Results 71 to 80 of about 6,061 (205)
, 2019 针对电力负荷预测中存在的随机性、不确定性的问题,结合深度学习算法具有很强的自适应感知能力等特点,采用目前较为主流的深度学习方法,如长短时记忆(LSTM)网络、门循环单元(GRU)神经网络和栈式自编码器(SAE),分别研究其应用于电力负荷预测时的效果。研究发现,将历史负荷数据作为三种深度学习预测模型的输入时,三种预测模型的负荷预测精度指标评估结果各有不同。因此,为了全面评估三种预测模型的预测效果,提出将不同时间段内的相同历史负荷数据作为预测模型输入对比各模型的负荷预测精度,从中找出最佳的预测模型 ...
吉莹, 张建寰, 陈立东
core +1 more source
China's Eco‐Civilisation, Climate Leviathan, and Hobbesian Energy Transition
Antipode, Volume 57, Issue 3, Page 830-861, May 2025.Abstract Scholars have hitherto tended to theorise China's ecological civilisation project either as a form of environmental authoritarianism or as a vision of eco‐socialism. This paper contributes to the conversation by conducting a textual analysis of Chinese scholarly discussions on eco‐civilisation.
David Chen
wiley +1 more source
Dizhen xuebao2023年中国建成了全球规模最大的地震预警网，预警网中的台站配置了速度计、加速度计、简易烈度计（MEMS）等多种地震仪器。目前用于深度学习模型训练的数据集主要由速度计数据组成，不同类型仪器记录的数据在处理时精度会下降。为了解决这一问题，本文使用Yu等（2023）发布的BRNN模型作为预训练模型；然后使用2万6 739条人工标注的四川地区的速度计、加速度计和MEMS数据进行迁移学习。实验结果表明：迁移学习显著提升了模型对加速度计和MEMS预警仪器数据记录到的Pg，Sg震相的检测精度 ...
Yuqi Cai +6 more
doaj +1 more source
Conservation Biology, Volume 39, Issue 2, April 2025.Abstract Emerging infectious diseases are increasingly recognized as a significant threat to global biodiversity conservation. Elucidating the relationship between pathogens and the host microbiome could lead to novel approaches for mitigating disease impacts.
Alexander S. Romer +25 more
wiley +1 more source
Uncovering Xi Jinping's Policy Agenda: Text As Data Approach
The Developing Economies, Volume 63, Issue 1, Page 9-46, March 2025.How many agendas has Xi Jinping put forth and promoted since taking office in 2012, and what are the types of agendas? How much of political attention has each agenda received, and how has the allocation of attention changed over time? We utilize a dataset of presidential statements, speeches, and reports from 2012 to 2022 and employed automated text ...
Jaehwan Lim, Asei Ito, Hongyong Zhang
wiley +1 more source
, 2018 针对物体检测实时多目标回归算法中分别优化各四个位置参数,割裂了四个位置变量之间的关系,造成对物体的边框回归不够准确且训练不易收敛的问题,提出一种带检测评价函数(Intersection over Union,IoU)作为损失函数的实时多目标回归人脸检测算法。首先基于Redmond等提出实时多目标回归模型,采用该模型检测实时性的机制,然后融合了IoU函数作为位置参数的损失函数,将实时多目标回归模型中的四个独立位置参数整合成一个单元进行优化,避免了基础模型的缺陷。算法在人脸检测基准库FDDB上进行测试 ...
卓勇, 吴志洋, 廖生辉
core
International Journal of Applied Linguistics, Volume 35, Issue 1, Page 235-256, February 2025.Abstract The past decades have witnessed a significant increase in the number of global Chinese as a second language (L2) learners. Accompanying the surge is the growing body of research on their motivational factors. This mixed‐methods study was primarily informed by Dörnyei's L2 motivational self system (L2MSS), aiming to scrutinize Chinese as a ...
Junzhe Li, Linda Tsung
wiley +1 more source
Fujian Economic Forecasting Based on Deep Belief Network —Consumer price index and total imports prediction in fujian province as an example [PDF]
, 2017 对宏观经济走势做出准确的预测，对于分析宏观调控政策的得失、评价经济系统运行的质量和正确制定未来发展规划战略等具有重要的意义。本文将近年来机器学习领域备受关注的深度置信网络（DeepBeliefNetwork，DBN）引入到经济预测领域，用于解决传统BP(Backpropagation)人工神经网络经济预测方法所存在的问题，例如训练学习速度较慢、容易陷入局部极小、容易导致过拟合、泛化能力差等不足，使得神经网络方法在经济预测领域焕发新的生机。 本文首先介绍了经济预测的研究背景和现状。其次介绍了经济预测特点 ...
王敏
core
Staying on the democratic script? A deep learning analysis of the speechmaking of U.S. presidents
Policy Studies Journal, Volume 52, Issue 4, Page 709-729, November 2024.Abstract Dynamic agenda representation assumes a linkage between the policy emphases prescribed by various democratic inputs (electoral promises and public opinion polls) and policy agendas ranging from the media to executive orders. An extrapolation of this idea would propose that, in the U.S.
Amnon Cavari, Akos Mate, Miklós Sebők
wiley +1 more source
A Deep Learning Pan-sharpening Method Driven by Domain Knowledge [PDF]
, 2017 Pan-sharpening是将同一场景的全色（PAN）图像和多光谱（MS）图像相互融合以有效提高MS图像的空间分辨率。Pan-sharpening在无需升级硬件的情况下有效克服了单一传感器的物理局限性，因而成为遥感领域的研究热点，并已广泛应用于自然资源探测、环境监测、军事侦察、和灾害监控等领域。 Pan-sharpening的主要目标是在光谱基本不失真的前提下尽可能提高MS图像的空间分辨率，其中MS图像具有较高的谱分辨率但是空间分辨率较低，PAN图像则具有很高的空间分辨率但缺少光谱分辨能力 ...
胡宇雯
core