The paper presents the coupling of artificial intelligence-AI and Object-oriented methodology applied for the construction of the model-based decision support system MBDSS.The MBDSS is designed for support the strate...The paper presents the coupling of artificial intelligence-AI and Object-oriented methodology applied for the construction of the model-based decision support system MBDSS.The MBDSS is designed for support the strategic decision making lead to the achievemellt of optimal path towardsmarket economy from the central planning situation in China. To meet user's various requirements,a series of innovations in software development have been carried out, such as system formalization with OBFRAMEs in an object-oriented paradigm for problem solving automation and techniques of modules intelligent cooperation, hybrid system of reasoning, connectionist framework utilization,etc. Integration technology has been highly emphasized and discussed in this article and an outlook to future software engineering is given in the conclusion section.展开更多
为了能够准确高效地对离格信号的波达方向(Direction of Arrival, DOA)进行估计,利用卷积神经网络来提取信号协方差矩阵中的深度特征信息,并采用改进型标签策略来确保网络的估计精度和效率。具体来说,通过带小数的标签来注释协方差矩阵...为了能够准确高效地对离格信号的波达方向(Direction of Arrival, DOA)进行估计,利用卷积神经网络来提取信号协方差矩阵中的深度特征信息,并采用改进型标签策略来确保网络的估计精度和效率。具体来说,通过带小数的标签来注释协方差矩阵构成的张量,并配合上改进后的二进制交叉熵损失函数来使得所提出的小数标签能够用于网络训练。针对DOA估计对应的多标签—多分类的问题,使用了包含6层结构的卷积神经网络的输出单元类别以及幅度来分别对离格信号的DOA整数部分与小数部分进行重构。通过与6种现有典型方法的均方根误差(Root Mean Square Error, RMSE)仿真对比,所提方法能够在信噪比为-10 dB的情况下保持着RMSE<0.5°的优秀表现。虽然无法在较少快拍下正常工作,但该方法在快拍数大于8的条件下仍然保持着RMSE<1°的表现性能。同时,在信号数量为5时,所提方法依然具有较高的估计稳定性,且计算速度能够达到毫秒级,用时明显低于其他方法。展开更多
文摘The paper presents the coupling of artificial intelligence-AI and Object-oriented methodology applied for the construction of the model-based decision support system MBDSS.The MBDSS is designed for support the strategic decision making lead to the achievemellt of optimal path towardsmarket economy from the central planning situation in China. To meet user's various requirements,a series of innovations in software development have been carried out, such as system formalization with OBFRAMEs in an object-oriented paradigm for problem solving automation and techniques of modules intelligent cooperation, hybrid system of reasoning, connectionist framework utilization,etc. Integration technology has been highly emphasized and discussed in this article and an outlook to future software engineering is given in the conclusion section.
文摘为了能够准确高效地对离格信号的波达方向(Direction of Arrival, DOA)进行估计,利用卷积神经网络来提取信号协方差矩阵中的深度特征信息,并采用改进型标签策略来确保网络的估计精度和效率。具体来说,通过带小数的标签来注释协方差矩阵构成的张量,并配合上改进后的二进制交叉熵损失函数来使得所提出的小数标签能够用于网络训练。针对DOA估计对应的多标签—多分类的问题,使用了包含6层结构的卷积神经网络的输出单元类别以及幅度来分别对离格信号的DOA整数部分与小数部分进行重构。通过与6种现有典型方法的均方根误差(Root Mean Square Error, RMSE)仿真对比,所提方法能够在信噪比为-10 dB的情况下保持着RMSE<0.5°的优秀表现。虽然无法在较少快拍下正常工作,但该方法在快拍数大于8的条件下仍然保持着RMSE<1°的表现性能。同时,在信号数量为5时,所提方法依然具有较高的估计稳定性,且计算速度能够达到毫秒级,用时明显低于其他方法。
