网站首页
编程语言
数据库
系统相关
其他分享
编程问答
Forecasting
2024-10-27
【Motion Forecasting】SmartRefine:A Scenario-Adaptive Refinement Framework for Motion Prediction
SmartRefine:AScenario-AdaptiveRefinementFrameworkforEfficientMotionPrediction今天要分享的文章来自于商汤科技在CVPR2024发表的文章SmartRefine,这是一项关注于双阶段轨迹解码器的改进工作。Abstract预测自动驾驶车辆周围智能体的未来运动对于自动驾驶车辆
2024-09-09
UNIT BUSA3015 Business Forecasting
UNITBUSA3015BusinessForecasting,Session2,2024AssessmentTask Report1Duedate 11:59pmFriday13thSeptemberWeight(%) 20%Taskdescription
2024-08-06
ASTGNN (Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data forTraffic Forecasting)
引言 时空神经网络(STGNNs)被广泛应用于交通预测问题中,在STGNNs中每个节点代表一个交通监测站,边表示道路网络。 在动态预测中,物理量x(t)随时间的变化模型是一个黑盒模型,我们要做的事情就是对黑盒模型进行建模。线性自回归方法直接将动态变化规律看
2024-01-23
AI4Science 再填新成员:谷歌推出天气模型MetNet-3 已落地相关产品、谷歌天气预报模型GraphCast登刊Science
相关:https://zhidx.com/news/40169.htmlhttps://zhidx.com/news/40290.html论文地址:https://www.science.org/doi/10.1126/science.adi2336《Learningskillfulmedium-rangeglobalweatherforecasting》Editor’ssummaryThenumericalmodelsusedtopredictwea
2023-10-29
华为最高学术成果发表 —— 《Nature》正刊发表论文《Accurate medium-range global weather forecasting with 3D neural network
论文《Accuratemedium-rangeglobalweatherforecastingwith3Dneuralnetworks》的《Nature》地址:https://www.nature.com/articles/s41586-023-06185-3.pdf 论文的代码地址:https://github.com/198808xc/Pangu-Weather 这篇论文可以
2023-10-20
【论文阅读】DeepAR Probabilistic forecasting with autoregressive recurrent networks
原始题目:DeepAR:Probabilisticforecastingwithautoregressiverecurrentnetworks中文翻译:DeepAR:自回归递归网络的概率预测发表时间:2020年07月平台:InternationalJournalofForecasting文章链接:https://www.sciencedirect.com/science/article/pii/S0169207019301888
2023-10-10
Time Series Forecasting Methods
基于EEMD-Prophet-LSTM的滑坡位移预测LSTM与Prophet时间序列预测实验11ClassicalTimeSeriesForecastingMethodsinMATLAB-FileExchange-MATLABCentral(mathworks.com)
2023-08-22
学习笔记:DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting
DSTAGNN:DynamicSpatial-TemporalAwareGraphNeuralNetworkforTrafficFlowForecastingICML2022论文地址:https://proceedings.mlr.press/v162/lan22a.html代码地址:https://github.com/SYLan2019/DSTAGNN一个用于时空序列预测的交通流量预测模型。可学习的地方:提出
2023-05-26
PyTorch-Forecasting一个新的时间序列预测库
时间序列预测在金融、天气预报、销售预测和需求预测等各个领域发挥着至关重要的作用。PyTorch-forecasting是一个建立在PyTorch之上的开源Python包,专门用于简化和增强时间序列的工作。在本文中我们介绍PyTorch-Forecasting的特性和功能,并进行示例代码演示。完整文章:https://av
2023-04-05
时序预测Time Series Forecasting:实体店销售
1.探索性数据分析:在这个时间序列的"入门"比赛中,我们被要求预测来自CorporaciónFavorita的商店销售数据,这是一家位于厄瓜多尔的大型杂货零售商。我们需要一个能够预测不同商店所销售的数千种商品的单位销售额的模型。在这次比赛中,我们有不同的数据集,描述了厄瓜多尔2013年
2023-03-24
03.Forecasting the realized volatility of stock price index A hybrid model integrating CEEMDAN and L
ForecastingtherealizedvolatilityofstockpriceindexAhybridmodelintegratingCEEMDANandLSTM预测股票价格指数的实际波动率CEEMDAN和LSTM的混合模型波
2023-02-20
Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting(
原文:https://arxiv.org/pdf/2208.05233.pdf代码:https://github.com/zezhishao/STIDAbstractMTS预测越来越复杂,但是性能改进有限,这一现象促使作者探索MTS预测的关键因素,
2023-02-12
【论文阅读】DSTAGNN Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting
DSTAGNNDynamicSpatial-TemporalAwareGraphNeuralNetworkforTrafficFlowForecastingInfotitle:DSTAGNN:DynamicSpatial-TemporalAwareGraphNeuralNetw
2022-10-04
GBRT代码详解(来自论文:Do We Really Need Deep Learning Models for Time Series Forecasting?)
#-*-coding:utf-8-*-"""XGBoostWB_Forecasting_Using_Hybrid_DL_Framework_Pm2.5_(1,6)"""importsyssys.version#ImportLibrariesimportitertoolsimportp