Relevant bibliographies by topics / Feature Adaptation / Dissertations / Theses
To see the other types of publications on this topic, follow the link: Feature Adaptation.

Dissertations / Theses on the topic 'Feature Adaptation'

Author: Grafiati
Published: 10 December 2022
Last updated: 31 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 dissertations / theses for your research on the topic 'Feature Adaptation.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.

1

Harris, Matthew. "Flow feature aligned mesh generation and adaptation." Thesis, University of Sheffield, 2013. http://etheses.whiterose.ac.uk/4192/.

Full text
Abstract:
Methods which allow for construction of flow feature aligned meshes in two- and three-dimensions have been developed in this thesis to investigate their potential for improvements in the numerical solution relative to globally refining the mesh. Of particular interest in the work is the generation of high-quality quadrilateral and hexahedral elements aligned with the dominant flow features. The two-dimensional techniques are applied on unstructured quad-dominant meshes, whilst the three-dimensional problems involve embedding high-quality hex-dominant mesh blocks into a hybrid volume mesh to im
APA, Harvard, Vancouver, ISO, and other styles
2

Stoltzfus, Daniel Paul. "Predictions on markedness and feature resilience in loanword adaptation." Doctoral thesis, Université Laval, 2014. http://hdl.handle.net/20.500.11794/25567.

Full text
Abstract:
Normalement, un emprunt est adapté afin que ses éléments étrangers s’intègrent au système phonologique de la langue emprunteuse. Certains auteurs (cf. Miao 2005; Steriade 2001b, 2009) ont soutenu que, lors de l’adaptation d’une consonne, les traits de manière d’articulation sont plus résistants au changement que les traits laryngaux (ex. : le voisement) ou que ceux de place. Mes résultats montrent cependant que les traits de manière (ex. : [±continu]) sont impliqués dans les adaptations consonantiques aussi fréquemment que les autres traits (ex. [±voisé] et [±antérieur]). Par exemple, le /Z/ f
APA, Harvard, Vancouver, ISO, and other styles
3

Lu, Jianhua. "Missing feature decoding and model adaptation for noisy speech recognition." Thesis, Queen's University Belfast, 2010. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.527938.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Zennaro, Fabio. "Feature distribution learning for covariate shift adaptation using sparse filtering." Thesis, University of Manchester, 2017. https://www.research.manchester.ac.uk/portal/en/theses/feature-distribution-learning-for-covariate-shift-adaptation-using-sparse-filtering(67989db2-b8a0-4fac-8832-f611e9236ed5).html.

Full text
Abstract:
This thesis studies a family of unsupervised learning algorithms called feature distribution learning and their extension to perform covariate shift adaptation. Unsupervised learning is one of the most active areas of research in machine learning, and a central challenge in this field is to develop simple and robust algorithms able to work in real-world scenarios. A traditional assumption of machine learning is the independence and identical distribution of data. Unfortunately, in realistic conditions this assumption is often unmet and the performances of traditional algorithms may be severely
APA, Harvard, Vancouver, ISO, and other styles
5

Collet, Philippe. "Taming Complexity of Large Software Systems: Contracting, Self-Adaptation and Feature Modeling." Habilitation à diriger des recherches, Université de Nice Sophia-Antipolis, 2011. http://tel.archives-ouvertes.fr/tel-00657444.

Full text
Abstract:
Nos travaux s'inscrivent dans le domaine du génie logiciel pour les systèmes informatiques à large échelle. Notre objectif est de fournir des techniques et des outils pour aider les architectes logiciels à maîtriser la complexité toujours grandissante de ces systèmes. Principalement fondées sur des approches par ingénierie des modèles, nos contributions s'organisent autour de trois axes. Le premier axe concerne le développement de systèmes à la fois fiables et flexibles, et ce à base de composants hiérarchiques équipés de capacités de reconfiguration dynamique. Par l'utilisation de nouvelles f
APA, Harvard, Vancouver, ISO, and other styles
6

Yang, Baoyao. "Distribution alignment for unsupervised domain adaptation: cross-domain feature learning and synthesis." HKBU Institutional Repository, 2018. https://repository.hkbu.edu.hk/etd_oa/556.

Full text
Abstract:
In recent years, many machine learning algorithms have been developed and widely applied in various applications. However, most of them have considered the data distributions of the training and test datasets to be similar. This thesis concerns on the decrease of generalization ability in a test dataset when the data distribution is different from that of the training dataset. As labels may be unavailable in the test dataset in practical applications, we follow the effective approach of unsupervised domain adaptation and propose distribution alignment methods to improve the generalization abil
APA, Harvard, Vancouver, ISO, and other styles
7

Ahn, Euijoon. "Unsupervised Deep Feature Learning for Medical Image Analysis." Thesis, University of Sydney, 2020. https://hdl.handle.net/2123/23002.

Full text
Abstract:
The availability of annotated image datasets and recent advances in supervised deep learning methods are enabling the end-to-end derivation of representative image features that can impact a variety of image analysis problems. These supervised methods use prior knowledge derived from labelled training data and approaches, for example, convolutional neural networks (CNNs) have produced impressive results in natural (photographic) image classification. CNNs learn image features in a hierarchical fashion. Each deeper layer of the network learns a representation of the image data that is higher le
APA, Harvard, Vancouver, ISO, and other styles
8

TURRISI, Rosanna. "On Deep Learning strategies to address Automatic Speech Recognition (ASR) for dysarthric speech." Doctoral thesis, Università degli studi di Ferrara, 2021. http://hdl.handle.net/11392/2488127.

Full text
Abstract:
This thesis explores deep learning techniques to improve Automatic Speech Recognition (ASR) for people affected by dysarthria. Dysarthria is a widely spread motor disorder causing high speech unintelligibility and, often, also motor control abnormalities. Hence, ASR-based technologies may represent the only possibility for dysarthric individuals to interact with other people or machines. Unfortunately, traditional ASR systems fail in presence of dysarthric speech. For instance, we tested Google Speech API and IBM on a subset of the TORGO dataset. These provide more than 80% of WER, while the
APA, Harvard, Vancouver, ISO, and other styles
9

Lock, G. "'Petticoat Sailor' to 'She Crossing' : adaptation in process : a writer's reflection on adapting a feature length screenplay into a novel." Thesis, Nottingham Trent University, 2015. http://irep.ntu.ac.uk/id/eprint/27947/.

Full text
Abstract:
This PhD thesis consists of a novel entitled 'She Crossing', and a Commentary. The Commentary reflects on my practice of constructing the novel by adapting it from my previously existing screenplay, 'Petticoat Sailor'. They both derive from 'The Seafaring Maiden', a Nova Scotian newspaper article dating from 1957. All of these narratives are concerned with a nineteenth-century woman who had to captain a commercial sailing ship across the Atlantic. My screenplay, 'Petticoat Sailor', is set entirely in the nineteenth century. Both the newspaper article and my novel frame the protagonist’s voyage
APA, Harvard, Vancouver, ISO, and other styles
10

Kleynhans, Neil Taylor. "Automatic speech recognition for resource-scarce environments / N.T. Kleynhans." Thesis, North-West University, 2013. http://hdl.handle.net/10394/9668.

Full text
Abstract:
Automatic speech recognition (ASR) technology has matured over the past few decades and has made significant impacts in a variety of fields, from assistive technologies to commercial products. However, ASR system development is a resource intensive activity and requires language resources in the form of text annotated audio recordings and pronunciation dictionaries. Unfortunately, many languages found in the developing world fall into the resource-scarce category and due to this resource scarcity the deployment of ASR systems in the developing world is severely inhibited. In this thesis we pre
APA, Harvard, Vancouver, ISO, and other styles
11

Cardace, Adriano. "Learning Features Across Tasks and Domains." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20050/.

Full text
Abstract:
The absence of in-domain labeled data hinders the applicability of powerful deep neural networks. Unsupervised Domain Adaptation (UDA) methods have emerged to exploit such models even when labeled data is not available in the target domain. All these techniques aim to reduce the distribution shift problem that afflicts these models when trained on one dataset and tested in a different one. However, most of the works, do not consider relationships among tasks to further boost performances. In this thesis, we study a recent method called AT/DT (Across Tasks Domain Transfer), that seeks to apply
APA, Harvard, Vancouver, ISO, and other styles
12

Svensson, Ylva. "Embedded in a context : the adaptation of immigrant youth." Doctoral thesis, Örebro universitet, Institutionen för juridik, psykologi och socialt arbete, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-24172.

Full text
Abstract:
With rising levels of immigration comes a need to know what fosters positive adaptation for the youth growing up in a new culture of settlement.The issue is increasingly studied; however, little of the research conducted has combined a developmental with a contextual approach. The aim of this dissertation was to explore the adaptation of immigrant youth on the basis of developmental theories and models which put emphasis on setting or contextual conditions. This entailed viewing immigrant youths as developing organisms that actively interact with their environments. Further, immigrant youths w
APA, Harvard, Vancouver, ISO, and other styles
13

Liu, Ye. "Application of Convolutional Deep Belief Networks to Domain Adaptation." The Ohio State University, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=osu1397728737.

Full text
APA, Harvard, Vancouver, ISO, and other styles
14

Salman, Nader. "From 3D point clouds to feature preserving meshes." Nice, 2010. http://www.theses.fr/2010NICE4086.

Full text
Abstract:
La majorité des algorithmes de reconstruction de surface sont optimisés pour s’appliquer à des données de haute qualité. Les résultats obtenus peuvent alors être utilisables si les données proviennent de solutions d’acquisition bon marché. Notre première contribution est un algorithme de reconstruction de surfaces à partir de données de stéréo vision. Il combine les informations liées aux points 3D avec les images calibrées afin de combler l’imprécision des données. L’algorithme construit une soupe de triangles 3D à l’aide des images calibrées et à l’issue d’une phase de prétraitement du nuage
APA, Harvard, Vancouver, ISO, and other styles
15

DiCintio, Matt. "A Pilgrim, An Outlaw: Features of Dramatic Adaptation and Theodore Dreiser’s Sister Carrie." VCU Scholars Compass, 2012. http://scholarscompass.vcu.edu/etd/305.

Full text
Abstract:
Although there are countless manuals devoted to playwriting, very few take up the craft of dramatic adaptation in a practical context. My rendering of Theodore Dreiser’s Sister Carrie is an exploration of fundamental elements that require consideration when adapting for the stage. My approach to the characters’ inarticulateness reveals an inherent theatricality in the novel, which both respects Dreiser’s themes and makes them accessible through the conventions of the stage. I suggest the craft of dramatic adaptation should strike a delicate balance between being a “pilgrim” toward the intentio
APA, Harvard, Vancouver, ISO, and other styles
16

Xia, Tian. "Deep Domain Adaptation Learning Framework for Associating Image Features to Tumour Gene Profile." Thesis, The University of Sydney, 2018. http://hdl.handle.net/2123/18589.

Full text
Abstract:
While medical imaging and general pathology are routine in cancer diagnosis, genetic sequencing is not always assessable due to the strong phenotypic and genetic heterogeneity of human cancers. Image-genomics integrates medical imaging and genetics to provide a complementary approach to optimise cancer diagnosis by associating tumour imaging traits with clinical data and has demonstrated its potential in identifying imaging surrogates for tumour biomarkers. However, existing image-genomics research has focused on quantifying tumour visual traits according to human understanding, which may not
APA, Harvard, Vancouver, ISO, and other styles
17

Martin, Helen Mary. "Children's adaptations: A consideration of children's adaptations from popular written texts into stage, filmic and televisual formats. Examined are the features that determine their popularity and the pertinent questions that surround the role of adaptation, and its future possibilities." Thesis, Martin, Helen Mary (1996) Children's adaptations: A consideration of children's adaptations from popular written texts into stage, filmic and televisual formats. Examined are the features that determine their popularity and the pertinent questions that surround the role of adaptation, and its future possibilities. Masters by Coursework thesis, Murdoch University, 1996. https://researchrepository.murdoch.edu.au/id/eprint/52859/.

Full text
Abstract:
This dissertation considers selected children's popular texts in print form as they have been adapted for stage, film and television. Examined are the features that determine their popularity, in their written mode and adapted form, and the apparent similarities and differences found in both. There are also questions answered surrounding the 'why' and 'how' of adaptation, its role and future possibilities. The 'why' of adaptation looks at the reason to turn a successful story into a film or play, while the 'how' question looks at the transformation processes necessary to transpose a story
APA, Harvard, Vancouver, ISO, and other styles
18

ZHU, XIANGPING. "Learning Discriminative Features for Person Re-Identification." Doctoral thesis, Università degli studi di Genova, 2020. http://hdl.handle.net/11567/997742.

Full text
Abstract:
For fulfilling the requirements of public safety in modern cities, more and more large-scale surveillance camera systems are deployed, resulting in an enormous amount of visual data. Automatically processing and interpreting these data promote the development and application of visual data analytic technologies. As one of the important research topics in surveillance systems, person re-identification (re-id) aims at retrieving the target person across non-overlapping camera-views that are implemented in a number of distributed space-time locations. It is a fundamental problem for many practica
APA, Harvard, Vancouver, ISO, and other styles
19

Costa, Paulo Alexandre da Silva. "Uma ferramenta para anÃlise automÃtica de modelos de caracterÃsticas de linhas de produtos de software sensÃvel ao contexto." Universidade Federal do CearÃ, 2012. http://www.teses.ufc.br/tde_busca/arquivo.php?codArquivo=10462.

Full text
Abstract:
CoordenaÃÃo de AperfeiÃoamento de Pessoal de NÃvel Superior<br>As Linhas de produtos de software sÃo uma forma de maximizar o reuso de software, dado que proveem a customizaÃÃo de software em massa. Recentemente, Linhas de produtos de software (LPSs) tÃm sido usadas para oferecer suporte ao desenvolvimento de aplicaÃÃes sensÃveis ao contexto nas quais adaptabilidade em tempo de execuÃÃo à um requisito importante. Neste caso, as LPSs sÃo denominadas Linhas de produtos de software sensÃveis ao contexto (LPSSCs). O sucesso de uma LPSSC depende, portanto, da modelagem de suas caracterÃsticas e do
APA, Harvard, Vancouver, ISO, and other styles
20

Haque, Serajul. "Perceptual features for speech recognition." University of Western Australia. School of Electrical, Electronic and Computer Engineering, 2008. http://theses.library.uwa.edu.au/adt-WU2008.0187.

Full text
Abstract:
Automatic speech recognition (ASR) is one of the most important research areas in the field of speech technology and research. It is also known as the recognition of speech by a machine or, by some artificial intelligence. However, in spite of focused research in this field for the past several decades, robust speech recognition with high reliability has not been achieved as it degrades in presence of speaker variabilities, channel mismatch condi- tions, and in noisy environments. The superb ability of the human auditory system has motivated researchers to include features of human perception
APA, Harvard, Vancouver, ISO, and other styles
21

Charnay, Clément. "Enhancing supervised learning with complex aggregate features and context sensitivity." Thesis, Strasbourg, 2016. http://www.theses.fr/2016STRAD025/document.

Full text
Abstract:
Dans cette thèse, nous étudions l'adaptation de modèles en apprentissage supervisé. Nous adaptons des algorithmes d'apprentissage existants à une représentation relationnelle. Puis, nous adaptons des modèles de prédiction aux changements de contexte.En représentation relationnelle, les données sont modélisées par plusieurs entités liées par des relations. Nous tirons parti de ces relations avec des agrégats complexes. Nous proposons des heuristiques d'optimisation stochastique pour inclure des agrégats complexes dans des arbres de décisions relationnels et des forêts, et les évaluons sur des j
APA, Harvard, Vancouver, ISO, and other styles
22

Ramos, Jonathan da Silva. "Algoritmos de casamento de imagens com filtragem adaptativa de outliers." Universidade de São Paulo, 2016. http://www.teses.usp.br/teses/disponiveis/55/55134/tde-02022017-110428/.

Full text
Abstract:
O registro de imagens tem um papel importante em várias aplicações, tais como reconstrução de objetos 3D, reconhecimento de padrões, imagens microscópicas, entre outras. Este registro é composto por três passos principais: (1) seleção de pontos de interesse; (2) extração de características dos pontos de interesse; (3) correspondência entre os pontos de interesse de uma imagem para a outra. Para os passos 1 e 2, algoritmos como SIFT e SURF têm apresentado resultados satisfatórios. Entretanto, para o passo 3 ocorre a presença de outliers, ou seja, pontos de interesse que foram incorretamente cor
APA, Harvard, Vancouver, ISO, and other styles
23

Kuliešienė, Asta. "Vaikų iš socialiai remtinų šeimų ankstyvoji adaptacija ikimokyklinio ugdymo įstaigose." Master's thesis, Lithuanian Academic Libraries Network (LABT), 2013. http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2013~D_20130125_130134-90440.

Full text
Abstract:
Šiuolaikinėje industrinėje visuomenėje, kai susiklostė sudėtingos ekonominės sąlygos, iš esmės pakito ir bendravisuomeninė šeimos samprata. Vaikas kasdien suvokia realią tikrovę ir pats joje dalyvauja perimdamas iš tėvų įvairias elgesio, veiklos, charakterio savybes. Pakitusiose socialinėse ekonominėse sąlygose, tam tikros grupės žmonių jaučiasi nesaugios, joms sunku prisitaikyti prie šiuolaikinio gyvenimo tempo, adaptuotis prie socialinių ekonominių ir politinių pokyčių. Ypatingai didelis nedarbo lygis išryškino šeimų, gaunančių mažas pajamas, socialines problemas.Tyrime dalyvavo 185 apklaust
APA, Harvard, Vancouver, ISO, and other styles
24

Омаров, М. А., В. М. Карташов, and Р. И. Цехмистро. "Features of the Use of Microprocessors in the Systems of Ovojectors in their Adaptation to the Conditions of the Former CIS." Thesis, NURE, MC&FPGA, 2019. https://mcfpga.nure.ua/conf/2019-mcfpga/10-35598-mcfpga-2019-012.

Full text
Abstract:
This electronic document describes the use of microcontrollers in the regulations of automatic sorting of eggs with a live (dead) embryo with further automatic vaccination of live embryos. These installations are produced only in 3 countries and are called Ovojectors.
APA, Harvard, Vancouver, ISO, and other styles
25

Nicely, Kenneth Edward. "Middle Level Schools in an Era of Standards and Accountability: Adaptations of the Features of the Middle School Concept." Diss., Virginia Tech, 2012. http://hdl.handle.net/10919/26551.

Full text
Abstract:
The literature related to the development of education in the middle grades and to the features associated with the implementation of the middle school concept provides a theoretical grounding for the development and testing of an Innovation Configuration map for the middle school concept. The description provided of the historical development of middle-grades education presents the context for recent research studies and ongoing policy debate. In addition, features of the middle school concept as described within the literature are identified and an overview of salient research findings relat
APA, Harvard, Vancouver, ISO, and other styles
26

Muhammad, Aminu. "Contextual lexicon-based sentiment analysis for social media." Thesis, Robert Gordon University, 2016. http://hdl.handle.net/10059/1571.

Full text
Abstract:
Sentiment analysis concerns the computational study of opinions expressed in text. Social media domains provide a wealth of opinionated data, thus, creating a greater need for sentiment analysis. Typically, sentiment lexicons that capture term-sentiment association knowledge are commonly used to develop sentiment analysis systems. However, the nature of social media content calls for analysis methods and knowledge sources that are better able to adapt to changing vocabulary. Invariably existing sentiment lexicon knowledge cannot usefully handle social media vocabulary which is typically inform
APA, Harvard, Vancouver, ISO, and other styles
27

Farhat, Salman. "Safe Dynamic Reconfiguration of Applications with Features." Electronic Thesis or Diss., Université de Lille (2022-....), 2024. http://www.theses.fr/2024ULILB014.

Full text
Abstract:
Les applications déployées sur des environnement de type Cloud ou sur des systèmes cyber-physiques nécessitent une reconfiguration fréquente pendant leur exécution pour s'adapter à l'évolution des besoins et des exigences, ce qui souligne l'importance des capacités de reconfiguration dynamique. En outre, ces environnements peuvent étendre et modifier leurs services en cours d'exécution, ce qui nécessite une approche compositionnelle pour permettre la modification des configurations. Pour gérer la variabilité de l'architecture des grands systèmes, les modèles de caractéristiques sont largement
APA, Harvard, Vancouver, ISO, and other styles
28

Balan, André Guilherme Ribeiro. "Métodos adaptativos de segmentação aplicados à recuperação de imagens por conteúdo." Universidade de São Paulo, 2007. http://www.teses.usp.br/teses/disponiveis/55/55134/tde-15062007-150711/.

Full text
Abstract:
A possibilidade de armazenamento de imagens no formato digital favoreceu a evolução de diversos ramos de atividades, especialmente as áreas de pesquisa e clínica médica. Ao mesmo tempo, o volume crescente de imagens armazenadas deu origem a um problema de relevância e complexidade consideráveis: a Recuperação de Imagens Baseada em Conteúdo, que, em outras palavras, diz respeito à capacidade de um sistema de armazenamento processar operações de consulta de imagens a partir de características visuais, extraídas automaticamente por meio de métodos computacionais. Das principais questões que const
APA, Harvard, Vancouver, ISO, and other styles
29

Gangireddy, Siva Reddy. "Recurrent neural network language models for automatic speech recognition." Thesis, University of Edinburgh, 2017. http://hdl.handle.net/1842/28990.

Full text
Abstract:
The goal of this thesis is to advance the use of recurrent neural network language models (RNNLMs) for large vocabulary continuous speech recognition (LVCSR). RNNLMs are currently state-of-the-art and shown to consistently reduce the word error rates (WERs) of LVCSR tasks when compared to other language models. In this thesis we propose various advances to RNNLMs. The advances are: improved learning procedures for RNNLMs, enhancing the context, and adaptation of RNNLMs. We learned better parameters by a novel pre-training approach and enhanced the context using prosody and syntactic features.
APA, Harvard, Vancouver, ISO, and other styles
30

Sellami, Akrem. "Interprétation sémantique d'images hyperspectrales basée sur la réduction adaptative de dimensionnalité." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2017. http://www.theses.fr/2017IMTA0037/document.

Full text
Abstract:
L'imagerie hyperspectrale permet d'acquérir des informations spectrales riches d'une scène dans plusieurs centaines, voire milliers de bandes spectrales étroites et contiguës. Cependant, avec le nombre élevé de bandes spectrales, la forte corrélation inter-bandes spectrales et la redondance de l'information spectro-spatiale, l'interprétation de ces données hyperspectrales massives est l'un des défis majeurs pour la communauté scientifique de la télédétection. Dans ce contexte, le grand défi posé est la réduction du nombre de bandes spectrales inutiles, c'est-à-dire de réduire la redondance et
APA, Harvard, Vancouver, ISO, and other styles
31

Evmenova, Anna S. "Lights! Camera! Captions! The effects of picture and/or word captioning adaptations, alternative narration, and interactive features on video comprehension by students with intellectual disabilities /." Fairfax, VA : George Mason University, 2008. http://hdl.handle.net/1920/3071.

Full text
Abstract:
Thesis (Ph.D.)--George Mason University, 2008.<br>Vita: p. 388. Thesis director: Michael M. Behrmann. Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Education. Title from PDF t.p. (viewed July 3, 2008). Includes bibliographical references (p. 349-387). Also issued in print.
APA, Harvard, Vancouver, ISO, and other styles
32

Tomashenko, Natalia. "Speaker adaptation of deep neural network acoustic models using Gaussian mixture model framework in automatic speech recognition systems." Thesis, Le Mans, 2017. http://www.theses.fr/2017LEMA1040/document.

Full text
Abstract:
Les différences entre conditions d'apprentissage et conditions de test peuvent considérablement dégrader la qualité des transcriptions produites par un système de reconnaissance automatique de la parole (RAP). L'adaptation est un moyen efficace pour réduire l'inadéquation entre les modèles du système et les données liées à un locuteur ou un canal acoustique particulier. Il existe deux types dominants de modèles acoustiques utilisés en RAP : les modèles de mélanges gaussiens (GMM) et les réseaux de neurones profonds (DNN). L'approche par modèles de Markov cachés (HMM) combinés à des GMM (GMM-HM
APA, Harvard, Vancouver, ISO, and other styles
33

Lamago, Merlin Ferdinand. "Réingénierie des fonctions des plateformes LMS par l'analyse et la modélisation des activités d'apprentissage : application à des contextes éducatifs avec fracture numérique." Thesis, Bordeaux, 2017. http://www.theses.fr/2017BORD0589/document.

Full text
Abstract:
Cette thèse modélise l’activité d’apprentissage dans les plateformes LMS (Learning Management System) en vue d’optimiser l’efficacité des utilisateurs. Ce projet est né d’une préoccupation pratique, à savoir comment faciliter l’utilisation des plateformes LMS chez les enseignants et apprenants des pays en voie de développement qui font face à la fracture numérique et éducative. Cette recherche aborde le problème de l’adaptabilité des LMS et suppose deux niveaux de modélisation : l’outil d’apprentissage et le contexte d’utilisation projeté. Pour traiter cette question d’adaptabilité, nous procé
APA, Harvard, Vancouver, ISO, and other styles
34

Luo, Guoliang. "Segmentation de maillages dynamiques et son application pour le calcul de similarité." Thesis, Strasbourg, 2014. http://www.theses.fr/2014STRAD026/document.

Full text
Abstract:
Avec le développement important des techniques d’animation, les maillages animés sont devenus un sujet de recherche important en informatique graphique, comme la segmentation de maillages animés ou la compression. Ces maillages animés qui sont créés à l’aide de logiciels ou à partir de données de capture de mouvements sont composés d’une séquence ordonnée de maillages de forme statique et dont la topologie reste la même (nombre fixe de sommets et de triangles). Bien qu’un grand nombre de travaux ont été menés sur les maillages statiques durant les deux dernières décennies, le traitement et la
APA, Harvard, Vancouver, ISO, and other styles
35

Borelli, Helberth. "Uma linguagem de modelagem de domínio específico para linhas de produto de software dinâmicas." Universidade Federal de Goiás, 2016. http://repositorio.bc.ufg.br/tede/handle/tede/5893.

Full text
Abstract:
Submitted by Marlene Santos (marlene.bc.ufg@gmail.com) on 2016-08-09T16:58:08Z No. of bitstreams: 2 Dissertação - Helberth Borelli - 2016.pdf: 5479597 bytes, checksum: c182a5a918e2fda8bf310ba47bc494e4 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)<br>Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2016-08-10T11:31:18Z (GMT) No. of bitstreams: 2 Dissertação - Helberth Borelli - 2016.pdf: 5479597 bytes, checksum: c182a5a918e2fda8bf310ba47bc494e4 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)<br>Made available
APA, Harvard, Vancouver, ISO, and other styles
36

Kachouri, Rostom. "Classification multi-modèles des images dans les bases Hétérogènes." Phd thesis, Université d'Evry-Val d'Essonne, 2010. http://tel.archives-ouvertes.fr/tel-00526649.

Full text
Abstract:
La reconnaissance d'images est un domaine de recherche qui a été largement étudié par la communauté scientifique. Les travaux proposés dans ce cadre s'adressent principalement aux diverses applications des systèmes de vision par ordinateur et à la catégorisation des images issues de plusieurs sources. Dans cette thèse, on s'intéresse particulièrement aux systèmes de reconnaissance d'images par le contenu dans les bases hétérogènes. Les images dans ce type de bases appartiennent à différents concepts et représentent un contenu hétérogène. Pour ce faire, une large description permettant d'assure
APA, Harvard, Vancouver, ISO, and other styles
37

Ferreira, Leite Alessandro. "A user-centered and autonomic multi-cloud architecture for high performance computing applications." Thesis, Paris 11, 2014. http://www.theses.fr/2014PA112355/document.

Full text
Abstract:
Le cloud computing a été considéré comme une option pour exécuter des applications de calcul haute performance. Bien que les plateformes traditionnelles de calcul haute performance telles que les grilles et les supercalculateurs offrent un environnement stable du point de vue des défaillances, des performances, et de la taille des ressources, le cloud computing offre des ressources à la demande, généralement avec des performances imprévisibles mais à des coûts financiers abordables. Pour surmonter les limites d’un cloud individuel, plusieurs clouds peuvent être combinés pour former une fédérat
APA, Harvard, Vancouver, ISO, and other styles
38

Fang, Chao-Chi, and 方肇基. "Speech Recognition by Dynamic Adaptation of Speaker Feature." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/75694878163906105604.

Full text
Abstract:
碩士<br>中原大學<br>資訊工程研究所<br>94<br>This research uses Mel-Frequency Cepstrum Coefficients as the characteristic parameter at voice signal level. And making use of Discrete Hidden Markov Model constructs the monosyllabic model related to the speaker. After accumulating certain amounts of speaker models, we can dynamically generate a speaker model to nonspecific speaker by adopting the characteristic of the speaker, and execute the recognition of syllable cuttings and syllable models by continuing utilizing One Stage Dynamic Processing Algorithm. For the adoption of the speaker's pronunciation chara
APA, Harvard, Vancouver, ISO, and other styles
39

Chen, Chia-Hsin, and 陳佳欣. "Mandarin Syllable Recognition Based on Landmark Knowledge and Dynamic Feature Adaptation." Thesis, 1997. http://ndltd.ncl.edu.tw/handle/35990480683718161884.

Full text
Abstract:
碩士<br>國立臺灣大學<br>電機工程學系<br>85<br>For speech recognition research, there are two main approaches. One isknowledge based approach, the other is statistics approach. In this thesis,landmark knowledge is included into a statistics based system to enhance theperformance of the system. In the fist part of the thesis, landmark detection algorithm is developed.From the experiment result, the detection rate is higher than 88% for the 3test speakers. In the second part of the thesis, landmark knowle
APA, Harvard, Vancouver, ISO, and other styles
40

Hung, Ying-Ning, and 洪穎寧. "A Domain Adaptation Method Based on Feature-disentangling Generative Adversarial Networks." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/yft79s.

Full text
Abstract:
碩士<br>國立臺灣海洋大學<br>資訊工程學系<br>107<br>The purpose of this thesis focuses on the domain adaptation effects of a specific feature-disentangling generative adversarial networks, in which the characteristics of handwritten digit images are disentangled into class and style features automatically. The class characteristics consist of primarily the invariant information relevant to distinguish ten digits and the style characteristics contain other information common to all images like colors, fonts, thickness, and angles, etc. The training algorithm extracts the class-relevant feature vectors directly
APA, Harvard, Vancouver, ISO, and other styles
41

Wu, Chun Hsin, and 吳俊欣. "A Speaker Adaptation Method Based on MFCC Feature Space Coordinate System Mapping." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/26805190317076600956.

Full text
Abstract:
碩士<br>國立臺灣科技大學<br>資訊工程系<br>91<br>In this thesis, a speaker adaptation method is developed. This method needs only a small quantity of training utterances because the adaptation mechanism is operated on the level of MFCC feature parameter. First, an individual coordinate system is built for each new speaker in order that his MFCC feature vectors can be decomposed into coordinate coefficients of the system. Then, the coordinate coefficients are directly mapped as coefficients of the coordinate system for a target person. Even though this mechanism is simple, it can indeed obtain good adaptation
APA, Harvard, Vancouver, ISO, and other styles
42

Mazloom, Reza. "Classification of Twitter disaster data using a hybrid feature-instance adaptation approach." Thesis, 2018. http://hdl.handle.net/2097/38872.

Full text
Abstract:
Master of Science<br>Department of Computer Science<br>Doina Caragea<br>Huge amounts of data that are generated on social media during emergency situations are regarded as troves of critical information. The use of supervised machine learning techniques in the early stages of a disaster is challenged by the lack of labeled data for that particular disaster. Furthermore, supervised models trained on labeled data from a prior disaster may not produce accurate results. To address these challenges, domain adaptation approaches, which learn models for predicting the target, by using unlabeled da
APA, Harvard, Vancouver, ISO, and other styles
43

Chien, Yu-Lin, and 簡友琳. "Machine Learning Based Rate Adaptation with Elastic Feature Selection for HTTP-Based Streaming." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/59932945918614891709.

Full text
Abstract:
碩士<br>國立臺灣大學<br>電機工程學研究所<br>103<br>Dynamic Adaptive Streaming over HTTP (DASH) has become an emerging application nowadays. Video rate adaptation is a key to determine the video quality of HTTP-based media streaming. Recent works have proposed several algorithms that allow a DASH client to adapt its video encoding rate to network dynamics. While network conditions are typically affected by many different factors, these algorithms however usually consider only a few representative information, e.g., predicted available bandwidth or fullness of its playback buffer. In addition, the error in band
APA, Harvard, Vancouver, ISO, and other styles
44

Prabuchandran, K. J. "Feature Adaptation Algorithms for Reinforcement Learning with Applications to Wireless Sensor Networks And Road Traffic Control." Thesis, 2016. http://etd.iisc.ac.in/handle/2005/2664.

Full text
Abstract:
Many sequential decision making problems under uncertainty arising in engineering, science and economics are often modelled as Markov Decision Processes (MDPs). In the setting of MDPs, the goal is to and a state dependent optimal sequence of actions that minimizes a certain long-term performance criterion. The standard dynamic programming approach to solve an MDP for the optimal decisions requires a complete model of the MDP and is computationally feasible only for small state-action MDPs. Reinforcement learning (RL) methods, on the other hand, are model-free simulation based approaches for so
APA, Harvard, Vancouver, ISO, and other styles
45

Prabuchandran, K. J. "Feature Adaptation Algorithms for Reinforcement Learning with Applications to Wireless Sensor Networks And Road Traffic Control." Thesis, 2016. http://etd.iisc.ernet.in/handle/2005/2664.

Full text
Abstract:
Many sequential decision making problems under uncertainty arising in engineering, science and economics are often modelled as Markov Decision Processes (MDPs). In the setting of MDPs, the goal is to and a state dependent optimal sequence of actions that minimizes a certain long-term performance criterion. The standard dynamic programming approach to solve an MDP for the optimal decisions requires a complete model of the MDP and is computationally feasible only for small state-action MDPs. Reinforcement learning (RL) methods, on the other hand, are model-free simulation based approaches for so
APA, Harvard, Vancouver, ISO, and other styles
46

Peng, Xingchao. "Domain adaptive learning with disentangled features." Thesis, 2020. https://hdl.handle.net/2144/42065.

Full text
Abstract:
Recognizing visual information is crucial for many real artificial-intelligence-based applications, ranging from domestic robots to autonomous vehicles. However, the success of deep learning methods on visual recognition tasks is highly dependent on access to large-scale labeled datasets, which are expensive and cumbersome to collect. Transfer learning provides a way to alleviate the burden of annotating data, which transfers the knowledge learned from a rich-labeled source domain to a scarce-labeled target domain. However, the performance of deep learning models degrades significantly when te
APA, Harvard, Vancouver, ISO, and other styles
47

McCarthy, CL. "Are we who we watch? : Adapting multiculturalism as national heritage in Australian feature film–1992 to 2017." Thesis, 2020. https://eprints.utas.edu.au/35135/1/McCarthy_whole_thesis.pdf.

Full text
Abstract:
In the 1970s Australia embarked on two nation-building projects. One was a new cultural policy called “multiculturalism”, the other, public funding for a “national” film industry. As film rose in prominence as a national storyteller from the 1990s onwards, multicultural narratives became a way of re-imagining Australia on screen as culturally diverse. While there is extensive research into the history of migration and the success or failure of Australian multicultural policy, little has been said about its representation in film as a source of national heritage. To address this gap, this thes
APA, Harvard, Vancouver, ISO, and other styles
48

Nemri, Abdellatif. "Codage de l’information visuelle par la plasticité et la synchronisation des réponses neuronales dans le cortex visuel primaire du chat." Thèse, 2010. http://hdl.handle.net/1866/4756.

Full text
Abstract:
Les systèmes sensoriels encodent l’information sur notre environnement sous la forme d’impulsions électriques qui se propagent dans des réseaux de neurones. Élucider le code neuronal – les principes par lesquels l’information est représentée dans l’activité des neurones – est une question fondamentale des neurosciences. Cette thèse constituée de 3 études (E) s’intéresse à deux types de codes, la synchronisation et l’adaptation, dans les neurones du cortex visuel primaire (V1) du chat. Au niveau de V1, les neurones sont sélectifs pour des propriétés comme l’orientation des contours, la directi
APA, Harvard, Vancouver, ISO, and other styles
49

Hu, Shu-E., and 胡淑娥. "The relationship of cognitive features, coping, and adaptation in rheumatoid arthritis patients." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/vpx4m7.

Full text
Abstract:
碩士<br>中原大學<br>心理學研究所<br>93<br>ABSTRACT Derived the concepts of self-regulation and positive psychology, this study purposed to establish a hypothetical model about the coping and adaptation of the rheumatoid arthritis patients, and to examine the relations among four groups of variables of this model, which are expectation discrepancy, cognitive expectancy, coping types and adaptational outcomes. The study has been divided into three stages, Firstly, using analysis semistructure questions by interviewed with the rheumatoid arthritis patients, the researcher compiled two questionnaires, the
APA, Harvard, Vancouver, ISO, and other styles
50

Barrowman, Hannah M. "Assessing emerging governance features for community-based adaptation in Timor-Leste and Indonesia: What works and why?" Phd thesis, 2018. http://hdl.handle.net/1885/149421.

Full text
Abstract:
Community-based adaptation (CBA) aims to address local vulnerabilities and build the adaptive capacities of rural, remote and/or poor communities to plan for, and cope with, the impacts of future climate changes. Despite its growing popularity in international development, recent experience indicates that CBA interventions are rarely sustained past their project life cycle and often fail to reduce vulnerability. To address these challenges, calls have been made to embed CBA interventions into governance systems that engage stakeholder groups and ins
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the bibliographies on the topic 'Feature Adaptation' for other source types:
Journal articles Books
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography