Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204280010> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W3204280010 endingPage "661" @default.
- W3204280010 startingPage "652" @default.
- W3204280010 abstract "Deep learning can be used to learn huge volume of data, which will be processed through hidden layers and according to the number of hidden layers ,filter size and numbers and the required computation cost is increased because of the size of raw data, this problem can be avoided by using pooling techniques, different method s are proposed to extract the basic features of the signal instead of all signal, but unfortunately this operation may introduce some noise or omission because of elimination important data from the signal. In this paper, A novel pooling method are proposed based on discrete cosine transform , this method is utilized DCT technique to reduce spatial redundancy of image by transform the spatial domain into frequency domain , which can preserve the most significant image information from the other coefficients, which represents the other details information of the image, so discard these less important coefficients. Its effect will be slight and this can reduce the eliminated information as compared with other methods. After applying DCT, we crop the most significant coefficients to be used in the reconstructed data by applying inverse DCT . then the result is combined in different methods with Max pooling and average pooling methods, this new structure can reduce the effect of discarding most important information and reduce the drawbacks of average and Max. pooling method. لإhe results are proved that our proposed methods are outperformed some standard methods and can be used in more application." @default.
- W3204280010 created "2021-10-11" @default.
- W3204280010 creator A5076089289 @default.
- W3204280010 creator A5090675368 @default.
- W3204280010 date "2021-08-13" @default.
- W3204280010 modified "2023-09-23" @default.
- W3204280010 title "A novel pooling method for CNN model based on discrete cosine transform" @default.
- W3204280010 doi "https://doi.org/10.21533/pen.v9i3.2233.g911" @default.
- W3204280010 hasPublicationYear "2021" @default.
- W3204280010 type Work @default.
- W3204280010 sameAs 3204280010 @default.
- W3204280010 citedByCount "0" @default.
- W3204280010 crossrefType "journal-article" @default.
- W3204280010 hasAuthorship W3204280010A5076089289 @default.
- W3204280010 hasAuthorship W3204280010A5090675368 @default.
- W3204280010 hasConcept C106131492 @default.
- W3204280010 hasConcept C111919701 @default.
- W3204280010 hasConcept C11413529 @default.
- W3204280010 hasConcept C115961682 @default.
- W3204280010 hasConcept C152124472 @default.
- W3204280010 hasConcept C153180895 @default.
- W3204280010 hasConcept C154945302 @default.
- W3204280010 hasConcept C2221639 @default.
- W3204280010 hasConcept C31972630 @default.
- W3204280010 hasConcept C41008148 @default.
- W3204280010 hasConcept C70437156 @default.
- W3204280010 hasConceptScore W3204280010C106131492 @default.
- W3204280010 hasConceptScore W3204280010C111919701 @default.
- W3204280010 hasConceptScore W3204280010C11413529 @default.
- W3204280010 hasConceptScore W3204280010C115961682 @default.
- W3204280010 hasConceptScore W3204280010C152124472 @default.
- W3204280010 hasConceptScore W3204280010C153180895 @default.
- W3204280010 hasConceptScore W3204280010C154945302 @default.
- W3204280010 hasConceptScore W3204280010C2221639 @default.
- W3204280010 hasConceptScore W3204280010C31972630 @default.
- W3204280010 hasConceptScore W3204280010C41008148 @default.
- W3204280010 hasConceptScore W3204280010C70437156 @default.
- W3204280010 hasIssue "3" @default.
- W3204280010 hasLocation W32042800101 @default.
- W3204280010 hasOpenAccess W3204280010 @default.
- W3204280010 hasPrimaryLocation W32042800101 @default.
- W3204280010 hasRelatedWork W1846094795 @default.
- W3204280010 hasRelatedWork W1978315673 @default.
- W3204280010 hasRelatedWork W1997296225 @default.
- W3204280010 hasRelatedWork W2029032811 @default.
- W3204280010 hasRelatedWork W2038178854 @default.
- W3204280010 hasRelatedWork W2077096030 @default.
- W3204280010 hasRelatedWork W2097668112 @default.
- W3204280010 hasRelatedWork W2182326641 @default.
- W3204280010 hasRelatedWork W2183728785 @default.
- W3204280010 hasRelatedWork W2190083310 @default.
- W3204280010 hasRelatedWork W2291301299 @default.
- W3204280010 hasRelatedWork W2757610121 @default.
- W3204280010 hasRelatedWork W2776616646 @default.
- W3204280010 hasRelatedWork W2904528243 @default.
- W3204280010 hasRelatedWork W2969711245 @default.
- W3204280010 hasRelatedWork W3089726482 @default.
- W3204280010 hasRelatedWork W3103674113 @default.
- W3204280010 hasRelatedWork W3208262717 @default.
- W3204280010 hasRelatedWork W3211621043 @default.
- W3204280010 hasRelatedWork W2185975334 @default.
- W3204280010 hasVolume "9" @default.
- W3204280010 isParatext "false" @default.
- W3204280010 isRetracted "false" @default.
- W3204280010 magId "3204280010" @default.
- W3204280010 workType "article" @default.