DOUBLE MATRIX REGULATION AND FACTORIZATION WITH DEEP NEURAL NETWORKS FOR ELECTRODIVIGUE HEATING SYSTEMS

Array

Abstract

In multifactorial systems using textual and graphical information in matrix factorization to facilitate the problem of separate data processing. Recently, in some studies, the study of neural networks to understand the content of text and graphic elements more deeply and to achieve efficacy by creating more accurate patterns of recognition of elements. However, the open question remains about how to effectively use graphic data from the thermal imager in matrix factorization. In this paper, we proposed a double-regularized matrix factorization with deep neural networks (DRMF) to solve this problem. DRMF applies a multilayered neural network model by stacking a convolutional neural network and a secured repetitive neural network to create independent distributed views of user content and objects. Then representations serve to regularize the generation of hidden models for both users and for elements of matrix factorization. So the proposed new model of the neural network works better than a model with a single convergent neural network. Systems that are aimed at mitigating the negative effects of information overload by filtration and providing users with the most attractive and relevant elements (such as video from the display of the thermal imager in determining the thermal state of the electric motor), thus solving the problem for large data. Different methods of building recommendations for the last ten years from different systems, for example, joint filtration and network methods. Among them, matrix factorization on the basis of co-filtration (CF) is the dominant method due to its successful application in systems. In traditional SF methods, only a feedback matrix that contains explicit (eg, estimates) or implicit feedback for learning and prediction of an electric motor resource is used. Typically, the feedback matrix is ​​liquid, which means that most users are faced with several elements. Proceeding from this, was presented in Proc. BigDataCongress. However, this presentation was substantially expanded, using the new model of the deep neural network and adding new experimental contributions compared to the publication of the conference. Many researchers have suggested using content to mitigate the problem of data resolution in. In particular, representative work jobs consist of extracting semantic information from text content using a thematic model and deep neural network model.

Keywords: electric transport, rolling stock, electric motors, thermal state of the electric motor, factorization of matrices, deep neural networks.