ICU patients are vulnerable to medications,especially infusion medications,and the rate and dosage of infusion drugs may worsen the condition.The mortality prediction model can monitor the real-time response of patien...ICU patients are vulnerable to medications,especially infusion medications,and the rate and dosage of infusion drugs may worsen the condition.The mortality prediction model can monitor the real-time response of patients to drug treatment,evaluate doctors’treatment plans to avoid severe situations such as inverse Drug-Drug Interactions(DDI),and facilitate the timely intervention and adjustment of doctor’s treatment plan.The treatment process of patients usually has a time-sequence relation(which usually has the missing data problem)in patients’treatment history.The state-of-the-art method to model such time-sequence is to use Recurrent Neural Network(RNN).However,sometimes,patients’treatment can last for a long period of time,which RNN may not fit for modelling long time sequence data.Therefore,we propose to use the heterogeneous medication events driven LSTM to predict the outcome of the patient,and the Natural Language Processing and Gaussian Process(GP),which can handle noisy,incomplete,sparse,heterogeneous and unevenly sampled patients’medication records.In our work,we emphasize the semantic meaning of each medication event and the sequence of the medication events on patients,while also handling the missing value problem using kernel-based Gaussian process.We compare the performance of LSTM and Phased-LSTM on modelling the outcome of patients’treatment and data imputation using kernel-based Gaussian process and conduct an empirical study on different data imputation approaches.展开更多
Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularl...Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.展开更多
泵站机组运行受多种因素影响,导致泵站运行理论效率与实际效率误差较大。针对泵站机组运行效率精准模拟难题,运用基于高价多项式回归、回归树、多元线性回归、向量机回归、高斯过程回归、神经网络的10个回归算法,建立泵站机组效率模拟...泵站机组运行受多种因素影响,导致泵站运行理论效率与实际效率误差较大。针对泵站机组运行效率精准模拟难题,运用基于高价多项式回归、回归树、多元线性回归、向量机回归、高斯过程回归、神经网络的10个回归算法,建立泵站机组效率模拟模型并开展对比分析,优选出有效的泵站运行效率模拟建模方法。讨论分析采用“上下游水位+流量”代替传统“扬程+流量”开展泵站运行模拟的效果。以南水北调东线邳州站和遂宁二站共8台机组的历史数据开展实例分析,相关实验结果表明:在所有方法中,高斯过程回归(Gaussian process regression,GPR)模型在均方根误差(ERMS)、平均绝对误差(EMA)、均方误差(EMS)、决定系数(R2)和最大个体误差(EMI)指标上综合表现最佳,R2逼近0.95;使用站上、站下水位代替传统的扬程对模型进行训练,所有模型的综合评价指标整体有所改善。综合来看,使用GPR模型并使用上游、下游水位代替扬程进行模拟效率表现最好,以邳州站4号机为例,可将模拟效率的EMA和EMI分别从16.49%和20.40%减少至0.41%和2.30%,研究成果具有一定实际意义,可为我国调水工程泵站经济运行提供有力支撑。展开更多
燃烧排放监测对于优化燃烧质量、提高燃烧效率具有重要意义。为了实现燃烧NO_(x)排放的精确预测,本研究提出了一种基于火焰图像的半监督学习模型。在该模型中,火焰图像的深层特征首先由卷积自编码(Convolutional Autoencoder,CAE)提取,...燃烧排放监测对于优化燃烧质量、提高燃烧效率具有重要意义。为了实现燃烧NO_(x)排放的精确预测,本研究提出了一种基于火焰图像的半监督学习模型。在该模型中,火焰图像的深层特征首先由卷积自编码(Convolutional Autoencoder,CAE)提取,然后送至高斯过程回归(Gaussian Process Regression,GPR)进行分析,得到燃烧NO_(x)浓度。在重油燃烧炉膛上开展实验研究,利用不同工况下的火焰图像测试CAE-GPR性能。结果证实,CAE可以自动提取火焰图像的关键信息,GPR能够提供NO_(x)点预测及置信区间。展开更多
传统惯导/卫导组合导航在多元复杂环境下易受干扰,从而导致观测量异常影响导航性能。以无人驾驶车辆为研究对象,展开提升组合导航系统导航精度的研究。采用深度高斯过程(deep Gaussian process,DGP)辅助估计位置的方法减小组合导航误差...传统惯导/卫导组合导航在多元复杂环境下易受干扰,从而导致观测量异常影响导航性能。以无人驾驶车辆为研究对象,展开提升组合导航系统导航精度的研究。采用深度高斯过程(deep Gaussian process,DGP)辅助估计位置的方法减小组合导航误差,提高定位性能。基于DGP的辅助导航方法不仅可以预测无人驾驶车辆的标称轨迹,同时可以预测各时刻位置可信区间的概率分布,为基于深度学习模型的数据融合预测方法提供了严格的理论解释性。真实历史数据下的多重对比实验表明,该算法较传统深度神经网络算法具有更高的精度和可靠性。基于DGP的辅助导航方式能有效提高全球卫星定位系统信号失锁时的导航模型性能,实验表明相对于纯惯性导航系统(integral navigation system,INS)解算和长短期记忆(long and short term memory,LSTM)进行导航信号补偿定位精度分别提高了97.32%和52.13%。展开更多
为响应碳达峰、碳中和的需求,构建一套完整的"源-网-荷-储"的新能源电力系统,提出了一种基于Hamiltonian Monte Carlo推断深度高斯过程(HMCDGP)算法的分布式光伏净负荷预测模型.首先,分别使用直接预测和间接预测两种形式对预...为响应碳达峰、碳中和的需求,构建一套完整的"源-网-荷-储"的新能源电力系统,提出了一种基于Hamiltonian Monte Carlo推断深度高斯过程(HMCDGP)算法的分布式光伏净负荷预测模型.首先,分别使用直接预测和间接预测两种形式对预测模型的精度进行实验并得到点预测结果;其次,使用所提出的模型进行概率预测实验并得到区间预测结果;最后,通过以澳洲电网记录的300户净负荷数据为基础的对比实验验证所提模型的优越性.在得到准确的净负荷概率预测后,可以通过电力调度充分利用光伏产出,减少化石能源使用,从而减少碳排放.展开更多
基金This research is supported by Natural Science Foundation of Hunan Province(No.2019JJ40145)Scientific Research Key Project of Hunan Education Department(No.19A273)Open Fund of Key Laboratory of Hunan Province(2017TP1026).
文摘ICU patients are vulnerable to medications,especially infusion medications,and the rate and dosage of infusion drugs may worsen the condition.The mortality prediction model can monitor the real-time response of patients to drug treatment,evaluate doctors’treatment plans to avoid severe situations such as inverse Drug-Drug Interactions(DDI),and facilitate the timely intervention and adjustment of doctor’s treatment plan.The treatment process of patients usually has a time-sequence relation(which usually has the missing data problem)in patients’treatment history.The state-of-the-art method to model such time-sequence is to use Recurrent Neural Network(RNN).However,sometimes,patients’treatment can last for a long period of time,which RNN may not fit for modelling long time sequence data.Therefore,we propose to use the heterogeneous medication events driven LSTM to predict the outcome of the patient,and the Natural Language Processing and Gaussian Process(GP),which can handle noisy,incomplete,sparse,heterogeneous and unevenly sampled patients’medication records.In our work,we emphasize the semantic meaning of each medication event and the sequence of the medication events on patients,while also handling the missing value problem using kernel-based Gaussian process.We compare the performance of LSTM and Phased-LSTM on modelling the outcome of patients’treatment and data imputation using kernel-based Gaussian process and conduct an empirical study on different data imputation approaches.
文摘Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.
文摘泵站机组运行受多种因素影响,导致泵站运行理论效率与实际效率误差较大。针对泵站机组运行效率精准模拟难题,运用基于高价多项式回归、回归树、多元线性回归、向量机回归、高斯过程回归、神经网络的10个回归算法,建立泵站机组效率模拟模型并开展对比分析,优选出有效的泵站运行效率模拟建模方法。讨论分析采用“上下游水位+流量”代替传统“扬程+流量”开展泵站运行模拟的效果。以南水北调东线邳州站和遂宁二站共8台机组的历史数据开展实例分析,相关实验结果表明:在所有方法中,高斯过程回归(Gaussian process regression,GPR)模型在均方根误差(ERMS)、平均绝对误差(EMA)、均方误差(EMS)、决定系数(R2)和最大个体误差(EMI)指标上综合表现最佳,R2逼近0.95;使用站上、站下水位代替传统的扬程对模型进行训练,所有模型的综合评价指标整体有所改善。综合来看,使用GPR模型并使用上游、下游水位代替扬程进行模拟效率表现最好,以邳州站4号机为例,可将模拟效率的EMA和EMI分别从16.49%和20.40%减少至0.41%和2.30%,研究成果具有一定实际意义,可为我国调水工程泵站经济运行提供有力支撑。
文摘燃烧排放监测对于优化燃烧质量、提高燃烧效率具有重要意义。为了实现燃烧NO_(x)排放的精确预测,本研究提出了一种基于火焰图像的半监督学习模型。在该模型中,火焰图像的深层特征首先由卷积自编码(Convolutional Autoencoder,CAE)提取,然后送至高斯过程回归(Gaussian Process Regression,GPR)进行分析,得到燃烧NO_(x)浓度。在重油燃烧炉膛上开展实验研究,利用不同工况下的火焰图像测试CAE-GPR性能。结果证实,CAE可以自动提取火焰图像的关键信息,GPR能够提供NO_(x)点预测及置信区间。
文摘传统惯导/卫导组合导航在多元复杂环境下易受干扰,从而导致观测量异常影响导航性能。以无人驾驶车辆为研究对象,展开提升组合导航系统导航精度的研究。采用深度高斯过程(deep Gaussian process,DGP)辅助估计位置的方法减小组合导航误差,提高定位性能。基于DGP的辅助导航方法不仅可以预测无人驾驶车辆的标称轨迹,同时可以预测各时刻位置可信区间的概率分布,为基于深度学习模型的数据融合预测方法提供了严格的理论解释性。真实历史数据下的多重对比实验表明,该算法较传统深度神经网络算法具有更高的精度和可靠性。基于DGP的辅助导航方式能有效提高全球卫星定位系统信号失锁时的导航模型性能,实验表明相对于纯惯性导航系统(integral navigation system,INS)解算和长短期记忆(long and short term memory,LSTM)进行导航信号补偿定位精度分别提高了97.32%和52.13%。
文摘为响应碳达峰、碳中和的需求,构建一套完整的"源-网-荷-储"的新能源电力系统,提出了一种基于Hamiltonian Monte Carlo推断深度高斯过程(HMCDGP)算法的分布式光伏净负荷预测模型.首先,分别使用直接预测和间接预测两种形式对预测模型的精度进行实验并得到点预测结果;其次,使用所提出的模型进行概率预测实验并得到区间预测结果;最后,通过以澳洲电网记录的300户净负荷数据为基础的对比实验验证所提模型的优越性.在得到准确的净负荷概率预测后,可以通过电力调度充分利用光伏产出,减少化石能源使用,从而减少碳排放.
