Dissertations / Theses on the topic 'Information binaire'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Information binaire.'
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.
Shams, Bilal. "Codes LDPC non-binaire de nouvelle generation." Phd thesis, Université de Cergy Pontoise, 2010. http://tel.archives-ouvertes.fr/tel-00766409.
Full textKatz, Gil. "Détection binaire distribuée sous contraintes de communication." Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLC001/document.
Full textIn recents years, interest has been growing in research of different autonomous systems. From the self-dring car to the Internet of Things (IoT), it is clear that the ability of automated systems to make autonomous decisions in a timely manner is crucial in the 21st century. These systems will often operate under stricts constains over their resources. In this thesis, an information-theoric approach is taken to this problem, in hope that a fundamental understanding of the limitations and perspectives of such systems can help future engineers in designing them.Throughout this thesis, collaborative distributed binary decision problems are considered. Two statisticians are required to declare the correct probability measure of two jointly distributed memoryless process, denoted by $vct{X}^n=(X_1,dots,X_n)$ and $vct{Y}^n=(Y_1,dots,Y_n)$, out of two possible probability measures on finite alphabets, namely $P_{XY}$ and $P_{bar{X}bar{Y}}$. The marginal samples given by $vct{X}^n$ and $vct{Y}^n$ are assumed to be available at different locations.The statisticians are allowed to exchange limited amounts of data over a perfect channel with a maximum-rate constraint. Throughout the thesis, the nature of communication varies. First, only unidirectional communication is allowed. Using its own observations, the receiver of this communication is required to first identify the legitimacy of its sender by declaring the joint distribution of the process, and then depending on such authentication it generates an adequate reconstruction of the observations satisfying an average per-letter distortion. Bidirectional communication is subsequently considered, in a scenario that allows interactive communication between the participants
Crochet, Philippe. "Une approche lagrangienne pour caractériser la variabilité spatiale des champs de pluie : application à l'estimation des lames d'eau moyennes au Sahel, à partir d'une information binaire." Université Joseph Fourier (Grenoble ; 1971-2015), 1995. http://www.theses.fr/1995GRE10028.
Full textBecker, Jean-Marie. "Contribution à l'analyse d'images par des marches quadrantales." Saint-Etienne, 1991. http://www.theses.fr/1991STET4011.
Full textHernandez, Sierra Gabriel. "Métodos de representación y verificación del locutor con independencia del texto." Thesis, Avignon, 2014. http://www.theses.fr/2014AVIG0203/document.
Full textText-independent automatic speaker recognition is a recent method in biometric area. Its increasing interest is reflected both in the increasing participation in international competitions and in the performance progresses. Moreover, the accuracy of the methods is still limited by the quantity of speaker discriminant information contained in the representations of speech utterances. This thesis presents a study on speech representation for speaker recognition systems. It shows firstly two main weaknesses. First, it fails to take into account the temporal behavior of the voice, which is known to contain speaker discriminant information. Secondly, speech events rare in a large population of speakers although very present for a given speaker are hardly taken into account by these approaches, which is contradictory when the goal is to discriminate among speakers.In order to overpass these limitations, we propose in this thesis a new speech representation for speaker recognition. This method represents each acoustic vector in a a binary space which is intrinsically speaker discriminant. A similarity measure associated with a global representation (cumulative vectors) is also proposed. This new speech utterance representation is able to represent infrequent but discriminant events and to work on temporal information. It allows also to take advantage of existing « session » variability compensation approaches (« session » variability represents all the negative variability factors). In this area, we proposed also several improvements to the usual session compensation algorithms. An original solution to deal with the temporal information inside the binary speech representation was also proposed. Thanks to a linear fusion approach between the two sources of information, we demonstrated the complementary nature of the temporal information versus the classical time independent representations
El reconocimiento automático del locutor independiente del texto, es un método dereciente incorporación en los sistemas biométricos. El desarrollo y auge del mismo serefleja en las competencias internacionales, pero aun la eficacia de los métodos de reconocimientose encuentra afectada por la cantidad de información discriminatoria dellocutor que esta presente en las representaciones actuales de las expresiones de voz.En esta tesis se realizó un estudio donde se identificaron dos principales debilidadespresentes en las representaciones actuales del locutor. En primer lugar, no se tiene encuenta el comportamiento temporal de la voz, siendo este un rasgo discriminatorio dellocutor y en segundo lugar los eventos pocos frecuentes dentro de una población delocutores pero frecuentes en un locutor dado, apenas son tenidos en cuenta por estosenfoques, lo cual es contradictorio cuando el objetivo es discriminar los locutores. Motivadopor la solución de estos problemas, se confirmó la redundancia de informaciónexistente en las representaciones actuales y la necesidad de emplear nuevas representacionesde las expresiones de voz. Se propuso un nuevo enfoque con el desarrollo de unmétodo para la obtención de un modelo generador capaz de transformar la representación actual del espacio acústico a una representación en un espacio binario, dondese propuso una medida de similitud asociada con una representación global (vectoracumulativo) que contiene tanto los eventos frecuentes como los pocos frecuentes enuna expresión de voz. Para la compensación de la variabilidad de sesión se incorporóen la matriz de dispersión intra-clase, la información común de la población de locutores,lo que implicó la modificación de tres algoritmos de la literatura que mejoraronsu desempeño respecto a la eficacia en el reconocimiento del locutor, tanto utilizandoel nuevo enfoque propuesto como el enfoque actual de referencia. La información temporalexistente en las expresiones de voz fue capturada e incorporada en una nuevarepresentación, mejorando aun más la eficacia del enfoque propuesto. Finalmente sepropuso y evaluó una fusión lineal entre los dos enfoques que demostró la informacióncomplementaria existente entre ellos, obteniéndose los mejores resultados de eficaciaen el reconocimiento del locutor
Minard, Anne-Lyse. "Extraction de relations en domaine de spécialité." Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00777749.
Full textChenon, Christophe. "Vers une meilleure utilisabilité des mémoires de traduction, fondée sur un alignement sous-phrastique." Phd thesis, Université Joseph Fourier (Grenoble), 2005. http://tel.archives-ouvertes.fr/tel-00012126.
Full textPourtant ces mémoires recèlent des gisements d'information importants au niveau sous-phrastique dont les utilisateurs ne peuvent pas bénéficier. Le formalisme TransTree permet de représenter des correspondances sous-segmentales enchassées bilingues. Ces correspondances complexes (les amphigrammes) forment une structure arborescente exprimable en XML. Une transformation de surface conduit à une visualisation dynamique mettant en évidence les différents niveaux de correspondance entre sous-segments.
TransTree s'accompagne d'une méthode générale de construction par voie statistique, fondée sur les arbres binaires de sécabilité. Cette méthode permet d'établir des amphigrammes à partir des correspondances entre mots typographiques. Il est possible d'abstraire des patrons de traduction (amphigrammes génériques) par classification des exemples rencontrés dans le corpus.
Quelques expérimentations ont été effectuées pour valider le pouvoir d'expression du formalisme, explorer différentes options de construction et esquisser un algorithme de reconstitution d'un segment cible à partir d'un segment source inconnu avec la connaissance extraite des mémoires de traduction.
Kelan, Elisabeth Kristina. "Binary logic? : doing gender in information communication technology work." Thesis, London School of Economics and Political Science (University of London), 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.429370.
Full textSassatelli, Lucile. "Codes LDPC multi-binaires hybrides et méthodes de décodage itératif." Phd thesis, Université de Cergy Pontoise, 2008. http://tel.archives-ouvertes.fr/tel-00819413.
Full textVäyrynen, A. (Antti). "Finding third-party components with binary analysis." Master's thesis, University of Oulu, 2015. http://urn.fi/URN:NBN:fi:oulu-201504161389.
Full textFaris, Peter D. "Risk adjustment with binary outcomes when covariate information is incomplete." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape2/PQDD_0021/NQ49492.pdf.
Full textMorrison, Jeffrey Glenn. "The effects of hue and contrast on binary classification." Thesis, Georgia Institute of Technology, 1987. http://hdl.handle.net/1853/28758.
Full textChau, Ka-ki, and 周嘉琪. "Informative drop-out models for longitudinal binary data." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2003. http://hub.hku.hk/bib/B2962714X.
Full textZaumsegel, Daniel [Verfasser]. "Binary polymorphisms as ancestry informative markers / Daniel Zaumsegel." Köln : Deutsche Zentralbibliothek für Medizin, 2013. http://d-nb.info/1046231766/34.
Full textMöller, Nils. "Binary Large Objects i MongoDB och MariaDB : En komparativ studie över komplexitet och prestanda." Thesis, Karlstads universitet, Handelshögskolan (from 2013), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-78472.
Full textGorgolione, Matteo. "Analyse et construction de codes LDPC non-binaires pour des canaux à évanouissement." Phd thesis, Université de Cergy Pontoise, 2012. http://tel.archives-ouvertes.fr/tel-00819415.
Full textBenachour, Phillip. "Trellis decoding techniques for the multiple access binary adder channel." Thesis, Lancaster University, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.314240.
Full textWyrwas, Richard R. "Coding for binary image transmission over land mobile radio channels." Thesis, University of Manchester, 1988. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.328313.
Full textKaipala, J. (Jukka). "Automatic segmentation of bone tissue from computed tomography using a volumetric local binary patterns based method." Master's thesis, University of Oulu, 2018. http://urn.fi/URN:NBN:fi:oulu-201802101221.
Full textSkannattujen kudosrakenteiden segmentointi kolmiulotteisista (3D) tomografiakuvista tehdään usein ainakin osittain manuaalisesti, sillä standardoitua automaattista menetelmää ei ole. Täysin automatisoitujen lähestymistapojen kehitys on tarpeen, sillä se parantaisi sekä segmentoinnin objektiivisuutta että sen kokonaisnopeutta. Tässä työssä laajennamme automatisoitua local binary patterns (LBP) -perustaista trabekulaarisen luun 3D-segmentointimenetelmää adaptiivisella paikallisella kynnystyksellä ja segmentoinnin lisäparametreilla tavoitteenamme vahvistaa menetelmää mutta säilyttää silti riittävä suorituskyky verrattuna perinteiseen käyttäjäavusteiseen segmentointiin. Arvioimme koejärjestelyssämme parametrit uudelle automatisoidulle adaptiiviselle moniasteikkoiselle LBP-pohjaiselle 3Dsegmentointimenetelmälle (AMLM), ja teetämme sekä AMLM:n avulla että kahden kokeneen käyttäjän toimesta binäärisegmentoinnit kahdelle mikrotietokonetomografialla (μTT) tuotetulle kuvalle naudan trabekulaarisesta luukudoksesta. Tulosten vertailu osoittaa AMLM:n suorituskyvyltään selkeästi paremmaksi, mikä antaa vahvan viitteen tämän menetelmän soveltuvuudesta automatisoituun luusegmentointiin
Yakdan, Khaled [Verfasser]. "A Human-Centric Approach For Binary Code Decompilation / Khaled Yakdan." Bonn : Universitäts- und Landesbibliothek Bonn, 2018. http://d-nb.info/1160594139/34.
Full textJiang, Tao. "Information Approach for Change Point Detection of Weibull Models with Applications." Bowling Green State University / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=bgsu1434382384.
Full textKizhakkumkara, Muhamad Raees. "Polar Codes for secure binary Wyner-Ziv source coding." Thesis, KTH, Teknisk informationsvetenskap, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-215091.
Full textKällkodning, som ursprungligen planerades av Claude Shannon är 1948 i sittlandmärkes paper "A Mathematical Theory of Communication" var opraktiskför det mesta av 1900 talet. Men era framsteg gjordes i kodningsteoridär de senaste Polarkoderna infördes av Erdal Arikan 2008 är mycket lovande.Polära koder har blygsamma kodnings- och avkodningskomplexiteter,samtidigt som de ger en konstruktion som direkt leder till de grundläggandegränserna som erhållits av Shannon. Vi går vidare in i informationsåldern,där videoklipp med hög upplösning streamas över Internet och olika enhetersamlar massiva datamängder medan de är anslutna till varandrar i kommunikationsnät. Därför är den praktiska implikationen av ett effektivt och säkertkällkodningssystem väsentligt. I den här avhandlingen implementerar vi ettkällkodproblem som kallas den gemensamma hjälpen i ett Wyner-Ziv-nätverkmed polarkoder. Dessutom leder ovanstående konstruktion till en förlustfullkomprimering av en Bernoulli-källa och kan ge en inblick i hur man utvecklareffektiv förlustkällkomprimering över ett mer generellt nätverk.
Kozma, László [Verfasser], and Raimund [Akademischer Betreuer] Seidel. "Binary search trees, rectangles and patterns / László Kozma ; Betreuer: Raimund Seidel." Saarbrücken : Saarländische Universitäts- und Landesbibliothek, 2016. http://d-nb.info/1114735019/34.
Full textEkberg, Joakim. "Geometries of Binary Constant Weight Codes." Thesis, Karlstad University, Division for Engineering Sciences, Physics and Mathematics, 2006. http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-88.
Full textThis thesis shows how certain classes of binary constant weight codes can be represented geometrically using linear structures in Euclidean space. The geometric treatment is concerned mostly with codes with minimum distance 2(w - 1), that is, where any two codewords coincide in at most one entry; an algebraic generalization of parts of the theory also applies to some codes without this property. The presented theorems lead to a total of 18 improvements of the table of lower bounds on A(n,d,w) maintained by E. M. Rains and N. J. A. Sloane. Additional improvements have been made by finding new lexicographic codes.
Thangaraj, Andrew. "Iterative coding methods for the binary symmetric channel and magnetic recording channel." Diss., Georgia Institute of Technology, 2003. http://hdl.handle.net/1853/13387.
Full textSwaminathan, Jayashree. "Decoding algorithms for binary BCH and Reed-Solomon codes." Ohio : Ohio University, 1995. http://www.ohiolink.edu/etd/view.cgi?ohiou1178905628.
Full textVizenor, Katie Virginia. "Binary Lives| Digital Citizenship and Disability Participation in a User Content Created Virtual World." Thesis, State University of New York at Buffalo, 2014. http://pqdtopen.proquest.com/#viewpdf?dispub=3613110.
Full textDigital Citizenship is a concept typically used in discussions of how technology impacts our relationships with others and our physical world communities. It is also used to describe ways that we can leverage our technology use and skill to make our communities and nations better and stronger. Educators are now teaching "good digital citizenship" as part of a larger civics curriculum.
But, there is a second, emerging concept that I refer to as platform specific digital citizenship. I define this platform specific citizenship as the deep and abiding commitment and sense of responsibility that people develop in relation to a particular technology, such as software or technology brand. It may also refer to the ideas that people express in regard to how technology should ideally be used and what rights and responsibilities it requires of its adherents.
Massively Multiplayer Online Worlds (MMOWs) are one place researchers are finding this deep, platform specific digital citizenship emerging. These are persistent digital universes where people from all over the world develop online personas, leadership structures, discussion forums, and business and non-profit entities. The ability and extent to which this online organization is possible is largely due to the underlying structure, rules and allowances of the world of which people choose to be a part.
One online world, Second Life, has a large, active and vocal disabled population. They have committed to this environment because of the unique opportunities and freedoms that it provides. As a user content created environment, residents, as Second Life participants are referred to, are given an unprecedented amount of freedom to create the kind of experience they want. This may involve developing relationships and projects with other disabled residents. It can also involve exploring other aspects of themselves and their interests that are often neglected in their real lives due to social exclusion, and/or lack of financial and physical access.
Most of the research and popular media examinations of disability in Second Life centers on participation in disability specific communities or the benefits of identity exploration through avatar design. But, the reasons disabled people stay here is much broader and varied than what this limited discussion suggests. Commitment to Second Life is strong precisely because disability community commitment and disability expression are not the only options but exist among a wide range of choices. Moreover, the expression of disability and use of such mediated environments is constantly debated in both word and deed.
This dissertation explores the concept of digital citizenship and why people that identify as disabled in real life are attracted to committed participation in virtual worlds, in particular, Second Life. What opportunities and rights are disabled people afforded here through the technology structure? What are the avenues of entry into the Second Life community, and what does the variety of these entry points and special interest sub-communities tell us about what is important to them? How is commitment debated and deepened through the use of public spaces and forums? And, what can researchers, public health and information professionals learn from these features that can improve their own outreach?
Bhatt, Manish. "Leveraging Relocations in ELF-binaries for Linux Kernel Version Identification." ScholarWorks@UNO, 2018. https://scholarworks.uno.edu/td/2528.
Full textStollenwerk, Alexander Verfasser], Sjoerd [Akademischer Betreuer] Dirksen, and Holger [Akademischer Betreuer] [Rauhut. "One-bit compressed sensing and fast binary embeddings / Alexander Stollenwerk ; Sjoerd Dirksen, Holger Rauhut." Aachen : Universitätsbibliothek der RWTH Aachen, 2019. http://d-nb.info/1215927878/34.
Full textStollenwerk, Alexander [Verfasser], Sjoerd Akademischer Betreuer] Dirksen, and Holger [Akademischer Betreuer] [Rauhut. "One-bit compressed sensing and fast binary embeddings / Alexander Stollenwerk ; Sjoerd Dirksen, Holger Rauhut." Aachen : Universitätsbibliothek der RWTH Aachen, 2019. http://d-nb.info/1215927878/34.
Full textBen, Khadra Mohamed Ammar [Verfasser], and Wolfgang [Akademischer Betreuer] Kunz. "Techniques For Efficient Binary-Level Coverage Analysis / Mohamed Ammar Ben Khadra ; Betreuer: Wolfgang Kunz." Kaiserslautern : Technische Universität Kaiserslautern, 2021. http://d-nb.info/1236571959/34.
Full textGröpl, Clemens. "Binary Decision Diagrams for Random Boolean Functions." Doctoral thesis, Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät II, 1999. http://dx.doi.org/10.18452/14357.
Full textBinary Decision Diagrams (BDDs) are a data structure for Boolean functions which are also known as branching programs. In ordered binary decision diagrams (OBDDs), the tests have to obey a fixed variable ordering. In free binary decision diagrams (FBDDs), each variable can be tested at most once. The efficiency of new variants of the BDD concept is usually demonstrated with spectacular (worst-case) examples. We pursue another approach and compare the representation sizes of almost all Boolean functions. Whereas I. Wegener proved that for `most' values of n the expected OBDD size of a random Boolean function of n variables is equal to the worst-case size up to terms of lower order, we show that this is not the case for n within intervals of constant length around the values n = 2h + h. Furthermore, ranges of n exist for which minimal FBDDs are almost always at least a constant factor smaller than minimal OBDDs. Our main theorems have doubly exponentially small probability bounds (in n). We also investigate the evolution of random OBDDs and their worst-case size, revealing an oscillating behaviour that explains why certain results cannot be improved in general.
Turkmani, A. M. D. "Empirical and theoretical methods of BER prediction in binary FSK communication systems subjected to impulsive noise." Thesis, University of Liverpool, 1985. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.333098.
Full textIsawhe, Boladale Modupe. "Sequential frame synchronization over binary symmetrical channel for unequally distributed data symbols." Thesis, Kingston University, 2017. http://eprints.kingston.ac.uk/39287/.
Full textMartinek, Václav. "Rozpoznávání hudebních coververzí pomocí technik Music Information Retrieval." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2021. http://www.nusl.cz/ntk/nusl-442587.
Full textGarrammone, Giuliano [Verfasser]. "Non-Binary Codes with Applications to Satellite and Space Communications / Giuliano Garrammone." München : Verlag Dr. Hut, 2015. http://d-nb.info/1074063392/34.
Full textTanatmis, Akin [Verfasser], and Stefan [Akademischer Betreuer] Ruzika. "Mathematical Programming Approaches for Decoding of Binary Linear Codes / Akin Tanatmis. Betreuer: Stefan Ruzika." Kaiserslautern : Universitätsbibliothek Kaiserslautern, 2011. http://d-nb.info/1012812421/34.
Full textRaach, Alexander. "A Bayesian semiparametric latent variable model for binary, ordinal and continuous response." Diss., lmu, 2006. http://nbn-resolving.de/urn:nbn:de:bvb:19-48301.
Full textLubenko, Ivans. "Towards robust steganalysis : binary classifiers and large, heterogeneous data." Thesis, University of Oxford, 2013. http://ora.ox.ac.uk/objects/uuid:c1ae44b8-94da-438d-b318-f038ad6aac57.
Full textStinner, Markus Christian [Verfasser]. "Analysis of Spatially Coupled LDPC Codes on the Binary Erasure Channel / Markus Christian Stinner." München : Verlag Dr. Hut, 2016. http://d-nb.info/1122524463/34.
Full textKranz, Julian [Verfasser], Helmut [Akademischer Betreuer] Seidl, Antoine [Gutachter] Miné, and Helmut [Gutachter] Seidl. "Binary Analysis using On-Demand Tabulation of Function Summaries / Julian Kranz ; Gutachter: Antoine Miné, Helmut Seidl ; Betreuer: Helmut Seidl." München : Universitätsbibliothek der TU München, 2019. http://d-nb.info/1186256745/34.
Full textGarmany, Behrad [Verfasser], Thorsten [Gutachter] Holz, and Konrad [Gutachter] Rieck. "MENTALESE - an architecture-agnostic analysis framework for binary executables / Behrad Garmany ; Gutachter: Thorsten Holz, Konrad Rieck ; Fakultät für Elektrotechnik und Informationstechnik." Bochum : Ruhr-Universität Bochum, 2021. http://d-nb.info/123423694X/34.
Full textPareschi, Federico. "Applying partial virtualization on ELF binaries through dynamic loaders." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2013. http://amslaurea.unibo.it/5065/.
Full textMiklánek, Štěpán. "Určení místa původu hudebních interpretací české komorní a orchestrální hudby za pomoci technik Music Information Retrieval." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2019. http://www.nusl.cz/ntk/nusl-401985.
Full textBorokhovych, Yevgen [Verfasser], and Rolf [Akademischer Betreuer] Kraemer. "High-speed data capturing components for Super Resolution Maximum Length Binary Sequence UWB Radar / Yevgen Borokhovych. Betreuer: Rolf Kraemer." Cottbus : Universitätsbibliothek der BTU Cottbus, 2012. http://d-nb.info/1023040662/34.
Full textNeumann, Ursula [Verfasser], Dmitrij [Akademischer Betreuer] Frischmann, Dominik [Gutachter] Heider, and Dmitrij [Gutachter] Frischmann. "Stability and Accuracy Analysis of a Feature Selection Ensemble for Binary Classification in Biomedical Datasets / Ursula Neumann ; Gutachter: Dominik Heider, Dmitrij Frischmann ; Betreuer: Dmitrij Frischmann." München : Universitätsbibliothek der TU München, 2018. http://d-nb.info/1154931641/34.
Full textNordén, Frans, and Reis Marlevi Filip von. "A Comparative Analysis of Machine Learning Algorithms in Binary Facial Expression Recognition." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-254259.
Full textStaberg, Pontus. "Using Anomaly Detection to Identify Rejected Media Plans in Advertisement Planning : A feasibility study of using one-class classification and binary classification with artificially generated outliers to identify media plans most likely to be rejected." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-280581.
Full textMediaplanering kan vara en lång och komplicerad process. En mediaplan är en konsoliderad version av hur en mediainvestering ska distribueras beroende på annonsörens kravspecifikation. Annonsören måste godkänna mediaplanen innan den köps av mediabyrån; denna process kan ta långt tid. Den här masteruppsatsen jämför oövervakad med övervakad inlärning för att avgöra om maskininlärning kan användas för att identifiera mediaplaner som kommer att få avslag av annonsören. En samling av enklass- och binärklassificerare tränades och jämfördes på en oberoende mängd riktiga nekade mediaplaner. Det visas att en oövervakad one-class support vector machine, med ett recall på 0.69 och en precision på 0.77, kan identifiera mediaplaner som med stor sannolikhet kommer att få avslag. Det visas även att mediaplaner som agerar okaraktäristiskt kan modelleras genom att generera punkter nära beslutsytan av godkända mediaplaner. Med den artificiella datan tränades en binärklassificerare och fick liknande resultat som one-class support vector machine. En parameterranking genomfördes för att öka förståelsen av modellerna. Slutsatsen är att både oövervakad och övervakad inlärning med artificiella datapunkter presterar likvärdigt och kan båda identifiera mediaplaner med ökad sannolikhet att bli nekade. Det ska noteras att testmängden var begränsad och att mer data behövs för att öka resultatets statistiska signifikans.
Mohanty, Pragyan Paramita. "Function-based Algorithms for Biological Sequences." OpenSIUC, 2015. https://opensiuc.lib.siu.edu/dissertations/1120.
Full textSeger, Cedric. "An investigation of categorical variable encoding techniques in machine learning: binary versus one-hot and feature hashing." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-237426.
Full textMaskininlärningsmetoder kan användas för att lösa viktiga binära klassificeringsuppgifter i domäner som displayannonsering och rekommendationssystem. I många av dessa domäner är kategoriska variabler vanliga och ofta av hög kardinalitet. Användning av one-hot-kodning under sådana omständigheter leder till väldigt högdimensionella vektorrepresentationer. Detta orsakar minnesoch beräkningsproblem för maskininlärningsmodeller. Denna uppsats undersökte användbarheten för ett binärt kodningsschema där kategoriska värden var avbildade på heltalvärden som sedan kodades i ett binärt format. Detta binära system tillät att representera kategoriska värden med hjälp av log2(d) -dimensionella vektorer, där d är dimensionen förknippad med en one-hot kodning. För att utvärdera prestandan för den binära kodningen jämfördes den mot one-hot och en hashbaserad kodning. En linjär logistikregression och ett neuralt nätverk tränades med hjälp av data från två offentligt tillgängliga dataset: Criteo och Census, och den slutliga prestandan jämfördes. Resultaten visade att en one-hot kodning med en linjär logistisk regressionsmodell gav den bästa prestandan enligt PR-AUC måttet. Denna metod använde dock 118 och 65,953 dimensionella vektorrepresentationer för Census respektive Criteo. En binär kodning ledde till en lägre prestanda generellt, men använde endast 35 respektive 316 dimensioner. Den binära kodningen presterade väsentligt sämre specifikt för Criteo datan, istället var hashbaserade kodningen en mer attraktiv lösning. Försämringen i prestationen associerad med binär och hashbaserad kodning kunde mildras av att använda ett neuralt nätverk.