Advances in vision-based technologies allow robots to perform sophisticated and intelligent tasks. Even with these advances, there still remain inherent problems with using vision-based technologies. Slow sampling rat...
详细信息
ISBN:
(纸本)9781479901777
Advances in vision-based technologies allow robots to perform sophisticated and intelligent tasks. Even with these advances, there still remain inherent problems with using vision-based technologies. Slow sampling rate and large latency is a problem associated with most vision hardware used in industry. We refer to these characteristics as the sensing dynamics associated with the vision sensor. This paper presents a compensation method that alleviates sensing dynamics issues in visual feedback tracking problems. We view the sensing dynamics compensation problem as two separate mathematical problems. Namely, we first deal with identifying the target model and then we deal with estimating the target position using the identified model and delayed measurements. The expectation-Maximization algorithm and Kalman filtering are utilized to solve each problem respectively. The visual servo scheme associated with the proposed approach is also studied. Simulations and experiments are designed to test the performance capability of the proposed method.
Perfect channel estimation is crucial to the detection of the V-BLAST(Vertical Bell Laboratories Layered Space-Time). The performance of V-BLAST will degrade dramatically when there exists large channel estimation err...
详细信息
ISBN:
(纸本)078039335X
Perfect channel estimation is crucial to the detection of the V-BLAST(Vertical Bell Laboratories Layered Space-Time). The performance of V-BLAST will degrade dramatically when there exists large channel estimation error. Conventionally, the channel estimation is processed independently from the V-BLAST signal processing. In this paper, we propose an EM based algorithm to detect the transmitted V-BLAST structured signals in MIMO OFDM systems while estimate the channel impulse response (CIR) iteratively. Simulation results show that compared with conventional channel estimation methods, this algorithm is bandwidth efficient and has better performance in fast fading multi-path channels.1
We propose a new variational EM algorithm for fitting factor analysis models with mixed continuous and categorical observations. The algorithm is based on a simple quadratic bound to the log-sum-exp function. In the s...
详细信息
ISBN:
(纸本)9781617823800
We propose a new variational EM algorithm for fitting factor analysis models with mixed continuous and categorical observations. The algorithm is based on a simple quadratic bound to the log-sum-exp function. In the special case of fully observed binary data, the bound we propose is significantly faster than previous variational methods. We show that EM is significantly more robust in the presence of missing data compared to treating the latent factors as parameters, which is the approach used by exponential family PCA and other related matrix-factorization methods. A further benefit of the variational approach is that it can easily be extended to the case of mixtures of factor analyzers, as we show. We present results on synthetic and real data sets demonstrating several desirable properties of our proposed method.
Our challenge is the design of a "universal" bit-efficient image compression approach. The prime goal is to allow reconstruction of images with high quality. In addition, we attempt to design the coder and d...
详细信息
ISBN:
(纸本)9781467399623
Our challenge is the design of a "universal" bit-efficient image compression approach. The prime goal is to allow reconstruction of images with high quality. In addition, we attempt to design the coder and decoder "universal", such that MPEG-7-like low-and mid-level descriptors are an integral part of the coded representation. To this end, we introduce a sparse Mixture-of-Experts regression approach for coding images in the pixel domain. The underlying stochastic process of the pixel amplitudes are modelled as a 3-dimensional and multi-modal Mixture-of-Gaussians with K modes. This closed form continuous analytical model is estimated using the expectation-Maximization algorithm and describes segments of pixels by local 3-D Gaussian steering kernels with global support. As such, each component in the mixture of experts steers along the direction of highest correlation. The conditional density then serves as the regression function. Experiments show that a considerable compression gain is achievable compared to JPEG for low bitrates for a large class of images, while forming attractive low-level descriptors for the image, such as the local segmentation boundaries, direction of intensity flow and the distribution of these parameters over the image.
The simulation and evaluation of land vehicle performance requires accurate representation of driving conditions. The ability to effectively interpret this condition to estimate the power demand is important for the e...
详细信息
The simulation and evaluation of land vehicle performance requires accurate representation of driving conditions. The ability to effectively interpret this condition to estimate the power demand is important for the energy management and plays crucial role in the battery utilization. After collecting driving status of vehicle, two algorithms (K-means Clustering and EM algorithm) are employed for clustering the working condition blocks. Finally, compare the clustering effects of the two algorithms, and draw the conclusion that EM algorithm is better.
The accuracy of a power system dynamic model is essential to its secure and efficient operation. Lower confidence in model accuracy usually leads to conservative operation and lowers asset usage. To improve model accu...
详细信息
ISBN:
(纸本)9781479913022
The accuracy of a power system dynamic model is essential to its secure and efficient operation. Lower confidence in model accuracy usually leads to conservative operation and lowers asset usage. To improve model accuracy, this paper proposes an expectation-maximization (EM) method to calibrate the synchronous machine model using phasor measurement unit (PMU) data. First, an extended Kalman filter (EKF) is applied to estimate the dynamic states using measurement data. Then, the parameters are calculated based on the estimated states using the maximum likelihood estimation (MLE) method. The EM method iterates over the preceding two steps to improve estimation accuracy. The proposed EM method’s performance is evaluated using a single-machine infinite bus system and compared with a method where both state and parameters are estimated using an EKF method. Sensitivity studies of the parameter calibration using the EM method also are presented to show the robustness of the proposed method for different levels of measurement noise and initial parameter uncertainty.
In this paper, we consider Tipping's relevance vector machine (RVM) and formalize an incremental training strategy as a variant of the expectation-maximization (EM) algorithm that we call Subspace EM (SSEM). Worki...
详细信息
ISBN:
(纸本)0262025507
In this paper, we consider Tipping's relevance vector machine (RVM) and formalize an incremental training strategy as a variant of the expectation-maximization (EM) algorithm that we call Subspace EM (SSEM). Working with a subset of active basis functions, the sparsity of the RVM solution will ensure that the number of basis functions and thereby the computational complexity is kept low. We also introduce a mean field approach to the intractable classification model that is expected to give a very good approximation to exact Bayesian inference and contains the Laplace approximation as a special case. We test the algorithms on two large data sets with O(10~3 ― 10~4) examples. The results indicate that Bayesian learning of large data sets, e.g. the MNIST database is realistic.
We consider the problem of semi-supervised segmentation of textured images. In this paper, we propose a new Bayesian framework by modeling two-dimensional textured images as the concatenation of two one-dimensional hi...
详细信息
ISBN:
(纸本)9781617388767
We consider the problem of semi-supervised segmentation of textured images. In this paper, we propose a new Bayesian framework by modeling two-dimensional textured images as the concatenation of two one-dimensional hidden Markov autoregressive models for the lines and the columns, respectively. A new segmentation algorithm, which is similar to turbo decoding in the context of error-correcting codes, is obtained based on a factor graph approach. The proposed method estimates the unknown parameters using the expectation-Maximization algorithm.
Crowdsourcing has become a popular paradigm for labeling large datasets. However, it has given rise to the computational task of aggregating the crowdsourced labels provided by a collection of unreliable annotators. W...
详细信息
ISBN:
(纸本)9781627480031
Crowdsourcing has become a popular paradigm for labeling large datasets. However, it has given rise to the computational task of aggregating the crowdsourced labels provided by a collection of unreliable annotators. We approach this problem by transforming it into a standard inference problem in graphical models, and applying approximate variational methods, including belief propagation (BP) and mean field (MF). We show that our BP algorithm generalizes both majority voting and a recent algorithm by Karger et al. [1], while our MF method is closely related to a commonly used EM algorithm. In both cases, we find that the performance of the algorithms critically depends on the choice of a prior distribution on the workers' reliability; by choosing the prior properly, both BP and MF (and EM) perform surprisingly well on both simulated and real-world datasets, competitive with state-of-the-art algorithms based on more complicated modeling assumptions.
Sparse principal component analysis combines the idea of sparsity with principal component analysis (PCA). There are two kinds of sparse PCA;sparse loading PCA (slPCA) which keeps all the variables but zeroes out some...
详细信息
ISBN:
(纸本)9781424442959
Sparse principal component analysis combines the idea of sparsity with principal component analysis (PCA). There are two kinds of sparse PCA;sparse loading PCA (slPCA) which keeps all the variables but zeroes out some of their loadings;and sparse variable PCA (svPCA) which removes whole variables by simultaneously zeroing out all the loadings on some variables. In this paper we propose a model based svPCA method based on the l_(0) penalty. We compare the detection performance of the proposed method with other subset selection method using a simulated data set. Additionally, we apply the method on a real high dimensional functional magnetic resonance imaging (fMRI) data set.
暂无评论