• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 17
  • 3
  • 1
  • Tagged with
  • 25
  • 25
  • 25
  • 25
  • 11
  • 6
  • 5
  • 5
  • 5
  • 4
  • 4
  • 4
  • 4
  • 4
  • 4
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
11

AIRS: a resource limited artificial immune classifier

Watkins, Andrew B. January 2001 (has links)
Thesis (M.S.)--Mississippi State University. Department of Computer Science. / Title from title screen. Includes bibliographical references.
12

Application of Artificial Intelligence/Machine Learning for Cardiovascular Diseases

Aryal, Sachin January 2021 (has links)
No description available.
13

Text Classificaton In Turkish Marketing Domain And Context-sensitive Ad Distribution

Engin, Melih 01 February 2009 (has links) (PDF)
Online advertising has a continuously increasing popularity. Target audience of this new advertising method is huge. Additionally, there is another rapidly growing and crowded group related to internet advertising that consists of web publishers. Contextual advertising systems make it easier for publishers to present online ads on their web sites, since these online marketing systems automatically divert ads to web sites with related contents. Web publishers join ad networks and gain revenue by enabling ads to be displayed on their sites. Therefore, the accuracy of automated ad systems in determining ad-context relevance is crucial. In this thesis we construct a method for semantic classification of web site contexts in Turkish language and develop an ad serving system to display context related ads on web documents. The classification method uses both semantic and statistical techniques. The method is supervised, and therefore, needs processed sample data for learning classification rules. Therefore, we generate a Turkish marketing dataset and use it in our classification approaches. We form successful classification methods using different feature spaces and support vector machine configurations. Our results present a good comparison between these methods.
14

Boot camp for cognitive systems a model for preparing systems with machine learning for deployment /

Lange, Douglas S. January 2007 (has links) (PDF)
Dissertation (Ph.D. in Software Engineering)--Naval Postgraduate School, March 2007.D / Dissertation supervisor: Berzins, Valdis. "March 2007." Description based on title screen as viewed on April 14, 2010. DTIC Descriptors: Software Engineering, Cognition, Learning Machines, Artificial Intelligence, Computer Programming, Simulation, Military Training, Vision, User Needs, Patterns, Employment, Command And Control Systems, Humans. DTIC Identifier(s): Software Engineering, Cognitive Systems, Machine Learning, Simulation, System Deployment, Artificial Intelligence, System Evaluation, Software Evaluation. Author(s) subject terms: Software Engineering, Cognitive Systems, Machine Learning, Simulation, System Deployment, Artificial Intelligence, System Evaluation, Software Evaluation. Includes bibliographical references (p. 395-399). Also available in print.
15

Detection of Non-Ferrous Materials with Computer Vision

Almin, Fredrik January 2020 (has links)
In one of the facilities at the Stena Recycling plant in Halmstad, Sweden, about 300 tonnes of metallic waste is processed each day with the aim of sorting out all non-ferrous material. At the end of this process, non-ferrous materials are manually sorted out from the ferrous materials. This thesis investigates a computer vision based approach to identify and localize the non-ferrous materials and eventually automate the sorting.Images were captured of ferrous and non-ferrous materials. The images areprocessed and segmented to be used as annotation data for a deep convolutionalneural segmentation network. Network models have been trained on different kinds and amounts of data. The resulting models are evaluated and tested in ac-cordance with different evaluation metrics. Methods of creating advanced train-ing data by merging imaging information were tested. Experiments with using classifier prediction confidence to identify objects of unknown classes were per-formed. This thesis shows that it is possible to discern ferrous from non-ferrous mate-rial with a purely vision based system. The thesis also shows that it is possible to automatically create annotated training data. It becomes evident that it is possi-ble to create better training data, tailored for the task at hand, by merging image data. A segmentation network trained on more than two classes yields lowerprediction confidence for objects unknown to the classifier.Substituting manual sorting with a purely vision based system seems like aviable approach. Before a substitution is considered, the automatic system needsto be evaluated in comparison to the manual sorting.
16

Characterising heterogeneity of glioblastoma using multi-parametric magnetic resonance imaging

Li, Chao January 2018 (has links)
A better understanding of tumour heterogeneity is central for accurate diagnosis, targeted therapy and personalised treatment of glioblastoma patients. This thesis aims to investigate whether pre-operative multi-parametric magnetic resonance imaging (MRI) can provide a useful tool for evaluating inter-tumoural and intra-tumoural heterogeneity of glioblastoma. For this purpose, we explored: 1) the utilities of habitat imaging in combining multi-parametric MRI for identifying invasive sub-regions (I & II); 2) the significance of integrating multi-parametric MRI, and extracting modality inter-dependence for patient stratification (III & IV); 3) the value of advanced physiological MRI and radiomics approach in predicting epigenetic phenotypes (V). The following observations were made: I. Using a joint histogram analysis method, habitats with different diffusivity patterns were identified. A non-enhancing sub-region with decreased isotropic diffusion and increased anisotropic diffusion was associated with progression-free survival (PFS, hazard ratio [HR] = 1.08, P < 0.001) and overall survival (OS, HR = 1.36, P < 0.001) in multivariate models. II. Using a thresholding method, two low perfusion compartments were identified, which displayed hypoxic and pro-inflammatory microenvironment. Higher lactate in the low perfusion compartment with restricted diffusion was associated with a worse survival (PFS: HR = 2.995, P = 0.047; OS: HR = 4.974, P = 0.005). III. Using an unsupervised multi-view feature selection and late integration method, two patient subgroups were identified, which demonstrated distinct OS (P = 0.007) and PFS (P < 0.001). Features selected by this approach showed significantly incremental prognostic value for 12-month OS (P = 0.049) and PFS (P = 0.022) than clinical factors. IV. Using a method of unsupervised clustering via copula transform and discrete feature extraction, three patient subgroups were identified. The subtype demonstrating high inter-dependency of diffusion and perfusion displayed higher lactate than the other two subtypes (P = 0.016 and P = 0.044, respectively). Both subtypes of low and high inter-dependency showed worse PFS compared to the intermediate subtype (P = 0.046 and P = 0.009, respectively). V. Using a radiomics approach, advanced physiological images showed better performance than structural images for predicting O6-methylguanine-DNA methyltransferase (MGMT) methylation status. For predicting 12-month PFS, the model of radiomic features and clinical factors outperformed the model of MGMT methylation and clinical factors (P = 0.010). In summary, pre-operative multi-parametric MRI shows potential for the non-invasive evaluation of glioblastoma heterogeneity, which could provide crucial information for patient care.
17

How Machine Learning Artificial Intelligence Improves Users’ Perceptions of Facebook Ads: A Model of Personalization, Advertising Value and Purchase Intention

Chap, Chetra 23 May 2022 (has links)
No description available.
18

A PROGNOSTIC AND PREDICTIVE COMPUTATIONAL PATHOLOGY BASED COMPANION DIAGNOSTIC APPROACH: PRECISION MEDICINE FOR LUNG CANCER

Wang, Xiangxue January 2019 (has links)
No description available.
19

Ein Framework zur Analyse komplexer Produktportfolios mittels Machine Learning

Mehlstäubl, Jan 08 December 2023 (has links)
Die Nachfrage der Kunden nach individualisierten Produkten, die Globalisierung, neue Konsummuster sowie kürzere Produktlebenszyklen führen dazu, dass Unternehmen immer mehr Varianten anbieten. Aufgrund der Arbeitsteilung und der unterschiedlichen Perspektiven können einzelne Entwickler die Komplexität des Produktportfolios nicht durchdringen. Dennoch sind die heutigen Verfahren im Produktportfolio- und Variantenmanagement geprägt durch manuelle und erfahrungsbasierte Aktivitäten. Eine systematische Analyse und Optimierung des Produktportfolios sind damit nicht möglich. Unternehmen benötigen stattdessen intelligente Lösungen, welche das gespeicherte Wissen in Daten nutzen und einsetzen, um Entscheidungen über Innovation, Differenzierung und Elimination von Produktvarianten zu unterstützen. Zielstellung dieses Forschungsvorhabens ist die Entwicklung eines Frameworks zur Analyse komplexer Produktportfolios mittels Machine Learning. Machine Learning ermöglicht es, Wissen aus Daten unterschiedlicher Lebenszyklusphasen einer Produktvariante automatisiert zu generieren und zur Unterstützung des Produktportfolio- und Variantenmanagements einzusetzen. Für die Unterstützung der Entscheidungen über Produktvarianten ist Wissen über deren Abhängigkeiten und Beziehungen sowie die Eigenschaften der einzelnen Elemente erforderlich. Dadurch soll ein Beitrag zur besseren Handhabung komplexer Produktportfolios geleistet werden. Das Framework zur Analyse komplexer Produktportfolios mittels Machine Learning besteht aus drei Bausteinen, die das zentrale Ergebnis dieser Arbeit darstellen. Zuerst wird in Baustein 1 auf die Wissensbedarfe bei der Analyse und Anpassung komplexer Produktportfolios eingegangen. Anschließend werden in Baustein 2 die Daten, welche für Entscheidungen und somit für die Wissensgenerierung im Produktportfolio- und Variantenmanagement erforderlich sind, beschrieben und charakterisiert. Abschließend findet in Baustein 3 die Datenvorbereitung und die Implementierung der Machine Learning Verfahren statt. Es wird auf unterschiedliche Verfahren eingegangen und eine Unterstützung bei der Auswahl und Evaluation der Algorithmen sowie die Möglichkeiten zum Einsatz des generierten Wissens für die Analyse komplexer Produktportfolios aufgezeigt. Das Framework wird in einer Fallstudie bei einem Industriepartner aus der Nutzfahrzeugbranche mit einem besonders komplexen Produktportfolio angewendet. Dabei werden die drei Anwendungsfälle Prognose von „marktspezifischen und technischen Eigenschaften der Produktvarianten“, Ermittlung von „Ähnlichkeiten von Produktvarianten“ und Identifikation von „Korrelationen zwischen Merkmalsausprägungen“ mit realen Daten des Industriepartners umgesetzt. Das Framework sowie die in der Fallstudie beim Industriepartner erzielten Ergebnisse werden anschließend Experten im Produktportfolio- und Variantenmanagement vorgestellt. Diese bewerten die Ergebnisse hinsichtlich der funktionalen Eigenschaften sowie dem Mehrwert aus Sicht der Forschung und industriellen Praxis anhand zuvor definierter Kriterien.:1 Einführung 1.1 Motivation 1.2 Komplexe Produktportfolios: Eine Industrieperspektive 1.3 Zielsetzung und Forschungsfragen 1.4 Aufbau der Arbeit 2 Grundlagen zur Analyse von Produktportfolios mittels Machine Learning 2.1 Komplexe Produktportfolios 2.1.1 Terminologie komplexer Produktportfolios 2.1.2 Strukturierung komplexer Produktportfolios 2.1.3 Analyse und Anpassung komplexer Produktportfolios 2.1.4 Zusammenfassung: Komplexe Produktportfolios 2.2 Machine Learning 2.2.1 Machine Learning als Teil der künstlichen Intelligenz 2.2.2 Terminologie Machine Learning 2.2.3 Wissensgenerierung mit Machine Learning 2.2.4 Datenanalyseprozess 2.2.5 Machine Learning Verfahren und Algorithmen 2.2.6 Zusammenfassung: Machine Learning 3 Ansätze zur Analyse von Produktportfolios mittels Machine Learning 3.1 Kriterien zur Bewertung bestehender Ansätze 3.2 Bestehende Ansätze aus der Literatur 3.2.1 Einsatz überwachter Lernverfahren 3.2.2 Einsatz unüberwachter Lernverfahren 3.2.3 Einsatz kombinierter Lernverfahren 3.3 Resultierender Forschungsbedarf 4 Forschungsvorgehen 4.1 Design Research Methodology (DRM) 4.2 Vorgehen und Methodeneinsatz 4.3 Kriterien für die Entwicklung des Frameworks 4.4 Schlussfolgerungen zum Forschungsvorgehen 5 Framework zur Analyse komplexer Produktportfolios 5.1 Übersicht über das Framework 5.2 Baustein 1: Wissensbedarfe zur Analyse komplexer Produktportfolios 5.2.1 Informationssuche 5.2.2 Formulierung von Alternativen 5.2.3 Prognose 5.2.4 Kriterien zur Auswahl der Wissensbedarfe 5.3 Baustein 2: Datenbasierte Beschreibung komplexer Produktportfolios 5.3.1 Produktdatenmodell 5.3.2 Vertriebsdaten 5.3.3 Nutzungsdaten 5.4 Baustein 3: Systematische Generierung und Einsatz von Wissen 5.4.1 Baustein 3.0: Vorbereitung von Produktportfoliodaten 5.4.2 Baustein 3.1: Regressionsanalyse 5.4.3 Baustein 3.2: Klassifikationsanalyse 5.4.4 Baustein 3.3: Clusteranalyse 5.4.5 Baustein 3.4: Assoziationsanalyse 5.5 Anwendung des Frameworks 5.6 Schlussfolgerung zum Framework 6 Validierung des Frameworks 6.1 Konzept der Validierung 6.2 Baustein 1: Wissensbedarfe zur Analyse komplexer Produktportfolios 6.3 Baustein 2: Datenbasierte Beschreibung komplexer Produktportfolios 6.4 Baustein 3: Systematische Generierung und Einsatz von Wissen 6.4.1 Marktspezifische und technische Produkteigenschaften 6.4.2 Ähnlichkeiten von Produktvarianten 6.4.3 Korrelationen zwischen Merkmalsausprägungen 6.5 Erfolgsvalidierung mit einer Expertenbefragung 6.6 Schlussfolgerung zur Validierung 7 Diskussion 7.1 Nutzen und Einschränkungen 7.2 Ergebnisbeitrag für die Forschung 7.3 Ergebnisbeitrag für die Industrie 8 Zusammenfassung und Ausblick 8.1 Zusammenfassung 8.2 Ausblick 9 Literaturverzeichnis 10 Abbildungsverzeichnis 11 Tabellenverzeichnis Anhang A-1
20

On Tractability and Consistency of Probabilistic Inference in Relational Domains

Malhotra, Sagar 10 July 2023 (has links)
Relational data is characterised by the rich structure it encodes in the dependencies between the individual entities of a given domain. Statistical Relational Learning (SRL) combines first-order logic and probability to learn and reason over relational domains by creating parametric probability distributions over relational structures. SRL models can succinctly represent the complex dependencies in relational data and admit learning and inference under uncertainty. However, these models are significantly limited when it comes to the tractability of learning and inference. This limitation emerges from the intractability of Weighted First Order Model Counting (WFOMC), as both learning and inference in SRL models can be reduced to instances of WFOMC. Hence, fragments of first-order logic that admit tractable WFOMC, widely known as domain-liftable, can significantly advance the practicality and efficiency of SRL models. Recent works have uncovered another limitation of SRL models, i.e., they lead to unintuitive behaviours when used across varying domain sizes, violating fundamental consistency conditions expected of sound probabilistic models. Such inconsistencies also mean that conventional machine learning techniques, like training with batched data, cannot be soundly used for SRL models. In this thesis, we contribute to both the tractability and consistency of probabilistic inference in SRL models. We first expand the class of domain-liftable fragments with counting quantifiers and cardinality constraints. Unlike the algorithmic approaches proposed in the literature, we present a uniform combinatorial approach, admitting analytical combinatorial formulas for WFOMC. Our approach motivates a new family of weight functions allowing us to express a larger class of probability distributions without losing domain-liftability. We further expand the class of domain-liftable fragments with constraints inexpressible in first-order logic, namely acyclicity and connectivity constraints. Finally, we present a complete characterization for a statistically consistent (a.k.a projective) models in the two-variable fragment of a widely used class of SRL models, namely Markov Logic Networks.

Page generated in 0.1498 seconds