• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 101
  • 9
  • 8
  • 6
  • 2
  • 2
  • 2
  • 1
  • 1
  • 1
  • Tagged with
  • 173
  • 173
  • 91
  • 61
  • 46
  • 44
  • 31
  • 30
  • 27
  • 22
  • 19
  • 18
  • 15
  • 15
  • 15
  • 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.
91

Towards an Image-based Indicator for Peripheral Artery Disease Classification and Localization

Gillmann, Christina, Matsuura, John M., Hagen, Hans, Wischgoll, Thomas 25 January 2019 (has links)
Peripheral Artery Disease (PAD) is an often occurring problem caused by narrowed veins. With this type of disease, mostly the legs receive an insufficient supply of blood to sustain their functions. This can result in an amputation of extremities or strokes. In order to quantify the risks, doctors consult a classification table which is based on the pain response of a patient. This classification is subjective and does not indicate the exact origin of the PAD symptoms. Resulting from this, complications can occur unprompted. We present the first results for an image-based indicator assisting medical doctors in estimating the stage of PAD and its location. Therefore, a segmentation tree is utilized to compare the changes in a healthy versus diseased leg. We provide a highlighting mechanism that allows users to review the location of changes in selected structures. To show the effectiveness of the presented approach, we demonstrate a localization of the PAD and show how the presented technique can be utilized for a novel image-based indicator of PAD stages.
92

Matrix of guidelines to improve the understandability of non-expert users in process mining projects

Teran, Bryhan Chise, Bravo, Jimmy Manuel Hurtado, Armas-Aguirre, Jimmy, Mayorga, Santiago Aguirre 01 June 2020 (has links)
El texto completo de este trabajo no está disponible en el Repositorio Académico UPC por restricciones de la casa editorial donde ha sido publicado. / Process Mining is a discipline that recognizes three types of analysis: Discovery, monitoring, and process improvement. Organizations are focusing on redesigning and automating their major processes, according to a report published in 2018 [1]. In this way, a challenge n process mining is to show the results of the process analysis in a way that is understandable to non-expert users. Therefore, this research paper introduces a matrix of guidelines to guide process mining specialists/tool developers to improve the results of the analysis in process mining projects. This matrix is composed of 2 study fields that throughout the literature have been merging their virtues. First, process mining under 2 of its 3 types of projects: (1) based on objectives and (2) based on questions. The last type is based on data (exploratory analysis). Second, visualization of data with its techniques to represent data graphically. This research proposes a matrix of guidelines that integrates the discipline of process mining and the set of data visualization techniques based on the purpose of each graph (technique), the question / objective to be achieved and the importance that colors take in the analysis results in the process mining projects. / Revisión por pares
93

Visual Analysis of Industrial Multivariate Time-Series Data : Effective Solution to Maximise Insights from Blow Moulding Machine Sensory Data

Musleh, Maath January 2021 (has links)
Developments in the field of data analytics provides a boost for small-sized factories. These factories are eager to take full advantage of the potential insights in the remotely collected data to minimise cost and maximise quality and profit. This project aims to process, cluster and visualise sensory data of a blow moulding machine in a plastic production factory. In collaboration with Lean Automation, we aim to develop a data visualisation solution to enable decision-makers in a plastic factory to improve their production process. We will investigate three different aspects of the solution: methods for processing multivariate time-series data, clustering approaches for the sensory-data cultivated, and visualisation techniques that maximises production process insights. We use a formative evaluation method to develop a solution that meets partners' requirements and best practices within the field. Through building the MTSI dashboard tool, we hope to answer questions on optimal techniques to represent, cluster and visualise multivariate time series data.
94

VISUELL PRESENTATION AV VÄDERDATA OCH ELPRISERE TT ARBETE OM DATABASMODELLERING I MOLNET MED BUSINESS INTELLIGENCE

Björnbom, Willie, Eklöf, Alexander January 2019 (has links)
In an environment where data flows everywhere and in all forms, it can be difficult to extract something valuable of it. Business Intelligence, also known as BI, is a technology used to transform information into a valuable resource for primarily companies with a lot of information. But what opportunities does BI offer? In this essay, we use standardized techniques, popular tools and cloud services to perform a pure BI project. We will generate a report in which we will analyze whether there is any correlation between electricity prices and different types of weather data. After the practical part of the work, we will use our experience of the cloud to dig deeper into how safe the cloud reallys is. We will compare the concerns that an ordinary user has to the cloud and compare with how the cloud service provider (CSP) Azure adapts to this. / ett samhälle där information flödar i alla dess former så kan det vara svårt att utvinna någontingvärdefullt av detta. Business intelligence, även kallat BI, är en teknik som används för att kunnaomvandla informationen till en värdefull resurs för främst företag. Men vad kan man egentligengöra med BI? I denna uppsats används standardiserade tekniker, nya verktyg och molntjänster föratt utföra ett helt BI-projekt. Projektet innefattar en visuell rapport där det ska göras en grundliganalys om det finns någon korrelation mellan elpriser och olika typer av väderdata.Efter det praktiska arbetet så kommer en teoretiskt fördjupning inom molntjärnes säkerhet attutföras. Den teoretiska fördjupningen kommer att omfatta en jämförelse mellan de mestförekommande orosmoment som användare har inför molnet och hur Azure faktiskt ställer sig tilldessa.
95

Feature selection through visualisation for the classification of online reviews

Koka, Keerthika 17 April 2017 (has links)
Indiana University-Purdue University Indianapolis (IUPUI) / The purpose of this work is to prove that the visualization is at least as powerful as the best automatic feature selection algorithms. This is achieved by applying our visualization technique to the online review classification into fake and genuine reviews. Our technique uses radial chart and color overlaps to explore the best feature selection through visualization for classification. Every review is treated as a radial translucent red or blue membrane with its dimensions determining the shape of the membrane. This work also shows how the dimension ordering and combination is relevant in the feature selection process. In brief, the whole idea is about giving a structure to each text review based on certain attributes, comparing how different or how similar the structure of the different or same categories are and highlighting the key features that contribute to the classification the most. Colors and saturations aid in the feature selection process. Our visualization technique helps the user get insights into the high dimensional data by providing means to eliminate the worst features right away, pick some best features without statistical aids, understand the behavior of the dimensions in different combinations.
96

UTILIZING BIG TRAJECTORY DATA FOR URBAN VISUAL ANALYTICS AND ACCESSIBILITY STUDIES

Kamw, Farah Shleemon 17 April 2019 (has links)
No description available.
97

Interpreting and Diagnosing Deep Learning Models: A Visual Analytics Approach

Wang, Junpeng 11 July 2019 (has links)
No description available.
98

A Study of the Effectiveness of Mobile Technology in the Major Fields and Opioid Epidemic

Aboturkia, Amna 21 October 2019 (has links)
No description available.
99

A Mixed-Methods Approach to Understanding the Effects of Visual Analytic Strategies on Organizational Decision Making

Williams, Brian G. January 2016 (has links)
No description available.
100

Making Interoperability Visible : A Novel Approach to Understand Interoperability in Cyber-Physical Systems Toolchains

Gürdür, Didem January 2016 (has links)
In CPS development and production environments, tightly integrated processes include different engineering disciplines, development and production departments, and software tools working together, where all of the technical engineering processes become strictly intertwined. CPS development and production toolchains have a highly heterogeneous nature, and supporting toolchain architects is necessary for improving the understanding of the interrelationships between tools. To this end, this thesis mainly concentrates on the interoperability of CPS toolchains with an ambition to improve the understanding of interoperability. A literature survey was conducted to analyze the literature on interoperability with an aim to understand how the interoperability is assessed. Findings of the literature review showed that the existing methods mainly use maturity-like assessment models to assess interoperability and they focus on selective aspects of interoperability. These models use distinct levels and do not guide the stakeholders on how to improve the current state of interoperability. This revealed the need for a more flexible approach for assessing interoperability of CPS toolchains. A case study was developed and exercised with an ambition to test the applicability of the visualization approach. In total, three different visualization techniques were evaluated: circular ideogram, node-link diagram, and balloon layout with a clustering algorithm as an extended version of node-link diagram. This thesis concluded by highlighting that data visualizations and visual analytics are not only a method for understanding the interoperability of CPS toolchains, but also a necessity. Data visualization approaches create many opportunities to make interoperability finally visible and the CPS industry should focus its effort on appropriate data collection, usage, and sharing methods in order to best use data visualization and visual analytics technologies. / Cyber-fysiska system (CPS) är ett resultat av mångfacetterade produktutvecklingsprocesser, som innefattar flerdimensionell komplexitet. I CPS:s utvecklings- och produktionsmiljöer, innefattar dessa tätt integrerade processer olika tekniska discipliner, utvecklings- och produktionsavdelningar, och programvaruverktyg som arbetar tillsammans, där alla tekniska ingenjörsprocesser blir strikt sammanflätade. Beslut som fattas av en intressent kan således ha en inverkan på andra intressenter. Verktygskedjor för CPS:s utveckling och produktion har därför en mycket heterogen karaktär, och det är därför nödvändigt med stödjande utvecklare av verktygskedjan för att förbättra förståelsen av sambanden mellan verktyg. För detta ändamål fokuserar denna avhandling främst på interoperabiliteten hos CPS:s verktygskedjor, med ambitionen att förbättra förståelsen för interoperabilitet och, som en följd, vägleda verktygskedjans utvecklare att fatta kostnadseffektiva och hållbara beslut baserade på förbättrad förståelse. En litteraturundersökning genomfördes för att analysera litteratur om interoperabilitet med syfte att förstå hur interoperabilitet bedöms. Resultaten av litteraturgenomgången visade att de befintliga metoderna huvudsakligen använder mognadsliknande bedömningsmodeller för att bedöma interoperabiliteten, och de fokuserar på selektiva aspekter av interoperabiliteten. Dessa modeller använder olika nivåer och vägleder inte intressenterna i hur det aktuella läget för interoperabilitet kan förbättras. Detta visade att det behövs en mer flexibel inställning för att bedöma interoperabiliteten av CPS:s verktygskedjor. Den systematiska litteraturöversikten avslutades genom att tydliggöra att visualisering och visuell analys visar lovande möjligheter för att externalisera den kunskap som nås av bedömningsmodeller med de möjligheter som visualiseringar kan ge. För att studera situationen gällande interoperabilitet i utvecklingen av CPS, utvecklades och genomfördes en fallstudie med ambitionen att testa visualiseringsmetodens tillämplighet. Fallstudien visade en verktygskedjas interoperabilitet, som används för att utveckla ett inbäddat slutet loopkontrollsystem med olika visualiseringstekniker. Totalt har tre olika visualiseringstekniker utvärderas: (a) cirkulärt ideogram, (b) nod- länkdiagram, och (c) ballonglayout med en klusteralgoritm som en utökad version av nodlänkdiagram, vilket gav vissa insikter om vilka tekniker som är mest lämpliga. Varje teknik diskuteras i detalj med ett interoperabilitetsperspektiv. De utmaningar och möjligheter som datavisualisering och visuella analyser ger förklaras dessutom för att synliggöra interoperabilitet. Denna avhandling avslutas med att lyfta fram att datavisualiseringar och visuella analyser inte bara är metoder för att förstå interoperabiliteten av CPS:s verktygskedjor utan också en nödvändighet. Datavisualiseringsmetoder skapar många möjligheter att slutligen göra interoperabilitet synlig och CPS- industrin bör fokusera sina ansträngningar på lämplig datainsamling, användande och delningsmetoder för att på bästa sätt utnyttja datavisualisering och visuella analystekniker. / <p>QC 20170203</p>

Page generated in 0.0893 seconds