Дисертації з теми "Prognostics prediction model"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-31 дисертацій для дослідження на тему "Prognostics prediction model".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
Mishra, Madhav. "Model-based Prognostics for Prediction of Remaining Useful Life." Licentiate thesis, Luleå tekniska universitet, Drift, underhåll och akustik, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-17263.
Повний текст джерелаGodkänd; 2015; 20151116 (madmis); Nedanstående person kommer att hålla licentiatseminarium för avläggande av teknologie licentiatexamen. Namn: Madhav Mishra Ämne: Drift och underhållsteknik/Operation and Maintenance Engineering Uppsats: Model-based Prognostics for Prediction of Remaining Useful Life Examinator: Professor Uday Kumar Institutionen för samhällsbyggnad och naturresurser Avdelning Drift, underhåll och akustik Luleå tekniska universitet Diskutant: Accos. Professor Jyoti Kumar Sinha University of Manchester, Aerospace and Civil Engineering, Manchester Tid: Torsdag 17 december 2015 kl 10.00 Plats: F1031, Luleå tekniska universitet
Nguyen, Hoang-Phuong. "Model-based and data-driven prediction methods for prognostics." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASC021.
Повний текст джерелаDegradation is an unavoidable phenomenon that affects engineering components and systems, and which may lead to their failures with potentially catastrophic consequences depending on the application. The motivation of this Thesis is trying to model, analyze and predict failures with prognostic methods that can enable a predictive management of asset maintenance. This would allow decision makers to improve maintenance planning, thus increasing system availability and safety by minimizing unexpected shutdowns. To this aim, research during the Thesis has been devoted to the tailoring and use of both model-based and data-driven approaches to treat the degradation processes that can lead to different failure modes in industrial components, making use of different information and data sources for performing predictions on the degradation evolution and estimating the Remaining Useful Life (RUL).The Ph.D. work has addressed two specific prognostic applications: model-based prognostics for fatigue crack growth prediction and data-driven prognostics for multi-step ahead predictions of time series data of Nuclear Power Plant (NPP) components.Model-based prognostics relies on the choice of the adopted Physics-of-Failure (PoF) models. However, each degradation model is appropriate only to certain degradation process under certain operating conditions, which are often not precisely known. To generalize this, ensembles of multiple degradation models have been embedded in the model-based prognostic method in order to take advantage of the different accuracies of the models specific to different degradations and conditions. The main contributions of the proposed ensemble of models-based prognostic approaches are the integration of filtering approaches, including recursive Bayesian filtering and Particle Filtering (PF), and novel weighted ensemble strategies considering the accuracies of the individual models in the ensemble at the previous time steps of prediction. The proposed methods have been validated by case studies of fatigue crack growth simulated with time-varying operating conditions.As for multi-step ahead prediction, it remains a difficult task of Prognostics and Health Management (PHM) because prediction uncertainty tends to increase with the time horizon of the prediction. Large prediction uncertainty has limited the development of multi-step ahead prognostics in applications. To address the problem, novel multi-step ahead prediction models based on Long Short- Term Memory (LSTM), a deep neural network developed for dealing with the long-term dependencies in the time series data have been developed in this Thesis. For realistic practical applications, the proposed methods also address the additional issues of anomaly detection, automatic hyperparameter optimization and prediction uncertainty quantification. Practical case studies have been considered, concerning time series data collected from Steam Generators (SGs) and Reactor Coolant Pumps (RCPs) of NPPs
Alrabady, Linda Antoun Yousef. "An online-integrated condition monitoring and prognostics framework for rotating equipment." Thesis, Cranfield University, 2014. http://dspace.lib.cranfield.ac.uk/handle/1826/9204.
Повний текст джерелаGorjian, Nima. "Asset health prediction using the explicit hazard model." Thesis, Queensland University of Technology, 2012. https://eprints.qut.edu.au/57314/1/Nima_Gorjian_Jolfaei_Thesis.pdf.
Повний текст джерелаTamssaouet, Ferhat. "Towards system-level prognostics : modeling, uncertainty propagation and system remaining useful life prediction." Thesis, Toulouse, INPT, 2020. http://www.theses.fr/2020INPT0079.
Повний текст джерелаPrognostics is the process of predicting the remaining useful life (RUL) of components, subsystems, or systems. However, until now, the prognostics has often been approached from a component view without considering interactions between components and effects of the environment, leading to a misprediction of the complex systems failure time. In this work, a prognostics approach to system-level is proposed. This approach is based on a new modeling framework: the inoperability input-output model (IIM), which allows tackling the issue related to the interactions between components and the mission profile effects and can be applied for heterogeneous systems. Then, a new methodology for online joint system RUL (SRUL) prediction and model parameter estimation is developed based on particle filtering (PF) and gradient descent (GD). In detail, the state of health of system components is estimated and predicted in a probabilistic manner using PF. In the case of consecutive discrepancy between the prior and posterior estimates of the system health state, the proposed estimation method is used to correct and to adapt the IIM parameters. Finally, the developed methodology is verified on a realistic industrial system: The Tennessee Eastman Process. The obtained results highlighted its effectiveness in predicting the SRUL in reasonable computing time
Sánchez, Sardi Héctor Eloy. "Prognostics and health aware model predictive control of wind turbines." Doctoral thesis, Universitat Politècnica de Catalunya, 2017. http://hdl.handle.net/10803/463321.
Повний текст джерелаEls components dels aerogeneradors estan sotmesos a considerable estrès i fatiga, degut a les condicions ambientals extremes a les quals estan exposats, especialment els localitzats en alta mar. Per aquest motiu, al comunitat científica durant els últims anys ha investigat les averies més comunes presents en els aerogeneradors, fet que ha portat a proposar un cas d'estudi de diagnosi i control tolerant de fallades que inclou un conjunt de fallades que afecten a diversos components dels aerogeneradors. Aquesta tesi presenta algunes contribucions en els camps de la diagnosi de fallades, el control tolerant de fallades i la prognosi, així com la seva integració amb el control d'aerogeneradors, fet que ha portat a proposar una tècnica de control anomenada control predictiu basada en models conscients de la salut del sistema (HAMPC). Concretament les aportacions es poden resumir en: - Diagnosi de fallades basada en models: per a la detecció s'utilitzen observadors intervalars i l'aïllament de la fallada es fa en base el conjunt d'ARRs obtinguts de l'anàlisi estructural i de la matriu de signatures de fallades que relaciona les ARRs amb les fallades. - Control tolerant de fallades: es proposa un esquema de control tolerant a fallades que integra la detecció de fallades i algoritme d'acomodació de fallades, i té per objectiu evitar l'augment de càrregues en la pala i la torre quan es produeix una fallada en el sensor azimuth quan es fa un control individual de la inclinació de les pales (IPC). - Prognosi de la fatiga i la degradació de les pales: la fatiga s'avalua amb un algorisme denominat "rainflow counting" amb el qual es fa estimació del dany acumulat i per a la degradació es fa servir un model de degradació de la rigidesa del material amb el qual es fan prediccions de la vida útil restant (RUL). - Control de la salut d'aerogeneradors: s'ha integrat la gestió de la salut del sistema basat en danys per fatiga o prediccions de RUL amb control predictiu basat en models (MPC) donant lloc al control que anomenem HAMPC. Les contribucions presentades en aquesta tesi han sigut validades en un cas d'estudi d'aerogeneradors basat en un aerogenerador de referència de 5MW de potència implementat en el simulador d'aerogeneradors d'alta fidelitat conegut amb el nom de FAST.
Moskowitz, Chaya S. "Quantifying and comparing the predictive accuracy of prognostic factors /." Thesis, Connect to this title online; UW restricted, 2002. http://hdl.handle.net/1773/9610.
Повний текст джерелаIwakami, Naotsugu. "Optimal Sampling in Derivation Studies was Associated with Improved Discrimination in External Validation for Heart Failure Prognostic Models." Kyoto University, 2020. http://hdl.handle.net/2433/259731.
Повний текст джерелаGwilliam, Bridget. "The development of prognostic models for predicting survival in patients with advanced cancer." Thesis, St George's, University of London, 2010. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.546796.
Повний текст джерелаMarques, Maria João Pereira Vicente Dias. "Análise retrospetiva de 92 casos de cólica em equinos admitidos em segunda opinião para tratamento hospitalar." Master's thesis, Universidade de Lisboa, Faculdade de Medicina Veterinária, 2018. http://hdl.handle.net/10400.5/15833.
Повний текст джерелаA cólica é uma patologia de importância preeminente em equinos, cuja identificação da causa nem sempre é fácil, fazendo com que a determinação precoce de um prognóstico seja essencial. Assim, foi realizado um estudo retrospetivo em 92 casos de cólica recebidos pelo Serviço de Cirurgia e Urgência em Equinos da FMV-ULisboa. Os objetivos do presente estudo foram: 1) caracterizar os casos de cólica referenciados para o SCUE FMV-ULisboa, avaliando o tipo de intervenção clínica, a causa de cólica e a taxa de alta hospitalar; 2) avaliar o valor prognóstico de cada um dos indicadores recolhidos na admissão; 3) comparar o valor destes indicadores entre os dois tipos de intervenção clínica, médica e cirúrgica; e 4) elaborar um modelo multivariado de predição de prognóstico. Estimou-se que 82% dos animais submetidos a intervenção cirúrgica e 75% dos animais tratados medicamente tiveram alta hospitalar, e que 25% dos animais submetidos a laparotomia sofreram íleo pós-cirúrgico. Foram recolhidos na admissão os seguintes dados: idade, tempo entre sinalização e admissão hospitalar, refluxo gastrointestinal, frequência cardíaca, hematócrito, proteínas totais séricas, proteínas totais do líquido peritoneal, lactato peritoneal e lactato sanguíneo. Nas cólicas médicas, os indicadores hematócrito, frequência cardíaca e lactato peritoneal foram considerados estatisticamente significativos (p<0,05), o lactato sanguíneo marginalmente significativo (p=0,053) e as proteínas do líquido peritoneal tendencialmente significativas (p<0,10). Foram elaborados dois modelos de predição multivariável. O modelo de 3 preditores (lactato sanguíneo, frequência cardíaca e hematócrito) com especificidade de 42,9% e sensibilidade de 96,0%. O modelo de 5 preditores (lactato sanguíneo, frequência cardíaca, hematócrito, idade e proteínas totais séricas) com especificidade de 71,4% e sensibilidade de 95,7%. Nas cólicas cirúrgicas, não foi possível determinar preditores significativos nem elaborar modelos de predição. Foi, ainda, criada uma aplicação informática de cálculo de probabilidade de alta hospitalar com base nos modelos descritos. Finalmente, conclui-se que a recolha de líquido peritoneal deverá ser feita com mais frequência pois os seus indicadores parecem transmitir informação valiosa. O modelo de 3 preditores, apesar de ter uma especificidade menor para a amostra em estudo, será provavelmente mais fiável do ponto de vista clínico, para utilização futura. Para além disso, é espectado que com o aumento da dimensão da amostra, estes modelos se tornem mais robustos.
ABSTRACT - A RETROSPECTIVE REVIEW OF 92 EQUINE COLIC CASES REFERRED FOR HOSPITAL TREATMENT - Colic is a really important syndrome in the equine species. To identify a diagnosis can be a true challenge, so the early determination of a prognosis is essential. Therefore, a retrospective study was performed in 92 colic cases admitted at the “Equine Surgery and Emergency Services” (Lisbon University). The objectives of this study were: 1) describe the colic cases and evaluate the clinical approach (medical or surgical), the origin of the problem and rate of survival; 2) estimate the prognostic value of each one of the collected predictors at the admission process; 3) compare the predictors according to the clinical approach; and 4) elaborate a multivariable prognostic prediction model. In this study, the survival rate was 82% for the horses submitted to surgical intervention and 75% for the horses treated medically; and, 25% of the horses in which laparotomy was performed developed post-operative ileus. The following data were collected during admission at the hospital: age, time between the onset of clinical signs and referral, gastrointestinal reflux, cardiac frequency, haematocrit, blood total protein, peritoneal fluid total protein, peritoneal fluid lactate, blood lactate. In medical colics, haematocrit, cardiac frequency and peritoneal fluid lactate were statistically significant (p<0,05), blood lactate was marginally significant (p=0,053) and peritoneal fluid total protein was tendentially significant (p<0,10). Two multivariable prognostic prediction models were elaborated. The three predictors model (blood lactate, cardiac frequency and haematocrit) had a specificity of 42,9% and a sensibility of 96,0%. The five predictors model (blood lactate, cardiac frequency, haematocrit, blood total protein and age) had a specificity of 71,4% and a sensibility of 95,7%. In surgical colics, it wasn’t possible to determine statistically significant predictors neither to elaborate prediction models. Based on the previously descript models, a computerized application to calculate the survival probability was created. It was concluded that peritoneal fluid should be collected more often, since peritoneal lactate and peritoneal fluid total protein seem to be providers of valuable information. Even though, the three predictors model has a reduced specificity for the study sample, it will be probably more reliable from the clinical point of view for further applications. Furthermore, it’s expected that with the increasing of the sample size, these models will get more robust.
N/A
Fernandes, Ana Sofia Fachada. "Prognostic modelling of breast cancer patients: a benchmark of predictive models with external validation." Doctoral thesis, Faculdade de Ciências e Tecnologia, 2010. http://hdl.handle.net/10362/5087.
Повний текст джерелаThere are several clinical prognostic models in the medical field. Prior to clinical use, the outcome models of longitudinal cohort data need to undergo a multi-centre evaluation of their predictive accuracy. This thesis evaluates the possible gain in predictive accuracy in multicentre evaluation of a flexible model with Bayesian regularisation, the (PLANN-ARD), using a reference data set for breast cancer, which comprises 4016 records from patients diagnosed during 1989-93 and reported by the BCCA, Canada, with follow-up of 10 years. The method is compared with the widely used Cox regression model. Both methods were fitted to routinely acquired data from 743 patients diagnosed during 1990-94 at the Christie Hospital, UK, with follow-up of 5 years following surgery. Methodological advances developed to support the external validation of this neural network with clinical data include: imputation of missing data in both the training and validation data sets; and a prognostic index for stratification of patients into risk groups that can be extended to non-linear models. Predictive accuracy was measured empirically with a standard discrimination index, Ctd, and with a calibration measure, using the Hosmer-Lemeshow test statistic. Both Cox regression and the PLANN-ARD model are found to have similar discrimination but the neural network showed marginally better predictive accuracy over the 5-year followup period. In addition, the regularised neural network has the substantial advantage of being suited for making predictions of hazard rates and survival for individual patients. Four different approaches to stratify patients into risk groups are also proposed, each with a different foundation. While it was found that the four methodologies broadly agree, there are important differences between them. Rules sets were extracted and compared for the two stratification methods, the log-rank bootstrap and by direct application of regression trees, and with two rule extraction methodologies, OSRE and CART, respectively. In addition, widely used clinical breast cancer prognostic indexes such as the NPI, TNM and St. Gallen consensus rules, were compared with the proposed prognostic models expressed as regression trees, concluding that the suggested approaches may enhance current practice. Finally, a Web clinical decision support system is proposed for clinical oncologists and for breast cancer patients making prognostic assessments, which is tailored to the particular characteristics of the individual patient. This system comprises three different prognostic modelling methodologies: the NPI, Cox regression modelling and PLANN-ARD. For a given patient, all three models yield a generally consistent but not identical set of prognostic indices that can be analysed together in order to obtain a consensus and so achieve a more robust prognostic assessment of the expected patient outcome.
Bert, Dulanto Aimée. "Predicting mortality in patients diagnosed with pulmonary tuberculosis: a systematic review of prognostic models." Bachelor's thesis, Universidad Peruana de Ciencias Aplicadas (UPC), 2021. http://hdl.handle.net/10757/656150.
Повний текст джерелаOBJETIVO Sintetizar la evidencia acerca de modelos pronósticos que predicen mortalidad en pacientes con tuberculosis pulmonar. METODOLOGÍA. El siguiente estudio sigue las guías PRISMA del año 2020 (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). Se realizó una búsqueda literaria, por tres revisores, de modelos pronósticos que se enfocaban en predecir mortalidad en pacientes diagnosticados con tuberculosis pulmonar. Se incluyeron estudios prospectivos y retrospectivos, donde los modelos pronósticos que predecían mortalidad habían sido desarrollados o validados en pacientes con tuberculosis pulmonar. De manera independiente, tres revisores evaluaron la calidad de los estudios incluidos usando la herramienta PROBAST (¨Prediction model study Risk Of Bias Assessment Tool¨), la cual evalúa el riesgo de sesgo y la aplicabilidad de cada modelo. Se realizó un análisis descriptivo de cada modelo de predicción, su performance, y las características de la población. RESULTADOS. Solo 6 artículos cumplieron los criterios de selección. Hubo un total de 6 modelos pronósticos, uno en cada artículo. La mayoría de los estudios (5 de 6) fueron cohortes retrospectivas, y solo uno fue un estudio de casos y controles prospectivo. Al sumar la población total de los estudios, hubo un total de 3,553 participantes, con muestras desde 103 hasta 1070 participantes. Todos los estudios obtuvieron un alto riesgo de sesgo, de acuerdo a la herramienta PROBAST, en la evaluación global. Además, la evaluación global mostró que 3 estudios obtuvieron una baja preocupación de aplicabilidad, 2 alta preocupación y un estudio preocupación indeterminada. Solo 5 estudios desarrollaron nuevas reglas de predicción, mientras que uno válido una ya existente. En general los modelos de predicción mostraron una buena habilidad discriminatoria, con valores de área bajo la curva que fluctuaban entre 0.65 hasta 0.91. El modelo de predicción con mayor poder discriminatorio fue el reportado por Horita, et – al con un valor de área bajo la curva de 0.910 en la cohorte de desarrollo y 0.893 en la cohorte de validación. CONCLUSIÓN. Tomando en cuenta que la tuberculosis pulmonar es una enfermedad prevalente en países de desarrollo, sería útil contar con herramientas que ayuden a los profesionales de la salud a catalogar a los pacientes con mayor riesgo de mortalidad, para que así ellos puedan recibir atención médica prioritaria.
Tesis
Bole, Brian McCaslyn. "Load allocation for optimal risk management in systems with incipient failure modes." Diss., Georgia Institute of Technology, 2013. http://hdl.handle.net/1853/50394.
Повний текст джерелаKawada, Hironori. "Incorporation of apical lymph node status into the seventh edition of the TNM classification improves prediction of prognosis in stage Ⅲ colonic cancer." Kyoto University, 2016. http://hdl.handle.net/2433/215450.
Повний текст джерелаSOUTO, MAIOR Caio Bezerra. "Remainig useful life prediction via empirical mode decomposition, wavelets and support vector machine." Universidade Federal de Pernambuco, 2017. https://repositorio.ufpe.br/handle/123456789/24930.
Повний текст джерелаMade available in DSpace on 2018-06-26T22:26:10Z (GMT). No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) DISSERTAÇÃO Caio Bezerra Souto Maior.pdf: 3924685 bytes, checksum: 6968386bf75059f45ee80306322d2a56 (MD5) Previous issue date: 2017-02-21
CAPES
The useful life time of equipment is an important variable related to reliability and maintenance. The knowledge about the useful remaining life of operation system by means of a prognostic and health monitoring could lead to competitive advantage to the corporations. There are numbers of models trying to predict the reliability’s variable behavior, such as the remaining useful life, from different types of signal (e.g. vibration signal), however several could not be realistic due to the imposed simplifications. An alternative to those models are the learning methods, used when exist many observations about the variable. A well-known method is Support Vector Machine (SVM), with the advantage that is not necessary previous knowledge about neither the function’s behavior nor the relation between input and output. In order to achieve the best SVM’s parameters, a Particle Swarm Optimization (PSO) algorithm is coupled to enhance the solution. Empirical Mode Decomposition (EMD) and Wavelets rise as two preprocessing methods seeking to improve the input data analysis. In this paper, EMD and wavelets are used coupled with PSO+SVM to predict the rolling bearing Remaining Useful Life (RUL) from a vibration signal and compare with the prediction without any preprocessing technique. As conclusion, EMD models presented accurate predictions and outperformed the other models tested.
O tempo de vida útil de um equipamento é uma importante variável relacionada à confiabilidade e à manutenção, e o conhecimento sobre o tempo útil remanescente de um sistema em operação, por meio de um monitoramento do prognóstico de saúde, pode gerar vantagens competitivas para as corporações. Existem diversos modelos utilizados na tentativa de prever o comportamento de variáveis de confiabilidade, tal como a vida útil remanescente, a partir de diferentes tipos de sinais (e.g. sinal de vibração), porém alguns podem não ser realistas, devido às simplificações impostas. Uma alternativa a esses modelos são os métodos de aprendizado, utilizados quando se dispõe de diversas observações da variável. Um conhecido método de aprendizado supervisionado é o Support Vector Machine (SVM), que gera um mapeamento de funções de entrada-saída a partir de um conjunto de treinamento. Para encontrar os melhores parâmetros do SVM, o algoritmo de Particle Swarm Optimization (PSO) é acoplado para melhorar a solução. Empirical Mode Decomposition (EMD) e Wavelets são usados como métodos pré-processamento que buscam melhorar a qualidade dos dados de entrada para PSO+SVM. Neste trabalho, EMD e Wavelets foram usadas juntamente com PSO+SVM para estimar o tempo de vida útil remanescente de rolamentos a partir de sinais de vibração. Os resultados obtidos com e sem as técnicas de pré-processamento foram comparados. Ao final, é mostrado que modelos baseados em EMD apresentaram boa acurácia e superaram o desempenho dos outros modelos testados.
Pradella, Lorenzo. "A data-driven prognostic approach based on AR identification and hidden Markov models." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020.
Знайти повний текст джерелаBegum, Mubeena. "Gene expression profiles and clinical parameters for survival prediction in stage II and III colorectal cancer." [Tampa, Fla] : University of South Florida, 2006. http://purl.fcla.edu/usf/dc/et/SFE0001554.
Повний текст джерелаRamis, Mary-Anne. "Factors that influence and predict undergraduate nursing and paramedic students' intention and use of evidence-based practice." Thesis, Queensland University of Technology, 2017. https://eprints.qut.edu.au/109614/1/Mary-Anne_Ramis_Thesis.pdf.
Повний текст джерелаSantos, Hellen Geremias dos. "Comparação da performance de algoritmos de machine learning para a análise preditiva em saúde pública e medicina." Universidade de São Paulo, 2018. http://www.teses.usp.br/teses/disponiveis/6/6141/tde-09102018-132826/.
Повний текст джерелаPredictive models estimate the risk of health-related events or injuries and can be used as an auxiliary tool in decision-making by public health officials and health care professionals. Machine learning (ML) algorithms have the potential to identify complex and non-linear relationships, with positive implications in the predictive performance of these models. The present research aimed to apply various ML supervised techniques and compare their performance in classification and regression problems to predict outcomes of interest to public health and medicine. Results and discussion are organized into three articles. The first, presents a tutorial for the use of ML in health research, using as an example the prediction of death up to 5 years (outcome frequency=15%; n=395) in elderly participants of the study \"Saúde, Bemestar e Envelhecimento\" (n=2,677), using variables related to demographic, socioeconomic and health characteristics. In the learning step, five algorithms were applied: logistic regression with and without regularization, neural networks, gradient boosted trees and random forest, whose hyperparameters were optimized by 10-fold cross-validation (CV). The area under receiver operating characteristic (AUROC) curve was greater than 0.70 for all models. For those with higher AUROC (neural networks and logistic regression with and without regularization), the quality of the predicted probability was evaluated and it showed low calibration. The second article aimed to predict the risk of quality-adjusted life up to 30 days (outcome frequency=44.7%; n=347) in oncologic patients admitted to the Intensive Care Unit (ICU) (n=777), using patients\' characteristics obtained at ICU admission. Six algorithms (logistic regression with and without regularization, neural networks, basic decision trees, gradient boosted trees and random forest) were used with nested CV to estimate hyperparameters values and to evaluate predictive performance. All algorithms, with exception of basic decision trees, presented acceptable discrimination (AUROC > 0.80) and calibration. For the third article, socioeconomic and demographic characteristics were used to predict the life expectancy at birth of Brazilian municipalities with more than 10,000 inhabitants (n=3,052). Nested CV and the Super Learner (SL) algorithm were used to adjust the predictive model, and for evaluating performance, the mean squared error (MSE). The SL showed good performance (MSE=0.17) and its vector of predicted values was used for the identification of underachievers and overachievers (i.e. municipalities showing worse and better outcome than predicted, respectively). Health characteristics were analyzed revealing that overachievers performed better on primary health care indicators, while underachievers fared better on secondary health care indicators. Techniques for constructing and evaluating predictive models are constantly evolving and there is scarce theoretical justification for preferring one algorithm over another. In this thesis no substantial differences were observed in the predictive performance of the algorithms applied to the classification and regression problems analyzed herein. It is expected that increase in data availability will encourage the use of more flexible ML algorithms in future health research.
Salazar, Cortés Jean Carlo. "Contribution to reliable control of dynamic systems." Doctoral thesis, Universitat Politècnica de Catalunya, 2018. http://hdl.handle.net/10803/669250.
Повний текст джерелаAquesta tesi presenta algunes contribucions al camp del control basat en la salut dels components "Health-Aware Control" (HAC) de sistemes dinàmics. A la primera part d'aquesta tesi, es presenta una revisió dels conceptes i metodologies relacionats amb la fiabilitat versus degradació, el control tolerant a fallades versus el HAC. En primer lloc, i per unificar els conceptes, s'introdueixen els conceptes de degradació i fiabilitat, models de fiabilitat i de HAC incloent algunes de les contribucions teòriques i aplicades més rellevants. La tesi, a més, el modelatge de la fiabilitat es formalitza i exemplifica utilitzant la funció d'estructura del sistema, xarxes bayesianes (BN) i xarxes bayesianes dinamiques (DBN) com a eines de modelat i anàlisi de la fiabilitat com també presenta algunes mesures d'importància de la fiabilitat (RIMs). En particular, aquesta tesi desenvolupa models de BNs per a l'anàlisi de la fiabilitat del sistema a través de l'ús de tècniques d'inferència bayesiana. Les xarxes bayesianes són eines poderoses en l'avaluació de la fiabilitat del sistema gràcies a la seva flexibilitat en el modelat de la fiabilitat de sistemes complexos. Per a la implementació de l?esquema de HAC, aquesta tesi presenta i discuteix la integració de la informació sobre la salut i degradació dels actuadors mitjançant les RIMs en algoritmes de control predictiu basat en models (MPC) i control lineal quadràtic (LQR). En les estratègies proposades, els paràmetres de la funció de cost s'ajusten utilitzant els RIMs. Aquestes tècniques de control fiable permetran millorar la disponibilitat i la seguretat dels sistemes evitant l'aparició de fallades a través de la incorporació d'aquesta informació de la salut dels components en l'algoritme de control. Les estratègies de HAC proposades s'apliquen a una xarxa d'aigua potable (DWN) i a un sistema UAV multirrotor. A més, un tercer enfocament fent servir la degradació dels actuadors com a restricció dins l'algoritme de control MPC s'aplica a un sistema aeri a dos graus de llibertat (TRMS). Finalment, aquesta tesi també presenta i discuteix dues interpretacions de la fiabilitat. Aquestes interpretacions, nomenades instantània i esperada, difereixen en la forma en què s'avalua la fiabilitat i com es considera la seva evolució al llarg del temps. Aquesta comparació es realitza en el marc del control HAC i estudia la fiabilitat del sistema en tots dos enfocaments.
Esta tesis presenta algunas contribuciones en el campo del control basado en la salud de los componentes “Health-Aware Control” (HAC) de sistemas dinámicos. En la primera parte de esta tesis, se presenta una revisión de los conceptos y metodologíasrelacionados con la fiabilidad versus degradación, el control tolerante a fallos versus el HAC. En primer lugar, y para unificar los conceptos, se introducen los conceptos de degradación y fiabilidad, modelos de fiabilidad y de HAC incluyendo algunas de las contribuciones teóricas y aplicadas más relevantes. La tesis, demás formaliza y ejemplifica el modelado de fiabilidad utilizando la función de estructura del sistema, redes bayesianas (BN) y redes bayesianas diná-micas (DBN) como herramientas de modelado y análisis de fiabilidad como también presenta algunas medidas de importancia de la fiabilidad (RIMs). En particular, esta tesis desarrolla modelos de BNs para el análisis de la fiabilidad del sistema a través del uso de técnicas de inferencia bayesiana. Las redes bayesianas son herramientas poderosas en la evaluación de la fiabilidad del sistema gracias a su flexibilidad en el modelado de la fiabilidad de sistemas complejos. Para la implementación del esquema de HAC, esta tesis presenta y discute la integración de la información sobre la salud y degradación de los actuadores mediante las RIMs en algoritmos de control predictivo basado en modelos (MPC) y del control cuadrático lineal (LQR). En las estrategias propuestas, los parámetros de la función de coste se ajustan utilizando las RIMs. Estas técnicas de control fiable permitirán mejorar la disponibilidad y la seguridad de los sistemas evitando la aparición de fallos a través de la incorporación de la información de la salud de los componentes en el algoritmo de control. Las estrategias de HAC propuestas se aplican a una red de agua potable (DWN) y a un sistema UAV multirotor. Además, un tercer enfoque que usa la degradación de los actuadores como restricción en el algoritmo de control MPC se aplica a un sistema aéreo con dos grados de libertad (TRMS). Finalmente, esta tesis también presenta y discute dos interpretaciones de la fiabilidad. Estas interpretaciones, llamadas instantánea y esperada, difieren en la forma en que se evalúa la fiabilidad y cómo se considera su evolución a lo largo del tiempo. Esta comparación se realiza en el marco del control HAC y estudia la fiabilidad del sistema en ambos enfoques.
Le, Thanh Trung. "Contribution to deterioration modeling and residual life estimation based on condition monitoring data." Thesis, Université Grenoble Alpes (ComUE), 2015. http://www.theses.fr/2015GREAT099/document.
Повний текст джерелаPredictive maintenance plays a crucial role in maintaining continuous production systems since it can help to reduce unnecessary intervention actions and avoid unplanned breakdowns. Indeed, compared to the widely used condition-based maintenance (CBM), the predictive maintenance implements an additional prognostics stage. The maintenance actions are then planned based on the prediction of future deterioration states and residual life of the system. In the framework of the European FP7 project SUPREME (Sustainable PREdictive Maintenance for manufacturing Equipment), this thesis concentrates on the development of stochastic deterioration models and the associated remaining useful life (RUL) estimation methods in order to be adapted in the project application cases. Specifically, the thesis research work is divided in two main parts. The first one gives a comprehensive review of the deterioration models and RUL estimation methods existing in the literature. By analyzing their advantages and disadvantages, an adaption of the state of the art approaches is then implemented for the problem considered in the SUPREME project and for the data acquired from a project's test bench. Some practical implementation aspects, such as the issue of delivering the proper RUL information to the maintenance decision module are also detailed in this part. The second part is dedicated to the development of innovative contributions beyond the state-of-the-are in order to develop enhanced deterioration models and RUL estimation methods to solve original prognostics issues raised in the SUPREME project. Specifically, to overcome the co-existence problem of several deterioration modes, the concept of the "multi-branch" models is introduced. It refers to the deterioration models consisting of different branches in which each one represent a deterioration mode. In the framework of this thesis, two multi-branch model types are presented corresponding to the discrete and continuous cases of the systems' health state. In the discrete case, the so-called Multi-branch Hidden Markov Model (Mb-HMM) and the Multi-branch Hidden semi-Markov model (Mb-HsMM) are constructed based on the Markov and semi-Markov models. Concerning the continuous health state case, the Jump Markov Linear System (JMLS) is implemented. For each model, a two-phase framework is carried out for both the diagnostics and prognostics purposes. Through numerical simulations and a case study, we show that the multi-branch models can help to take into account the co-existence problem of multiple deterioration modes, and hence give better performances in RUL estimation compared to the ones obtained by standard "single branch" models
Wang, Yiwei. "Développement de stratégies de maintenance structurales prédictives pour aéronefs utilisant le pronostic à base de modèles." Thesis, Toulouse, INSA, 2017. http://www.theses.fr/2017ISAT0005/document.
Повний текст джерелаAircraft maintenance represents a major economic cost for the aviation industry. Traditionally, the aircraft maintenance is highly regulated based on fixed schedules (thus called scheduled maintenance) in order to ensure safety. The frequency of scheduled maintenance is designed to be very conservative to maintain a desirable level of reliability. Developing efficient maintenance can be an important way for airlines to allow a new profit growth. With the development of sensor technology, structural health monitoring (SHM) system, which employ a sensor network sealing inside aircraft structures to monitor the damage state, are gradually being introduced in the aviation industry. Once it is possible to monitor the structure damage state automatically and continuously by SHM systems, it enables to plan the maintenance activities according to the actual or predicted health state of the aircraft rather than a fixed schedule. This work focus on the fatigue crack propagation in the fuselage panels. The SHM system is assumed to be employed. A model-based prognostics method is developed, which enables to filter the noise of SHM data to estimate the crack size, and to predict the future health state of the panels. This predictive information is integrated into the maintenance decision-making and two types of predictive maintenance are developed. The numerical study shows that the predictive maintenance significantly reduces the maintenance cost by reducing the number of maintenance stop and the repaired panels
Huang, Wei. "A Population-Based Perspective on Clinically Recognized Venous Thromboembolism: Contemporary Trends in Clinical Epidemiology and Risk Assessment of Recurrent Events: A Dissertation." eScholarship@UMMS, 2014. https://escholarship.umassmed.edu/gsbs_diss/730.
Повний текст джерелаHuang, Wei. "A Population-Based Perspective on Clinically Recognized Venous Thromboembolism: Contemporary Trends in Clinical Epidemiology and Risk Assessment of Recurrent Events: A Dissertation." eScholarship@UMMS, 2011. http://escholarship.umassmed.edu/gsbs_diss/730.
Повний текст джерелаDias, Cláudia Camila Rodrigues Pereira. "Prognostic models for Inflammatory Bowel Disease: evidence, classification and prediction." Doctoral thesis, 2017. https://repositorio-aberto.up.pt/handle/10216/102537.
Повний текст джерелаDias, Cláudia Camila Rodrigues Pereira. "Prognostic models for Inflammatory Bowel Disease: evidence, classification and prediction." Tese, 2017. https://repositorio-aberto.up.pt/handle/10216/102537.
Повний текст джерелаMartins, Andreia Sofia Santos. "Learning models using disease progression patterns for prognostic prediction in ALS." Master's thesis, 2021. http://hdl.handle.net/10451/49345.
Повний текст джерелаA Esclerose Lateral Amiotrófica (ELA) é uma doença neurodegenerativa devastadora que causa degeneração rápida dos neurónios motores e geralmente leva à morte por falência respiratória. Não existe cura, pelo que o principal objetivo dos tratamentos consiste em melhorar os sintomas e prolongar a sobrevivência. A Ventilação não invasiva (VNI) é um tratamento eficaz que estende a expectativa de vida e melhora a sua qualidade. Neste contexto, é imperativo prever a necessidade de VNI de modo a administrá-¬la preventiva e adequadamente. Assim, propomos utilizar métodos de extração de padrões transacionais e sequenciais para descobrir padrões de apresentação e progressão da doença, respetivamente. Isto é feito analisando dados estáticos recolhidos aquando do diagnóstico, e dados longitudinais recolhidos no seguimento dos pacientes. O objetivo é utilizar estes padrões como variáveis em modelos de prognóstico, assim permitindo a utilização da progressão da doença na predição e melhorando a interpretação dos modelos. Inicialmente previmos a necessidade de VNI a 90, 180 e 365 dias da última consulta (predições a curto, médio e longo prazo) para os pacientes da coorte portuguesa, através do Portuguese ALS dataset. Os modelos de prognósticos obtiveram resultados promissores, especialmente quando introduzidas medidas de similaridade que permitem a verificação parcial de padrões. A avaliação de padrões através de taxas de crescimento de suporte entre classes sugere que a função bulbar e amplitude de resposta do nervo frénico, para além da função respiratória, são variáveis significantes para determinar a evolução dos pacientes. Isto confirma o conhecimento clínico em relação a biomarcadores de progressão de doença para a insuficiência respiratória. Devido a heterogeneidade existente entre doentes de ELA, dividimos também os pacientes em três grupos de progressão: Rápida, Neutra e Lenta, de acordo com as taxas de declínio da escala ALS¬FRS¬R, aplicando a abordagem a cada um dos grupos individualmente. Os resultados melhoraram significativamente relativamente àqueles obtidos inicialmente. Também foram exploradas janelas de predição específicas a cada grupo, que obtiveram resultados igualmente bons. A avaliação de padrões pode indicar que a função bulbar é mais relevante para a necessidade de VNI em pacientes com progressão da doença mais lenta, sendo as variáveis respiratórias os principais indicadores em pacientes com progressão rápida.
Amyotrophic Lateral Sclerosis (ALS) is a devastating neurodegenerative disease causing rapid degeneration of motor neurons and usually leading to death by respiratory failure. Since there is no cure, treatment’s goal is to improve symptoms and prolong survival. Non¬invasive Ventilation (NIV) is an effective treatment, leading to extended life expectancy and improved quality of life. In this scenario, it is paramount to predict its need in order to allow preventive or timely administration. Thus, we propose to use itemset mining together with sequential pattern mining to unravel disease presentation patterns together with disease progression patterns by analysing, respectively, static data collected at diagnosis and longitudinal data from patient follow¬up. The goal is to use these static and temporal patterns as features in prognostic models, enabling to take disease progression into account in predictions and promoting model interpretability. We initially predict the need for NIV within 90, 180 and 365 days of the last appointment (short, mid and long¬term predictions) for the portuguese ALS cohort, through the Portuguese ALS dataset. The learnt prognostic models are promising, especially when using similarity measures to assess partial pattern verification. Pattern evaluation through support growth rates suggests bulbar function and phrenic nerve response amplitude, additionally to respiratory function, are significant features towards determining patient evolution. This confirms clinical knowledge regarding relevant biomarkers of disease progression towards respiratory insufficiency. Due to known heterogeneity among ALS patients, we have also split the population into three progression groups: Fast, Neutral and Slow progressors, according to decline rates of the ALS¬FRS¬R score, and applied the approach separately to each group. Results have greatly improved from the initial approach. Group ¬specific prediction windows have also been explored, obtaining equally good results. Pattern evaluation through growth rates may indicate that bulbar function is more relevant towards needing NIV in patients with slower disease progression, with respiratory tests being the main indicators in Fast progressors.
Lee, Yee Mei. "Predicting chemotherapy-induced febrile neutropenia outcomes in adult cancer patients: an evidence-based prognostic model." Thesis, 2014. http://hdl.handle.net/2440/83772.
Повний текст джерелаThesis (Ph.D.) -- University of Adelaide, School of Translational Health Science, 2014
Lin, Yu-Chang, and 林育漳. "Prognostic-Based Lifetime Prediction of Lithium-Ion Battery through Accelerated Degradation Test and Stochastic Process Model." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/j3wkcm.
Повний текст джерела國立彰化師範大學
機電工程學系
107
In this work, a compositional prognostic-based assessment using the gamma process and Monte Carlo simulation was implemented to monitor the likelihood values of test Lithium-ion batteries on the failure threshold associated with capacity loss whose evaluation used a novel dual dynamic stress accelerated degradation test, called D2SADT for the test LiFePO4 batteries. D2SADT is an enable technique developed by us to simulate a situation when driving an electric vehicle in the city. The Norris and Landzberg reliability model was applied to estimate activation energy of the test batteries. The test results show that the battery capacity always decreased at each measurement time-step during D2SADT to enable the novel test method. The variation of the activation energies for the test batteries indicate that the capacity loss of the test battery operated under certain power and temperature cycling conditions, which can be accelerated when the charge–discharge cycles increase. The modeling results show that the gamma process combined with Monte Carlo simulations provides superior accuracy for predicting the lifetimes of the test batteries compared with the baseline lifetime data (i.e., real degradation route and lifetimes). The results presented high prediction quality for the proposed model as the error rates were close-or-within ±5% and were obtained for all test batteries after a certain quantity of capacity loss. In conclusion, the proposed model and test method could help engineers not only understand the degradation behavior according to the indicator of activation energy, but also enable monitoring of the health states of Li-ion batteries more precisely in certain real conditions.
Lopes, Cláudia Rodrigues. "Computational Intelligence Models for Length of Stay Prediction." Master's thesis, 2020. http://hdl.handle.net/10316/92126.
Повний текст джерелаA previsão do tempo de internamento dos pacientes é de grande importância para os hospitais, uma vez que pode determinar a utilização de recursos, melhorar o agendamento de futuros internamentos e cirurgias, e auxiliar no planeamento dos cuidados de saúde dos pacientes, desde a admissão até à alta. Consequentemente, uma melhor qualidade dos cuidados de saúde prestados pode ser proporcionada aos pacientes, sendo este o principal objetivo dos hospitais. Neste projecto, quatro abordagens diferentes foram implementadas para desenvolver modelos de previsão de tempo de internamento: i) exploração de modelos de risco existentes (SCORE), ii) aplicação de modelos típicos de inteligência computacional (Random Forest, Support Vector Machine e Multilayer Perceptron), iii) desenvolvimento de um modelo interpretável e personalizável ao paciente com base em regras e iv) integração de dados dinâmicos (sinais vitais) nos modelos anteriores. Os dados clínicos usados neste trabalho foram fornecidos pelo CHUC (Centro Hospitalar e Universitário de Coimbra) e pela Philips Electronics Nederland B.V., compreendendo 1544 pacientes admitidos na unidade de cuidados intensivos de cardiologia do Hospital dos Covões (Coimbra) e 189 pacientes bariátricos admitidos para cirurgia no Catharina Hospital (Eindhoven), respetivamente.O conjunto inicial de variáveis dos pacientes cardíacos foi obtido através de uma revisão da literatura e do conhecimento clínico de um cardiologista da unidade de cuidados intensivos de cardiologia do CHUC. Para os pacientes bariátricos, este conjunto resultou de uma revisão da literatura para a determinação das variáveis relevantes. Posteriormente, as variáveis de entrada dos modelos de previsão de tempo de internamento foram selecionadas desse conjunto inicial usando o coeficiente de correlação tau de Kendall. Adicionalmente, as variáveis de entrada selecionadas para os pacientes cardíacos foram também validadas pelo cardiologista. O desempenho dos modelos referidos, medido através da média geométrica (GE) e do F1 score, foi determinado aplicando este conjunto final de variáveis de entrada a cada um deles.Finalmente, através da aplicação do teste Friedman e do correspondente teste post-hoc Nemenyi, foi possível ordenar os modelos em função do seu desempenho.A performance do modelo baseado no SCORE foi significativamente baixa, obtendo uma GE de 0.50. Assim, apesar deste modelo de risco ser de grande importância na prática cardiológica europeia, não é adequado para estimar o tempo de internamento hospitalar. A segunda abordagem (modelo Black-box) superou o modelo anterior. Os melhores resultados foram obtidos pelo Multilayer perceptron com uma GE de 0.62 ± 0.03 para os pacientes cardíacos e 0.64 ± 0.08 para os bariátricos, respetivamente. Verificou-se ainda que o desempenho do modelo interpretável e personalizável foi superior ao modelo Black-box, para os dois tipos de pacientes, com uma GE de 0.66 ± 0.02 para os pacientes cardíacos e 0.83 ± 0.05 para os pacientes bariátricos. Adicionalmente, a inclusão de sinais vitais aos modelos de previsão mostrou-se vantajosa por levar a um aumento da performance em todos os classificadores. Estes resultados sugerem que a incorporação de dados dinâmicos em modelos de previsão de tempo de internamento deve ser explorada de forma aprofundada em estudos posteriores.A análise dos resultados permitiu-nos concluir que, apesar de aceitável, a performance dos modelos desenvolvidos não parece ser adequada para o seu uso na prática clínica (GE máxima de 0.66 e 0.83 para os pacientes cardíacos e bariátricos, respetivamente). Este facto pode-se justificar pela dificuldade e complexidade que o problema apresenta. O estudo de outras variáveis, não só determinadas aquando a admissão, mas durante as primeiras horas ou no primeiro dia de internamento do doente, poderia ser uma estratégia a explorar no futuro.
Predicting the patients' length of stay (LOS) is of major importance for hospitals, since it can determine the resource utilization, improve the scheduling of admissions and surgeries and helping in the development of effective clinical pathways. Consequently, a better quality of care can be provided to the patients, which is the main goal of the hospitals.In this project, four different approaches were implemented to develop LOS prediction models: i) exploration of available risk tools (SCORE), ii) application of typical computational intelligence models (Random Forest, Support Vector Machine and Multilayer Perceptron), iii) development of an interpretable and patient customized model based on rules and iv) integration of dynamic data (vital signs) in the previous models. The clinical data used in this work was provided by the CHUC (Coimbra Hospital and University Center) and by Philips Electronics Nederland B.V., comprising 1544 patients admitted in the cardiac intensive care unit of Hospital dos Covões (Coimbra) and 189 bariatric patients admitted to surgery in Catharina Hospital (Eindhoven), respectively.The initial set of features of the cardiac patients was obtained through a literature review and the clinical knowledge of an ICU cardiologist of CHUC. For the bariatric patients, this set resulted from a literature review for the determination of the relevant features. Then, the input features of the LOS prediction models were selected from this initial set using the Kendall's tau coefficient correlation. Moreover, the selected input features for the cardiac patients were also validated by the cardiologist. The performance of the referred models, measured in terms of the geometric mean (GE) and F1 score, was determined by employing this final set of input variables to each one of them. Finally, through the application of the Friedman test and the corresponding post-hoc Nemenyi test, it was possible to order the models according to their performance.The SCORE model performance was significantly low, achieving a geometric mean (GE) of 0.50. Thus, although this risk tool is of high importance in the European cardiology practice, it is not sufficiently accurate to estimate the actual LOS. The second approach (Black-box model) outperformed the previous model. The best results were achieved by the multilayer perceptron with a GE of 0.62 ± 0.03 for the cardiac patients and 0.64 ± 0.08 for the bariatric ones. Furthermore, we verified that the performance of the interpretable and customized model was higher than the Black-box model, for both types of patients, obtaining a GE of 0.66 ± 0.02 for the cardiac patients and 0.83 ± 0.05 for the bariatric patients. Moreover, the addition of the vital signs to the prediction models was proved to be advantageous since it leaded to an increase of performance in all the classifiers. These results suggest that the incorporation of dynamic data in LOS prediction models is worthy of further exploratory studies.The analysis of the results allowed us to conclude that, although acceptable, the performance of the developed models does not seem to be adequate for their use in clinical practice (maximum GE of 0.66 and 0.83 for the cardiac and bariatric patients, respectively). This fact may be justified by the difficulty and complexity that the problem presents. The study of other variables, not only determined at admission time, but during the first hours or on the first day of the patient's stay, could be a strategy to explore in the future.
Banjar, Haneen Reda. "Personalized Medicine Support System for Chronic Myeloid Leukemia Patients." Thesis, 2018. http://hdl.handle.net/2440/117837.
Повний текст джерелаThesis (Ph.D.) -- University of Adelaide, School of Computer Science, 2018