In this paper, the Foxconn epidemic event in Zhengzhou was taken as an example to analyze the evolution of online public opinion on public health emergencies. In order to improve the performance of online public opini...In this paper, the Foxconn epidemic event in Zhengzhou was taken as an example to analyze the evolution of online public opinion on public health emergencies. In order to improve the performance of online public opinion analysis, based on the life cycle theory and LDA theory, the emotional changes of Internet users in four stages of the Foxconn incident centered on the evolution of inscription were divided. The emotions of netizen speech at different stages are analyzed based on CNN-BiLSTM + Attention model, which uses Convolutional Neural Network (CNN) to extract local features. Bi-directional Long Short-Term Memory (BiLSTM) is used to efficiently extract contextual semantic features and long distance dependencies, and then combined with attention mechanism to add emotional features. Finally, Softmax classifier realizes text emotion prediction. The experimental results show that: compared with TextCNN, BiLSTM, BiLSTM + Attenion, CNN-BiLSTM model, the emotion classification model has better effects in the accuracy rate, accuracy rate, recall rate and F value. By analyzing the emotional distribution and evolution trend of public opinion under “text topic”, the paper accurately deconstructs the development characteristics of public opinion in public health emergencies, in order to provide reference for relevant departments to deal with public opinion in public health emergencies. .展开更多
锂离子电池的健康状态(state of health,SOH)准确估计对于储能电站的稳定高效运行至关重要。为了进一步提高数据驱动方法对SOH估计的精度,本团队提出了一种利用交叉验证训练的线性回归加权融合模型的方法。首先,从放电电压曲线、充电和...锂离子电池的健康状态(state of health,SOH)准确估计对于储能电站的稳定高效运行至关重要。为了进一步提高数据驱动方法对SOH估计的精度,本团队提出了一种利用交叉验证训练的线性回归加权融合模型的方法。首先,从放电电压曲线、充电和放电温度曲线中提取了健康特征,并使用Pearson相关系数对所选特征进行了相关性分析,确定了网络模型输入的健康因子参数。随后,通过在LSTM与GRU中加入注意力机制,建立了LSTM-Attention与GRU-Attention模型,分别以NASA电池老化数据集B0005、B0006、B0007和B0018电池的前50%作为模型训练集,用剩余数据对模型进行验证,分别得到了模型对应的ŷ_(L-A)与ŷ_(G-A)估计值,然后使用所提融合模型方法对两个估计值进行线性回归加权,结果显示该方法的最大均方根误差和平均绝对误差分别为0.00291和0.00200。最后,为验证所提模型的抗干扰能力,在输入模型的健康因子中加入不同比例的高斯白噪声,实验结果显示融合模型的抗干扰能力较强,最大均方根误差和平均绝对误差仅为0.03562和0.02889。展开更多
Nowadays,several studies demonstrate that viewing nature has positive effects on human health and well-being.This essay discusses about the essential methods of viewing natural environment and their impacts on human w...Nowadays,several studies demonstrate that viewing nature has positive effects on human health and well-being.This essay discusses about the essential methods of viewing natural environment and their impacts on human well-being by clarifying four important theoretical models:reducing stress,lowering heart rate,improving outcome of surgery,and increasing attention.In addition,some important research results in this field are taken as examples to introduce research methods.By collecting and organizing existing studies and theories about the relationship between viewing nature and human well-being,the methods of viewing nature can be divided into two parts:viewing nature through specific media(e.g.,through a window,a book,a painting or a videotape)and being with the presence of nature.This study aims to clarify the research significance of viewing nature and find deficiency in this field to maximize the role of landscapes in human health and well-being.展开更多
Objective: Health materials need to target individuals who resist or are not interested in health behaviors. Attracting the interest of this audience is a crucial aspect of materials’ design. The present study aimed ...Objective: Health materials need to target individuals who resist or are not interested in health behaviors. Attracting the interest of this audience is a crucial aspect of materials’ design. The present study aimed to review the findings of psychological studies on causes of interest and to discuss the applicability of these studies to the design of health materials. Methods: We used the backward and forward snowball method for our literature review. We identified 10 relevant publications as initial sources for snowballing through a systematic search of EBSCOhost (searching PsycINFO, PsycARTICLES, ERIC, CINAHL and MEDLINE). Through backward and forward snowballing from these sources, 76 relevant publications were identified. Results: We identified properties and variables relevant to attracting interest and grouped them into four tactics: surprise;question;visualization;emotional appeal. Conclusion: Lessons from psychology gained in the present study may guide future studies and practices for attracting interest in health materials. The four tactics can be used to make health materials more interesting, as an example showed in the present study.展开更多
全球心理健康问题形势严峻,由于心理健康服务的从业人员不足,遭受心理健康困扰的人并不总是能获得专业的心理健康服务.检索式心理健康社区自动问答可以快速地为需要心理健康服务的人提供相应的信息自助服务.与传统检索式社区问答中的文...全球心理健康问题形势严峻,由于心理健康服务的从业人员不足,遭受心理健康困扰的人并不总是能获得专业的心理健康服务.检索式心理健康社区自动问答可以快速地为需要心理健康服务的人提供相应的信息自助服务.与传统检索式社区问答中的文本匹配不同,在匹配支持帖和求助帖时,需要考虑2种不同层面的匹配准则:语义层面和心理层面.为了解决该问题,提出融合角色心理画像的2阶段文本匹配模型(two-stage text matching model integrating characters’mental portrait,T2CMP),该模型引入心理特征用于构建角色心理画像,从而辅助模型理解文本心理层面的内容和匹配关系.同时为了提升检索效率以及减少大量负样例带来的噪声问题,将文本匹配任务拆分为2阶段的序列型子任务.首先针对每条求助帖,使用基于语义的筛选模型甄别出候选支持帖;然后依据用户的角色心理画像,使用多层注意力机制将其与语义信息有效融合,提高模型的总体效果.在MHCQA数据集上的实验结果显示,T2CMP比现有优秀算法拥有更高的F1值.展开更多
心理咨询场景下的情感分类旨在获得咨询者话语的情感倾向,为建立心理咨询AI助手提供支持。现有的方法利用语境信息获取文本情感倾向,但未考虑对话记录中当前句与前向近邻句之间的情感传递。针对这一问题,提出一种基于交互注意力(AOA)机...心理咨询场景下的情感分类旨在获得咨询者话语的情感倾向,为建立心理咨询AI助手提供支持。现有的方法利用语境信息获取文本情感倾向,但未考虑对话记录中当前句与前向近邻句之间的情感传递。针对这一问题,提出一种基于交互注意力(AOA)机制的心理咨询文本情感分类模型,根据时序对历史情感词分配权重,进而提高分类准确率。利用构建的心理健康情感词典分别提取对话双方的历史情感词序列,再将当前句和历史情感词序列输入到双向长短期记忆(BiLSTM)网络获取对应的特征向量,并利用艾宾浩斯遗忘曲线对历史情感词序列分配权重。通过AOA机制获得惯性特征和交互特征,并结合文本特征输入到分类层计算情感倾向概率。在公开数据集Emotional First Aid Dataset上的实验结果表明,相较于Caps-DGCN(Capsule network and Directional Graph Convolutional Network)模型,所提模型的F1值提高了1.55%。可见,所提模型可以有效提升心理咨询文本的情感分类效果。展开更多
文摘In this paper, the Foxconn epidemic event in Zhengzhou was taken as an example to analyze the evolution of online public opinion on public health emergencies. In order to improve the performance of online public opinion analysis, based on the life cycle theory and LDA theory, the emotional changes of Internet users in four stages of the Foxconn incident centered on the evolution of inscription were divided. The emotions of netizen speech at different stages are analyzed based on CNN-BiLSTM + Attention model, which uses Convolutional Neural Network (CNN) to extract local features. Bi-directional Long Short-Term Memory (BiLSTM) is used to efficiently extract contextual semantic features and long distance dependencies, and then combined with attention mechanism to add emotional features. Finally, Softmax classifier realizes text emotion prediction. The experimental results show that: compared with TextCNN, BiLSTM, BiLSTM + Attenion, CNN-BiLSTM model, the emotion classification model has better effects in the accuracy rate, accuracy rate, recall rate and F value. By analyzing the emotional distribution and evolution trend of public opinion under “text topic”, the paper accurately deconstructs the development characteristics of public opinion in public health emergencies, in order to provide reference for relevant departments to deal with public opinion in public health emergencies. .
文摘锂离子电池的健康状态(state of health,SOH)准确估计对于储能电站的稳定高效运行至关重要。为了进一步提高数据驱动方法对SOH估计的精度,本团队提出了一种利用交叉验证训练的线性回归加权融合模型的方法。首先,从放电电压曲线、充电和放电温度曲线中提取了健康特征,并使用Pearson相关系数对所选特征进行了相关性分析,确定了网络模型输入的健康因子参数。随后,通过在LSTM与GRU中加入注意力机制,建立了LSTM-Attention与GRU-Attention模型,分别以NASA电池老化数据集B0005、B0006、B0007和B0018电池的前50%作为模型训练集,用剩余数据对模型进行验证,分别得到了模型对应的ŷ_(L-A)与ŷ_(G-A)估计值,然后使用所提融合模型方法对两个估计值进行线性回归加权,结果显示该方法的最大均方根误差和平均绝对误差分别为0.00291和0.00200。最后,为验证所提模型的抗干扰能力,在输入模型的健康因子中加入不同比例的高斯白噪声,实验结果显示融合模型的抗干扰能力较强,最大均方根误差和平均绝对误差仅为0.03562和0.02889。
文摘Nowadays,several studies demonstrate that viewing nature has positive effects on human health and well-being.This essay discusses about the essential methods of viewing natural environment and their impacts on human well-being by clarifying four important theoretical models:reducing stress,lowering heart rate,improving outcome of surgery,and increasing attention.In addition,some important research results in this field are taken as examples to introduce research methods.By collecting and organizing existing studies and theories about the relationship between viewing nature and human well-being,the methods of viewing nature can be divided into two parts:viewing nature through specific media(e.g.,through a window,a book,a painting or a videotape)and being with the presence of nature.This study aims to clarify the research significance of viewing nature and find deficiency in this field to maximize the role of landscapes in human health and well-being.
文摘Objective: Health materials need to target individuals who resist or are not interested in health behaviors. Attracting the interest of this audience is a crucial aspect of materials’ design. The present study aimed to review the findings of psychological studies on causes of interest and to discuss the applicability of these studies to the design of health materials. Methods: We used the backward and forward snowball method for our literature review. We identified 10 relevant publications as initial sources for snowballing through a systematic search of EBSCOhost (searching PsycINFO, PsycARTICLES, ERIC, CINAHL and MEDLINE). Through backward and forward snowballing from these sources, 76 relevant publications were identified. Results: We identified properties and variables relevant to attracting interest and grouped them into four tactics: surprise;question;visualization;emotional appeal. Conclusion: Lessons from psychology gained in the present study may guide future studies and practices for attracting interest in health materials. The four tactics can be used to make health materials more interesting, as an example showed in the present study.
文摘全球心理健康问题形势严峻,由于心理健康服务的从业人员不足,遭受心理健康困扰的人并不总是能获得专业的心理健康服务.检索式心理健康社区自动问答可以快速地为需要心理健康服务的人提供相应的信息自助服务.与传统检索式社区问答中的文本匹配不同,在匹配支持帖和求助帖时,需要考虑2种不同层面的匹配准则:语义层面和心理层面.为了解决该问题,提出融合角色心理画像的2阶段文本匹配模型(two-stage text matching model integrating characters’mental portrait,T2CMP),该模型引入心理特征用于构建角色心理画像,从而辅助模型理解文本心理层面的内容和匹配关系.同时为了提升检索效率以及减少大量负样例带来的噪声问题,将文本匹配任务拆分为2阶段的序列型子任务.首先针对每条求助帖,使用基于语义的筛选模型甄别出候选支持帖;然后依据用户的角色心理画像,使用多层注意力机制将其与语义信息有效融合,提高模型的总体效果.在MHCQA数据集上的实验结果显示,T2CMP比现有优秀算法拥有更高的F1值.
文摘心理咨询场景下的情感分类旨在获得咨询者话语的情感倾向,为建立心理咨询AI助手提供支持。现有的方法利用语境信息获取文本情感倾向,但未考虑对话记录中当前句与前向近邻句之间的情感传递。针对这一问题,提出一种基于交互注意力(AOA)机制的心理咨询文本情感分类模型,根据时序对历史情感词分配权重,进而提高分类准确率。利用构建的心理健康情感词典分别提取对话双方的历史情感词序列,再将当前句和历史情感词序列输入到双向长短期记忆(BiLSTM)网络获取对应的特征向量,并利用艾宾浩斯遗忘曲线对历史情感词序列分配权重。通过AOA机制获得惯性特征和交互特征,并结合文本特征输入到分类层计算情感倾向概率。在公开数据集Emotional First Aid Dataset上的实验结果表明,相较于Caps-DGCN(Capsule network and Directional Graph Convolutional Network)模型,所提模型的F1值提高了1.55%。可见,所提模型可以有效提升心理咨询文本的情感分类效果。
