This study examines three applications of control charts used for monitoring syndromic data with different characteristics. The first part develops a seasonal autoregressive integrated moving average (SARIMA) based surveillance chart, and compares it with the CDC Early Aberration Reporting System (EARS) W2c method using both authentic and simulated data. After successfully removing the long-term trend and the seasonality involved in syndromic data, the performance of the SARIMA approach is shown to be better than the performance of the EARS method in terms of two key surveillance characteristics, the false alarm rate and the average time to detect the outbreaks. In the second part, we propose a generalized likelihood ratio (GLR) control chart to detect a wide range of shifts in the mean of Poisson distributed biosurveillance data. The application of a sign function on the original GLR chart statistics leads to downward-sided, upward-sided, and two-sided GLR chart statistics in an unified framework. To facilitate the use of such charts in practice, we provide detailed guidance on developing and implementing the GLR chart. Under the steady-state framework, this study indicates that the overall GLR chart performance in detecting a range of shifts of interest is superior to the performance of traditional control charts including the EARS method, Shewhart charts, EWMA charts, and CUSUM charts. There is often an excessive number of zeros involved in health care related data. Zero-inflated Poisson (ZIP) models are more appropriate than Poisson models to describe such data. The last part of the dissertation considers the GLR chart for ZIP data under a research framework similar to the second part. Because small sample sizes may influence the estimation of ZIP parameters, the efficiency of MLEs is investigated in depth, followed by suggestions for improvement. Numerical approaches to solving for the MLEs are discussed as well. Statistics for a set of GLR charts are derived, followed by modifications changing them from two-sided statistics to one-sided statistics. Although not a complete study of GLR charts for ZIP processes, due to limited time and resources, suggestions for future work are proposed at the end of this dissertation. / Ph. D.

When a reliability experiment is used, practitioners can understand better what lifetimes to expect of a product under different operating conditions and what factors are important to designing reliability into a product. Reliability experiments, however, can be very challenging to analyze because often the reliability or lifetime data tend to follow distinctly non-normal distributions and the experiments typically involve censoring. Time and cost constraints may also lead to reliability experiments with experimental protocols that are not completely randomized. In many industrial experiments, for example, the split-plot structure arises when the randomization of the experimental runs is restricted. Additionally, for many reliability experiments, it is often cost effective to apply a treatment combination to a stand with multiple units on it as opposed to each unit individually, which introduces subsampling. The analysis of lifetime data assuming a completely randomized design has been well studied, but until recently analysis methodologies for more complex experimental designs with multiple error terms have not been a focus of the reliability field. This dissertation provides two analysis methods for analyzing right-censored Weibull distributed lifetime data from a split-plot experiment with subsampling. We evaluate the proposed methods through a simulation study. Companies also routinely perform life tests on their products to ensure that products meet requirements. Each of these life tests typically involves testing several units simultaneously with interest in the times to failure. Again, the fact that lifetime data tend to be nonnormally distributed and censored make the development of a control charting procedure more demanding. In this dissertation, one-sided lower and upper likelihood ratio based cumulative sum (CUSUM) control charting procedures are developed for right-censored Weibull lifetime data to monitor changes in the scale parameter, also known as the characteristic life, for a fixed value of the Weibull shape parameter. Because a decrease in the characteristic life indicates a decrease in the mean lifetime of a product, a one-sided lower CUSUM chart is the main focus. We illustrate the development and implementation of the chart and evaluate the properties through a simulation study. / Ph. D.

In many US homes, 15% of the energy that can be saved is hidden beneath complex mathematical calculations. Hidden energy savings can be revealed by converting mathematical calculations to data visualizations, creating a story for residents to see how they are consuming energy. Cloud-based data visualization platforms offer the ability to appropriately communicate complex building energy data to a broad set of stakeholders. Unfortunately, proprietary solutions are too expensive and open-source options lack standardization for cloud-based energy monitoring. This study aims to create a comprehensive energy dashboard display to increase residents' energy awareness of how energy is consumed throughout their homes. But before energy dashboards can be created, a content analysis of current visualization chart types used on utility bills and energy monitoring devices were discovered to see how energy data has been visualized in the energy domain. Next, a literature review was conducted to reveal other visualization chart types outside of the energy domain that could be used to visualize energy data. The content analysis results identified eight visualization chart types that are used on utility bills and energy monitoring devices. In addition, the literature review uncovered eight additional visualization chart types that have the functionality to visualize energy data. Next, the visualization chart types were combined with data modeling design techniques to create prototype energy dashboard displays to communicate energy insights to residents. Soon utility companies will begin to provide data visualizations for the majority of their customers. The insights from this study can help to inform and lead the development of commercially used data visualizations. In addition, this research can provide utility companies with a blueprint on how to share energy consumption data with customers. / Master of Science / For residents to live an energy-efficient lifestyle, they must first begin by learning about one's energy consumption behaviors in the home. Unfortunately, utility bills miss out on communicating energy insights to customers based on how the energy data appears on the utility bill. Graphs on utility bills that display aggregate monthly energy consumption do not provide enough information for residents to comprehend how energy is consumed through their homes or provide information on how to lower energy consumption. There are commercial energy consumption devices on the market such as CURB and eGauge that provide an energy dashboard display, but the visuals are too complex to draw conclusions. This study aims to create an energy dashboard display that allows residents to see how energy is consumed throughout their homes. But before energy dashboards can be created, a content analysis of current visualization chart types used on utility bills and energy monitoring devices were discovered to see how energy data has been visualized in the energy domain. Next, a literature review was conducted to reveal other visualization chart types outside of the energy domain that could be used to visualize energy data. The content analysis results identified eight chart types used of utility bills and energy monitoring devices. In addition, the literature review results uncovered eight additional chart types not used on utility bills and energy monitoring devices that have the potential to visualize energy data. Next, the identified and uncovered chart types were combined with data modeling design techniques to create example energy dashboard displays. Changing the way energy data is displayed to residents, can educate residents on how energy is consumed throughout their home. In addition, the insights from this study can provide utility companies with a model for displaying energy data to increase their customers' energy awareness. Living an energy-efficient lifestyle, first began by understanding how energy is consumed throughout one's home.

Submitted by JOSIANE SANTOS DE OLIVEIRA (josianeso) on 2017-05-22T13:46:14Z No. of bitstreams: 1 Rossano Santos Noronha_.pdf: 585085 bytes, checksum: 88117b318c3e9c30134fce5bf0bdc22e (MD5) / Made available in DSpace on 2017-05-22T13:46:14Z (GMT). No. of bitstreams: 1 Rossano Santos Noronha_.pdf: 585085 bytes, checksum: 88117b318c3e9c30134fce5bf0bdc22e (MD5) Previous issue date: 2017-03-07 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Devido à dificuldade em se estimar os custos de operação associados ao monitoramento estatístico do processo nos trabalhos identificados na literatura, este trabalho tem por objetivo propor um modelo de otimização econômico para a carta de controle _X que considere as incertezas em relação aos custos variáveis e dependentes do desvio em relação à média do processo. O levantamento bibliográfico efetuado auxiliou no entendimento de como a incerteza em relação aos custos na utilização das cartas de controle são tratados. Percebeu-se o tratamento dos custos bem como do parâmetro de desvio do processo em relação a média _ como variáveis discretas e que impactavam na carta. A proposta aqui apresentada consiste em tratar não apenas o desvio em relação a média mas também dois dos custos associados à operação da carta de controle _X como variáveis aleatórias de distribuição contínua, inserindo assim um componente de incerteza na sua estimação. Desenvolveu-se assim uma nova formulação para o problema de otimização. Foram escolhidas instâncias para a otimização e comparados os resultados com os obtidos por autores da literatura. Os resultados foram obtidos por meio da metaheurística simulated annealing. Como resultados, o método mostrou-se eficiente, mostrando que o nível de dependência entre o parâmetro de mudança de processo e o custo e, da incerteza que se tem quanto aos valores definidos de custo de operação impactam nos custos totais de operação do CEP. A principal contribuição deste trabalho de pesquisa está na apresentação de uma formulação matemática de otimização da carta de controle _X que trata não somente o desvio em relação à média do processo mas também os custos de operação do CEP como variáveis aleatórias. A originalidade da formulação está em considerar os custos linearmente dependentes do tamanho do desvio do processo em relação a sua média. / Due to the difficulty in estimating the operating costs associated to the statistical monitoring of the process described in the literature, this paper aims to propose a model of economic optimization for the _X control chart that considers the uncertainties in relation to the variable costs and dependent on the deviation in relation to the average of the process. The literature review performed supported the understanding of how the uncertainty in relation to costs in the use of control charts is treated. The treatment of the costs as well as the parameter of deviation of the process in relation to the _ average were indicated as discrete variables and that impacted on the chart. The proposal presented here consists of treating not only the deviation from the mean but also two costs associated with the operation of the _X control chart as random variables of continuous distribution, thus inserting a component of uncertainty in its estimation. A new formulation for the optimization problem was developed. Instances for optimization were chosen and the results were compared with those obtained by authors described in the literature. The results were obtained through simulated annealing metaheuristics. As a result, the method proved to be efficient, showing that the level of dependence between the process change parameter and the cost, as well as the uncertainty regarding the defined operating cost values impact on the total cost of operation of the SPC. The main contribution of this research work is the presentation of a mathematical formulation of optimization of the _X control chart that treats not only the deviation in relation to the average of the process but also the operating costs of the SPC as random variables. The originality of the formulation is to consider costs linearly dependent on the size of the process deviation in relation to its mean.

Statistical process control (SPC) applies the science of statistics to various process control in order to provide higher-quality products and better services. The K chart is one among the many important tools that SPC offers. Creation of the K chart is based on Support Vector Data Description (SVDD), a popular data classifier method inspired by Support Vector Machine (SVM). As any methods associated with SVM, SVDD benefits from a wide variety of choices of kernel, which determines the effectiveness of the whole model. Among the most popular choices is the Euclidean distance-based Gaussian kernel, which enables SVDD to obtain a flexible data description, thus enhances its overall predictive capability. This thesis explores an even more robust approach by incorporating the Mahalanobis distance-based kernel (hereinafter referred to as Mahalanobis kernel) to SVDD and compare it with SVDD using the traditional Gaussian kernel. Method's sensitivity is benchmarked by Average Run Lengths obtained from multiple Monte Carlo simulations. Data of such simulations are generated from multivariate normal, multivariate Student's (t), and multivariate gamma populations using R, a popular software environment for statistical computing. One case study is also discussed using a real data set received from Halberg Chronobiology Center. Compared to Gaussian kernel, Mahalanobis kernel makes SVDD and thus the K chart significantly more sensitive to shifts in mean vector, and also in covariance matrix.

Detta projekt har genomförts under våren 2016 som ett examensarbete för högskole- ingenjörsprogrammet i innovationsteknik och design vid fakulteten för hälsa, natur- och teknikvetenskap på Karlstads universitet. Den största delen av arbetet utfördes på BAE Systems Bofors ABs eftermarknads- avdelning i Karlskoga. Där gjordes intervjuer och observationer för att kartlägga det nuvarande flödet och tillämpa metoder kring ett förbättringsarbete som studerats under projektets förstudie. Förstudien omfattade en stor litteraturunder-sökning kring arbetssätt och metoder för förbättringsarbeten, som sammanfattades i rapportens teoretiska referensram. De metoder som användes under projektet grundades i arbetssätten Lean och Sex Sigma samt den produktutvecklingsprocess som studerats tidigare under utbildningen. Några exempel på metoder som utfördes under projektet var administrativt spagettidiagram, värdeflödesanalys, ABC-analys och brainstorming. Sammanlagt hittades tolv problemområden i eftermarknadsflödet som studerades närmre. Dessa sammanfattades slutligen i en manual tillsammans med en djupare analys varför de olika problemen uppstått, förslag på hur de skulle kunna lösas eller förbättras samt förslag på hur ett eventuellt utslag av ett infört förbättringsarbete skulle kunna mätas. Exempel på ett problemområde som hittades under arbetet och sammanställdes i manualen var att företaget inte arbetade integrerat och behövde prioritera sitt eftermarknadsflöde. I lösningsförslaget förklarades varför företaget skulle ha fördel till att satsa mer på sin eftermarknad och dess flöde, hur viktigt det är att sätta kunden i fokus och att motivera samtliga medarbetare i flödet att arbeta effektivt. Det måttförslag som presenterades tillsammans med detta problemområde var en medarbetarenkät. I slutet av manualen presenterades även en prioritetsordning på de tolv avsnitten, för att företaget skulle ha underlag till att enkelt föra en diskussion om hur ett förbättrings- arbete skulle kunna påbörjas. / The project has been implemented as a thesis of Bachelor of Science in Innovation and Design at the Faculty of Health, Science and Technology at Karlstad University in the spring of 2016. Most of the work has been performed at BAE Systems Bofors AB’s aftermarket section in Karlskoga. The work included interviews and observations to identify the current flow and to apply methods of improvement on it. The feasibility study involved a large literature study on the methods and techniques of improvement, as summarized in the report's theoretical chapter. The methods that were used in the project were found in Lean, Six Sigma and the product development process, all of which were studied earlier in the education. Some examples of methods that were applied in the project were administrative spaghetti diagrams, Value Stream Mapping-analysis, ABC-analysis and brainstorming. A lot of problems were found in the aftermarket flow and twelve of those were more closely studied. These twelve problems were then summarized in a manual along with an in-depth analysis on why the problem had occurred, suggestions on how they could be resolved or improved and proposals on how a possible alteration of an introduced improvement could be measured. One example of problems that were found and gathered in the manual was that the company doesn’t work in an integrated way and need to prioritize the aftermarket flow. The suggested solution was to explain to the company why they would have to spend more resources on the aftermarket flow and motivate all employees that are involved. The solution also explained how important it is to focus on the customer and get the employees in the flow to work more efficiently. At the end of the manual a priority list of the twelve problem areas is presented. This priority list was made so the company more easily could start a discussion about the improvement work and how it could begin.

Detta examensarbete handlar om hur man kan gå tillväga för att finna orsaken till att kvalitetsfel uppstår i en tillverkningsprocess och hur man kan förhindra att samma kvalitetsproblem fortsätter att existera. En central del i examensarbetet har även varit att belysa vikten av att identifiera ett problems grundorsak. Syftet med studien är att belysa några av flera metoder som kan användas för att hitta orsaker till kvalitetsrelaterade fel inom tillverkningsindustrin. De data som samlats in och står i grund för resultatet och slutsatserna har bestått av litteraturstudier, observationer och intervjuer. De kvalitetsverktygen som framfördes i studien är ”Fem varför” och Ishikawadiagram, vilket är två verktyg som bland annat gör det möjligt att upptäcka grundorsaken till ett problems uppkomst. De praktiska tillämpningarna av kvalitetsverktygen är presenterade i en fallstudie som har utförts på Johnson Controls AB i Göteborg, Sverige. Fallstudien är gjord på en av flera produktionslinor där ett rådande problem med kvalitet ansågs vara kritiskt. Slutsatserna som har dragits av detta examenarbete är att det är viktigt att identifiera grundorsaken till ett problems uppkomst för att kunna implementera en långsiktig åtgärd. Risken med att endast lindra ett problems symptom (och inte roten till dess uppkomst) är att det aldrig elimineras utan existerar och ständigt kräver resurser för att lindras. Genom att identifiera ett problems grundorsak kan man därmed se till att det inte uppstår igen, eftersom det då kan elimineras. Det finns olika metoder och verktyg som kan användas för att identifiera grundorsaken till ett problem, två stycken som nämns i rapporten är ”Fem varför” och Ishikawadiagram. Det är viktigt att fokus och resurser läggs på ett sådant långsiktigt arbete. / This thesis is about how you can find the cause of quality defects in manufacturing processes and how to prevent that the same issue continue to exist. A part of the thesis illuminate the importance of identifying the root cause of a problem. The purpose of the study is to highlight some of the many methods that can be used to fins the causes for defects concerning quality in the industrial sector. The data that is collected and are the basis for the result and conclusions of the case study consisted of literature studies, observations and interviews. The quality tools that are presented in the study are “Five Whys” and the Ishikawa chart, which are two tools that, among others, makes it possible to find the root cause of a problems occurrence. The practical applications of the quality tools are presented in a case study that was conducted at Johnson Controls AB in Gothenburg, Sweden. The case study was based on observations concerning one of several production lines, where the current quality problem was critical. The conclusions drawn from this thesis is that it is important to identify the root cause of the occurrence of a problem in order to implement long-term actions and measures. The risk that comes with only reliving the symptom of a problem (and not the root of it) is that it will not be eliminated but exists and constantly requires resources to be alleviated. By identifying the root cause of a problem, one can be assure that it will not occur again, since it will be eliminated. There are various methods and tools that can be used to identify the root cause of a problem; two of them that are mentioned in the report is “Five Whys” and the Ishikawa chart. It is important to focus and resources are spent on such a long-term actions and efforts.

A l’hôpital, le bloc opératoire représente un environnement à risque pour le patient. La réalisation d’une chirurgie thyroïdienne demeure une tâche complexe dont le résultat dépend de la combinaison d’une multitude de facteurs qui demeurent mal connus. L’application des méthodes de contrôle qualité développées dans l’industrie peut être utile à leur découverte. Pendant quatre années, nous avons suivi la performance collective et individuelle d’une équipe chirurgicale à l’aide de cartes de contrôle. Des cartes de Shewhart et des cartes CUSUM ont été conçues pour analyser les variations des complications de la thyroïdectomie au cours du temps. Leur mise en place s’est accompagnée d’une réduction immédiate des hypocalcémies postopératoires, puis d’une stabilisation progressive des paralysies récurrentielles. La suractivité chirurgicale a été identifiée comme cause à l’origine d’une dégradation momentanée de la performance de l’équipe. Cette expérience de terrain a montré l’applicabilité des cartes de contrôle à la chirurgie thyroïdienne ainsi que leur intérêt pour aider les chirurgiens à interpréter la variabilité de leurs résultats et à maitriser les facteurs y concourant. Cependant, seules des actions concrètes destinées à améliorer la qualité de la prise en charge peuvent réduire la survenue de complications opératoires. Leur conception implique de mieux comprendre les facteurs influençant la performance du chirurgien et le travail en équipe au bloc opératoire pour garantir la sécurité du patient. / The operating room represents a high risk environment for the patient. Thyroid surgery remains a complex task whose outcome depends on the combination of poorly understood factors. Implementation of industrial quality control methods can be helpful in discovering them. For four years, we have monitored the individual and collective performance of a surgical team using control charts. Shewhart and CUSUM charts have been designed for analyzing the variations of thyroidectomy related complications over time. Their introduction immediately led to a reduction of postoperative hypocalcaemia, and then to a gradual stabilization of recurrent nerve palsy. The surgical overactivity was identified as a root cause of a temporary worsening of the team performance. This field study has shown the applicability of control charts in thyroid surgery and their value to assist surgeons in interpreting and controlling their results' variability. However, only concrete actions aiming at improving the quality of care may reduce the incidence of surgical complications. Designing these actions involves understanding the factors that influence the surgeon's performance and teamwork within operating room to ensure the patient safety.

The thesis discusses the possibilities of project management and analysis and it is focused on solving project analysis using the network analysis. The text describes chosen used methods of analysis. This text together with other findings in the theoretical part is used in the solution of practice part. The aim of this thesis was to create a functional Microsoft Project-based add-in of Microsoft Excel to ensure planning and management of simple projects. This created add-in can manage the project, manage project resources, allocate these resources to individual project activities and carry out simple analysis of the project, including a Gantt chart.

The project was performed at Parker Hannifin Cylinder Division at Falköping, where a station in the most critical flow at the production has been studied, which is the hand welding station. Within this report, the purpose is to identify disturbances, in order to eliminate and reduce these by coming up with improvement proposals. Furthermore, the aim is to help improve the company's work with 5S and TPM (Total Productive Maintenance). A combination of tools and concepts are being used in this project when generating improvement proposals to avoid the risk of falling back into old habits and facilitate the work. The combination of concepts, intends to be continued to work with, in order to facilitate for the company to reach even higher results.The methodology of TPM is the basis of the project, although it is not about a complete implementation of TPM, but is limited to chosen parts since it is a time consuming process that can go on for years. The main focus of TPM is about the first pillar, 5S. Action plans for how to solve these problems and how to achieve the desired state has been established.Thereafter, the researchers in cooperation with the company´s staff have implemented a couple of small improvement proposals. Further improvement proposals have also been presented in this report, but due to the limited time no implementations was made.Moreover, this project is divided into a couple of phases. Situational analysis has been made through both interviews with staff and observation studies. Analysis has also been made by some numeric data taken out by researchers and partly through mapping the equipment. The intention of this is to create a status image of the current situation over the hand welding station. The current state has shown the appearance of problems and challenges that exist. Additional wastages and disturbances in the station can come up to the surface and can thus easily be identified. In turn, occurring wastages and disturbances can be eliminated and the amount of wasted time reduced with help of the action plans to reach a future state.Another method that occurs is spaghetti charts. It has been used for mapping up the existing procedures during the process of the orders in the station, and by that identified different types of disturbances. In addition, the creation of a Value Stream Mapping (VSM) has been made. The map is used as a measurement to identify how much time on a working day that is spent as value adding time and non-value adding time of work.