In order to enhance the accuracy and reliability of wireless location under non-line-of-sight （NLOS） environments,a novel neural network （NN） location approach using the digital broadcasting signals is presented. ...In order to enhance the accuracy and reliability of wireless location under non-line-of-sight （NLOS） environments,a novel neural network （NN） location approach using the digital broadcasting signals is presented. By the learning ability of the NN and the closely approximate unknown function to any degree of desired accuracy,the input-output mapping relationship between coordinates and the measurement data of time of arrival （TOA） and time difference of arrival （TDOA） is established. A real-time learning algorithm based on the extended Kalman filter （EKF） is used to train the multilayer perceptron （MLP） network by treating the linkweights of a network as the states of the nonlinear dynamic system. Since the EKF-based learning algorithm approximately gives the minimum variance estimate of the linkweights,the convergence is improved in comparison with the backwards error propagation （BP） algorithm. Numerical results illustrate thatthe proposedalgorithmcanachieve enhanced accuracy,and the performance ofthe algorithmis betterthanthat of the BP-based NN algorithm and the least squares （LS） algorithm in the NLOS environments. Moreover,this location method does not depend on a particular distribution of the NLOS error and does not need line-of-sight （ LOS ） or NLOS identification.展开更多
针对尾矿坝在线监测重建设、轻利用的现状,基于尾矿坝位移在线监测时间序列,通过多步逆向云变换算法(Multi-step Backward Cloud Transformation Algorithm Based on Sampling with Replacement,MBCT-SR)改进云模型,根据“3E_(n)原则”...针对尾矿坝在线监测重建设、轻利用的现状,基于尾矿坝位移在线监测时间序列,通过多步逆向云变换算法(Multi-step Backward Cloud Transformation Algorithm Based on Sampling with Replacement,MBCT-SR)改进云模型,根据“3E_(n)原则”和内外包络曲线确定在线监测位移的正常运行值,从而建立尾矿坝位移分级预警阈值模型,并利用某尾矿坝全球导航卫星(Global Navigation Satellite System,GNSS)技术表面位移在线监测数据进行实例验证。结果表明:该尾矿坝水平方向位移的黄、橙、红预警阈值分别为8.41 mm/d、12.94 mm/d、19.41 mm/d,呈现出坝体中间预警阈值最大、并由中间向两侧减小的空间变化规律;尾矿坝垂直方向位移的黄、橙、红预警阈值分别为16.56 mm/d、25.48 mm/d、38.22 mm/d,且随着子坝的堆积,预警阈值逐渐增大。展开更多
近年来,深度学习在自然语言处理(NLP)领域获得了很大成功,尤其是语义识别方面优势突出。但是,深度学习在分析句法构成和识别句法成分方面的效果较差。其中序列标注是自然语言处理领域中历史最悠久的研究课题之一,包括词性标签(Part of s...近年来,深度学习在自然语言处理(NLP)领域获得了很大成功,尤其是语义识别方面优势突出。但是,深度学习在分析句法构成和识别句法成分方面的效果较差。其中序列标注是自然语言处理领域中历史最悠久的研究课题之一,包括词性标签(Part of speech tagging)。对范畴语法标签这一任务进行研究,提出了一些技术,可以让赋予每个输入词的词法类别数目减少。研究目标是开发一个简单而准确的系统模型来解决范畴标签的挑战,同时利用神经网络后向传播算法必要的间接表示以避免复杂的人工特征选择。基于深度学习算法的研究,用Haskell语言设计并实现范畴语法系统,对词嵌入过程的监测,能更好地反映范畴的变化。展开更多
基金The National High Technology Research and Development Program of China (863 Program) (No.2008AA01Z227)the Cultivatable Fund of the Key Scientific and Technical Innovation Project of Ministry of Education of China (No.706028)
文摘In order to enhance the accuracy and reliability of wireless location under non-line-of-sight （NLOS） environments,a novel neural network （NN） location approach using the digital broadcasting signals is presented. By the learning ability of the NN and the closely approximate unknown function to any degree of desired accuracy,the input-output mapping relationship between coordinates and the measurement data of time of arrival （TOA） and time difference of arrival （TDOA） is established. A real-time learning algorithm based on the extended Kalman filter （EKF） is used to train the multilayer perceptron （MLP） network by treating the linkweights of a network as the states of the nonlinear dynamic system. Since the EKF-based learning algorithm approximately gives the minimum variance estimate of the linkweights,the convergence is improved in comparison with the backwards error propagation （BP） algorithm. Numerical results illustrate thatthe proposedalgorithmcanachieve enhanced accuracy,and the performance ofthe algorithmis betterthanthat of the BP-based NN algorithm and the least squares （LS） algorithm in the NLOS environments. Moreover,this location method does not depend on a particular distribution of the NLOS error and does not need line-of-sight （ LOS ） or NLOS identification.
文摘近年来,深度学习在自然语言处理(NLP)领域获得了很大成功,尤其是语义识别方面优势突出。但是,深度学习在分析句法构成和识别句法成分方面的效果较差。其中序列标注是自然语言处理领域中历史最悠久的研究课题之一,包括词性标签(Part of speech tagging)。对范畴语法标签这一任务进行研究,提出了一些技术,可以让赋予每个输入词的词法类别数目减少。研究目标是开发一个简单而准确的系统模型来解决范畴标签的挑战,同时利用神经网络后向传播算法必要的间接表示以避免复杂的人工特征选择。基于深度学习算法的研究,用Haskell语言设计并实现范畴语法系统,对词嵌入过程的监测,能更好地反映范畴的变化。
