Sharif Digital Repository

Blind Source Separation (BSS) is the problem of separating signals which are mixed through an unknown function from a number of observations, without any information about the mixing model. Although it has been mathematically proven that the separation can be done when the mixture is linear, there is not any proof for the separability of nonlinearly mixed signals. Our contribution in this paper is performing nonlinear BSS for sparse sources. It is shown in this case, sources are separable even if the problem is under-determined (the number of observations is less than the number of source signals). However in the most general case (when the nonlinear mixing model can be of any kind and there... 

Due to the automatic feature extraction procedure via multi-layer nonlinear transformations, the deep learning-based visual trackers have recently achieved a great success in challenging scenarios for visual tracking purposes. Although many of those trackers utilize the feature maps from pre-trained convolutional neural networks (CNNs), the effects of selecting different models and exploiting various combinations of their feature maps are still not compared completely. To the best of our knowledge, all those methods use a fixed number of convolutional feature maps without considering the scene attributes (e.g., occlusion, deformation, and fast motion) that might occur during tracking. As a... 

Most current speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well each state of each HMM fits a frame or a short window of frames of coefficients that represents the acoustic input. In these systems acoustic inputs are represented by Mel Frequency Cepstral Coefficients temporal spectrogram known as frames. But MFCC is not robust to noise. Consequently, with different train and test conditions the accuracy of speech recognition systems decreases. On the other hand, using MFCCs of larger window of frames in GMMs needs more computational power. In this paper, Deep Belief Networks... 

Distance metric has an important role in many machine learning algorithms. Recently, metric learning for semi-supervised algorithms has received much attention. For semi-supervised clustering, usually a set of pairwise similarity and dissimilarity constraints is provided as supervisory information. Until now, various metric learning methods utilizing pairwise constraints have been proposed. The existing methods that can consider both positive (must-link) and negative (cannot-link) constraints find linear transformations or equivalently global Mahalanobis metrics. Additionally, they find metrics only according to the data points appearing in constraints (without considering other data... 

In this study, an algebraic closed-form method for jointly locating the target and refining the antenna positions in multiple-input-multiple-output radar systems is proposed. First, a set of linear equations is formed by non-linear transformation and nuisance parameters elimination, and then, an estimate of the target position is obtained by employing a weighted least-squares estimator. To jointly refine the target and antenna positions, the associated error terms are estimated in the sequence. The proposed method is shown analytically and confirmed by simulations to attain the Cramér-Rao lower bound performance under small-error conditions. Numerical simulations are given to support the...