<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Disertacione Matematikë e Aplikuar Archives - UNIVERSITETI I TIRANËS</title>
	<atom:link href="https://unitir.edu.al/category/fakulteti-i-shkencave-te-natyres/departamenti-matematike-e-aplikuar/feed/" rel="self" type="application/rss+xml" />
	<link></link>
	<description></description>
	<lastBuildDate>Wed, 03 Jun 2026 12:23:12 +0000</lastBuildDate>
	<language>sq</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=6.6.5</generator>

<image>
	<url>https://unitir.edu.al/wp-content/uploads/2019/08/cropped-logo-1-32x32.png</url>
	<title>Disertacione Matematikë e Aplikuar Archives - UNIVERSITETI I TIRANËS</title>
	<link></link>
	<width>32</width>
	<height>32</height>
</image> 
	<item>
		<title>Viola BAKIASI &#8211; ANALIZA E PARASHIKIMEVE DHE KLASIFIKIME NË MACHINE LEARNING DUKE PËRDORUR TEORINË BAYESIANE: MODELET SHUMËPËRMASORE TË MIKSUARA BETA DHE TË TJERA NË NJOHJEN E MIKRO-SHPREHJEVE</title>
		<link>https://unitir.edu.al/viola-bakiasi-analiza-e-parashikimeve-dhe-klasifikime-ne-machine-learning-duke-perdorur-teorine-bayesiane-modelet-shumepermasore-te-miksuara-beta-dhe-te-tjera-ne-njohjen-e-mikro-shprehjeve/</link>
		
		<dc:creator><![CDATA[education]]></dc:creator>
		<pubDate>Wed, 03 Jun 2026 12:17:57 +0000</pubDate>
				<category><![CDATA[Disertacione FSHN]]></category>
		<category><![CDATA[Disertacione Matematikë e Aplikuar]]></category>
		<category><![CDATA[Doktoraturat]]></category>
		<category><![CDATA[F.SH te Natyres]]></category>
		<guid isPermaLink="false">https://unitir.edu.al/?p=38243</guid>

					<description><![CDATA[<p>Titulli i Disertacionit: ANALIZA E PARASHIKIMEVE DHE KLASIFIKIME NË MACHINE LEARNING DUKE PËRDORUR TEORINË BAYESIANE: MODELET SHUMËPËRMASORE TË MIKSUARA BETA DHE TË TJERA NË NJOHJEN [&#8230;]</p>
<p>The post <a href="https://unitir.edu.al/viola-bakiasi-analiza-e-parashikimeve-dhe-klasifikime-ne-machine-learning-duke-perdorur-teorine-bayesiane-modelet-shumepermasore-te-miksuara-beta-dhe-te-tjera-ne-njohjen-e-mikro-shprehjeve/">Viola BAKIASI &#8211; ANALIZA E PARASHIKIMEVE DHE KLASIFIKIME NË MACHINE LEARNING DUKE PËRDORUR TEORINË BAYESIANE: MODELET SHUMËPËRMASORE TË MIKSUARA BETA DHE TË TJERA NË NJOHJEN E MIKRO-SHPREHJEVE</a> appeared first on <a href="https://unitir.edu.al">UNIVERSITETI I TIRANËS</a>.</p>
]]></description>
										<content:encoded><![CDATA[<h6 style="box-sizing: border-box; font-size: 1rem; clear: both; color: #484848; margin: 0px 0px 0.5rem; line-height: 1.2; font-family: 'PT Serif', sans-serif; font-weight: 500; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; letter-spacing: 0.5px; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;"><strong>Titulli i Disertacionit:</strong> ANALIZA E PARASHIKIMEVE DHE KLASIFIKIME NË MACHINE LEARNING DUKE PËRDORUR TEORINË BAYESIANE: MODELET SHUMËPËRMASORE TË MIKSUARA BETA DHE TË TJERA NË NJOHJEN E MIKRO-SHPREHJEVE</h6>
<ul style="box-sizing: border-box; margin: 0px 0px 1rem; padding-left: 1.5em; list-style: disc; color: #222222; font-family: Arial, Helvetica, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: 0.5px; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">
<li style="box-sizing: border-box;"><strong style="box-sizing: border-box; font-weight: bolder;">Autori:</strong> Viola BAKIASI&nbsp;</li>
<li style="box-sizing: border-box;"><strong style="box-sizing: border-box; font-weight: bolder;">Institucioni:</strong>&nbsp;Universiteti i Tiranës, Fakulteti i Shkencave të Natyrës, Departamenti: Matematikë e Aplikuar</li>
<li style="box-sizing: border-box;"><strong style="box-sizing: border-box; font-weight: bolder;">Fusha e studimit:</strong> Matematikë e Aplikuar</li>
<li style="box-sizing: border-box;"><strong style="box-sizing: border-box; font-weight: bolder;">Data e publikimit:</strong> 03/06/2026</li>
<li style="box-sizing: border-box;">Disertacioni gjendet i publikuar në Gjuhën Shqipe</li>
</ul>
<p style="box-sizing: border-box; margin: 0px 0px 1rem; color: #484848; letter-spacing: 0.5px; font-size: 16px; font-weight: 400; text-align: justify !important; font-family: Arial, Helvetica, sans-serif; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;"><strong>© E drejta e autorit</strong>: Viola BAKIASI&nbsp;</p>
<p style="box-sizing: border-box; margin: 0px 0px 1rem; color: #484848; letter-spacing: 0.5px; font-size: 16px; font-weight: 400; text-align: justify !important; font-family: Arial, Helvetica, sans-serif; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Publikuar nga Universiteti i Tiranës. Bazuar në aktet ligjore,rregulloreve dhe politikave të UT-ës.</p>
<p class="pdf-link" style="box-sizing: border-box; margin: 0px 0px 1rem; color: #484848; letter-spacing: 0.5px; font-size: 16px; font-weight: 400; text-align: justify !important; font-family: Arial, Helvetica, sans-serif; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">👉<a href="https://unitiredu-my.sharepoint.com/:b:/g/personal/support_teams_unitir_edu_al/IQD9PBQiMhCkSJ-QzJeWRAzrAerhwZwi-MeejSRzYcuziBk?e=FP4FZp">Klikoni këtu për të parë disertacionin e plotë (PDF)</a></p>
<p>&nbsp;</p>
<p><strong>PËRMBLEDHJE</strong></p>
<p>Njohja automatike e mikro-shprehjeve të fytyrës përbën një sfidë të rëndësishme në kompjuterikën afektive për shkak të intensitetit shumë të ulët vizual, kohëzgjatjes së shkurtër të sinjalit emocional dhe pabalancimit të klasave në dataset-et ekzistuese. Ky disertacion trajton këtë problem përmes zhvillimit të një kornize metodologjike hibride që integron zvogëlimin e përmasave, klasifikimin e mbikëqyrur dhe inferencën Bayesiane në një proces të unifikuar.</p>
<p>Metodologjia përfshin përpunimin paraprak të imazheve, nxjerrjen e veçorive diskriminuese dhe zvogëlimin e përmasave përmes Analizës së Komponentëve Kryesorë (PCA), Analizës së Komponentëve Kryesorë me Kernel (KPCA) dhe t-Shpërndarjes Stokastike të Fqinjit më të Afërt (t-SNE). Mbi këto përfaqësime të reduktuara aplikohen klasifikues të ndryshëm të nxënies së mbikëqyrur, përfshirë Ndarësin me Vektorë Mbështetës (SVM), K-Fqinjët më të Afërt (K-NN), Pyllin e Rastit (RF), Bayes-in Naiv dhe klasifikimin e kombinuar. Inferenca Bayesiane përdoret për kalibrimin e probabiliteteve të klasifikimit dhe vlerësimin sasior të pasigurisë së parashikimeve.</p>
<p>Sistemi është implementuar në Python dhe është testuar mbi dataset-et AffectNet dhe CASME II, si dhe është zhvilluar një Ndërfaqe Grafike e Përdoruesit (GUI) për zbulimin në kohë reale të mikro-shprehjeve. Rezultatet tregojnë se ndërthurja e zvogëlimit të përmasave me klasifikuesit e mbikëqyrur dhe me modelimin probabilitar përmirëson stabilitetin e performancës dhe balancën ndërmjet saktësisë dhe vlerës F1 në kushte me të dhëna të pabalancuara.</p>
<p><strong>Fjalë kyçe:</strong> mikro-shprehje, kompjuterikë afektive, zvogëlim i përmasave, nxënie e mbikëqyrur, klasifikim i kombinuar, inferencë Bayesiane, GUI.</p>
<p>&nbsp;</p>
<p><strong>BSTRACT</strong></p>
<p>Automatic recognition of facial micro-expressions represents a significant challenge in affective computing due to their extremely low visual intensity, short duration of the emotional signal, and class imbalance in existing datasets. This dissertation addresses this problem through the development of a hybrid methodological framework that integrates dimensionality reduction, supervised classification, and Bayesian inference within a unified pipeline.</p>
<p>The methodology includes image preprocessing, extraction of discriminative features, and dimensionality reduction through Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA), and t-Distributed Stochastic Neighbor Embedding (t-SNE). On these reduced representations, several supervised learning classifiers are applied, including Support Vector Machines (SVM), K-Nearest Neighbors (K-NN), Random Forest (RF), Naive Bayes, and stacking. Bayesian inference is employed for probability calibration and quantitative uncertainty estimation of classification predictions.</p>
<p>The system is implemented in Python and evaluated on the AffectNet and CASME II datasets. Additionally, a Graphical User Interface (GUI) has been developed for real-time micro-expression detection. The results demonstrate that combining dimensionality reduction with supervised classifiers and Bayesian calibration improves performance stability and enhances the balance between accuracy and F1-score under class-imbalanced conditions.</p>
<p><span class="TextRun SCXW98818393 BCX8" lang="EN-US" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text; font-variant-ligatures: none !important; color: #000000; font-variant-caps: normal; letter-spacing: normal; orphans: 2; text-align: justify; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; font-size: 10pt; font-style: italic; line-height: 18.4px; font-family: 'Times New Roman', 'Times New Roman_EmbeddedFont', 'Times New Roman_MSFontService', serif; font-weight: bold;" xml:lang="EN-US" data-contrast="none"><span class="NormalTextRun SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text;">Keywords:</span></span><span class="TextRun Highlight SCXW98818393 BCX8" lang="EN-US" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text; outline: transparent solid 1px; font-variant-ligatures: none !important; color: #000000; font-style: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: justify; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; background-color: #ffffff; font-size: 12pt; line-height: 20.7px; font-family: 'Times New Roman', 'Times New Roman_EmbeddedFont', 'Times New Roman_MSFontService', serif;" xml:lang="EN-US" data-contrast="none"><span class="NormalTextRun SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text;">&nbsp;</span></span><span class="TextRun SCXW98818393 BCX8" lang="EN-GB" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text; font-variant-ligatures: none !important; color: #000000; font-style: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: justify; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; font-size: 10pt; line-height: 18.4px; font-family: 'Times New Roman', 'Times New Roman_EmbeddedFont', 'Times New Roman_MSFontService', serif;" xml:lang="EN-GB" data-contrast="none"><span class="NormalTextRun SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text;">micro-expressions,&nbsp;</span><span class="NormalTextRun SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text;">affective computing</span></span><span class="TextRun SCXW98818393 BCX8" lang="EN-US" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text; font-variant-ligatures: none !important; color: #000000; font-style: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: justify; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; font-size: 10pt; line-height: 18.4px; font-family: 'Times New Roman', 'Times New Roman_EmbeddedFont', 'Times New Roman_MSFontService', serif;" xml:lang="EN-US" data-contrast="none"><span class="NormalTextRun SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text;">,</span></span><span class="TextRun SCXW98818393 BCX8" lang="EN-GB" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text; font-variant-ligatures: none !important; color: #000000; font-style: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: justify; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; font-size: 10pt; line-height: 18.4px; font-family: 'Times New Roman', 'Times New Roman_EmbeddedFont', 'Times New Roman_MSFontService', serif;" xml:lang="EN-GB" data-contrast="none"><span class="NormalTextRun SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text;">&nbsp;dimensionality reduction,&nbsp;</span><span class="NormalTextRun SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text;">supervised learning,&nbsp;</span><span class="NormalTextRun SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text;">stacking</span><span class="NormalTextRun SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text;">,</span></span><span class="TextRun SCXW98818393 BCX8" lang="EN-US" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text; font-variant-ligatures: none !important; color: #000000; font-style: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: justify; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; font-size: 10pt; line-height: 18.4px; font-family: 'Times New Roman', 'Times New Roman_EmbeddedFont', 'Times New Roman_MSFontService', serif;" xml:lang="EN-US" data-contrast="none"><span class="NormalTextRun SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text;">&nbsp;</span></span><span class="TextRun SCXW98818393 BCX8" lang="EN-GB" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text; font-variant-ligatures: none !important; color: #000000; font-style: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: justify; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; font-size: 10pt; line-height: 18.4px; font-family: 'Times New Roman', 'Times New Roman_EmbeddedFont', 'Times New Roman_MSFontService', serif;" xml:lang="EN-GB" data-contrast="none"><span class="NormalTextRun SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text;">Bayesian inference,&nbsp;</span></span><span class="TextRun SCXW98818393 BCX8" lang="EN-US" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text; font-variant-ligatures: none !important; color: #000000; font-style: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: justify; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: #ffffff; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; font-size: 10pt; line-height: 18.4px; font-family: 'Times New Roman', 'Times New Roman_EmbeddedFont', 'Times New Roman_MSFontService', serif;" xml:lang="EN-US" data-contrast="none"><span class="NormalTextRun SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text;">GUI.</span></span><span class="EOP Selected SCXW98818393 BCX8" style="-webkit-user-drag: none; -webkit-tap-highlight-color: transparent; margin: 0px; padding: 0px; user-select: text; cursor: default; background-color: #c6c6c6 !important; border-color: #c6c6c6 !important; color: #000000; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: justify; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; font-size: 10pt; line-height: 18.4px; font-family: 'Times New Roman', 'Times New Roman_EmbeddedFont', 'Times New Roman_MSFontService', serif;" data-ccp-props="{&quot;201341983&quot;:0,&quot;335551550&quot;:6,&quot;335551620&quot;:6,&quot;335559739&quot;:0,&quot;335559740&quot;:276}">&nbsp;</span></p>
<p>The post <a href="https://unitir.edu.al/viola-bakiasi-analiza-e-parashikimeve-dhe-klasifikime-ne-machine-learning-duke-perdorur-teorine-bayesiane-modelet-shumepermasore-te-miksuara-beta-dhe-te-tjera-ne-njohjen-e-mikro-shprehjeve/">Viola BAKIASI &#8211; ANALIZA E PARASHIKIMEVE DHE KLASIFIKIME NË MACHINE LEARNING DUKE PËRDORUR TEORINË BAYESIANE: MODELET SHUMËPËRMASORE TË MIKSUARA BETA DHE TË TJERA NË NJOHJEN E MIKRO-SHPREHJEVE</a> appeared first on <a href="https://unitir.edu.al">UNIVERSITETI I TIRANËS</a>.</p>
]]></content:encoded>
					
		
		
			</item>
	</channel>
</rss>
