F_(10.7)指数是太阳活动的重要指标,准确预测F_(10.7)指数有助于预防和缓解太阳活动对无线电通信、导航和卫星通信等领域的影响.基于F_(10.7)射电流量的特性,在双向长短时记忆网络(Bidirectional Long Short-Term Memory Network,BiLSTM...F_(10.7)指数是太阳活动的重要指标,准确预测F_(10.7)指数有助于预防和缓解太阳活动对无线电通信、导航和卫星通信等领域的影响.基于F_(10.7)射电流量的特性,在双向长短时记忆网络(Bidirectional Long Short-Term Memory Network,BiLSTM)基础上融入注意力机制(Attention),提出了一种基于BiLSTM-Attention的F_(10.7)预报模型.在加拿大DRAO数据集上其平均绝对误差(MAE)为5.38,平均绝对百分比误差(MAPE)控制在5%以内,相关系数(R)高达0.987,与其他RNN模型相比拥有优越的预测性能.针对中国廊坊L&S望远镜观测的F_(10.7)数据集,提出了一种转换平均校准(Conversion Average Calibration,CAC)方法进行数据预处理,处理后的数据与DRAO数据集具有较高的相关性.基于该数据集对比分析了RNN系列模型的预报效果,实验结果表明,BiLSTM-Attention和BiLSTM两种模型在预测F_(10.7)指数方面具有较好的优势,表现出较好的预测性能和稳定性.展开更多
The temporal evolution and spatial distribution characteristics of network attention of Tengwang Pavilion, a 5 A tourist attraction in Nanchang City from 2011 to 2019 were analyzed by using Baidu index search platform...The temporal evolution and spatial distribution characteristics of network attention of Tengwang Pavilion, a 5 A tourist attraction in Nanchang City from 2011 to 2019 were analyzed by using Baidu index search platform. The results showed that network attention of Tengwang Pavilion in China was increasing year by year, but the annual growth rate was different. There were two peak periods of network attention in a year. They were in April and October respectively. From a weekly point of view, the network attention of Tengwang Pavilion was the lowest on Friday, the highest on Saturdays, and higher on Saturdays and Sundays than on weekdays. From the point of view of geographical distribution, the province that paid the most attention to Tengwang Pavilion on network was Jiangxi Province and the largest city was Nanchang. Tengwang Pavilion scenic spot should pay more attention to the network attention and distribution characteristics of tourists, grasp the potential needs to better guide the development and marketing of tourism products, ensure the safety of tourist attractions, and promote the sustainable development of scenic spots.展开更多
Based on the data of climate and Baidu Index, the temporal and spatial variation of climate comfort and toudsts9 network attention in Inner Mongolia was analyzed, and the effect of dimate comfort on tourists, net...Based on the data of climate and Baidu Index, the temporal and spatial variation of climate comfort and toudsts9 network attention in Inner Mongolia was analyzed, and the effect of dimate comfort on tourists, network attention. The results showed, tiiat ① Inner Mongolia had a summer-comfortable toudsm climate, and it was uncomfortable to visit Inner Mongolia in winter. With the decrease of latitude, the climate comfort index gradually rose in Inner Mongolia, with a distribution pattern of l＂ow in the east and high in the west＂. There were three types of distribution of the climate comfort index： M-shaped, inverted U-shaped, and inverted V-shaped ② Toutasts5 network attention had certain dependence on the development level of tourism in wrious regions. The degree of network attention of regions with a high level of tourism development was also relatively high, and its distribution was more uniform. Monthly indexes of the tourists, network attention had three types： M-shaped, inverted U-shaped, and inverted V-shaped. ③ On the whole, climate comfort had a positive impact on the degree of network attention, butwith the improvement of the level of tourism development, the impact of climate comfort on the degree of attention of visitors would be weakened.④ The impact of climate comfort on the tourists, network.展开更多
文摘F_(10.7)指数是太阳活动的重要指标,准确预测F_(10.7)指数有助于预防和缓解太阳活动对无线电通信、导航和卫星通信等领域的影响.基于F_(10.7)射电流量的特性,在双向长短时记忆网络(Bidirectional Long Short-Term Memory Network,BiLSTM)基础上融入注意力机制(Attention),提出了一种基于BiLSTM-Attention的F_(10.7)预报模型.在加拿大DRAO数据集上其平均绝对误差(MAE)为5.38,平均绝对百分比误差(MAPE)控制在5%以内,相关系数(R)高达0.987,与其他RNN模型相比拥有优越的预测性能.针对中国廊坊L&S望远镜观测的F_(10.7)数据集,提出了一种转换平均校准(Conversion Average Calibration,CAC)方法进行数据预处理,处理后的数据与DRAO数据集具有较高的相关性.基于该数据集对比分析了RNN系列模型的预报效果,实验结果表明,BiLSTM-Attention和BiLSTM两种模型在预测F_(10.7)指数方面具有较好的优势,表现出较好的预测性能和稳定性.
基金Sponsored by Humanities and Social Sciences Research Projects in Colleges and Universities in Jiangxi Province(JC1542)
文摘The temporal evolution and spatial distribution characteristics of network attention of Tengwang Pavilion, a 5 A tourist attraction in Nanchang City from 2011 to 2019 were analyzed by using Baidu index search platform. The results showed that network attention of Tengwang Pavilion in China was increasing year by year, but the annual growth rate was different. There were two peak periods of network attention in a year. They were in April and October respectively. From a weekly point of view, the network attention of Tengwang Pavilion was the lowest on Friday, the highest on Saturdays, and higher on Saturdays and Sundays than on weekdays. From the point of view of geographical distribution, the province that paid the most attention to Tengwang Pavilion on network was Jiangxi Province and the largest city was Nanchang. Tengwang Pavilion scenic spot should pay more attention to the network attention and distribution characteristics of tourists, grasp the potential needs to better guide the development and marketing of tourism products, ensure the safety of tourist attractions, and promote the sustainable development of scenic spots.
基金Sponsored by Scientific Research Projects of Colleges and Universities in the Inner Mongolia Autonomous Region(NJSY17019)
文摘Based on the data of climate and Baidu Index, the temporal and spatial variation of climate comfort and toudsts9 network attention in Inner Mongolia was analyzed, and the effect of dimate comfort on tourists, network attention. The results showed, tiiat ① Inner Mongolia had a summer-comfortable toudsm climate, and it was uncomfortable to visit Inner Mongolia in winter. With the decrease of latitude, the climate comfort index gradually rose in Inner Mongolia, with a distribution pattern of l＂ow in the east and high in the west＂. There were three types of distribution of the climate comfort index： M-shaped, inverted U-shaped, and inverted V-shaped ② Toutasts5 network attention had certain dependence on the development level of tourism in wrious regions. The degree of network attention of regions with a high level of tourism development was also relatively high, and its distribution was more uniform. Monthly indexes of the tourists, network attention had three types： M-shaped, inverted U-shaped, and inverted V-shaped. ③ On the whole, climate comfort had a positive impact on the degree of network attention, butwith the improvement of the level of tourism development, the impact of climate comfort on the degree of attention of visitors would be weakened.④ The impact of climate comfort on the tourists, network.
