股票市场快速发展,股票价格波动性研究备受关注,准确预测股价走势对投资者决策和市场稳定意义重大。鉴于股票价格波动的不确定性与非线性特征,单一模型预测效果欠佳。为此,本文提出将GARCH与BP神经网络相结合的组合预测方法,以中国农业...股票市场快速发展,股票价格波动性研究备受关注,准确预测股价走势对投资者决策和市场稳定意义重大。鉴于股票价格波动的不确定性与非线性特征,单一模型预测效果欠佳。为此,本文提出将GARCH与BP神经网络相结合的组合预测方法,以中国农业银行股票日收盘价数据为例,基于误差修正思想构建组合模型,运用BP神经网络对GARCH模型的残差数据进行预测校正。研究结果表明组合模型预测效果优于单一模型,验证了该组合模型在提高股票价格预测准确度方面的有效性。With the rapid development of the stock market, the study of stock price volatility has attracted much attention, and accurate prediction of stock price movements is of great significance to investors’ decision-making and market stability. In view of the uncertainty and nonlinear characteristics of stock price volatility, the prediction effect of a single model is not good. For this reason, this paper proposes a combined prediction method combining GARCH and BP neural network, taking the daily closing price data of Agricultural Bank of China as an example, constructing a combined model based on the idea of error correction, and utilizing BP neural network to correct the residual data of the GARCH model for prediction. The results show that the combination model predicts better than a single model, which verifies the effectiveness of the combination model in improving the accuracy of stock price prediction.展开更多
黑碳仪是最常用的气溶胶吸光碳测试仪器,但其测得的吸光性能受到滤膜多重散射效应、颗粒物散射效应、颗粒物遮蔽效应的影响,只能算是 b ATN (光衰减系数),而不是 b in-situ (原位吸光系数).虽然已有学者提出几种将 b ATN 转换为 b cor ...黑碳仪是最常用的气溶胶吸光碳测试仪器,但其测得的吸光性能受到滤膜多重散射效应、颗粒物散射效应、颗粒物遮蔽效应的影响,只能算是 b ATN (光衰减系数),而不是 b in-situ (原位吸光系数).虽然已有学者提出几种将 b ATN 转换为 b cor (校正后吸光系数)的算法,但多是基于实验室模拟或高海拔地区气溶胶而开展的,与我国城市的气溶胶在理化性质方面有明显差别.为探索我国城市气溶胶将 b ATN 转换为 b cor 的问题,于2016—2017年冬季在北京市城区使用黑碳仪及光声消光仪分别测量 b ATN 和 b in-situ ,在分析多种算法的基础上,提出了面向城市气溶胶的校正方法.结果显示:在我国北方城市(以北京市为例),适应城市气溶胶的 f 值(遮蔽因子,为计算遮蔽校正系数的一个参数)为1.13, C (综合散射效应系数)为5.44;使用这些校正系数,将观测点由黑碳仪获取的 b ATN 转换为 b cor .与光声消光仪测定的 b in-situ 对比发现,无论是滤膜样点周期内还是长期观测时间内, b cor 与 b in-situ 均呈一致性,其中,长期观测时间内二者的相关性表达为 y =0.954 x +0.829(r 2为0.996),证明了校正方法的有效性和可信性.研究显示, b cor 与 b in-situ 整体相关性较高,并且获得了本地化的校正因子,实现了仅通过黑碳仪获取准确颗粒物吸光系数的目的.展开更多
基于理工科学生学习物理化学的同时还须兼顾几门其他专业课,导致其复习课堂知识的整块时间不足的情况,文章以天津大学主编的《物理化学》第六版的课后习题为依托,通过录制课后习题解析短视频的方式,增加课内知识点与课后习题中涉及知识...基于理工科学生学习物理化学的同时还须兼顾几门其他专业课,导致其复习课堂知识的整块时间不足的情况,文章以天津大学主编的《物理化学》第六版的课后习题为依托,通过录制课后习题解析短视频的方式,增加课内知识点与课后习题中涉及知识点的关联性,进一步加强学生对课程知识的理解与复习,有效提高学生利用碎片化时间学习的效率。根据两届学生的试用结果,在每个章节增加一次小测验,能够大力提高学生利用视频复习知识点的积极性,进而深入掌握物理化学知识。As students have to learn physical chemistry together with other major courses at the same time, the time for reviewing in-class knowledge of physical chemistry is not sufficient. In the current work, the problem-solving videos of the typical after-class problems of the sixth edition of “Physical Chemistry” edited by Tianjin University are designed and recorded in a new mode. The video contents contain illustrations of after-class problem solutions and the correlation of in-class knowledge with after-class problems. Each video is short and aims to improve the fragmented time utilization of students and their learning efficiency. The application of these videos in course teaching showed that the set of one quiz after each chapter had been taught can facilitate the enthusiasm of students to review the course knowledge and help them to master the course knowledge.展开更多
文摘股票市场快速发展,股票价格波动性研究备受关注,准确预测股价走势对投资者决策和市场稳定意义重大。鉴于股票价格波动的不确定性与非线性特征,单一模型预测效果欠佳。为此,本文提出将GARCH与BP神经网络相结合的组合预测方法,以中国农业银行股票日收盘价数据为例,基于误差修正思想构建组合模型,运用BP神经网络对GARCH模型的残差数据进行预测校正。研究结果表明组合模型预测效果优于单一模型,验证了该组合模型在提高股票价格预测准确度方面的有效性。With the rapid development of the stock market, the study of stock price volatility has attracted much attention, and accurate prediction of stock price movements is of great significance to investors’ decision-making and market stability. In view of the uncertainty and nonlinear characteristics of stock price volatility, the prediction effect of a single model is not good. For this reason, this paper proposes a combined prediction method combining GARCH and BP neural network, taking the daily closing price data of Agricultural Bank of China as an example, constructing a combined model based on the idea of error correction, and utilizing BP neural network to correct the residual data of the GARCH model for prediction. The results show that the combination model predicts better than a single model, which verifies the effectiveness of the combination model in improving the accuracy of stock price prediction.
文摘黑碳仪是最常用的气溶胶吸光碳测试仪器,但其测得的吸光性能受到滤膜多重散射效应、颗粒物散射效应、颗粒物遮蔽效应的影响,只能算是 b ATN (光衰减系数),而不是 b in-situ (原位吸光系数).虽然已有学者提出几种将 b ATN 转换为 b cor (校正后吸光系数)的算法,但多是基于实验室模拟或高海拔地区气溶胶而开展的,与我国城市的气溶胶在理化性质方面有明显差别.为探索我国城市气溶胶将 b ATN 转换为 b cor 的问题,于2016—2017年冬季在北京市城区使用黑碳仪及光声消光仪分别测量 b ATN 和 b in-situ ,在分析多种算法的基础上,提出了面向城市气溶胶的校正方法.结果显示:在我国北方城市(以北京市为例),适应城市气溶胶的 f 值(遮蔽因子,为计算遮蔽校正系数的一个参数)为1.13, C (综合散射效应系数)为5.44;使用这些校正系数,将观测点由黑碳仪获取的 b ATN 转换为 b cor .与光声消光仪测定的 b in-situ 对比发现,无论是滤膜样点周期内还是长期观测时间内, b cor 与 b in-situ 均呈一致性,其中,长期观测时间内二者的相关性表达为 y =0.954 x +0.829(r 2为0.996),证明了校正方法的有效性和可信性.研究显示, b cor 与 b in-situ 整体相关性较高,并且获得了本地化的校正因子,实现了仅通过黑碳仪获取准确颗粒物吸光系数的目的.
文摘基于理工科学生学习物理化学的同时还须兼顾几门其他专业课,导致其复习课堂知识的整块时间不足的情况,文章以天津大学主编的《物理化学》第六版的课后习题为依托,通过录制课后习题解析短视频的方式,增加课内知识点与课后习题中涉及知识点的关联性,进一步加强学生对课程知识的理解与复习,有效提高学生利用碎片化时间学习的效率。根据两届学生的试用结果,在每个章节增加一次小测验,能够大力提高学生利用视频复习知识点的积极性,进而深入掌握物理化学知识。As students have to learn physical chemistry together with other major courses at the same time, the time for reviewing in-class knowledge of physical chemistry is not sufficient. In the current work, the problem-solving videos of the typical after-class problems of the sixth edition of “Physical Chemistry” edited by Tianjin University are designed and recorded in a new mode. The video contents contain illustrations of after-class problem solutions and the correlation of in-class knowledge with after-class problems. Each video is short and aims to improve the fragmented time utilization of students and their learning efficiency. The application of these videos in course teaching showed that the set of one quiz after each chapter had been taught can facilitate the enthusiasm of students to review the course knowledge and help them to master the course knowledge.
