改进的变分稀疏贝叶斯学习离格DOA估计方法

为提高阵列信号处理运算速率,改善其方位估计性能,提出了一种改进变分稀疏贝叶斯学习离格波达方向(direction-of-arrival, DOA)估计方法。该方法利用实值变换,将向量化后的接收信号协方差矩阵转化到实数域,结合变分稀疏贝叶斯学习和网格演化的思想,在迭代过程中使网格从初始的均匀网格自适应地演化为非均匀网格,通过网格更新和网格裂变交替迭代使演化后的网格点逐渐逼近真实信源方位。仿真结果表明,改进方法与传统压缩感知类方法相比,减小了运算量,提高了运算速率,且具有更高的方位估计精度和方位分辨能力,在少快拍和低信噪比情况下,改进方法性能提升的优势更明显。湖上试验数据处理结果进一步验证了该方法的有效性和工程实用性。

子空间聚类的非参数模型及变分贝叶斯学习

子空间聚类的目标是在不同的特征子集上对给定的一组数据归类.此非监督学习方法试图发现数据"在不同表达下的相似"模式,并且引起了相关领域大量的关注和研究.首先扩展Hoff提出的"均值与方差平移"模型为一个新的基于特征子集的非参数聚类模型,其优点是能应用变分贝叶斯方法学习模型参数.此模型结合Dirichlet过程混合模型和选择特征子集的非参数模型,能自动选择聚类个数和进行子空间聚类.然后给出基于马尔可夫链蒙特卡罗的参数后验推断算法.出于计算速度上的考虑,提出应用变分贝叶斯方法学习模型参数.在仿真数据上的实验结果及在人脸聚类问题上的应用均表明了此模型能同时选择相关特征和在这些特征上具有相似模式的数据点.在UCI"多特征数据库"上应用无需抽样的变分贝叶斯方法,其实验结果说明此方法能快速推断模型参数.

基于变分对抗与强化学习的行人重识别

行人重识别技术在实际应用中易受行人姿态变化的干扰,由于行人姿态的变化不仅丢失部分行人信息,而且还会引起大于身份差异的外观变化,导致现有工作难以学到鲁棒的行人特征.为了解决上述问题,本文提出一种基于变分对抗与强化学习的生成式对抗网络(RL-VGAN)用于多姿态行人重识别任务.该方法的核心思想是在不受姿态变化干扰的情况下通过外观编码器和姿态编码器将行人属性分解为外观特征和姿态特征,用以学习鲁棒的身份视觉特征.首先,设计的变分生成网络利用Kullback-Leibler散度损失促进外观编码器推断与身份信息相关的连续隐变量.其次,为了使生成式对抗网络逐步收敛到稳定状态,采用强化学习策略平衡变分生成网络和判别网络的性能.此外,针对基于姿态引导图像生成任务,提出一种新的Inception Score损失用于规范变分生成网络生成图像质量的过程.实验结果证明,所提出的RL-VGAN方法在多个基准数据集上优于其他方法.

基于变分稀疏贝叶斯学习的频谱检测方法

为了降低对宽带信号进行压缩频谱感知的复杂度,提出了一种基于变分稀疏贝叶斯学习的频谱检测方法.该算法直接利用压缩测量值对授权用户的位置、个数以及功率传播图进行了估计,在先验知识未知的情况下,利用变分稀疏贝叶斯求解稀疏权值.而且用简单函数因子逼近的方法降低了边缘似然函数的计算难度.实验结果表明:该方法在感知精度和速度上有显著提高.

基于快速变分稀疏贝叶斯学习的频谱感知与定位

针对稀疏贝叶斯压缩感知算法存在复杂度高、收敛速度慢等缺陷,提出了一种快速变分稀疏贝叶斯学习的频谱检测与定位算法.该算法在原始问题求解过程中增加了辅助变量,消除了原问题模型中未知变量之间耦合度高的问题.并依据稀疏参数的收敛情况,自适应删除不收敛稀疏参数对应的基函数,从而进一步加快了算法的收敛速度.实验结果表明:该算法在收敛速度和频谱检测精度上有显著的改善.

基于k-means聚类和变分位鲁棒极限学习机的短期负荷预测方法

随着售电侧市场的逐步开放,集中式的供售电模式被打破,为获取更精确的区域短期负荷预测值,提出一种基于k-means聚类和变分位鲁棒极限学习机的短期负荷预测方法。首先利用传统的k-means聚类算法对历史电力负荷数据进行负荷模式的提取,获取相同用电行为的用户负荷曲线。然后采用变分位鲁棒极限学习机对不同类负荷曲线分别建立预测模型,最后叠加单个的预测值形成最终的预测结果。通过设定不同的分位值来模拟不同的预测场景,以此得到所有可能性的预测值,即实现变分位-多场景的VQR-ORELM灵活预测。为验证所提方法的有效性,采用2个实际案例进行仿真分析。结果表明,相对于支持向量机、BP神经网络、极限学习机模型、鲁棒极限学习机模型,所提模型在聚类前后预测精度始终最高,进一步验证了所提方法的优越性和灵活性。通过k-means聚类后,所有模型预测性能都有较大提高。

基于因子图的分布式变分稀疏贝叶斯压缩感知

提出了一种基于因子图的分布式变分稀疏贝叶斯压缩感知算法。该算法利用因子图和变分方法将全局感知问题分解为简单的局部问题,通过认知用户邻居间的置信传播实现"软融合",使每个认知用户能够获得全局最优估计。且充分利用邻居间传递的信息所具有的时间和空间二维相关性,提高认知用户在低信噪比下的感知性能。同时,算法在迭代过程中自适应地删除不收敛的超参数及对应的基函数,降低通信负载。实验结果表明:该方法在低采样率和低信噪比下有较好的感知性能。

鲁棒贝叶斯混合分布的模型选择

提出一种基于偏差信息准则(deriance information criterion,DIC)的鲁棒贝叶斯混合分布模型选择算法.在变分逼近框架下,给出鲁棒贝叶斯混合模型的DIC计算公式;设计的模型选择算法能同时学习模型参数推断和进行模型选择,避免在大的候选模型集中根据模型选择准则选取最优模型.给出试验参数初始值设置方法,在含有较多离群点的仿真数据和Old Faithful Geyser数据上的试验结果表明了好的性能:得到鲁棒的混合分量参数和较准确的混合分量个数.

Slope displacement prediction based on multisource domain transfer learning for insufficient sample data

Accurate displacement prediction is critical for the early warning of landslides.The complexity of the coupling relationship between multiple influencing factors and displacement makes the accurate prediction of displacement difficult.Moreover,in engineering practice,insufficient monitoring data limit the performance of prediction models.To alleviate this problem,a displacement prediction method based on multisource domain transfer learning,which helps accurately predict data in the target domain through the knowledge of one or more source domains,is proposed.First,an optimized variational mode decomposition model based on the minimum sample entropy is used to decompose the cumulative displacement into the trend,periodic,and stochastic components.The trend component is predicted by an autoregressive model,and the periodic component is predicted by the long short-term memory.For the stochastic component,because it is affected by uncertainties,it is predicted by a combination of a Wasserstein generative adversarial network and multisource domain transfer learning for improved prediction accuracy.Considering a real mine slope as a case study,the proposed prediction method was validated.Therefore,this study provides new insights that can be applied to scenarios lacking sample data.

共形极化敏感阵列单元失效下的稳健参数估计

传统极化-DOA参数估计方法在部分阵列单元失效的情况下,其估计性能会严重恶化甚至失效;同时,面临着日益复杂的电磁环境,部分阵列失效单元不可避免地引入错误数据,这对算法的稳健性是一个巨大挑战。针对以上问题,为了充分探究部分阵列单元失效和错误数据对算法参数估计性能的影响,在共形极化敏感阵列中考虑了部分单元完全失效和部分单元出错概率两种情况,提出了一种基于变分稀疏贝叶斯学习的稳健空域二维联合稀疏极化-DOA参数估计方法。首先利用信源的空域稀疏特性,建立基于共形极化敏感阵列包含错误数据的二维稀疏接收信号模型;其次,采用奇异值分解方法来降低阵列输出矩阵的维度,从而减小算法运算量;然后,利用变分稀疏贝叶斯学习算法来获得信源稳健的DOA估计;最后,通过模值约束算法获得信源的极化参数估计。仿真结果表明,在阵列单元失效的情况下,所提算法具有相对稳健的参数估计性能,具有较高的估计精度和角度分辨率。

自动驾驶奖励函数贝叶斯逆强化学习方法

研究具有广泛场景适应性的自动驾驶汽车的驾驶策略,对实现安全、舒适、和谐的自动驾驶至关重要。深度强化学习以其优异的函数逼近和表示能力,在驾驶策略学习方面展示了巨大潜力。但设计适用于各种复杂驾驶场景的奖励函数极具挑战性,驾驶策略的场景泛化能力亟待提升。针对复杂驾驶场景下的奖励函数难以设计问题,考虑人类驾驶行为偏好,建立人类驾驶策略的近似似然函数模型,通过基于曲线插值的动作空间稀疏采样和近似变分推理方法,学习奖励函数的近似后验分布,建立基于贝叶斯神经网络的奖励函数模型。针对神经网络奖励函数不确定性产生的错误奖励,采用蒙特卡洛方法,对贝叶斯神经网络奖励函数不确定性进行度量,在最大化奖励函数的同时,对认知不确定性进行适当惩罚,提出基于奖励函数后验分布的不确定性认知型类人驾驶策略训练方法。采用NGSIM US-101高速公路数据集和nuPlan城市道路数据集,对所提出方法的有效性进行测试和验证。研究结果表明,基于贝叶斯逆强化学习的近似变分奖励学习方法,克服基于人工构造状态特征线性组合的奖励函数性能不佳的问题,实现奖励函数不确定性的度量,提升奖励函数对高维非线性问题的泛化能力,其学习的奖励函数及训练稳定性明显优于主流逆强化学习方法。在奖励函数中适当引入不确定性的惩罚,有利于提升驾驶策略的类人性、安全性及其训练的稳定性,提出的不确定性认知型类人驾驶策略显著优于行为克隆学习的策略和基于最大熵逆强化学习的策略。

Sparsity-Assisted Intelligent Condition Monitoring Method for Aero-engine Main Shaft Bearing

Weak feature extraction is of great importance for condition monitoring and intelligent diagnosis of aeroengine.Aimed at achieving intelligent diagnosis of aero-engine main shaft bearing,an enhanced sparsity-assisted intelligent condition monitoring method is proposed in this paper.Through analyzing the weakness of convex sparse model,i.e.the tradeoff between noise reduction and feature reconstruction,this paper proposes an enhanced-sparsity nonconvex regularized convex model based on Moreau envelope to achieve weak feature extraction.Accordingly,a sparsity-assisted deep convolutional variational autoencoders network is proposed,which achieves the intelligent identification of fault state through training denoised normal data.Finally,the effectiveness of the proposed method is verified through aero-engine bearing run-to-failure experiment.The comparison results show that the proposed method is good at abnormal pattern recognition,showing a good potential for weak fault intelligent diagnosis of aero-engine main shaft bearings.

Impulsive component extraction using shift-invariant dictionary learning and its application to gear-box bearing early fault diagnosis

The impulsive components induced by bearing faults are key features for assessing gear-box bearing faults.However,because of heavy background noise and the interferences of other vibrations,it is difficult to extract these impulsive components caused by faults,particularly early faults,from the measured vibration signals.To capture the high-level structure of impulsive components embedded in measured vibration signals,a dictionary learning method called shift-invariant K-means singular value decomposition(SI-K-SVD)dictionary learning is used to detect the early faults of gear-box bearings.Although SI-K-SVD is more flexible and adaptable than existing methods,the improper selection of two SI-K-SVD-related parameters,namely,the number of iterations and the pattern lengths,has an adverse influence on fault detection performance.Therefore,the sparsity of the envelope spectrum(SES)and the kurtosis of the envelope spectrum(KES)are used to select these two key parameters,respectively.SI-K-SVD with the two selected optimal parameter values,referred to as optimal parameter SI-K-SVD(OP-SI-K-SVD),is proposed to detect gear-box bearing faults.The proposed method is verified by both simulations and an experiment.Compared to the state-of-the-art methods,namely,empirical model decomposition,wavelet transform and K-SVD,OP-SI-K-SVD has better performance in diagnosing the early faults of a gear-box bearing.

Efficient scheme of low-dose CT reconstruction using TV minimization with an adaptive stopping strategy and sparse dictionary learning for post-processing

Recently, low-dose computed tomography （CT） has become highly desirable because of the growing concern for the potential risks of excessive radiation. For low-dose CT imaging, it is a significant challenge to guarantee image quality while reducing radiation dosage. Compared with classical filtered backprojection algorithms, compressed sensing-based iterative re- construction has achieved excellent imaging performance, but its clinical application is hindered due to its computational ineffi- ciency. To promote low-dose CT imaging, we propose a promising reconstruction scheme which combines total-variation mini- mization and sparse dictionary learning to enhance the reconstruction performance, and properly schedule them with an adaptive iteration stopping strategy to boost the reconstruction speed. Experiments conducted on a digital phantom and a physical phantom demonstrate a superior performance of our method over other methods in terms of image quality and computational efficiency, which validates its potential for low-dose CT imaging.

Variations in soil moisture over the ‘Huang-Huai-Hai Plain＇ in China due to temperature change using the CNOP-P method and outputs from CMIP5

In this study, the variations in surface soil liquid water(SSLW) due to future climate change are explored in the‘Huang-Huai-Hai Plain'(‘3H') region in China with the Common Land Model(CoLM). To evaluate the possible maximum response of SSLW to climate change, the combination of the conditional nonlinear optimal perturbation related to the parameter(CNOP-P) approach and projections from 10 general circulation models(GCMs) of the Coupled Model Intercomparison Project5(CMIP5) are used. The CNOP-P-type temperature change scenario, a new type of temperature change scenario, is determined by using the CNOP-P method and constrained by the temperature change projections from the 10 GCMs under a high-emission scenario(the Representative Concentration Pathway 8.5 scenario). Numerical results have shown that the response of SSLW to the CNOP-P-type temperature scenario is stronger than those to the 11 temperature scenarios derived from the 10 GCMs and from their ensemble average in the entire ‘3H' region. In the northern region, SSLW under the CNOP-P-type scenario increases to0.1773 m^3 m^(-3); however, SSLW in the scenarios from the GCMs fluctuates from 0.1671 to 0.1748 m^3 m^(-3). In the southern region,SSLW decreases, and its variation(–0.0070 m^3 m^(-3)) due to the CNOP-P-type scenario is higher than each of the variations(–0.0051 to –0.0026 m^3 m^(-3)) due to the scenarios from the GCMs.