This study presents a Bayesian spectral density approach for identification and uncertainty quantification of flutter derivatives of bridge sections utilizing buffeting displacement responses, where the wind tunnel test is conducted in turbulent flow
. Different from traditional time-domain approaches (e.g., least square method and stochastic subspace identification), the newly-proposed approach is operated in frequency domain. Based on the affine invariant ensemble sampler algorithm, Markov chain Monte-Carlo sampling is employed to accomplish the Bayesian inference. The probability density function of flutter derivatives is modeled based on complex Wishart distribution, where probability serves as the measure. By the Bayesian spectral density approach, the most probable values and corresponding posterior distributions (namely identification uncertainty here) of each flutter derivative can be obtained at the same time. Firstly, numerical simulations are conducted and the identified results are accurate. Secondly, thin plate model, flutter derivatives of which have theoretical solutions, is chosen to be tested in turbulent flow for the sake of verification. The identified results of thin plate model are consistent with the theoretical solutions. Thirdly, the center-slotted girder model, which is widely-utilized long-span bridge sections in current engineering practice, is employed to investigate the applicability of the proposed approach on a general bridge section. For the center-slotted girder model, the flutter derivatives are also extracted by least square method in uniform flow to cross validate the newly-proposed approach. The identified results by two different approaches are compatible.
Assessment of structural safety status is of paramount importance for existing bridges, where accurate evaluation of flutter probability is essential for long-span bridges. In current engineering practice, at the design stage, flutter critical wind s
peed is usually estimated by the wind tunnel test, which is sensitive to modal frequencies and damping ratios. After construction, structural properties of existing structures will change with time due to various factors, such as structural deteriorations and periodic environments. The structural dynamic properties, such as modal frequencies and damping ratios, cannot be considered as the same values as the initial ones, and the deteriorations should be included when estimating the life-cycle flutter probability. This paper proposes an evaluation framework to assess the life-cycle flutter probability of long-span bridges considering the deteriorations of structural properties, based on field monitoring data. The Bayesian approach is employed for modal identification of a suspension bridge with the main span of 1650 m, and the field monitoring data during 2010-2015 is analyzed to determine the deterioration functions of modal frequencies and damping ratios, as well as their inter-seasonal fluctuations. According to the historical trend, the long-term structural properties can be predicted, and the probability distributions of flutter critical wind speed for each year in the long term are calculated. Consequently, the life-cycle flutter probability is estimated, based on the predicted modal frequencies and damping ratios.
We present a novel approach for completing and reconstructing 3D shapes from incomplete scanned data by using deep neural networks. Rather than being trained on supervised completion tasks and applied on a testing shape, the network is optimized from
scratch on the single testing shape, to fully adapt to the shape and complete the missing data using contextual guidance from the known regions. The ability to complete missing data by an untrained neural network is usually referred to as the deep prior. In this paper, we interpret the deep prior from a neural tangent kernel (NTK) perspective and show that the completed shape patches by the trained CNN are naturally similar to existing patches, as they are proximate in the kernel feature space induced by NTK. The interpretation allows us to design more efficient network structures and learning mechanisms for the shape completion and reconstruction task. Being more aware of structural regularities than both traditional and other unsupervised learning-based reconstruction methods, our approach completes large missing regions with plausible shapes and complements supervised learning-based methods that use database priors by requiring no extra training data set and showing flexible adaptation to a particular shape instance.
Together with the rapid development of the Internet of Things (IoT), human activity recognition (HAR) using wearable Inertial Measurement Units (IMUs) becomes a promising technology for many research areas. Recently, deep learning-based methods pave
a new way of understanding and performing analysis of the complex data in the HAR system. However, the performance of these methods is mostly based on the quality and quantity of the collected data. In this paper, we innovatively propose to build a large database based on virtual IMUs and then address technical issues by introducing a multiple-domain deep learning framework consisting of three technical parts. In the first part, we propose to learn the single-frame human activity from the noisy IMU data with hybrid convolutional neural networks (CNNs) in the semi-supervised form. For the second part, the extracted data features are fused according to the principle of uncertainty-aware consistency, which reduces the uncertainty by weighting the importance of the features. The transfer learning is performed in the last part based on the newly released Archive of Motion Capture as Surface Shapes (AMASS) dataset, containing abundant synthetic human poses, which enhances the variety and diversity of the training dataset and is beneficial for the process of training and feature transfer in the proposed method. The efficiency and effectiveness of the proposed method have been demonstrated in the real deep inertial poser (DIP) dataset. The experimental results show that the proposed methods can surprisingly converge within a few iterations and outperform all competing methods.
In high-dimensional data space, semi-supervised feature learning based on Euclidean distance shows instability under a broad set of conditions. Furthermore, the scarcity and high cost of labels prompt us to explore new semi-supervised learning method
s with the fewest labels. In this paper, we develop a novel Minor Constraint Disturbances-based Deep Semi-supervised Feature Learning framework (MCD-DSFL) from the perspective of probability distribution for feature representation. There are two fundamental modules in the proposed framework: one is a Minor Constraint Disturbances-based restricted Boltzmann machine with Gaussian visible units (MCDGRBM) for modelling continuous data and the other is a Minor Constraint Disturbances-based restricted Boltzmann machine (MCDRBM) for modelling binary data. The Minor Constraint Disturbances (MCD) consist of less instance-level constraints which are produced by only two randomly selected labels from each class. The Kullback-Leibler (KL) divergences of the MCD are fused into the Contrastive Divergence (CD) learning for training the proposed MCDGRBM and MCDRBM models. Then, the probability distributions of hidden layer features are as similar as possible in the same class and they are as dissimilar as possible in the different classes simultaneously. Despite the weak influence of the MCD for our shallow models (MCDGRBM and MCDRBM), the proposed deep MCD-DSFL framework improves the representation capability significantly under its leverage effect. The semi-supervised strategy based on the KL divergence of the MCD significantly reduces the reliance on the labels and improves the stability of the semi-supervised feature learning in high-dimensional space simultaneously.
Sensor-based human activity recognition (HAR) is now a research hotspot in multiple application areas. With the rise of smart wearable devices equipped with inertial measurement units (IMUs), researchers begin to utilize IMU data for HAR. By employin
g machine learning algorithms, early IMU-based research for HAR can achieve accurate classification results on traditional classical HAR datasets, containing only simple and repetitive daily activities. However, these datasets rarely display a rich diversity of information in real-scene. In this paper, we propose a novel method based on deep learning for complex HAR in the real-scene. Specially, in the off-line training stage, the AMASS dataset, containing abundant human poses and virtual IMU data, is innovatively adopted for enhancing the variety and diversity. Moreover, a deep convolutional neural network with an unsupervised penalty is proposed to automatically extract the features of AMASS and improve the robustness. In the on-line testing stage, by leveraging advantages of the transfer learning, we obtain the final result by fine-tuning the partial neural network (optimizing the parameters in the fully-connected layers) using the real IMU data. The experimental results show that the proposed method can surprisingly converge in a few iterations and achieve an accuracy of 91.15% on a real IMU dataset, demonstrating the efficiency and effectiveness of the proposed method.
In this paper, we propose an unsupervised collaborative representation deep network (UCRDNet) which consists of novel collaborative representation RBM (crRBM) and collaborative representation GRBM (crGRBM). The UCRDNet is a novel deep collaborative f
eature extractor for exploring more sophisticated probabilistic models of real-valued and binary data. Unlike traditional representation methods, one similarity relation between the input instances and another similarity relation between the features of the input instances are collaboratively fused together in the representation process of the crGRBM and crRBM models. Here, we use the Locality Sensitive Hashing (LSH) method to divide the input instance matrix into many mini blocks which contain similar instance and local features. Then, we expect the hidden layer feature units of each block gather to block center as much as possible in the training processes of the crRBM and crGRBM. Hence, the correlations between the instances and features as collaborative relations are fused in the hidden layer features. In the experiments, we use K-means and Spectral Clustering (SC) algorithms based on four contrast deep networks to verify the deep collaborative representation capability of the UCRDNet architecture. One architecture of the UCRDNet is composed with a crGRBM and two crRBMs for modeling real-valued data and another architecture of it is composed with three crRBMs for modeling binary data. The experimental results show that the proposed UCRDNet has more outstanding performance than the Autoencoder and DeepFS deep networks (without collaborative representation strategy) for unsupervised clustering on the MSRA-MM2.0 and UCI datasets. Furthermore, the proposed UCRDNet shows more excellent collaborative representation capabilities than the CDL deep collaborative networks for unsupervised clustering.
Recently, multi-user multiple input multiple output (MU-MIMO) systems with low-resolution digital-to-analog converters (DACs) has received considerable attention, owing to the capability of dramatically reducing the hardware cost. Besides, it has bee
n shown that the use of low-resolution DACs enable great reduction in power consumption while maintain the performance loss within acceptable margin, under the assumption of perfect knowledge of channel state information (CSI). In this paper, we investigate the precoding problem for the coarsely quantized MU-MIMO system without such an assumption. The channel uncertainties are modeled to be a random matrix with finite second-order statistics. By leveraging a favorable relation between the multi-bit DACs outputs and the single-bit ones, we first reformulate the original complex precoding problem into a nonconvex binary optimization problem. Then, using the S-procedure lemma, the nonconvex problem is recast into a tractable formulation with convex constraints and finally solved by the semidefinite relaxation (SDR) method. Compared with existing representative methods, the proposed precoder is robust to various channel uncertainties and is able to support a MUMIMO system with higher-order modulations, e.g., 16QAM.
This paper develops a new deep neural network optimized equalization framework for massive multiple input multiple output orthogonal frequency division multiplexing (MIMOOFDM) systems that employ low-resolution analog-to-digital converters (ADCs) at
the base station (BS). The use of lowresolution ADCs could largely reduce hardware complexity and circuit power consumption, however, it makes the channel station information almost blind to the BS, hence causing difficulty in solving the equalization problem. In this paper, we consider a supervised learning architecture, where the goal is to learn a representative function that can predict the targets (constellation points) from the inputs (outputs of the low-resolution ADCs) based on the labeled training data (pilot signals). Especially, our main contributions are two-fold: 1) First, we design a new activation function, whose outputs are close to the constellation points when the parameters are finally optimized, to help us fully exploit the stochastic gradient descent method for the discrete optimization problem. 2) Second, an unsupervised loss is designed and then added to the optimization objective, aiming to enhance the representation ability (so-called generalization). Lastly, various experimental results confirm the superiority of the proposed equalizer over some existing ones, particularly when the statistics of the channel state information are unclear.
Power system state estimation is heavily subjected to measurement error, which comes from the noise of measuring instruments, communication noise, and some unclear randomness. Traditional weighted least square (WLS), as the most universal state estim
ation method, attempts to minimize the residual between measurements and the estimation of measured variables, but it is unable to handle the measurement error. To solve this problem, based on random matrix theory, this paper proposes a data-driven approach to clean measurement error in matrix-level. Our method significantly reduces the negative effect of measurement error, and conducts a two-stage state estimation scheme combined with WLS. In this method, a Hermitian matrix is constructed to establish an invertible relationship between the eigenvalues of measurements and their covariance matrix. Random matrix tools, combined with an optimization scheme, are used to clean measurement error by shrinking the eigenvalues of the covariance matrix. With great robustness and generality, our approach is particularly suitable for large interconnected power grids. Our method has been numerically evaluated using different testing systems, multiple models of measured noise and matrix size ratios.
