Dual-level segmentation method for feature extraction enhancement strategy in speech emotion recognition

This study explored the possibility of using quarry dust as a replacement for natural river sand in concrete production. The behaviors of individual materials such as quarry dust (QD), ground granulated blast-furnace slag (GGBS), pulverized fly ash (PFA) and silica fume (SF) were determined. Laborat...

Full description

Saved in:
Bibliographic Details
Main Author: Abdullah, Jaharatul Dini Karen Lee
Format: Thesis
Language:English
Published: 2022
Subjects:
Online Access:http://eprints.utm.my/id/eprint/101517/1/JaharatulDiniKarenPSKA2022.pdf
http://eprints.utm.my/id/eprint/101517/
http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:150597
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.101517
record_format eprints
spelling my.utm.1015172023-06-21T10:27:26Z http://eprints.utm.my/id/eprint/101517/ Dual-level segmentation method for feature extraction enhancement strategy in speech emotion recognition Abdullah, Jaharatul Dini Karen Lee TA Engineering (General). Civil engineering (General) This study explored the possibility of using quarry dust as a replacement for natural river sand in concrete production. The behaviors of individual materials such as quarry dust (QD), ground granulated blast-furnace slag (GGBS), pulverized fly ash (PFA) and silica fume (SF) were determined. Laboratory investigations were also conducted to evaluate the characterization of quarry dust and by-products materials in terms of microstructure, physical and chemical properties. Furthermore, mix design and the evaluation of the fresh and hardened properties of the ternary blend concrete were executed. Series of concrete were prepared with ternary blend proportion of OPC with sand (control), QD, GGBS, PFA and SF using water to cement ratio (w/c) of 0.30 and 0.20. Fresh properties of mixtures in terms of concrete slumps and density were studied. The hardened properties were examined based on mechanical strengths, deformation characteristics, durability properties and corrosion measurement. Finally, microstructural tests in terms of X-ray diffraction (XRD) and field emission scanning microscopy (FESEM), were concurrently conducted on control and ternary blended concrete to determine the interaction and effect of the ternary material that brings about the performance of the concrete. Results showed that QD and by-products materials affect mixture workability negatively. The inclusion of super plasticizer showed tremendous influence in increasing the workability and reduced this drawback. Blended concrete mixes at various replacement of GGBS, PFA and SF with quarry dust takes longer time to set within 3 to 4 hours whereas control mix is the fastest to set at an hour. Quarry dust blended with concrete indicates that the compressive strength gained between 5.3% to 7.3% compared to control concrete. Furthermore, the constituents of ternary blended it has the quality to be used as partial replacement cement. 2022 Thesis NonPeerReviewed application/pdf en http://eprints.utm.my/id/eprint/101517/1/JaharatulDiniKarenPSKA2022.pdf Abdullah, Jaharatul Dini Karen Lee (2022) Dual-level segmentation method for feature extraction enhancement strategy in speech emotion recognition. PhD thesis, Universiti Teknologi Malaysia. http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:150597
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic TA Engineering (General). Civil engineering (General)
spellingShingle TA Engineering (General). Civil engineering (General)
Abdullah, Jaharatul Dini Karen Lee
Dual-level segmentation method for feature extraction enhancement strategy in speech emotion recognition
description This study explored the possibility of using quarry dust as a replacement for natural river sand in concrete production. The behaviors of individual materials such as quarry dust (QD), ground granulated blast-furnace slag (GGBS), pulverized fly ash (PFA) and silica fume (SF) were determined. Laboratory investigations were also conducted to evaluate the characterization of quarry dust and by-products materials in terms of microstructure, physical and chemical properties. Furthermore, mix design and the evaluation of the fresh and hardened properties of the ternary blend concrete were executed. Series of concrete were prepared with ternary blend proportion of OPC with sand (control), QD, GGBS, PFA and SF using water to cement ratio (w/c) of 0.30 and 0.20. Fresh properties of mixtures in terms of concrete slumps and density were studied. The hardened properties were examined based on mechanical strengths, deformation characteristics, durability properties and corrosion measurement. Finally, microstructural tests in terms of X-ray diffraction (XRD) and field emission scanning microscopy (FESEM), were concurrently conducted on control and ternary blended concrete to determine the interaction and effect of the ternary material that brings about the performance of the concrete. Results showed that QD and by-products materials affect mixture workability negatively. The inclusion of super plasticizer showed tremendous influence in increasing the workability and reduced this drawback. Blended concrete mixes at various replacement of GGBS, PFA and SF with quarry dust takes longer time to set within 3 to 4 hours whereas control mix is the fastest to set at an hour. Quarry dust blended with concrete indicates that the compressive strength gained between 5.3% to 7.3% compared to control concrete. Furthermore, the constituents of ternary blended it has the quality to be used as partial replacement cement.
format Thesis
author Abdullah, Jaharatul Dini Karen Lee
author_facet Abdullah, Jaharatul Dini Karen Lee
author_sort Abdullah, Jaharatul Dini Karen Lee
title Dual-level segmentation method for feature extraction enhancement strategy in speech emotion recognition
title_short Dual-level segmentation method for feature extraction enhancement strategy in speech emotion recognition
title_full Dual-level segmentation method for feature extraction enhancement strategy in speech emotion recognition
title_fullStr Dual-level segmentation method for feature extraction enhancement strategy in speech emotion recognition
title_full_unstemmed Dual-level segmentation method for feature extraction enhancement strategy in speech emotion recognition
title_sort dual-level segmentation method for feature extraction enhancement strategy in speech emotion recognition
publishDate 2022
url http://eprints.utm.my/id/eprint/101517/1/JaharatulDiniKarenPSKA2022.pdf
http://eprints.utm.my/id/eprint/101517/
http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:150597
_version_ 1769842066802606080
score 13.18916