针对实物保护系统(Physical Protection System,PPSY)中单一传感器报警准确率较低的问题,提出了一种基于改进ID3的CAC-ID3(Confidence And Correlation-ID3)算法在多传感器实物保护系统中数据融合的新方法。与传统的单一传感器数据信息...针对实物保护系统(Physical Protection System,PPSY)中单一传感器报警准确率较低的问题,提出了一种基于改进ID3的CAC-ID3(Confidence And Correlation-ID3)算法在多传感器实物保护系统中数据融合的新方法。与传统的单一传感器数据信息处理相比,多传感器数据融合能够更加准确、全面的得到被测对象的数据信息,有效地利用多传感器资源。CAC-ID3算法首先在ID3的基础上引入属性置信度重新计算期望熵,解决属性和价值不对等的问题,克服多传感器数据分类时多值偏向的缺点,其值由经验和相关领域知识决定。然后通过引入属性间的相关度来调整信息增益值,提高分类精度。实验结果表明:基于CAC-ID3的决策树算法的多传感器PPSY能有效提高报警准确率和可靠性,防止敌对分子入侵,提高传感器对PPSY的检测的效能,且该算法的分类精度高于ID3算法。展开更多
应激反应和凝血反应联系密切,甚至可以将凝血反应视为应激反应其中的一种,大量的研究已经证实机体针对应激的凝血反应可以导致血液的高凝状态,进而防止受伤部位的失血过多,因此应激诱导的高凝状态可能代表对出血的适应性反应。并且在生...应激反应和凝血反应联系密切,甚至可以将凝血反应视为应激反应其中的一种,大量的研究已经证实机体针对应激的凝血反应可以导致血液的高凝状态,进而防止受伤部位的失血过多,因此应激诱导的高凝状态可能代表对出血的适应性反应。并且在生化上,心理压力与凝血途径之间的关系已经建立起来。由于血栓形成是心血管疾病最常见的潜在病理学,因此理解应激与该病理之间关联的机制非常有价值。本综述全面回顾在健康个体和心血管疾病患者中应激与血栓形成之间关系的细胞和分子机制。Stress response and coagulation response are closely related, and can even be regarded as a type of stress response, and a large number of studies have confirmed that the body’s coagulation response to stress can lead to a hypercoagulable state of blood, thereby preventing excessive blood loss in the injured area, so stress-induced hypercoagulability may represent an adaptive response to bleeding. And biochemically, the relationship between psychological stress and coagulation pathways has been established. Since thrombosis is the most common underlying pathology of cardiovascular disease, it is valuable to understand the mechanisms underlying the association between stress and this pathology. This review comprehensively reviews the cellular and molecular mechanisms of the relationship between stress and thrombosis in healthy individuals and people with cardiovascular disease.展开更多
作为重要的动力学参数,刚度辨识及预测对于涡轮泵动力特性具有关键意义,为此提出一种融合注意力机制和双向长短期记忆(Bi⁃directional long short⁃term memory,BiLSTM)网络的预测模型。将动力学响应融合输入,使用LSTM神经网络有效挖掘...作为重要的动力学参数,刚度辨识及预测对于涡轮泵动力特性具有关键意义,为此提出一种融合注意力机制和双向长短期记忆(Bi⁃directional long short⁃term memory,BiLSTM)网络的预测模型。将动力学响应融合输入,使用LSTM神经网络有效挖掘时序相关的历史特征。再将两层LSTM网络反向叠加组成BiLSTM模型,适应动力学信息复杂、序列冗长特点,深入挖掘参数间的非线性特征。随后引入Attention层,利用注意力机制获取特征分配权重,增强关键信息。最后通过某型涡轮泵的动力学数据训练辨识模型。结果表明,对于涡轮泵刚度特性,Attention⁃BiLSTM模型在序列数据处理方面具有显著优势,预测平均绝对百分比误差(Mean absolute percentage error,MAPE)可达2.1945%。而单一结构的RNN、LSTM和BiLSTM模型的预测MAPE分别为10.4977%、5.4973%和2.7986%。可见该方法有效避免了复杂的动力学反问题求解,实现了非线性参数的动态识别。展开更多
文摘针对实物保护系统(Physical Protection System,PPSY)中单一传感器报警准确率较低的问题,提出了一种基于改进ID3的CAC-ID3(Confidence And Correlation-ID3)算法在多传感器实物保护系统中数据融合的新方法。与传统的单一传感器数据信息处理相比,多传感器数据融合能够更加准确、全面的得到被测对象的数据信息,有效地利用多传感器资源。CAC-ID3算法首先在ID3的基础上引入属性置信度重新计算期望熵,解决属性和价值不对等的问题,克服多传感器数据分类时多值偏向的缺点,其值由经验和相关领域知识决定。然后通过引入属性间的相关度来调整信息增益值,提高分类精度。实验结果表明:基于CAC-ID3的决策树算法的多传感器PPSY能有效提高报警准确率和可靠性,防止敌对分子入侵,提高传感器对PPSY的检测的效能,且该算法的分类精度高于ID3算法。
文摘应激反应和凝血反应联系密切,甚至可以将凝血反应视为应激反应其中的一种,大量的研究已经证实机体针对应激的凝血反应可以导致血液的高凝状态,进而防止受伤部位的失血过多,因此应激诱导的高凝状态可能代表对出血的适应性反应。并且在生化上,心理压力与凝血途径之间的关系已经建立起来。由于血栓形成是心血管疾病最常见的潜在病理学,因此理解应激与该病理之间关联的机制非常有价值。本综述全面回顾在健康个体和心血管疾病患者中应激与血栓形成之间关系的细胞和分子机制。Stress response and coagulation response are closely related, and can even be regarded as a type of stress response, and a large number of studies have confirmed that the body’s coagulation response to stress can lead to a hypercoagulable state of blood, thereby preventing excessive blood loss in the injured area, so stress-induced hypercoagulability may represent an adaptive response to bleeding. And biochemically, the relationship between psychological stress and coagulation pathways has been established. Since thrombosis is the most common underlying pathology of cardiovascular disease, it is valuable to understand the mechanisms underlying the association between stress and this pathology. This review comprehensively reviews the cellular and molecular mechanisms of the relationship between stress and thrombosis in healthy individuals and people with cardiovascular disease.
