational Journal of Applied Linguistics, EarlyView.
ABSTRACT Despite artificial intelligence (AI) emerging as a key driver of innovation and transformation in language education, how to enhance language teachers’ AI literacy and understand their emotional experiences in AI‐mediated teaching remains largely unexplored.
Xiao Xie   +3 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

Discussion for the method of environmental impact assessment on PM2. 5 in thermal power plants(火电厂PM2.5环境影响评价方法探讨)

open access: yesZhejiang Daxue xuebao. Lixue ban, 2014
现行的大气导则中尚缺乏针对PM2.5的评价模型、方法及监测要求.通过长三角重点控制区某扩建火电厂排放的一次PM2. 5和产生的光化学二次PM2. 5对周围环境的影响预测,提出了火电厂一次PM2. 5排放量估算的方法,并提出了火电厂PM2. 5(包括一次和二次)对周围环境影响的预测方法.评价结果表明,具有光化学反应的CALPUFF模型能有效预测一次和二次PM2. 5的生成,在环境影响评价现状监测因子中,因氮氧化物的削减对降低空气中PM2.
MOHua(莫华)   +3 more
doaj   +1 more source

ARIMA-LSTM model based on least square weighting to predict number of inbound tourists: A case study of Shanghai(基于最小二乘法赋权的ARIMA-LSTM模型预测入境旅游人数——以上海市为例)

open access: yesZhejiang Daxue xuebao. Lixue ban, 2023
为降低新冠病毒感染疫情大流行对旅游业的二次冲击,对疫情防控期间入境旅游市场的需求进行准确预测可为后期旅游业复苏提供科学依据。以上海市为研究区域,选取入境旅游人数、主要客源国、谷歌搜索指数、新增确诊病例数等数据,定量分析疫情前后入境旅游人数的空间变化特征及时间变化趋势,并用基于最小二乘法赋权的ARIMA-LSTM模型预测疫情后的入境旅游人数。结果表明:(1)疫情发生前后,亚洲客源市场一直占据入境旅游市场的核心地位,且传统入境游客与非传统入境游客的比例约为9∶1;(2 ...
康俊锋(KANG Junfeng)   +5 more
doaj   +1 more source

Home - About - Disclaimer - Privacy