期刊文献+
共找到10,042篇文章
< 1 2 250 >
每页显示 20 50 100
How Investor Sentiment Influences Stock Price Informativeness of Firms’Future Earnings:Evidence From China’s Stock Market
1
作者 Junfeng Wang 《Journal of Sustainable Business and Economics》 2024年第4期1-32,共32页
This paper explores whether the level of stock price informativeness about listed companies’future earnings is influenced by investor sentiment.In prior studies,investor sentiment,which can be regarded as the mood of... This paper explores whether the level of stock price informativeness about listed companies’future earnings is influenced by investor sentiment.In prior studies,investor sentiment,which can be regarded as the mood of the market,is defined as a belief about unjustified firms’future cash flow,investment returns and risks in capital markets.At the same time,stock price informativeness indicates how much information about a firm’s future earnings is reflected by stock prices.Higher price informativeness indicates a higher market efficiency level.Using linear regression analysis based on panel data from China’s stock market and listed companies,this research documents how stock price informativeness can be reduced by investor sentiment during market pessimism.However,although the explanatory power of future earnings over stock returns is strengthened by positive sentiment,it is not certain that positive sentiment increases price informativeness since the asset price bubble exists with extreme market optimism.Furthermore,the effect of sentiment on price informativeness would be weakened by higher state-owned shareholding.These empirical results imply that sentiment,to a certain degree,causes the investors’ignorance during pessimism and exaggeration during optimism over firms’earning prospects.Moreover,investors usually lack favour for state-owned enterprises during optimism,even though these companies actually have considerable earning prospects.While during pessimism,which usually happens after a crisis,the profitability and reliability of these state-owned enterprises are again emphasised by investors. 展开更多
关键词 SENTIMENT informativeness Stock market efficiency State-owned shareholding
在线阅读 下载PDF
Research of Impact of Geografical Latitute and Residual Ionospheric Noises on Informativeness of Measuring of Zenith Wet Delay of GPS Signals
2
作者 A. Sh. Mehdiyev R. A. Eminov +1 位作者 N. Y. Ismayilov H. H. Asadov 《Positioning》 2015年第3期44-48,共5页
It is noted that necessity of further increase of accuracy of GPS positioning systems requires de-velopment of more perfect methods to compensate information losses occurred due to residual ionospheric delay by using ... It is noted that necessity of further increase of accuracy of GPS positioning systems requires de-velopment of more perfect methods to compensate information losses occurred due to residual ionospheric delay by using optimization procedures. According to the conditions of formulated optimization task, the signal/noise ratio in measurements of zenith wet delay depends on the second order ionospheric errors, geographic latitude and day of year. At the same time if we assume that the number of measurements at the fixed geographic site is proportional to geographic latitude and if we accept existence of only two antiphase scenarios for variation of residual ionospheric delay on latitude normed by their specific constant, there should be optimum functional dependence of precipitated water on latitude upon which the quantity of measuring information reaches the maximum. The mathematical grounding of solution of formulated optimization task is given. 展开更多
关键词 Zenith Wet Delay Information Optimization GPS Measurements IONOSPHERE GEOGRAPHIC LATITUDE
暂未订购
Informer-LSTM融合算法在蓝莓基质温湿度预测中的研究与应用
3
作者 胡玲艳 陈鹏宇 +6 位作者 郭占俊 徐国辉 秦山 付康 盖荣丽 汪祖民 张雨萌 《郑州大学学报(理学版)》 北大核心 2026年第1期78-86,共9页
为了精准预测温室蓝莓基质的温湿度变化趋势,提出一种融合Informer-LSTM算法的温湿度预测方法。以温室蓝莓现场环境数据为研究对象,使用LSTM算法捕捉时间序列数据中的依赖关系并与自注意力机制相结合,使模型在聚焦自注意力特征的同时兼... 为了精准预测温室蓝莓基质的温湿度变化趋势,提出一种融合Informer-LSTM算法的温湿度预测方法。以温室蓝莓现场环境数据为研究对象,使用LSTM算法捕捉时间序列数据中的依赖关系并与自注意力机制相结合,使模型在聚焦自注意力特征的同时兼顾LSTM特征,以增强其长期记忆力。在生成初步预测序列后,再应用LSTM算法修正模型的短期注意力,提高模型的反应速度。实验结果显示,Informer-LSTM预测模型在预测准确率、鲁棒性和响应速度等方面都有显著的优势。当温度湿度等时序输入数据发生明显变化时,模型能快速捕获短期内输入数据的动态模式变化。该模型在智慧温室管理中,对辅助人工决策及实现智能化控制具有较高实际价值。 展开更多
关键词 智慧农业 温室蓝莓 Informer模型 LSTM模型 温湿度预测
在线阅读 下载PDF
Employee Stock Ownership Plans and Stock-price Informativeness 被引量:1
4
作者 Yuehua Zuo Xin Huang +1 位作者 Xiaojun Liu Yunhao Dai 《China & World Economy》 2024年第3期162-190,共29页
This study examines the impact of employee stock ownership plans(ESOPs)on stock-price informativeness in Chinese stock markets.Its findings indicate that firms implementing ESOPs experienced an average 11.89 percent i... This study examines the impact of employee stock ownership plans(ESOPs)on stock-price informativeness in Chinese stock markets.Its findings indicate that firms implementing ESOPs experienced an average 11.89 percent increase in stock-price informativeness.The plans improved stock-price informativeness through increased external attention and supervision.An event study shows that ESOPs gave rise to an announcement effect,driven by anticipated performance improvements and the novelty associated with ESOPs.A mechanism analysis demonstrates that the implementation of ESOPs attracted market attention,and the increased market supervision resulting from this mitigated the moral hazards of management associated with ESOPs.Plans with more positive signals exerted a greater influence.Notably,ESOPs that prioritized management incentives gained more recognition in the market.As the incentive effects of ESOPs were weaker than those of equity incentive plans and the ESOPs lost novelty over time,the annual announcement effect diminished gradually.These findings underscore the necessity of strengthening ESOP incentives for continued optimization of priceefficiency. 展开更多
关键词 announcement effect corporate governance employee stock ownership plan stock-price informativeness
原文传递
Biogeographical informativeness of Y-STR haplotypes
5
作者 Jacobo Pardo-Seco Alberto Gómez-Carballa +2 位作者 Xabier Bello Federico Martinón-Torres Antonio Salas 《Science Bulletin》 SCIE EI CAS CSCD 2019年第19期1381-1384,共4页
Research on biogeographical ancestry(BGA)is becoming of growing interest in forensic genetics and in the biomedical literature(1)Thus,for instance,the need to predict ethnicity of an unknown suspect based on DNA profi... Research on biogeographical ancestry(BGA)is becoming of growing interest in forensic genetics and in the biomedical literature(1)Thus,for instance,the need to predict ethnicity of an unknown suspect based on DNA profiles found at the crime scene is of maximum interest in criminalistics[2],and several autosomal SNP panels have been designed and tested for BGA investigations[3,4].Most of these panels aim at discriminating three main continental groups(sub-Saharan Africans,Europeans,and Asians)by way of testing a number of ancestry informative markers(AIMs)that run from a few dozens to a few hundred[5](see more background in Supplementary data online). 展开更多
关键词 BGA STR Biogeographical informativeness of Y-STR haplotypes
原文传递
Right patient approach to experimental stromal cell therapies for gastrointestinal tumors
6
作者 Francesca Vescio Silvia Curcio +2 位作者 Isabella Aquila Michele Ammendola Alessandro Pasquale Tarallo 《World Journal of Gastrointestinal Oncology》 2026年第1期282-286,共5页
Experimental therapies targeting immune and stromal cells,such as mast cells,cancer-associated fibroblasts,dendritic cells,and tumor endothelial cells,in the treatment of gastrointestinal solid tumors pose new and com... Experimental therapies targeting immune and stromal cells,such as mast cells,cancer-associated fibroblasts,dendritic cells,and tumor endothelial cells,in the treatment of gastrointestinal solid tumors pose new and complex surgical and medico-legal challenges.These innovative treatments require that informed consent not be limited to simple acceptance of the medical procedure,but instead reflect a true relational and cognitive process grounded in understanding,free choice,and the ability to revoke consent at any time.In particular,it is essential that the patient understands the experimental nature of the therapy,its development stage,potential benefits and risks,as well as the implications for their health and personal dignity.In the case of stromal cell-based treatments,which may exert complex immunomodulatory effects or activate angiogenic pathways that are not yet fully understood,patients must be made fully aware that they are participating in a non-standardized therapy whose outcomes,whether beneficial or harmful,cannot yet be predicted with certainty.This requires particularly careful medical communication,using simple yet scientifically accurate explanations delivered in appropriate language,along with a final verification of the patient’s actual understanding. 展开更多
关键词 Experimental therapies SURGERY Non-standardized treatment Gastrointestinal tumor Informed consent
暂未订购
Extreme Attitude Prediction of Amphibious Vehicles Based on Improved Transformer Model and Extreme Loss Function
7
作者 Qinghuai Zhang Boru Jia +3 位作者 Zhengdao Zhu Jianhua Xiang Yue Liu Mengwei Li 《哈尔滨工程大学学报(英文版)》 2026年第1期228-238,共11页
Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instabili... Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instability,occur frequently in both experimental and operational data.This infrequency causes events to be overlooked by existing prediction models,which lack the precision to accurately predict inclination attitudes in amphibious vehicles.To address this gap in predicting attitudes near extreme inclination points,this study introduces a novel loss function,termed generalized extreme value loss.Subsequently,a deep learning model for improved waterborne attitude prediction,termed iInformer,was developed using a Transformer-based approach.During the embedding phase,a text prototype is created based on the vehicle’s operation log data is constructed to help the model better understand the vehicle’s operating environment.Data segmentation techniques are used to highlight local data variation features.Furthermore,to mitigate issues related to poor convergence and slow training speeds caused by the extreme value loss function,a teacher forcing mechanism is integrated into the model,enhancing its convergence capabilities.Experimental results validate the effectiveness of the proposed method,demonstrating its ability to handle data imbalance challenges.Specifically,the model achieves over a 60%improvement in root mean square error under extreme value conditions,with significant improvements observed across additional metrics. 展开更多
关键词 Amphibious vehicle Attitude prediction Extreme value loss function Enhanced transformer architecture External information embedding
在线阅读 下载PDF
The Relationship between Firm-Specific Return Variation and Price Informativeness:Some Cross-Sectional Evidence
8
作者 Xiao Li Dehua Shen Silvano Cincotti 《Journal of Management Science and Engineering》 2017年第1期55-68,共14页
The progressive removal of short-selling constraints in the Chinese stock market provides us with a natural experiment to investigate the relationship between firm-specific return variation(FSRV)and price informativen... The progressive removal of short-selling constraints in the Chinese stock market provides us with a natural experiment to investigate the relationship between firm-specific return variation(FSRV)and price informativeness.Based on the empirical finding that idiosyncratic volatility is a satisfied proxy for FSRV when the information environment for individual firms improves,we mainly find that the FSRV is negatively related to price informativeness.This negative relationship is robust to alternative model specifications,alternative proxies for price informativeness,and alternative estimation windows.Generally speaking,our results complement the extant literature on the mixed relationships between FSRV and price informativeness by providing cross-sectional evidence. 展开更多
关键词 Firm-specific return variation SHORT-SELLING Idiosyncratic volatility Price informativeness Natural experiment
原文传递
The effect of fair disclosure regulation on timeliness and informativeness of earnings announcements
9
作者 Yeonhee Park Inman Song +2 位作者 Dong-Hoon Yang Mahmud Hossain Jeong-Ho Koo 《China Journal of Accounting Research》 2013年第1期35-49,共15页
This paper examines the effect of Korea's fair disclosure regulation on the timeliness and informativeness of earnings announcements. The present regulation for Korean listed firms requires that if a company's... This paper examines the effect of Korea's fair disclosure regulation on the timeliness and informativeness of earnings announcements. The present regulation for Korean listed firms requires that if a company's sales revenue, operating income(or loss) and net income(or loss) have changed by over 30%compared to the prior year, the firm must disclose this information through a preliminary financial report(PFR) even before the company is audited by external auditors. To analyze the effects of this policy, we first investigate the timeliness of preliminary financial report disclosures. We examine the extent to which Korean listed companies actually comply with the requirement for prompt notification of information concerning material changes in financial performance. Second, we investigate the informativeness of preliminary financial reports by analyzing differential stock market reactions to different timings of preliminary financial report disclosures. Our empirical results reveal that more than half of our sample firms release their preliminary financialreports after external audits are completed, thereby potentially invalidating the effectiveness of the regulation. In addition, we find that preliminary financial reports have information value only if they are disclosed prior to annual audit report dates. This finding supports the notion that timeliness increases the informativeness of preliminary financial report disclosure by curbing insiders' ability to potentially profit from their information advantage. 展开更多
关键词 Fair disclosure Preliminary reports Interim information Timeliness of information Korea
原文传递
BIM技术赋能在役桥梁安全与高效运维 被引量:2
10
作者 张丽萍 王广 +2 位作者 王力 陈云峰 李子奇 《中国安全生产科学技术》 北大核心 2025年第1期101-108,共8页
为了保证运维阶段桥梁结构安全,提升桥梁运维工作的效率,开展公路混凝土梁式桥运维阶段建筑信息模型(building information modeling,BIM)技术应用研究。在对公路桥梁现行编码体系进行扩展的基础上,提出1种参数化快速建模方法,以快速完... 为了保证运维阶段桥梁结构安全,提升桥梁运维工作的效率,开展公路混凝土梁式桥运维阶段建筑信息模型(building information modeling,BIM)技术应用研究。在对公路桥梁现行编码体系进行扩展的基础上,提出1种参数化快速建模方法,以快速完成桥梁构件族的创建与整体模型的集成。借助Autodesk Revit软件应用程序编程接口(application programming interface,API),采用C#语言,开发公路混凝土梁式桥智慧运维状态评估系统,以实际工程应用进行验证分析。研究结果表明:全面统一的桥梁信息编码体系,能够提高桥梁信息统计与检索效率;提出的快速建模方法能够显著减少建模工作量,建模时间较传统建模方法可减少60%,并保证模型的准确性与规范性;运维状态评估系统能够实现养护数据的充分利用与桥梁评定工作的自动化,通过对桥梁运维信息的有效组织,实现服役性能的长期追踪,从而确保运营期桥梁结构状态安全稳定。研究结果可为公路混凝土梁式桥运维管理提供技术支撑,提升桥梁运维的数字化水平。 展开更多
关键词 桥梁工程 运维状态评估系统 Building Information Modeling 公路混凝土梁式桥
在线阅读 下载PDF
改进Informed RRT^(*)算法移动机器人路径规划 被引量:3
11
作者 鲁宇明 周羽逵 +2 位作者 郭鑫 池吕庭 戴骏 《计算机工程与应用》 北大核心 2025年第8期283-293,共11页
Informed RRT^(*)算法对初始解不敏感,规划出的路径太接近障碍物,导致路径不平滑。提出一种改进的Informed RRT^(*)路径规划算法,该算法改进了约束采样空间和引导策略。在采样初期,将采样区域限制在一个圆形区域,加快初始解收敛,在算法... Informed RRT^(*)算法对初始解不敏感,规划出的路径太接近障碍物,导致路径不平滑。提出一种改进的Informed RRT^(*)路径规划算法,该算法改进了约束采样空间和引导策略。在采样初期,将采样区域限制在一个圆形区域,加快初始解收敛,在算法规划的过程中引入人工势场中引力场和斥力场的思想,使机器人与障碍物保持安全距离,并向目标位置行进。对Informed RRT^(*)算法和基于目标偏置的Informed RRT^(*)算法(Goal-bias-Informed RRT^(*))以及改进后的Informed RRT^(*)算法进行比较实验,实验结果验证了改进后Informed RRT^(*)算法的有效性和优越性及稳定性。该算法较Informed RRT^(*)算法和Goal-bias-Informed RRT^(*)效率更高、更容易得到初始解、更安全、更平滑、更稳定。 展开更多
关键词 移动机器人 路径规划 随机采样 Informed RRT^(*)算法 目标偏置 约束采样空间
在线阅读 下载PDF
基于DWT-CNN-Informer模型的液压支架压力多步长预测 被引量:2
12
作者 张传伟 张刚强 +1 位作者 路正雄 李林岳 《中国安全生产科学技术》 北大核心 2025年第4期57-63,共7页
为了实现液压支架压力多步长精准预测,提出1种基于DWT-CNN-Informer模型的压力多步长预测方法,该方法利用离散小波变换(discrete wavelet transform, DWT)将预处理后的压力时序数据分解为趋势项和周期项频率分量;各频率分量输入卷积神... 为了实现液压支架压力多步长精准预测,提出1种基于DWT-CNN-Informer模型的压力多步长预测方法,该方法利用离散小波变换(discrete wavelet transform, DWT)将预处理后的压力时序数据分解为趋势项和周期项频率分量;各频率分量输入卷积神经网络(CNN)模型提取频率特征;提取的频率特征输入Informer编码器,经位置编码和多头概率稀疏自注意力机制捕捉时序变化特征,并结合自注意力蒸馏减少特征冗余;将Informer解码器改为全连接层,直接输出各分量多步长预测结果;重构叠加各分量多步长预测结果得到液压支架压力多步长预测结果。研究结果表明:在预测步长分别为6,12,24时,DWT-CNN-Informer模型相比LSTM、Informer、CNN-Informer模型在平均绝对误差(MAE)、均方根误差(RMSE)、对称平均绝对百分比误差(SMAPE)指标上均表现出更高预测精度。研究结果为液压支架压力精准预测提供有效方法。 展开更多
关键词 液压支架压力 多步长预测 离散小波变换 CNN模型 Informer模型
在线阅读 下载PDF
基于多任务Informer模型的船舶轨迹预测及行为识别研究
13
作者 李世刚 刘克中 +3 位作者 陈立家 周乃祺 周阳 黄嘉韬 《中国航海》 北大核心 2025年第3期157-165,共9页
为有效预判航行风险,并为船舶避碰、交通管理等决策提供重要依据,研究了一种基于多任务Informer模型的船舶轨迹预测及行为识别模型。该模型以Informer框架为基础,并引入多任务学习模式,通过设计多任务损失函数将船舶行为识别与轨迹预测... 为有效预判航行风险,并为船舶避碰、交通管理等决策提供重要依据,研究了一种基于多任务Informer模型的船舶轨迹预测及行为识别模型。该模型以Informer框架为基础,并引入多任务学习模式,通过设计多任务损失函数将船舶行为识别与轨迹预测并联训练,解决了AIS数据中船舶行为不准确无法作为模型输入的问题;在模型训练时,并设计基于同方差不确定性的损失函数自适应更新策略,自适应分配两个任务的损失权重。利用太仓航段水域中的真实AIS数据进行试验中多任务的Informer船舶轨迹预测模型在轨迹预测中的损失比LSTM和Informer模型分别降低了40.2%和14.7%;在行为识别任务中多任务模型的识别准确率比LSTM和Informer模型分别提升了11.7%和5.95%。表明了多任务模型能在有效提升船舶轨迹预测的性能的同时实现船舶对行为的准确识别。 展开更多
关键词 轨迹预测 行为识别 AIS数据 Informer模型 多任务学习
在线阅读 下载PDF
基于融合劣化指标和VMD-Informer的水电机组劣化趋势预测
14
作者 宋阿妮 陈亦真 +2 位作者 詹云峰 李超顺 付波 《中国农村水利水电》 北大核心 2025年第5期90-96,共7页
水电机组长期运行在恶劣环境下,异常振动更加频繁,逐渐出现疲劳、磨损,导致机组性能劣化。为保障机组的安全稳定运行,需要准确直观地反映水电机组运行并预测机组未来劣化状况,为机组状态检修提供重要依据。提出了一种基于融合劣化指标和... 水电机组长期运行在恶劣环境下,异常振动更加频繁,逐渐出现疲劳、磨损,导致机组性能劣化。为保障机组的安全稳定运行,需要准确直观地反映水电机组运行并预测机组未来劣化状况,为机组状态检修提供重要依据。提出了一种基于融合劣化指标和VMD-Informer的机组劣化趋势预测方法。首先构建KAN健康模型拟合工况参数与振摆值之间的映射关系,然后通过对比模型输出值与实测振摆值在不同指标下的差异得到多个劣化序列,运用遗传算法对多个劣化序列进行寻优获取融合劣化指标,兼顾多个指标的优势,更为准确地反映机组劣化趋势。之后用变分模态分解(VMD)将融合劣化序列分解为多个分量,最后利用Informer预测模型对分解后的各个分量进行多步预测并重构得到最终的预测结果,从而实现对机组运行状况的准确评估和预测。实例分析表明,所提方法能够生成可靠的劣化趋势,同时在预测上能学习劣化趋势序列的长期趋势和局部特征,预测精度更高。 展开更多
关键词 水电机组 劣化评估 退化预测 Kolmogorov-Arnold Network 遗传算法 INFORMER
在线阅读 下载PDF
山区双车道公路借道超车轨迹预测模型
15
作者 覃文文 彭栋梁 +4 位作者 戢晓峰 徐迎豪 李冰 李武 曾浩 《交通运输系统工程与信息》 北大核心 2025年第3期96-106,共11页
为提高山区双车道公路的车辆轨迹预测精度,本文设计一种考虑借道超车影响的车辆轨迹预测模型。首先,基于无人机视频轨迹数据,根据航向角将借道超车过程划分为跟驰、借道、超车和返回这4种状态;其次,构建包含借道超车状态、车辆运动特征... 为提高山区双车道公路的车辆轨迹预测精度,本文设计一种考虑借道超车影响的车辆轨迹预测模型。首先,基于无人机视频轨迹数据,根据航向角将借道超车过程划分为跟驰、借道、超车和返回这4种状态;其次,构建包含借道超车状态、车辆运动特征、空间位置属性和交通状态的多元特征数据集,通过梯度提升决策树算法拟合借道超车状态与车辆运动特征、空间位置和交通状态之间的复杂关系,采用SHAP(SHapley Additive exPlanations)方法识别影响借道超车状态变化的关键因素;然后,将借道超车状态、影响借道超车状态的关键因素和历史轨迹数据集,以滑动时间窗口形式输入至Informer模型,预测山区双车道公路的借道超车轨迹;最后,与未考虑借道超车影响的传统超车轨迹预测模型进行对比,验证本文模型的有效性。结果表明:车头时距、主体车辆横向速度和横向偏移是影响借道超车状态变化的关键因素;所构建的模型在山区双车道借道超车场景下,具有良好的适用性和预测精度;与未考虑借道超车影响的轨迹预测模型相比,本文模型的均方误差和平均绝对误差均值分别降低53.05%和38.11%,决定系数均值提升23.58%。 展开更多
关键词 交通工程 超车轨迹预测 Informer时间序列模型 借道超车 山区双车道
在线阅读 下载PDF
基于RF-Informer模型的月径流遥相关预报
16
作者 李继清 谢宇韬 +1 位作者 徐学军 吴亮 《水资源保护》 北大核心 2025年第3期39-45,共7页
为延长中长期径流预报的预见期,提高预报精度,从物理成因上考虑径流的影响因素,在前期降水径流的基础上增加遥相关因子,通过随机森林(RF)模型进行因子选择,引入长时间序列预报中表现良好的Informer模型,构建了月径流预报的RF-Informer模... 为延长中长期径流预报的预见期,提高预报精度,从物理成因上考虑径流的影响因素,在前期降水径流的基础上增加遥相关因子,通过随机森林(RF)模型进行因子选择,引入长时间序列预报中表现良好的Informer模型,构建了月径流预报的RF-Informer模型,并利用该模型对雅砻江流域两河口、锦西、二滩3个水库的入库月径流进行了预报。结果表明:将遥相关因子引入流域月径流预报可以延长预见期,提高预报精度;相较于线性相关法,基于RF模型选择预报因子可以挖掘因子间非线性关系,提升预报效果;与RF-LSTM、RF-SVM、RF-BP神经网络模型相比,RF-Informer模型的误差最小,预报精度最高。 展开更多
关键词 月径流预报 遥相关因子 随机森林模型 Informer模型 雅砻江流域
在线阅读 下载PDF
基于Informer模型的航班延误预测
17
作者 杨新湦 游超 朱承元 《科学技术与工程》 北大核心 2025年第19期8282-8288,共7页
为能更加精准预测不同时段的航班延误态势,选用美国亚特兰大机场2023年全年的运行数据与相关气象数据进行实验,提出基于相关系分析(correlation analysis,CA),主成分分析(principal components analysis,PCA)和Informer模型的CA-PCA-Inf... 为能更加精准预测不同时段的航班延误态势,选用美国亚特兰大机场2023年全年的运行数据与相关气象数据进行实验,提出基于相关系分析(correlation analysis,CA),主成分分析(principal components analysis,PCA)和Informer模型的CA-PCA-Informer航班延误预测模型,采用MAE(mean absolute error)和RMSE(root mean square error)作为模型的评价指标进行预测误差分析。结果表明,CA-PCA-Informer模型比简单的组合模型预测效果更好,与CA-PCA-LSTM和CA-PCA-GRU模型相比模型误差最低,MAE和RMSE分别降低了20.2%~20.7%和12.7%~14.1%;CA-PCA-Informer模型对预测步长为1 h时预测更为精准,该模型可以为决策者提供更加准确的航班延误态势以保证航班的高效运行。 展开更多
关键词 民航交通运输 航班延误预测 Informer模型 主成分分析 神经网络
在线阅读 下载PDF
考虑异常数据的多层神经网络交通流预测模型
18
作者 王庆荣 慕壮壮 +2 位作者 朱昌锋 何润田 高桓伊 《地球信息科学学报》 北大核心 2025年第10期2466-2481,共16页
【目的】交通流预测对于城市管理、智能交通至关重要。针对交通流数据中由外部干扰、突发事件等导致的异常数据、蕴含的复杂时空信息等问题。【方法】本文提出了一种考虑异常数据的多层神经网络预测模型(MLNN-CAD)。考虑孤立森林算法因... 【目的】交通流预测对于城市管理、智能交通至关重要。针对交通流数据中由外部干扰、突发事件等导致的异常数据、蕴含的复杂时空信息等问题。【方法】本文提出了一种考虑异常数据的多层神经网络预测模型(MLNN-CAD)。考虑孤立森林算法因参数单一而存在异常识别不精确的问题,结合各交通参数间的约束关系与交通流内在结构和规律,提出多级孤立森林算法,以提高异常数据识别精度;结合节点间的距离、皮尔逊相关系数及交通流量构建异常影响动态图,弥补传统M阶矩阵存在的缺陷,精准捕获异常影响动态范围;结合交通拥堵指数构建重要节点动态图,解决由节点出入都筛选重要区域的不足,并捕获交通流局部动态信息。融合图卷积网络(GCN)与含残差链接的多层图注意力网络(ResGAT),提取交通流的全局、异常影响及重要节点各动态空间信息。利用Informer提取全局时空信息,扩展长短期记忆网络(XLSTM)提取异常影响和重要节点时空信息,并通过卷积融合层获取交通流预测值。【结果】研究采用2018年1月1日—2月18日的PeMS04及PeMS08真实交通流量数据对本文模型预测精度进行验证。结果表明,本文模型优于Informer、XLSTM、STSGCN、STFGCN、VMD-AGCGRN等现有模型,相较于VMD-AGCGRN在PeMS04数据集上MAE、RMSE及MAPE提升7.68%、10.36%、6.06%。【结论】本文所提出的MLNN-CAD模型为异常数据下的短时交通流预测提供了具有可行性的理论基础。 展开更多
关键词 短时交通流预测 多层神经网络 多级孤立森林 INFORMER 扩展长短期记忆网络
原文传递
基于SDAE-EEMD降噪分解与改进Informer-BiLSTM模型的电力短期负荷预测方法
19
作者 蔡子龙 李嘉棋 +3 位作者 沈赋 王健 徐潇源 杨宇林 《电网技术》 北大核心 2025年第12期5009-5018,I0010-I0015,共16页
当前短期负荷预测模型在电价与负荷动态融合机制、负荷数据降噪与时序特征提取环节仍存在不足,制约了预测精度的提升。该文提出了一种集成电价及气象多维特征的短期电力负荷预测框架。首先,结合堆叠降噪自编码器(stacked denoising auto... 当前短期负荷预测模型在电价与负荷动态融合机制、负荷数据降噪与时序特征提取环节仍存在不足,制约了预测精度的提升。该文提出了一种集成电价及气象多维特征的短期电力负荷预测框架。首先,结合堆叠降噪自编码器(stacked denoising autoencoders,SDAE)和集合经验模态分解(ensemble empirical mode decomposition,EEMD)构建混合降噪分解模块,有效抑制负荷序列中的噪声干扰和模态混叠问题。EEMD将去噪后负荷序列分解为固有模态函数(intrinsic mode functions,IMFs)分量。其次,基于最大信息系数(maximum information coefficient,MIC)分析,将电价和气象特征分别融入高、低频IMFs分量中,实现差异化的特征动态融合。在此基础上,提出分频预测策略。针对高频分量,引入全局时间戳编码与稀疏注意力机制的改进Informer模型,以捕捉短时剧烈波动特征;对低频分量,采用Bi LSTM网络捕捉长期趋势与周期性。最后,基于澳大利亚国家电力市场公开数据集的实证结果表明,在平均绝对百分比误差和均方误差两个指标上均显著优于未引入电价特征或未采用分频策略的对比模型。通过高质量数据预处理、关键特征动态融合与针对性分频结构建模的协同优化,有效提升了短期负荷预测的精度与稳定性,可为电力市场动态定价机制下的负荷预测提供高效可靠的技术支撑。 展开更多
关键词 短期负荷预测 电价 SDAE EEMD 改进Informer BiLSTM 分频预测
原文传递
融合改进Informer与迁移学习的风电功率预测
20
作者 郭利进 孙淼 衡安阳 《太阳能学报》 北大核心 2025年第7期371-377,共7页
为克服风电功率序列的不稳定性导致预测精度低以及一些风电场历史数据有限的问题,提出一种特征交互Informer与迁移学习(FIITL)的风电功率预测模型。首先提出特征交互(FI)机制用双通道输入进一步提取信息,并将迁移学习(TL)引入到预测模型... 为克服风电功率序列的不稳定性导致预测精度低以及一些风电场历史数据有限的问题,提出一种特征交互Informer与迁移学习(FIITL)的风电功率预测模型。首先提出特征交互(FI)机制用双通道输入进一步提取信息,并将迁移学习(TL)引入到预测模型中,提出循环微调迁移学习,将模型从源监测站迁移到目标站,实现在有限历史数据情况下预测性能的提升。最后,通过与传统Informer模型及其他基线预测方法比较,FIITL模型展现了在有限数据情况下的性能优势。 展开更多
关键词 迁移学习 风电功率 预测 INFORMER 特征交互
原文传递
上一页 1 2 250 下一页 到第
使用帮助 返回顶部