Neutrosophy for physiological data compression: in particular by neural nets using deep learning
Journal Title: International Journal of Neutrosophic Science (IJNS) - Year 2020, Vol 1, Issue 2
Abstract
We would like to show the small distance in neutropsophy applications in sciences and humanities, has both finally consider as a terminal user a human. The pace of data production continues to grow, leading to increased needs for efficient storage and transmission. Indeed, the consumption of this information is preferably made on mobile terminals using connections invoiced to the user and having only reduced storage capacities. Deep learning neural networks have recently exceeded the compression rates of algorithmic techniques for text. We believe that they can also significantly challenge classical methods for both audio and visual data (images and videos). To obtain the best physiological compression, i.e. the highest compression ratio because it comes closest to the specificity of human perception, we propose using a neutrosophical representation of the information for the entire compression-decompression cycle. Such a representation consists for each elementary information to add to it a simple neutrosophical number which informs the neural network about its characteristics relative to compression during this treatment. Such a neutrosophical number is in fact a triplet (t,i,f) representing here the belonging of the element to the three constituent components of information in compression; 1° t = the true significant part to be preserved, 2° i = the inderterminated redundant part or noise to be eliminated in compression and 3° f = the false artifacts being produced in the compression process (to be compensated). The complexity of human perception and the subtle niches of its defects that one seeks to exploit requires a detailed and complex mapping that a neural network can produce better than any other algorithmic solution, and networks with deep learning have proven their ability to produce a detailed boundary surface in classifiers.
Authors and Affiliations
Philippe Schweizer
Keywords
Related Articles
- EP ID EP683512
- DOI -
- Views 233
- Downloads 0
On Refined Neutrosophic Quotient Groups
This paper is devoted to the study of refined neutrosophic quotient groups. It is shown that the classical isomorphism theorems of groups do not hold for the refined neutrosophic groups. Moreover, the existence of classi...
Using Moving Averages To Pave The Neutrosophic Time Series
In this paper, were using moving averages to pave the Neutrosophic time series. similar to use moving averages to pave the classical time series. the difference, here were dealing with inaccurate data and values of the t...
Erlang Service Queueing Model with Neutrosophic Parameters
In this paper, we generalize the classical Erlang service queueing model, which has determined and crisp parameters to neutrosophic Erlang service queueing model which is more accurate because it opens the ability to dea...
Concepts of Neutrosophic Complex Numbers
In this paper, concept of neutrosophic complex numbers and its properties were presented inculding the conjugate of neutrosophic complex number, division of neutrosophic complex numbers, the inverted neutrosophic complex...
On αω-closed sets and its connectedness in terms of neutrosophic topological spaces
The aim of this paper is to introduce the notion of neutrosophic αω-closed sets and study some of the prop-erties of neutrosophic αω-closed sets. Further, we investigated neutrosophic αω- continuity, neutrosophic αω-irre...