Action recognition is an important topic in computer vision. Recently, deep learning technologies have been successfully used in lots of applications including video data for sloving recognition problems. However, mos...Action recognition is an important topic in computer vision. Recently, deep learning technologies have been successfully used in lots of applications including video data for sloving recognition problems. However, most existing deep learning based recognition frameworks are not optimized for action in the surveillance videos. In this paper, we propose a novel method to deal with the recognition of different types of actions in outdoor surveillance videos. The proposed method first introduces motion compensation to improve the detection of human target. Then, it uses three different types of deep models with single and sequenced images as inputs for the recognition of different types of actions. Finally, predictions from different models are fused with a linear model. Experimental results show that the proposed method works well on the real surveillance videos.展开更多
目的解决当前中医医案命名实体识别模型识别效果欠佳的问题,提升中医医案结构化的效率与精准度。方法构建融合多维度信息的BDM-CRF命名实体识别神经网络模型,融合双向长短期记忆网络模型(Bidirectional long short-term memory,BiLSTM)...目的解决当前中医医案命名实体识别模型识别效果欠佳的问题,提升中医医案结构化的效率与精准度。方法构建融合多维度信息的BDM-CRF命名实体识别神经网络模型,融合双向长短期记忆网络模型(Bidirectional long short-term memory,BiLSTM)、门控空洞卷积神经网络模型(Gated-dilated convolutional neural networks,DGCNN)和多头注意力机制模型(Multi-head attention,MHA)进行多维度特征抽取,通过条件随机场(Conditional random field,CRF)模型对特征抽取结果进行约束输出;通过对比实验、消融实验、预训练模型对比实验及神经网络结构对比实验验证该模型的有效性,通过个案分析验证并展示模型的提取效果。结果本研究提出的模型比对照模型精确率平均提升2.30%、召回率平均提升4.73%、F1值平均提升3.53%。个案分析结果表明,本研究模型能正确识别出中医医案文本中的大部分实体内容。结论本研究提出的融合多维度信息的中医医案命名实体识别模型能取得更佳的识别效果,可有效提升中医医案结构化的精准度及效率,促进中医医案处理智能化。展开更多
为了提高短期风电功率预测的准确性,提出一种基于贝叶斯优化和特征融合的xLSTM(extended Long Short-Term Memory)-Transformer模型。该模型综合应用长短期记忆(LSTM)网络的时序处理能力和Transformer的自注意力机制的动态特征融合能力...为了提高短期风电功率预测的准确性,提出一种基于贝叶斯优化和特征融合的xLSTM(extended Long Short-Term Memory)-Transformer模型。该模型综合应用长短期记忆(LSTM)网络的时序处理能力和Transformer的自注意力机制的动态特征融合能力。借助贝叶斯优化方法,模型可在较少的迭代次数条件下优化超参数,显著降低模型对计算资源的依赖。实验结果表明,内蒙古某风电场数据集上,与单一的LSTM模型、Transformer模型、门控循环单元(GRU)模型以及未采用贝叶斯优化和特征融合的xLSTM-Transformer模型相比,当步长(LookBack)为4和8时,所提模型的决定系数R2较基准模型平均提升1.2%~11.3%;平均绝对误差(MAE)平均降低12.8%~38.4%;均方根误差(RMSE)平均降低8.6%~35.8%。结果表明,所提模型在短历史输入条件下具有更高的预测精度与稳定性。展开更多
According to the requirement of computer forensic and network forensic, a novel forensic computing model is presented, which exploits XML/OEM/RM data model, Data fusion technology, forensic knowledgebase, inference me...According to the requirement of computer forensic and network forensic, a novel forensic computing model is presented, which exploits XML/OEM/RM data model, Data fusion technology, forensic knowledgebase, inference mechanism of expert system and evidence mining engine. This model takes advantage of flexility and openness, so it can be widely used in mining evidence.展开更多
随着社交网络平台的迅速发展,网络欺凌问题日益突出,文本与图片相结合的多样化网络表达形式提高了网络欺凌的检测和治理难度.构建了一个包含文本和图片的中文多模态网络欺凌数据集,将BERT(bidirectional encoder representations from t...随着社交网络平台的迅速发展,网络欺凌问题日益突出,文本与图片相结合的多样化网络表达形式提高了网络欺凌的检测和治理难度.构建了一个包含文本和图片的中文多模态网络欺凌数据集,将BERT(bidirectional encoder representations from transformers)模型与ResNet50模型相结合,分别提取文本和图片的单模态特征,并进行决策层融合,对融合后的特征进行检测,实现了对网络欺凌与非网络欺凌2个类别的文本和图片的准确识别.实验结果表明,提出的多模态网络欺凌检测模型能够有效识别出包含文本与图片的具有网络欺凌性质的社交网络帖子或者评论,提高了多模态形式网络欺凌检测的实用性、准确性和效率,为社交网络平台的网络欺凌检测和治理提供了一种新的思路和方法,有助于构建更加健康、文明的网络环境.展开更多
文摘Action recognition is an important topic in computer vision. Recently, deep learning technologies have been successfully used in lots of applications including video data for sloving recognition problems. However, most existing deep learning based recognition frameworks are not optimized for action in the surveillance videos. In this paper, we propose a novel method to deal with the recognition of different types of actions in outdoor surveillance videos. The proposed method first introduces motion compensation to improve the detection of human target. Then, it uses three different types of deep models with single and sequenced images as inputs for the recognition of different types of actions. Finally, predictions from different models are fused with a linear model. Experimental results show that the proposed method works well on the real surveillance videos.
文摘目的解决当前中医医案命名实体识别模型识别效果欠佳的问题,提升中医医案结构化的效率与精准度。方法构建融合多维度信息的BDM-CRF命名实体识别神经网络模型,融合双向长短期记忆网络模型(Bidirectional long short-term memory,BiLSTM)、门控空洞卷积神经网络模型(Gated-dilated convolutional neural networks,DGCNN)和多头注意力机制模型(Multi-head attention,MHA)进行多维度特征抽取,通过条件随机场(Conditional random field,CRF)模型对特征抽取结果进行约束输出;通过对比实验、消融实验、预训练模型对比实验及神经网络结构对比实验验证该模型的有效性,通过个案分析验证并展示模型的提取效果。结果本研究提出的模型比对照模型精确率平均提升2.30%、召回率平均提升4.73%、F1值平均提升3.53%。个案分析结果表明,本研究模型能正确识别出中医医案文本中的大部分实体内容。结论本研究提出的融合多维度信息的中医医案命名实体识别模型能取得更佳的识别效果,可有效提升中医医案结构化的精准度及效率,促进中医医案处理智能化。
文摘为了提高短期风电功率预测的准确性,提出一种基于贝叶斯优化和特征融合的xLSTM(extended Long Short-Term Memory)-Transformer模型。该模型综合应用长短期记忆(LSTM)网络的时序处理能力和Transformer的自注意力机制的动态特征融合能力。借助贝叶斯优化方法,模型可在较少的迭代次数条件下优化超参数,显著降低模型对计算资源的依赖。实验结果表明,内蒙古某风电场数据集上,与单一的LSTM模型、Transformer模型、门控循环单元(GRU)模型以及未采用贝叶斯优化和特征融合的xLSTM-Transformer模型相比,当步长(LookBack)为4和8时,所提模型的决定系数R2较基准模型平均提升1.2%~11.3%;平均绝对误差(MAE)平均降低12.8%~38.4%;均方根误差(RMSE)平均降低8.6%~35.8%。结果表明,所提模型在短历史输入条件下具有更高的预测精度与稳定性。
基金Supported by the Scientific and TechnologicalBureau of the Ministry of Public Security of P.R.China ,the Projectof the Network Supervising Bureau(2005yycxhbst117) the Project ofthe 15th Overall Plan of Education Department of Hubei Province(2004d349) the Project of the 15th Overall Plan of Social ScienceFund of Hubei Province([2005]073)
文摘According to the requirement of computer forensic and network forensic, a novel forensic computing model is presented, which exploits XML/OEM/RM data model, Data fusion technology, forensic knowledgebase, inference mechanism of expert system and evidence mining engine. This model takes advantage of flexility and openness, so it can be widely used in mining evidence.
文摘随着社交网络平台的迅速发展,网络欺凌问题日益突出,文本与图片相结合的多样化网络表达形式提高了网络欺凌的检测和治理难度.构建了一个包含文本和图片的中文多模态网络欺凌数据集,将BERT(bidirectional encoder representations from transformers)模型与ResNet50模型相结合,分别提取文本和图片的单模态特征,并进行决策层融合,对融合后的特征进行检测,实现了对网络欺凌与非网络欺凌2个类别的文本和图片的准确识别.实验结果表明,提出的多模态网络欺凌检测模型能够有效识别出包含文本与图片的具有网络欺凌性质的社交网络帖子或者评论,提高了多模态形式网络欺凌检测的实用性、准确性和效率,为社交网络平台的网络欺凌检测和治理提供了一种新的思路和方法,有助于构建更加健康、文明的网络环境.
