81 |
A unified approach to the economic aspects of statistical quality control and improvementGhebretensae Manna, Zerai 12 1900 (has links)
Assignment (MSc)--Stellenbosch University, 2004. / ENGLISH ABSTRACT: The design of control charts refers to the selection of the parameters implied, including the
sample size n, control limit width parameter k, and the sampling interval h. The design of the
X -control chart that is based on economic as well as statistical considerations is presently one of
the more popular subjects of research. Two assumptions are considered in the development and
use of the economic or economic statistical models. These assumptions are potentially critical. It
is assumed that the time between process shifts can be modelled by means of the exponential
distribution. It is further assumed that there is only one assignable cause. Based on these
assumptions, economic or economic statistical models are derived using a total cost function per
unit time as proposed by a unified approach of the Lorenzen and Vance model (1986). In this
approach the relationship between the three control chart parameters as well as the three types of
costs are expressed in the total cost function. The optimal parameters are usually obtained by the
minimization of the expected total cost per unit time. Nevertheless, few practitioners have tried
to optimize the design of their X -control charts. One reason for this is that the cost models and
their associated optimization techniques are often too complex and difficult for practitioners to
understand and apply. However, a user-friendly Excel program has been developed in this paper
and the numerical examples illustrated are executed on this program. The optimization procedure
is easy-to-use, easy-to-understand, and easy-to-access. Moreover, the proposed procedure also
obtains exact optimal design values in contrast to the approximate designs developed by Duncan
(1956) and other subsequent researchers.
Numerical examples are presented of both the economic and the economic statistical designs of
the X -control chart in order to illustrate the working of the proposed Excel optimal procedure.
Based on the Excel optimization procedure, the results of the economic statistical design are
compared to those of a pure economic model. It is shown that the economic statistical designs
lead to wider control limits and smaller sampling intervals than the economic designs.
Furthermore, even if they are more costly than the economic design they do guarantee output of
better quality, while keeping the number of false alarm searches at a minimum. It also leads to
low process variability. These properties are the direct result of the requirement that the
economic statistical design must assure a satisfactory statistical performance.
Additionally, extensive sensitivity studies are performed on the economic and economic
statistical designs to investigate the effect of the input parameters and the effects of varying the bounds on, a, 1-f3 , the average time-to-signal, ATS as well as the expected shift size t5 on
the minimum expected cost loss as well as the three control chart decision variables. The
analyses show that cost is relatively insensitive to improvement in the type I and type II error
rates, but highly sensitive to changes in smaller bounds on ATS as well as extremely sensitive
for smaller shift levels, t5 .
Note: expressions like economic design, economic statistical design, loss cost and assignable
cause may seen linguistically and syntactically strange, but are borrowed from and used
according the known literature on the subject. / AFRIKAANSE OPSOMMING: Die ontwerp van kontrolekaarte verwys na die seleksie van die parameters geïmpliseer,
insluitende die steekproefgrootte n , kontrole limiete interval parameter k , en die
steekproefmterval h. Die ontwerp van die X -kontrolekaart, gebaseer op ekonomiese sowel as
statistiese oorwegings, is tans een van die meer populêre onderwerpe van navorsing. Twee
aannames word in ag geneem in die ontwikkeling en gebruik van die ekonomiese en ekonomies
statistiese modelle. Hierdie aannames is potensieel krities. Dit word aanvaar dat die tyd tussen
prosesverskuiwings deur die eksponensiaalverdeling gemodelleer kan word. Daar word ook
verder aangeneem dat daar slegs een oorsaak kan wees vir 'n verskuiwing, of te wel 'n
aanwysbare oorsaak (assignable cause). Gebaseer op hierdie aannames word ekonomies en
ekonomies statistiese modelle afgelei deur gebruik te maak van 'n totale kostefunksie per
tydseenheid soos voorgestel deur deur 'n verenigende (unified) benadering van die Lorenzen en
Vance-model (1986). In hierdie benadering word die verband tussen die drie kontrole
parameters sowel as die drie tipes koste in die totale kostefunksie uiteengesit. Die optimale
parameters word gewoonlik gevind deur die minirnering van die verwagte totale koste per
tydseenheid. Desnieteenstaande het slegs 'n minderheid van praktisyns tot nou toe probeer om
die ontwerp van hulle X -kontrolekaarte te optimeer. Een rede hiervoor is dat die kosternodelle
en hulle geassosieerde optimeringstegnieke té kompleks en moeilik is vir die praktisyns om te
verstaan en toe te pas. 'n Gebruikersvriendelike Excelprogram is egter hier ontwikkel en die
numeriese voorbeelde wat vir illustrasie doeleindes getoon word, is op hierdie program
uitgevoer. Die optimeringsprosedure is maklik om te gebruik, maklik om te verstaan en die
sagteware is geredelik beskikbaar. Wat meer is, is dat die voorgestelde prosedure eksakte
optimale ontwerp waardes bereken in teenstelling tot die benaderde ontwerpe van Duncan (1956)
en navorsers na hom.
Numeriese voorbeelde word verskaf van beide die ekonomiese en ekonomies statistiese
ontwerpe vir die X -kontrolekaart om die werking van die voorgestelde Excel optimale
prosedure te illustreer. Die resultate van die ekonomies statistiese ontwerp word vergelyk met
dié van die suiwer ekomomiese model met behulp van die Excel optimerings-prosedure. Daar
word aangetoon dat die ekonomiese statistiese ontwerpe tot wyer kontrole limiete en kleiner
steekproefmtervalle lei as die ekonomiese ontwerpe. Al lei die ekonomies statistiese ontwerp tot
ietwat hoër koste as die ekonomiese ontwerpe se oplossings, waarborg dit beter kwaliteit terwyl
dit die aantal vals seine tot 'n minimum beperk. Hierbenewens lei dit ook tot kleiner prosesvartasie. Hierdie eienskappe is die direkte resultaat van die vereiste dat die ekonomies
statistiese ontwerp aan sekere statistiese vereistes moet voldoen.
Verder is uitgebreide sensitiwiteitsondersoeke op die ekonomies en ekonomies statistiese
ontwerpe gedoen om die effek van die inset parameters sowel as van variërende grense op a,
1- f3 , die gemiddelde tyd-tot-sein, ATS sowel as die verskuiwingsgrootte 8 op die minimum
verwagte kosteverlies sowel as die drie kontrolekaart besluitnemingsveranderlikes te bepaal. Die
analises toon dat die totale koste relatief onsensitief is tot verbeterings in die tipe I en die tipe II
fout koerse, maar dat dit hoogs sensitief is vir wysigings in die onderste grens op ATS sowel as
besonder sensitief vir klein verskuiwingsvlakke, 8.
Let op: Die uitdrukkings ekonomiese ontwerp (economic design), ekonomies statistiese ontwerp
(economic statistical design), verlies kostefunksie (loss cost function) en aanwysbare oorsaak
(assignable cause) mag taalkundig en sintakties vreemd voordoen, maar is geleen uit, en word so
gebruik in die bekende literatuur oor hierdie onderwerp.
|
82 |
Fetal and postnatal patterns of growth in a bi-ethnic sample of childrenNorris, Thomas January 2015 (has links)
Background: Substantial variation exists between ethnicities in both birth weight and the prevalence of obesity-related non-communicable diseases (OR-NCDs). South Asians, who display a reduced birth weight and increased risk of developing these OR-NCDS, have been the focus of much of the research into the developmental origins of health and disease (DOHaD) paradigm. However, little research utilising ultrasonically derived estimates of fetal growth has been conducted. The use of more direct measures of fetal growth may also enable the identification of relationships between patterns of fetal growth with patterns of postnatal growth, explicitly, whether periods of restricted or rapid growth lead to postnatal catch-up or down, respectively. The known differences in birth weight existing between South Asians and White British infants may also have implications for the assessment of neonatal health in these sub-groups when using a population derived birth weight chart, such as the UK-World Health Organisation (UK-WHO). Customised charts, which adjust for maternal variables including ethnicity, have been recommended for clinical practice, yet evidence for their efficacy is varied. Objectives: The aims of this thesis were to: 1) investigate whether fetal growth patterns differ between Pakistani and White British foetuses and determine whether maternal size and demographic variables mediate any such differences; 2) produce a birth weight chart adjusting for ethnicity and compare this to the UK-WHO and customised birth weight charts to determine which chart better identifies neonates at risk of the adverse delivery and neonatal outcomes associated with small-for-gestational-age (SGA) and large-for-gestational age (LGA); 3) identify whether there is evidence of weight growth tracking between fetal and infant periods and determine whether patterns of fetal growth predict patterns of postnatal growth. Methods: All data come from the Born in Bradford (BiB) birth cohort. Objective 1: Multilevel models and fractional polynomials were employed for the modelling of fetal weight, head circumference (HC) and abdominal circumference (AC) growth. Potential mediators of the effect of being of Pakistani origin were entered into the model and the effect on the ethnicity variable was assessed. Objective 2: Ethnic specific birth weight charts (BiB) were constructed using the LMS method. SGA and LGA were defined as a birth weight <10th and >90th relative to the BiB, the UK-WHO or the customised charts. Sensitivity, specificity, positive & negative predictive values and area-under-the curve were calculated for each of the three charts SGA and LGA cut-offs, to assess the predictive ability of each chart for a range of delivery and neonatal outcomes. Objective 3: Multilevel models were employed for the modelling of fetal and postnatal growth. Fitted values were produced at 20, 30, 40 prenatal weeks & 1, 3, 6, 9, 12, 24 postnatal months in both an internal reference and the sample population. Z scores were calculated and conditional Z scores were generated to account for regression to the mean. Growth tracking was defined as change in Z score ≤ 0.67 & ≥ -0.67. Restricted and rapid fetal growth were defined as a change in Z score in the fetal period of <-0.67 and >0.67, respectively. Catch-down and catch-up growth were defined in the same way, except in the postnatal period. ANOVAs were used to test for differences in size and growth by type of fetal growth. Furthermore, logistic regression and a sensitivity and specificity analysis were employed to examine the predictive ability of the type of fetal growth. Results: Objective 1: Pakistani fetuses were significantly smaller and lighter than White British fetuses, throughout gestation. In terms of weight, Pakistani fetuses were approximately 2.25% lighter at 20 weeks, 4.13% at 30 weeks and 5.94% at 40 weeks. The differences in size for AC and HC between the two groups were not as great, with the AC and HC of Pakistani fetuses being approximately 4.1% and 1.25% smaller, respectively, at 40 weeks. Despite these significant differences in size the pattern of growth for HC and weight was not significantly different between the two groups. There was a trend for Pakistani fetuses to display a greater deceleration of growth in the final trimester (figure 4-12). The biggest mediators of the effect of being of Pakistani origin were maternal height and weight. Objective 2: Classifying infants as SGA or LGA by the BiB, UK-WHO or customised charts had low predictive utility for the outcomes under investigation. Despite the fact that the BiB ethnic specific birth weight reference provided significantly better prediction for more outcomes than both the UK-WHO and customised charts in both White British and Pakistani infants, with the exception of shoulder dystocia, AUROC values for all three charts were all below 0.61. Objective 3: The prevalence of tracking within the same centile band from 20 weeks gestation to 2 years was 10.82%. Infants who experienced restricted fetal growth remained significantly lighter than those who had not, for the duration of infancy. In this group however, there was a pattern of greater growth than expected during infancy. This was opposite to the pattern observed in infants who had experienced rapid fetal growth, who exhibited less growth than expected during infancy. However, the ability of the type of fetal growth to predict the pattern of postnatal growth was minimal, with only rapid fetal growth being significantly associated with increased odds of catch-down growth in infancy. Conclusions: No ethnic difference in the pattern of growth was found in terms of the whole body (weight) or in HC. The trend for reduced growth of the AC in Pakistanis may be a result of a reduced growth of the visceral organs during the third trimester, which may lead to both an altered liver metabolism and impaired renal function in post-natal life. Although being small or large at birth may increase the risk of an adverse neonatal outcome, size alone is not sensitive or specific enough with current detection to be a useful clinical tool. The finding that neither restricted nor rapid fetal growth predicted postnatal catch-up growth may suggest that the timing of canalisation is outside of the fetal period. If infant catch-up and down growth are not associated with periods of restricted or rapid fetal growth, the definitions of these growth patterns may need revising.
|
83 |
Research into the usability of software produced in a utility for the utility and consultantsStanford, Gareth 12 May 2008 (has links)
RSAT (Reticulation Sag And Tension) software is a tool available for use as part of the
medium voltage Eskom Distribution standard. This software is scrutinised for its usability
and for errors such that it can be revised to improve the usability of the tool.
The type of software being studied is used to ensure optimum design performance and
reduce the probability of a conductor failure on distribution lines. The algorithms for
calculating tension, sag and clearance values take into account research into optimum
design tensions. This ensures low bending forces due to conductor vibration. An
algorithm for creep is designed based on common life expectancy of line conductors.
The design methodology and algorithms were then put into software form as RSAT.
Review and alterations include the changing of compiler, user interface, data storage
mechanisms and the inclusion of options allowing the addition of new data.
|
84 |
[en] EWMA CHART WITH ADAPTIVE SMOOTHING CONSTANT FOR STATISTICAL PROCESS CONTROL / [pt] GRÁFICO EWMA COM CONSTANTE DE AMORTECIMENTO ADAPTATIVA PARA CONTROLE ESTATÍSTICO DE PROCESSOSBRUNO FRANCISCO TEIXEIRA SIMOES 25 April 2006 (has links)
[pt] Este trabalho propõe um gráfico de controle EWMA para
observações
individuais ou médias amostrais, com a constante de
amortecimento variando
entre dois valores de acordo com o valor mais recente da
estatística EWMA, para
obter detecção mais rápida de alterações pequenas a
moderadas na média do
processo, e sem a complexidade operacional apresentada por
outros esquemas
adaptativos, pois o tamanho da amostra e o intervalo de
amostragem são mantidos
fixos. Já existe um outro trabalho propondo a variação da
constante de
amortecimento dos gráficos EWMA, mas com base em outro
critério: Capizzi e
Masarotto (2003). O esquema EWMA adaptativo foi combinado
com limites de
Shewhart para os valores individuais (ou médias
amostrais), para acelerar a
detecção de grandes deslocamentos da média do processo,
também sem aumento
da complexidade operacional. Os NMA1´s - números esperados
de amostras até
um sinal verdadeiro - foram calculados por um método de
aproximação numérica
usando um modelo matemático por cadeias de Markov, e
comparados com os do
esquema EWMA tradicional (com parâmetros fixos) e com os
do esquema
adaptativo de Capizzi e Masarotto (2003). O esquema
proposto tende a fornecer
NMA1´s menores para alterações na média acima de 1,0
desvio-padrão, e o
esquema de Capizzi e Masarotto (2003) tende a fornecer
NMA1´s menores para
pequenas alterações. Ambos os esquemas possuem melhor
desempenho que o
gráfico EWMA com parâmetros fixos. Uma vantagem que pode
se tornar decisiva
para a adoção do esquema proposto é a simplicidade dos
cálculos requeridos para
o monitoramento. / [en] This work proposes an EWMA process control chart for
individual
observations or subgroup averages, in which the smoothing
constant varies
between two values according to the most recent value of
the EWMA statistic, in
order to achieve faster detection of small to moderate
shifts in the process mean,
and without the operational complexities presented by
other adaptive schemes,
since its sample size and sampling interval do not vary.
There is one other work
proposing the adaptive variation of the smoothing constant
of EWMA charts, but
based on a different criterion: Capizzi and Masarotto
(2003). The adaptive
EWMA scheme was combined with Shewhart limits for the
individual values (or
subgroup averages), to enhance its sensitivity to large
shifts, again with no extra
operational burden. The out-of-control average run lengths
(ARL1´s) were
calculated through a numerical approximation method based
on a Markov chain
model. The ARL1´s were compared of the proposed scheme, of
the traditional
(fixed parameter) EWMA chart and of Capizzi and
Masarottos´s adaptive EWMA
scheme. The proposed scheme generally provides the
shortest ARL1´s for shifts in
the mean above one standard deviation, and Capizzi and
Masarotto´s scheme
tends to outperform it for smaller shifts. Both schemes
perform better than the
fixed parameter EWMA. An advantage that can become
decisive for the adoption
of the proposed scheme is the simplicity of the
calculations required for the
monitoring.
|
85 |
Generalized autoregressive and moving average models: control charts, multicollinearity, and a new modified model / Modelos generalizados auto-regressivos e de médias móveis: gráficos de controle, multicolinearidade e novo modelo modificadoAlbarracin, Orlando Yesid Esparza 24 October 2017 (has links)
Recently, in the health surveillance area, control charts have been proposed to decide if the morbidity or mortality of a specific disease reached an epidemic level. This thesis is composed by 3 papers. In the first two papers, CUSUM and EWMA control charts were proposed to monitor count time series with seasonal and trend effects using the Generalized Autoregressive and Moving Average models (GARMA), instead of the independent Generalized Linear Model (GLM) as it is usually used in practice. Different statistics based on transformations, for variables that follow a Negative Binomial distribution, were used in these control charts. In the second paper, two new statistics were proposed based on the ratio of log-likelihood function. Different scenarios describing disease profiles were considered to evaluate the effect of omission of serial correlation in EWMA and CUSUM control charts. The performance of CUSUM and EWMA charts when the serial correlation is neglected in the regression model was measure in terms of average run length (ARL). In summary, when the autocorrelation is neglected, fitting a pure GLM instead of a GARMA model will lead to an increase of false alarms. However, no statistics among the tested ones seem to be robust, in a sense to produce the smallest increase of false alarms in all scenarios. In general, all monitored statistics presented a smaller ARL_0 for higher values of autocorrelation. \\\\ In the last paper, the GARMA models (p, q) with p and q simultaneously different from zero were studied since that two features were observed in practice. One is the multicollinearity, which may lead to a non-convergence of the maximum likelihood, using iteratively reweighted least squares. The second is the inclusion of the same lagged observations into the autoregressive and moving average components confounding the interpretation of the parameters. In a general sense, simulation studies show that the modified model provide estimators closer to the parameters and offer confidence intervals with higher coverage percentage than obtained with the GARMA model, but some restrictions in the parametric space are imposed to guarantee the stationarity of the process. Also, a real data analysis illustrate the GARMA-M fit for daily hospilatization rates of elderly people due to respiratory diseases from October 2012 to April 2015 in São Paulo city, Brazil. / Recentemente, no campo da saúde, gráficos de controle têm sido propostos para monitorar a morbidade ou a mortalidade decorrentes de doenças. Este trabalho está composto por três artigos. Nos dois primeiros artigos, gráficos de controle CUSUM e EWMA foram propostos para monitorar séries temporais de contagens com efeitos sazonais e de tendência usando os modelos Generalized autoregressive and moving average models (GARMA), em vez dos modelos lineares generalizados (GLM), como usualmente são utilizados na prática. Diferentes estatísticas baseadas em transformações, para variávies que seguem uma distribuição Binomial Negativa, foram usadas nestes gráficos de controle. No segundo artigo foram propostas duas novas estatísticas baseadas na razão da função de log-verossimilhança. Diferentes cenários que descrevem perfis de doenças foram considerados para avaliar o efeito da omissão da correlação serial nesses gráficos de controle. Este impacto foi medido em termos do Average Run Lenght (ARL). Notou-se que a negligência da correlação serial induz um aumento de falsos alarmes. Em geral, todas as estatísticas monitoradas apresentaram menores valores de ARL_0 para maiores valores de autocorrelação. No entanto, nenhuma estatística entre as consideradas mostrou ser mais robusta, no sentido de produzir o menor aumento de falsos alarmes nos cenários considerados. No último artigo, foram estudados os modelos GARMA (p, q) com p e q simultaneamente diferentes de zero, uma vez que duas características foram observadas na prática. A primeira é a presença de multicolinearidade, que induz à não-convergência do método de máxima verossimilhança usando mínimos quadrados ponderados reiterados. A segunda é a inclusão dos mesmos termos defasados nos componentes autorregressivos e de médias móveis. Um modelo modificado, GARMA-M, foi apresentado para lidar com a multicolinearidade e melhorar a interpretação dos parâmetros. Em sentido geral, estudos de simulação mostraram que o modelo modificado fornece estimativas mais próximas dos parâmetros e intervalos de confiança com uma cobertura percentual maior do que a obtida nos modelos GARMA. No entanto, algumas restrições no espaço paramétrico são impostas para garantir a estacionariedade do processo. Por último, uma análise de dados reais ilustra o ajuste do modelo GARMA-M para o número de internações diárias de idosos devido a doenças respiratórias de outubro de 2012 a abril de 2015 na cidade de São Paulo, Brasil.
|
86 |
Monitoramento de processos com dependência espaço-temporal utilizando gráficos de controle. / Processes monitoring with space-time dependency using control charts.Moala, Adriano Buran 17 April 2017 (has links)
O combate ao roubo de veículos requer monitoramento constante e ações policiais para alterar a logística de rondas. A proposta deste trabalho é apresentar uma aplicação de como monitorar o índice de roubo de veículos nos 93 distritos da cidade de São Paulo e estabelecer alertas quando houver um aumento da criminalidade que é considerado fora do padrão histórico. Para modelar a taxa de roubo em todos os distritos da cidade foi utilizado o modelo STARMA (Spatio-Time Autoregressive Moving Average) que incorpora dependência espaço-temporal. Já para os gráficos de controle foram utilizados o MEWMA (Multivariate Exponentially Weighted Moving Average) e o MCUSUM (Multivariate Cumulative Sum) direcionado para capturar aumentos. Os resultados indicaram que o MCUSUM teve um tempo de reação a aumentos da criminalidade menor que o MEWMA. Além disso, foi testado como seria o tempo de reação dessas estatísticas sem a presença da componente espacial do modelo STARMA e o resultado foi uma reação incorreta, com aumento de falsos positivos. Palavras-chaves: logística, gráficos de controle, STARMA, MCUSUM, MEWMA. / A constant monitoring and police actions to change the routes of patrol vehicles are some requirements to act against the vehicle theft. The purpose of this dissertation is to present an application of monitoring the vehicle theft rates by control charts in the 93 police districts of the city of SãoPaulo. The control charts are built to detect increases in the crime rates, so a signal is triggered in regions where the crime rates are considered abnormal from the historical pattern. A STARMA (Spatio-Time Autoregressive Moving Average) model that incorporates space-time dependency is used to model the rate of robbery in all districts. MEWMA (Multivariate Exponentially Weighted Moving Average) and the MCUSUM (Multivariate Cumulative Sum) are built to meet some performance criteria. The results pointed out that MCUSUM outperforms MEWMA to capture increases in crime. Additionally earlier false alarms are observed in both charts as consequences when spatial components of STARMA model are wrongly omitted.
|
87 |
Improving User Interface and User Experience of MathSpring Intelligent Tutoring System for TeachersMenon, Neeraj 20 April 2018 (has links)
Common goals of Educational Data Mining are to model both student knowledge as well as student affect. While research continues along these lines of gathering data and building models of students' changing knowledge and affect states, little is being done to transform this collected (raw) data into meaningful entities that are more relatable to teachers, parents and other stakeholders, i.e. people who are not researchers. This research has entailed the iterative design and development of Teacher Tools, created with input from teachers and other experts. Teacher Tools is a web application designed as part of the MathSpring.org Intelligent Tutoring system --the component that teachers interact with, to set up classes as well as analyze resulting data from their students. In our study, we redesigned the existing version of MathSpring's Teacher Tools in three iterations, based on feedback gathered during each of those phases. The feedback captured from the first iteration clearly suggested for multiple design level changes with respect to math content organization, the interface, and the complexity level of the existing performance reports. Responses to Prototype I during the second iteration, designed on the basis of responses from the first iteration, were met by teachers with mixed to positive responses regarding usability and understandability. Experts at this point suggested further areas of improvement from a usability standpoint, which resulted in Prototype II of the Teacher Tools. Prototype II was then subjected to a third and final improvement iteration; this one was well received by a new set of 10 math teachers and other experts, who thought that Prototype II was very useful to them, in general. Teachers were able to appreciate the use they could give to these Teacher Tools to understand their students better, as well as guide future action plans that would alter their teaching based on information about their students' behavior, performance and affect of their students. In summary, we have created a software product for teachers that supplements the MathSpring tutoring system, which summarizes rich information from data logs into visualizations and other representations. These Teacher Tools have proved useful to teachers in Middle Schools in Massachusetts, who claim they are ready to use this information to change their teaching plans.
|
88 |
MusicVis : interactive visualization tool for exploring music rankings / MusicVis : ferramenta de visualização interativa para explorar rankings musicaisGuedes, Leandro Soares January 2017 (has links)
Os rankings musicais destinam-se principalmente a fins de marketing, mas também ajudam os usuários a descobrir novas músicas, bem como a comparar artistas, álbuns, etc. Este trabalho apresenta uma ferramenta interativa para visualizar, encontrar e comparar rankings musicais usando diferentes técnicas além de exibir atributos das músicas. A técnica foi concebida após uma pesquisa remota que coletou dados sobre como as pessoas escolhem música. As técnicas de visualização tornam mais fácil obter informações sobre artistas e faixas, e também comparar os dados obtidos a partir dos dois principais rankings de música, Billboard e Spotify. A ferrament também permite a interação com dados pessoais. Resultados de experimentos conduzidos com usuários potenciais mostraram que a ferramenta foi considerada interessante, com um layout atrativo. Comparando com as formas tradicionais de visualizar rankings de músicas, usuários preferiram a ferramenta aqui desenvolvida, mas a diferença para Billboard e Spotify não foi grande. Entretanto, quando avaliada a usabilidade da ferramenta, os resultados foram melhores, principalmente no que se refere à filtragem e às técnicas de comparação. MusicVis foi também considerado fácil de aprender. / Music rankings are mainly aimed at marketing purposes but also help users in discovering new music as well as comparing songs, artists, albums, etc. This work presents an interactive way to visualize, find and compare music rankings using different techniques, including the display of music attributes. The technique was conceived after a remote survey we conducted to collect data about how people choose music. Our visualization makes easier to obtain information about artists and tracks, and also to compare the data gathered from the two major music rankings, namely Billboard and Spotify. The tool also provides interaction with personal data. The results obtained from experiments with potential users showed that the tool was considered interesting, with an attractive layout. Compared to traditional music ranking tools users preferred ours, but with not such a large difference from using Billboard or Spotify. However, when evaluating the usability of our tool, results are positive, mainly concerning to data filtering and comparison features. MusicVis was also considered easy to learn.
|
89 |
Estudo de layout e avaliação de desempenho na área hospitalarBenitez, Guilherme Brittes January 2017 (has links)
Esta dissertação apresenta o uso de técnicas para o estudo de layout e avaliação de desempenho do setor de radiologia de um hospital universitário. A dissertação foi elaborada em formato de três artigos científicos, cujos temas e objetivos são: (i) aplicar a análise de conglomerados como etapa preliminar do planejamento sistemático de layout (Systematic Layout Planning – SLP) para planejar o layout do setor de radiologia de um hospital universitário; (ii) realizar uma revisão sistemática das técnicas e conceitos adotados para planejar layouts em ambientes hospitalares; e (iii) usar cartas de controle para avaliar o desempenho dos médicos do setor de radiologia de um hospital universitário. Os métodos desenvolvidos para os itens (i) e (iii) foram avaliados através da aplicação de estudos de caso, em exemplos com dados reais. Os métodos propostos para o item (i) foram adaptados especificamente para este caso. Para o item (ii) a metodologia proposta foi de pesquisa exploratória e descritiva, buscando referências na literatura para estudar e discorrer acerca do tema. Para o item (iii), o método foi implementado na prática em um ambiente onde existem apenas estudos de caráter conceitual. Os métodos apresentaram resultados satisfatórios em todos os casos. No primeiro artigo, chegou-se a um layout considerado ideal, separando zonas de ruído e de silêncio, e potencialmente melhorando a produtividade do setor de radiologia. Já no segundo artigo, conceitos, premissas e técnicas sobre o planejamento de layout em hospitais foram apresentados e difundidos, e lacunas e direcionamentos da pesquisa foram apontados. No terceiro artigo, foi possível avaliar o desempenho dos radiologistas através das cartas de controle e calcular a capacidade do processo usando os índices Cp e Cpk. / This study presents the use of techniques for the layout study and performance evaluation in a radiology sector of an university hospital. The study was performed in the form of three scientific articles, whose themes and objectives are: (i) to apply clustering analisys as the preliminary step of Systematic Layout Planning (SLP) to plan the layout of the radiology sector of a universitary hospital; (ii) to carry out a systematic review of the techniques and concepts adopted to plan layouts in hospital settings; and (iii) to use control charts to evaluate the performance of radiologists in a university hospital. The methods developed for items (i) and (iii) were evaluated through the application of case studies in examples with real data. The proposed methods for item (i) were adapted specifically for this case. For item (ii), the methodology proposed was exploratory and descriptive, seeking references in the literature to study and discuss the subject. For item (iii), the method was performed in a case study in an environment where there are only conceptual studies. The methods presented satisfactory results in all cases. In the first article, we reached an ideal layout, separating zones by noise and silence, and potentially improving the productivity of the radiology sector. In the second article, concepts, premises and techniques about layout planning in healthcare were presented and disseminated, gaps and directions of the research were pointed out. In the third article, it was possible to evaluate the performance of the radiologists through the control charts and to calculate the capacity of the process using the indexes Cp and Cpk.
|
90 |
Generalized autoregressive and moving average models: control charts, multicollinearity, and a new modified model / Modelos generalizados auto-regressivos e de médias móveis: gráficos de controle, multicolinearidade e novo modelo modificadoOrlando Yesid Esparza Albarracin 24 October 2017 (has links)
Recently, in the health surveillance area, control charts have been proposed to decide if the morbidity or mortality of a specific disease reached an epidemic level. This thesis is composed by 3 papers. In the first two papers, CUSUM and EWMA control charts were proposed to monitor count time series with seasonal and trend effects using the Generalized Autoregressive and Moving Average models (GARMA), instead of the independent Generalized Linear Model (GLM) as it is usually used in practice. Different statistics based on transformations, for variables that follow a Negative Binomial distribution, were used in these control charts. In the second paper, two new statistics were proposed based on the ratio of log-likelihood function. Different scenarios describing disease profiles were considered to evaluate the effect of omission of serial correlation in EWMA and CUSUM control charts. The performance of CUSUM and EWMA charts when the serial correlation is neglected in the regression model was measure in terms of average run length (ARL). In summary, when the autocorrelation is neglected, fitting a pure GLM instead of a GARMA model will lead to an increase of false alarms. However, no statistics among the tested ones seem to be robust, in a sense to produce the smallest increase of false alarms in all scenarios. In general, all monitored statistics presented a smaller ARL_0 for higher values of autocorrelation. \\\\ In the last paper, the GARMA models (p, q) with p and q simultaneously different from zero were studied since that two features were observed in practice. One is the multicollinearity, which may lead to a non-convergence of the maximum likelihood, using iteratively reweighted least squares. The second is the inclusion of the same lagged observations into the autoregressive and moving average components confounding the interpretation of the parameters. In a general sense, simulation studies show that the modified model provide estimators closer to the parameters and offer confidence intervals with higher coverage percentage than obtained with the GARMA model, but some restrictions in the parametric space are imposed to guarantee the stationarity of the process. Also, a real data analysis illustrate the GARMA-M fit for daily hospilatization rates of elderly people due to respiratory diseases from October 2012 to April 2015 in São Paulo city, Brazil. / Recentemente, no campo da saúde, gráficos de controle têm sido propostos para monitorar a morbidade ou a mortalidade decorrentes de doenças. Este trabalho está composto por três artigos. Nos dois primeiros artigos, gráficos de controle CUSUM e EWMA foram propostos para monitorar séries temporais de contagens com efeitos sazonais e de tendência usando os modelos Generalized autoregressive and moving average models (GARMA), em vez dos modelos lineares generalizados (GLM), como usualmente são utilizados na prática. Diferentes estatísticas baseadas em transformações, para variávies que seguem uma distribuição Binomial Negativa, foram usadas nestes gráficos de controle. No segundo artigo foram propostas duas novas estatísticas baseadas na razão da função de log-verossimilhança. Diferentes cenários que descrevem perfis de doenças foram considerados para avaliar o efeito da omissão da correlação serial nesses gráficos de controle. Este impacto foi medido em termos do Average Run Lenght (ARL). Notou-se que a negligência da correlação serial induz um aumento de falsos alarmes. Em geral, todas as estatísticas monitoradas apresentaram menores valores de ARL_0 para maiores valores de autocorrelação. No entanto, nenhuma estatística entre as consideradas mostrou ser mais robusta, no sentido de produzir o menor aumento de falsos alarmes nos cenários considerados. No último artigo, foram estudados os modelos GARMA (p, q) com p e q simultaneamente diferentes de zero, uma vez que duas características foram observadas na prática. A primeira é a presença de multicolinearidade, que induz à não-convergência do método de máxima verossimilhança usando mínimos quadrados ponderados reiterados. A segunda é a inclusão dos mesmos termos defasados nos componentes autorregressivos e de médias móveis. Um modelo modificado, GARMA-M, foi apresentado para lidar com a multicolinearidade e melhorar a interpretação dos parâmetros. Em sentido geral, estudos de simulação mostraram que o modelo modificado fornece estimativas mais próximas dos parâmetros e intervalos de confiança com uma cobertura percentual maior do que a obtida nos modelos GARMA. No entanto, algumas restrições no espaço paramétrico são impostas para garantir a estacionariedade do processo. Por último, uma análise de dados reais ilustra o ajuste do modelo GARMA-M para o número de internações diárias de idosos devido a doenças respiratórias de outubro de 2012 a abril de 2015 na cidade de São Paulo, Brasil.
|
Page generated in 0.0382 seconds