Aiming at the problem that complex working conditions affect effect of manual feature extraction in bearing fault diagnosis metro traction motor, a method motor based on improved stacked denoising autoencoder (SDAE) is proposed. This extracts features directly from original vibration signal through deep learning, reduces dependence processing technology and experience, solves unsatisfactory ext...

As various new radar systems are put into use in complex electromagnetic environments, the extraction of only time-domain parameters signals cannot achieve accurate cognition emitters. For this reason, a emitter structural inversion method is proposed based on stacked convolutional autoencoder and deep neural network (SCAE-DNN) to complete two processes forward modelling inversion. The complete...

Extracting an effective facial feature representation is the critical task for automatic expression recognition system. Local Binary Pattern (LBP) known to be a popular texture recognition. However, only few approaches utilize relationship between local neighborhood pixels itself. This paper presents Hybrid Texture Descriptor (HLTD) which derived from logical fusion of Neighborhood XNOR Pattern...

There has been a lot of prior work on representation learning for speech recognition applications, but not much emphasis has been given to an investigation of effective representations of affect from speech, where the paralinguistic elements of speech are separated out from the verbal content. In this paper, we explore denoising autoencoders for learning paralinguistic attributes, i.e. categori...

While determining model complexity is an important problem in machine learning, many feature learning algorithms rely on cross-validation to choose an optimal number of features, which is usually challenging for online learning from a massive stream of data. In this paper, we propose an incremental feature learning algorithm to determine the optimal model complexity for large-scale, online data...

Since tumor is seriously harmful to human health, effective diagnosis measures are in urgent need for tumor therapy. Early detection of tumor is particularly important for better treatment of patients. A notable issue is how to effectively discriminate tumor samples from normal ones. Many classification methods, such as Support Vector Machines (SVMs), have been proposed for tumor classification...

This paper proposes a deep autoencoder-based approach to identify signal features from lowlight images and adaptively brighten images without over-amplifying/saturating the lighter parts in images with a high dynamic range. In surveillance, monitoring and tactical reconnaissance, gathering visual information from a dynamic environment and accurately processing such data are essential to making ...