Marine life is very sensitive to changes in pH.Even slight changes can cause ecosystems to collapse.Therefore,understanding the future pH of seawater is of great significance for the protection of the marine environme...Marine life is very sensitive to changes in pH.Even slight changes can cause ecosystems to collapse.Therefore,understanding the future pH of seawater is of great significance for the protection of the marine environment.At present,the monitoring method of seawater pH has been matured.However,how to accurately predict future changes has been lacking effective solutions.Based on this,the model of bidirectional gated recurrent neural network with multi-headed self-attention based on improved complete ensemble empirical mode decomposition with adaptive noise combined with phase space reconstruction(ICPBGA)is proposed to achieve seawater pH prediction.To verify the validity of this model,pH data of two monitoring sites in the coastal sea area of Beihai,China are selected to verify the effect.At the same time,the ICPBGA model is compared with other excellent models for predicting chaotic time series,and root mean square error(RMSE),mean absolute error(MAE),mean absolute percentage error(MAPE),and coefficient of determination(R2)are used as performance evaluation indicators.The R2 of the ICPBGA model at Sites 1 and 2 are above 0.9,and the prediction errors are also the smallest.The results show that the ICPBGA model has a wide range of applicability and the most satisfactory prediction effect.The prediction method in this paper can be further expanded and used to predict other marine environmental indicators.展开更多
In this paper, according to the AR4JA codes in deep space communication, two kinds of iterative decoding including partly parallel decoding and overlapped partly parallel decoding are analyzed, and the advantages and ...In this paper, according to the AR4JA codes in deep space communication, two kinds of iterative decoding including partly parallel decoding and overlapped partly parallel decoding are analyzed, and the advantages and disadvantages of them are listed. A modified overlapped partly parallel decoding that not only inherits the advantages of the two algorithms, but also overcomes the shortcomings of the two algorithms is proposed. The simulation results show that the three kinds of decoding have the same decoding performance; modified overlapped partly parallel decoding improves the iterative convergence rate and the throughput of system.展开更多
兴趣点(Point-Of-Interest,POI)推荐是基于位置的社交网络(Location-based Social Networks,LBSNs)研究中最重要的任务之一。为了解决POI推荐中的空间稀疏性问题,提出一种用于位置推荐的长短期偏好时空注意力网络(LSAN)。首先,构建了签...兴趣点(Point-Of-Interest,POI)推荐是基于位置的社交网络(Location-based Social Networks,LBSNs)研究中最重要的任务之一。为了解决POI推荐中的空间稀疏性问题,提出一种用于位置推荐的长短期偏好时空注意力网络(LSAN)。首先,构建了签到序列的时空关系矩阵,使用多头注意力机制从中提取非连续签到和非相邻位置中的时空相关性,缓解签到数据稀疏所带来的困难。其次,在模型中设置用户短期偏好和长期偏好提取模块,自适应的将二者结合在一起,考虑了用户偏好对用户决策影响。最后,在Foursquare数据集上进行测试,并与其它模型结果进行对比,证实了提出的LSAN模型结果最优。研究表明LSAN模型能够获得最佳的推荐效果,为POI推荐提供新思路。展开更多
针对传统点积注意力缺乏方向性的问题,建立了一种基于余弦相似性的定向注意力模型(directed attention model,DAM)。为有效表示视频帧时空特征间的方向关系,运用余弦相似性理论,定义了注意力机制中关系函数,能够去除特征间关系绝对值;...针对传统点积注意力缺乏方向性的问题,建立了一种基于余弦相似性的定向注意力模型(directed attention model,DAM)。为有效表示视频帧时空特征间的方向关系,运用余弦相似性理论,定义了注意力机制中关系函数,能够去除特征间关系绝对值;为降低注意力机制计算量,从时间和空间两个维度上对运算进行分解;结合线性注意力运算,进一步优化计算复杂度。实验分为两个阶段:对定向注意力各模块开展了4个消融实验,以表现DAM在精确度和效率方面的最佳性能;该模型在Sth-Sth V1(somethingsomething V1)数据集上的精确度较I3D-NL(inflated 3D ConvNet non-local)高7.3%,在UCF101(101 human action classes from videos in the wild)数据集上的识别精确率为95.7%。研究成果在安全监控、自动驾驶等方面应用前景广泛。展开更多
基金The National Natural Science Foundation of China under contract No.62275228the S&T Program of Hebei under contract Nos 19273901D and 20373301Dthe Hebei Natural Science Foundation under contract No.F2020203066.
文摘Marine life is very sensitive to changes in pH.Even slight changes can cause ecosystems to collapse.Therefore,understanding the future pH of seawater is of great significance for the protection of the marine environment.At present,the monitoring method of seawater pH has been matured.However,how to accurately predict future changes has been lacking effective solutions.Based on this,the model of bidirectional gated recurrent neural network with multi-headed self-attention based on improved complete ensemble empirical mode decomposition with adaptive noise combined with phase space reconstruction(ICPBGA)is proposed to achieve seawater pH prediction.To verify the validity of this model,pH data of two monitoring sites in the coastal sea area of Beihai,China are selected to verify the effect.At the same time,the ICPBGA model is compared with other excellent models for predicting chaotic time series,and root mean square error(RMSE),mean absolute error(MAE),mean absolute percentage error(MAPE),and coefficient of determination(R2)are used as performance evaluation indicators.The R2 of the ICPBGA model at Sites 1 and 2 are above 0.9,and the prediction errors are also the smallest.The results show that the ICPBGA model has a wide range of applicability and the most satisfactory prediction effect.The prediction method in this paper can be further expanded and used to predict other marine environmental indicators.
基金Sponsored by the National Natural Science Foundation of China( Grant No. 61032003)the Fundamental Research Funds for the Central Universities( Grant No. HIT. NSRIF.2012021)
文摘In this paper, according to the AR4JA codes in deep space communication, two kinds of iterative decoding including partly parallel decoding and overlapped partly parallel decoding are analyzed, and the advantages and disadvantages of them are listed. A modified overlapped partly parallel decoding that not only inherits the advantages of the two algorithms, but also overcomes the shortcomings of the two algorithms is proposed. The simulation results show that the three kinds of decoding have the same decoding performance; modified overlapped partly parallel decoding improves the iterative convergence rate and the throughput of system.
文摘兴趣点(Point-Of-Interest,POI)推荐是基于位置的社交网络(Location-based Social Networks,LBSNs)研究中最重要的任务之一。为了解决POI推荐中的空间稀疏性问题,提出一种用于位置推荐的长短期偏好时空注意力网络(LSAN)。首先,构建了签到序列的时空关系矩阵,使用多头注意力机制从中提取非连续签到和非相邻位置中的时空相关性,缓解签到数据稀疏所带来的困难。其次,在模型中设置用户短期偏好和长期偏好提取模块,自适应的将二者结合在一起,考虑了用户偏好对用户决策影响。最后,在Foursquare数据集上进行测试,并与其它模型结果进行对比,证实了提出的LSAN模型结果最优。研究表明LSAN模型能够获得最佳的推荐效果,为POI推荐提供新思路。
文摘术前预测透明细胞肾细胞癌(clear cell renal cell carcinoma,ccRCC)的分级可有效评估患者的预后并指导临床治疗,但实现精准预测是目前本领域内的一项重要问题。该研究首先确定最优建模的CT类型与网络层数,提出了一种基于改进残差网络的ccRCC的CT影像分级模型,具体包括:利用大卷积操作对图像进行原始特征提取,利用混合注意力模块通过计算特征图中当前空间和临近空间以及当前空间和远距离空间之间的信息交互获取更多有用的特征,使得原始图像特征图在通道维度与空间维度上进行自适应特征细化,利用四个深度卷积网络层提取图像深度特征,并利用改进通道注意力模块产生通道注意力特征图信息,提取更多通道上的交互信息。实验结果表明,增强CT实质期图像和34层残差网络最有利于分级预测模型的开发,所提出的模型的总体加权准确率、AUC、精度、召回率和F1分数分别为90.8%、0.897、90.5%、90.8%、90.9%,各项指标优于其他常见网络结构,因此,该模型在预测ccRCC的国际泌尿病理学学会(International Society of Urological Pathology,ISUP)分级方面有良好的效能,对患者的临床辅助诊断和预后治疗具有重要的理论指导意义。
文摘针对传统点积注意力缺乏方向性的问题,建立了一种基于余弦相似性的定向注意力模型(directed attention model,DAM)。为有效表示视频帧时空特征间的方向关系,运用余弦相似性理论,定义了注意力机制中关系函数,能够去除特征间关系绝对值;为降低注意力机制计算量,从时间和空间两个维度上对运算进行分解;结合线性注意力运算,进一步优化计算复杂度。实验分为两个阶段:对定向注意力各模块开展了4个消融实验,以表现DAM在精确度和效率方面的最佳性能;该模型在Sth-Sth V1(somethingsomething V1)数据集上的精确度较I3D-NL(inflated 3D ConvNet non-local)高7.3%,在UCF101(101 human action classes from videos in the wild)数据集上的识别精确率为95.7%。研究成果在安全监控、自动驾驶等方面应用前景广泛。
