Дисертації з теми "Car model classification"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 дисертацій для дослідження на тему "Car model classification".
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.
Castellucci, Davide. "Model for car brand classification and estimation of price tag." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2022.
Знайти повний текст джерелаDodsworth, Joel Andrew. "The application of vehicle classification, vehicle-to-infrastructure communication and a car-following model to single intersection traffic signal control." Thesis, University of Leeds, 2018. http://etheses.whiterose.ac.uk/22741/.
Повний текст джерелаKato, Jien, Toyohide Watanabe, Sebastien Joga, Rittscher Jens, Blake Andrew, ジェーン 加藤, and 豊英 渡邉. "An HMM-based segmentation method for traffic monitoring movies." IEEE, 2002. http://hdl.handle.net/2237/6744.
Повний текст джерелаLindespång, Victor. "Bildklassificering av bilar med hjälp av deep learning." Thesis, Örebro universitet, Institutionen för naturvetenskap och teknik, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-58361.
Повний текст джерелаThis report describes how an image classifier was created with the ability to identify car makeand model from a given picture of a car. The classifier was developed using pictures that the company CAB had saved from insurance errands that was managed through their current products. First of all the report begins with a brief theoretical introduction to machine learning and deep learning to guide the reader in to the subject of the report, and then continues with problemspecific methods that were of good use for the project. The report brings up methods for how the data was processed before training took place, how the training process went with the chosen tools for this project and also discussion about the result and what effected it – with comments about what can be done in the future to improve the end product.
Ziegenfuss, Katharina. "Bewertung innovativer Geschäftsmodelle: Entwicklung eines Simulationsmodells und Anwendung auf die bedarfsabhängige Funktionserweiterung im vernetzten Fahrzeug: Development of a simulation model and application to the ‘Function on Demand’ concept of the connected car." Universitätsverlag Chemnitz, 2019. https://monarch.qucosa.de/id/qucosa%3A73123.
Повний текст джерелаBusiness model innovations provide powerful levers for creating sustainable competitive advantage and thus have a positive impact on the value of an enterprise. However, due to the complexity of business models, no practically applicable framework, evaluating an innovative business model with regard to its effect on a company’s success, has been established. Hence, a simulation model assessing the value contribution of a business model innovation is developed. Using the mathematical modeling technique ‘System Dynamics’ to frame the value drivers of a business allows for simulation experiments that reveal the effect of the business model’s design on its profitability, therewith guiding policymakers towards better decisions. As a result, the simulation model reports the net present value of a business model. In addition, the success indicators customer lifetime value and the value of the enterprises’ capabilities are identified as important assets that have to be monitored closely as they determine the company’s prospective performance. In combining financial standard calculations with the operationalization of non-financial measures, the simulation model represents a comprehensive approach for business model evaluation.:1 Einführung 2 Geschäftsmodelle und Geschäftsmodellbewertung 3 Entwicklungsprozess des systemdynamischen Geschäftsmodells bedarfsabhängiger Funktionserweiterungen 4 Aufbau des systemdynamischen Geschäftsmodells bedarfsabhängiger Funktionserweiterungen 5 Simulation des systemdynamischen Geschäftsmodells bedarfsabhängiger Funktionserweiterungen 6 Schlussbetrachtung
Padgett, Curtis. "A neural network model for facial affect classification /." Diss., Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campusesd, 1998. http://wwwlib.umi.com/cr/ucsd/fullcit?p9907599.
Повний текст джерелаHansen, Vedal Amund. "Comparing performance of convolutional neural network models on a novel car classification task." Thesis, KTH, Medieteknik och interaktionsdesign, MID, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-213468.
Повний текст джерелаNya neurala nätverksframsteg har lett till modeller som kan användas för en mängd olika bildklasseringsuppgifter, och är därför användbara många av dagens medietekniska applikationer. I detta projektet tränar jag moderna neurala nätverksarkitekturer på en nyuppsamlad bilbild-datasats för att göra både grov- och finkornad klassificering av fordonstyp. Resultaten visar att neurala nätverk kan lära sig att skilja mellan många mycket olika bilklasser, och även mellan några mycket liknande klasser. Mina bästa modeller nådde 50,8% träffsäkerhet vid 28 klasser och 61,5% på de mest utmanande 5, trots brusiga bilder och manuell klassificering av datasetet.
Pretty, Christopher Grant. "Analysis, classification and management of insulin sensitivity variability in a glucose-insulin system model for critical illness." Thesis, University of Canterbury. Mechanical Engineering, 2012. http://hdl.handle.net/10092/6580.
Повний текст джерелаGrundel, Martin, and Jutta Abulawi. "SkiPo – Ein skizzen- und portbasiertes Modell für die Entwicklung von mechanischen Systemen." Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2016. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-214760.
Повний текст джерелаMcDaniel, Cleve. "Retention classification models for an historically black university with an open admission policy /." free to MU campus, to others for purchase, 1997. http://wwwlib.umi.com/cr/mo/fullcit?p9841172.
Повний текст джерелаSaenyakul, Pimpanitta. "Depression Classification Among HIV–Infected Pregnant Women in Thailand." Kent State University / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=kent1448031641.
Повний текст джерелаVictors, Mason Lemoyne. "A Classification Tool for Predictive Data Analysis in Healthcare." BYU ScholarsArchive, 2013. https://scholarsarchive.byu.edu/etd/5639.
Повний текст джерелаPanchagavi, Renuka. "Survey of Electronic Health Records Data for Developing a Predictive Model of Pressure Ulcers in Critical Care Patients." The Ohio State University, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=osu1338371919.
Повний текст джерелаNuthmann, Antje, Wolfgang Einhäuser, and Immo Schütz. "How Well Can Saliency Models Predict Fixation Selection in Scenes Beyond Central Bias? A New Approach to Model Evaluation Using Generalized Linear Mixed Models." Universitätsbibliothek Chemnitz, 2018. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-qucosa-232614.
Повний текст джерелаThomas, Kerry J. "Teaching Mathematical Modelling to Tomorrow''s Mathematicians or, You too can make a million dollars predicting football results." Turning dreams into reality: transformations and paradigm shifts in mathematics education. - Grahamstown: Rhodes University, 2011. - S. 334 - 339, 2012. https://slub.qucosa.de/id/qucosa%3A1949.
Повний текст джерелаHolder, Mark Travis. "Using a complex model of sequence evolution to evaluate and improve phylogenetic methods." Access restricted to users with UT Austin EID Full text (PDF) from UMI/Dissertation Abstracts International, 2001. http://wwwlib.umi.com/cr/utexas/fullcit?p3037500.
Повний текст джерелаLakhani, Rubina. "Artifact-Supported Performance Management of Collaborative Care Teams." Thesis, Université d'Ottawa / University of Ottawa, 2021. http://hdl.handle.net/10393/42510.
Повний текст джерелаKabir, Md Faisal. "Extracting Useful Information and Building Predictive Models from Medical and Health-Care Data Using Machine Learning Techniques." Diss., North Dakota State University, 2020. https://hdl.handle.net/10365/31924.
Повний текст джерелаHüsig, Stefan. "A Conceptual Model of the Revised CAI-NPD-Systems Maturity." Universitätsbibliothek Chemnitz, 2015. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-qucosa-187877.
Повний текст джерелаHusung, Stephan, and Wolfgang Holle. "CAD-Produktmodell – Quelle der Produktbewertung nach Zeit und Kosten." Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2017. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-228209.
Повний текст джерелаHeinen, Eva, and David Ogilvie. "Variability in baseline travel behaviour as a predictor of changes in commuting by active travel, car and public transport: a natural experimental study." Elsevier, 2015. https://publish.fid-move.qucosa.de/id/qucosa%3A72785.
Повний текст джерелаCheifetz, Nicolas. "Détection et classification de signatures temporelles CAN pour l’aide à la maintenance de sous-systèmes d’un véhicule de transport collectif." Thesis, Paris Est, 2013. http://www.theses.fr/2013PEST1077/document.
Повний текст джерелаThis thesis is mainly dedicated to the fault detection step occurring in a process of industrial diagnosis. This work is motivated by the monitoring of two complex subsystems of a transit bus, which impact the availability of vehicles and their maintenance costs: the brake and the door systems. This thesis describes several tools that monitor operating actions of these systems. We choose a pattern recognition approach based on the analysis of data collected from a new IT architecture on-board the buses. The proposed methods allow to detect sequentially a structural change in a datastream, and take advantage of prior knowledge of the monitored systems. The detector applied to the brakes is based on the output variables (related to the brake system) from a physical dynamic modeling of the vehicle which is experimentally validated in this work. The detection step is then performed by multivariate control charts from multidimensional data. The detection strategy dedicated to doors deals with data collected by embedded sensors during opening and closing cycles, with no need for a physical model. We propose a sequential testing approach using a generative model to describe the functional data. This regression model allows to segment multidimensional curves in several regimes. The model parameters are estimated via a specific EM algorithm in a semi-supervised mode. The results obtained from simulated and real data allow to highlight the effectiveness of the proposed methods on both the study of brakes and doors
Zwergius, V. "The three worlds of welfare and the Greek welfare state : an analysis of the extent to which Esping-Andersen's welfare state classification model can be used to classify the Greek welfare state." Thesis, Swansea University, 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.636738.
Повний текст джерелаMahn, Uwe, Jörg Matthes, and Anna Maronek. "Topologieoptimierung und CAD- Modellaufbereitung für den 3D-Druck." Technische Universität Chemnitz, 2018. https://monarch.qucosa.de/id/qucosa%3A21510.
Повний текст джерелаInnovative function-related component geometries in small quantities can be produced efficiently with different methods of additive, generative manufacturing, in a popular science known as 3D printing. For the designer of such components it also means to use other methods as usual. Component geometries optimized regarding to a target size can be calculated using topology optimization based on a FE model. While topology optimization has been known and established for a long time, the consistent use of a common database was often characterized by obstacles. In this article today's possibilities are shown with the FE system ANSYS and evaluated with regard of the efficient practical use.
Bergholz, Katharina. "An extended bounding surface model for the application to general stress paths in sand." Institut für Geotechnik, 2019. https://tud.qucosa.de/id/qucosa%3A72600.
Повний текст джерелаDie Prognose von Setzungen für die Bemessung von Infrastrukturbauwerken stellt hohe Anforderungen an die numerische Untersuchung des Baugrunds und das damit verbundene Stoffgesetz: komplexe Herstellungsprozesse und zyklisch wiederkehrende Verkehrslasten stellen beachtliche Herausforderungen dar. Während das Hauptaugenmerk zumeist auf der realitätsnahen Abbildung des Bodenverhaltens liegt und damit die analytischen Anforderungen des geotechnischen Problems im Fokus stehen, sollten die Bedürfnisse der Ingenieurspraxis in der Stoffgesetzmodellierung nicht außer Acht gelassen werden. In diesem Sinne wurde im Rahmen der Elastoplastizität ein neues Materialmodell für nichtbindige Böden entwickelt. Auf dem Konzept der Bounding Surface Plastizität nach Manzari und Dafalias (1997) beruhend, sind Eigenschaften wie Festigkeit, Steifigkeit und Dilatanz Funktion des Abstands zwischen aktuellem Spannungszustand und einer zugeordneten Modellfläche im Spannungsraum. Auf diese Weise bildet das Mehrflächenmodell fundamentale Verhaltensmuster von Boden korrekt ab, einschließlich beispielsweise scherbezogener Phänomene wie Ver- und Entfestigung, Kontraktanz und Dilatanz oder das Erreichen des kritischen Zustands (Scherfestigkeit bei konstantem Volumen). Des Weiteren erfasst das Modell die Zustandsabhängigkeit des Bodenverhaltens (Barotropie und Pyknotropie). So kann mit nur einem Parametersatz das mechanische Verhalten einer großen Spannweite unterschiedlicher Anfangszustände hinsichtlich Spannung und Lagerungsdichte simuliert werden. Der kinematische Verfestigungsmechanismus der konusförmigen Fließfläche trägt bei Ent- und Wiederbelastungen zu einer realistischeren Steifigkeitsentwicklung bei und ist damit von essenzieller Bedeutung für die Akkumulation von Spannungen oder Verformungen infolge von Lastwechseln. Da sich der gewählte konstitutive Rahmen für Weiterentwicklungen eignet, wurde die ursprüngliche Formulierung des Stoffgesetzes erweitert, um das Modell an die definierten Anforderungen anzupassen. Um geotechnisch relevante Spannungspfade niedriger und höherer Komplexität adäquat reproduzieren zu können, wurde zunächst eine kappenförmige Fließfläche ergänzt. So können irreversible Verformungen nicht nur bei Scherung, sondern auch bei Belastungen ohne Änderung des Spannungsverhältnisses, wie z. B. bei isotroper oder ödometrischer Kompression, auftreten. Bei Spannungspfaden ungewöhnlicher Orientierung, bei Lastwechseln oder zusammengesetzten Spannungspfaden mit Änderung der Belastungsrichtung hat sich eine erhöhte Steifigkeit bei kleinen Dehnungen mit anschließendem dehnungsabhängigen Abfall als nützlich erwiesen. Darüber hinaus berücksichtigt ein zusätzlicher Mechanismus die rückläufige Akkumulation von Spannung oder Verformung mit zunehmender Zyklenanzahl (mittels dissipierter Energie). Im Hinblick auf die Eignung des Stoffgesetzes für die Praxis ist das Modell modular aufgebaut. So kann die Komplexität des Modells (und damit die Anzahl der Parameter) durch Ein- und Ausschalten bestimmter Erweiterungen an die Komplexität des geotechnischen Problems angepasst werden. Die Mehrzahl der Modellparameter wird mit Hilfe konventioneller Laborversuche bestimmt. Eine interne Routine erleichtert durch die Kalibrierung bestimmter Bounding Surface bezogener Größen anhand eines alternativen, stärker an Versuchsergebnissen orientierten User-Inputs bei Bedarf die Parameterwahl. Da die Kenntnis eines Stoffgesetzes entscheidend ist für dessen vernünftigen und verantwortungsvollen Einsatz, soll die vorliegende Arbeit eine fundierte und umfassende Dokumentation bieten. Der erste Teil vermittelt daher zunächst einen Überblick über das zugrunde liegende Bounding Surface Konzept und beschreibt die Neuerungen auf konstitutiver Ebene mit Bezug auf theoretische Hintergründe. Er wird gefolgt von einer detaillierten Darlegung von Potenzialen und Einschränkungen für die Nutzung des erweiterten Modells. Der nächste Abschnitt widmet sich der numerischen Implementierung des Stoffgesetzes und seiner Kalibrierung auf Basis von Versuchsergebnissen. Des Weiteren wird die Kalibrierungsroutine einschließlich des verwendeten Optimierungsalgorithmus präsentiert. Der nachfolgende Teil dient der Modellvalidierung: durch die Simulation von Elementversuchen, die Erzeugung von Antwortellipsen sowie die Abbildung allgemeinerer (beispielsweise zusammengesetzter) Spannungspfade wird die Leistungsfähigkeit des erweiterten Bounding Surface Modells demonstriert. Abschließend werden Schlussfolgerungen gezogen und potenzielle Perspektiven aufgezeigt.:1 Introduction 1.1 General aspects on constitutive modelling 1.2 Motivation and outline of the thesis 1.3 Basic assumptions and terminology 2 Literature review 2.1 From elastoplasticity to bounding surface plasticity 2.1.1 Bounding surface model according to Manzari and Dafalias (1997) 2.2 Further development of the original model 2.2.1 Papadimitriou and Bouckovalas (2002) 2.2.2 Taiebat and Dafalias (2008) 2.3 Small strain stiffness 2.3.1 Observations 2.3.2 Micromechanical considerations 2.3.3 Very small strain shear modulus G0 2.3.4 Constitutive modelling approaches 2.4 Dilatancy 3 The extended bounding surface model 3.1 Fundamental capabilities of the bounding surface concept 3.1.1 Elastic region 3.1.2 Critical state 3.1.3 Shear strength 3.1.4 Shear stiffness (monotonic) 3.1.5 Contractancy and dilatancy 3.1.6 Barotropy and pycnotropy 3.1.7 Compressive stiffness 3.1.8 Shear stiffness in reversed loading 3.1.9 Additional features 3.2 New features of the extended bounding surface model 3.2.1 Minor modifications 3.2.2 Dilatancy formulation 3.2.3 Cap yield surface 3.2.4 Small strain stiffness mechanism 3.2.5 Cyclic loading mechanism 3.2.6 Summary 3.3 Limitations of the bounding surface model 3.3.1 Intrinsic insuffciencies of the bounding surface concept 3.3.2 Remaining shortcomings of the advanced model version 3.3.3 Newly introduced deficiencies 4 The numerical model and its calibration procedure 4.1 Octave implementation of an element test programme 4.2 Calibration procedure 4.2.1 Sands for calibration 4.2.2 Calibration of basic parameters 4.2.3 Calibration of extended model parameters 4.3 User friendly calibration routine 4.3.1 Conceptual background 4.3.2 Optimisation algorithm 5 Performance of the extended bounding surface model 5.1 Model performance in element tests 5.1.1 Monotonic drained triaxial compression test 5.1.2 Monotonic undrained triaxial compression test 5.1.3 Monotonic eta-constant tests 5.2 Model performance in non-standard triaxial testing 5.2.1 Concept of response envelopes 5.2.2 Simulation of response envelopes 5.3 Model performance on general stress paths 5.3.1 Triaxial compression at small strains 5.3.2 Cyclic triaxial loading 6 Conclusions and perspectives 6.1 Conclusions 6.2 Future perspectives Bibliography Appendices A Mathematical background A.1 Fundamental equations of elastoplasticity A.2 Compilation of major constitutive equations (multiaxial formulation) A.3 Elastoplastic stiffness matrix for singular yield surfaces A.4 Coefficient matrices S and E for loading constraints A.5 Derivation of Mcap and Hcap A.6 Intergranular strain adjustment A.7 Intergranular strain correlation B Details on particle swarm optimisation C Compilation of simulation results C.1 Monotonic triaxial loading C.1.1 Toyoura sand C.1.2 Sacramento River sand C.1.3 Hostun sand C.2 Monotonic eta-constant loading C.2.1 Sacramento River sand C.2.2 Hostun sand C.3 Cyclic triaxial loading
Münster, Sander. "Entstehungs- und Verwendungskontexte von 3D-CAD-Modellen in den Geschichtswissenschaften." Technische Universität Dresden, 2011. https://tud.qucosa.de/id/qucosa%3A28070.
Повний текст джерелаMühlstedt, Jens, and Birgit Spanner-Ulmer. "Homo Sapiens Digitalis: über den Praxiseinsatz digitaler Menschmodelle." Universitätsbibliothek Chemnitz, 2010. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-201000215.
Повний текст джерелаA short overview of digital human models for ergonomic product and workplace design introduces this article. The results of a survey with users of these systems show the practical usage of digital human models. Approaches to further research and development are presented
Matthes, Jörg. "Systematische Auslegung von Kurvenkoppelgetrieben für Führungsbewegungen." Doctoral thesis, Universitätsbibliothek Chemnitz, 2002. http://nbn-resolving.de/urn:nbn:de:swb:ch1-200200320.
Повний текст джерелаStelzer, Ralph, and Christine Schöne. "Reverse Engineering in der Produktentwicklung – Aktuelle Herausforderungen." TUDpress - Verlag der Wissenschaften GmbH, 2012. https://tud.qucosa.de/id/qucosa%3A30506.
Повний текст джерелаSchultz, Grant George. "Developing a methodology to account for commercial motor vehicles using microscopic traffic simulation models." Diss., Texas A&M University, 2003. http://hdl.handle.net/1969.1/111.
Повний текст джерелаSilva, Marcos Barragan da. "Dimensões do Nursing Role Effectiveness Model no acompanhamento dos resultados de pacientes submetidos à artoplastia do quadril." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2017. http://hdl.handle.net/10183/163944.
Повний текст джерелаThe evaluation of health outcomes arises from the need for professions to demonstrate their effectiveness in patient outcomes. Several approaches have been used to identify the relationships between the Structure, Process and Outcomes variables in the quality care evaluation in the hospital. Canadian researchers to developed the Nursing Role Effectiveness Model (NREM) to identify the nursing contribution to health care. The NREM was not analyzed from the perspective of the Advanced Nursing Process, using the Standardized Language Systems NANDA-I, NIC and NOC for patients undergoing Hip Arthroplasty. This study aimed to analyze the relationships between the dimensions of the Nursing Role Effectiveness Model in the follow-up of the outcomes of patients undergoing for Hip Arthroplasty. It is a longitudinal study nested for descriptive correlative design. The data were collected at Hospital de Clínicas de Porto Alegre, Brazil. The population and sample consisted of patients undergoing to Hip Arthroplasty, and nurse assistants who prescribed care for these patients. In the longitudinal study patientes were followed for three to four postoperative day, on the March to December 2016. Nurses were interviewed in January and February 2017. Data were statistically analyzed. The findings were categorized according to the dimensions Structure, Process and Outcomes, from NREM. Results: Variables Structure, were included 85 patients predominantly female (58%), mean age 64 (± 13.5) years. The patients were diagnosed with Acute Pain (96%), Risk of Falls (62%) and Impaired Physical Mobility (54%), respectively. The majority of patients were resting in the Orthopedic Bed (99%). Nurses had a mean age of 33 years, being the majority (90%) female. Experience with orthopedic patients ranged from one to six years. Knowledge level in NANDA-I, NIC and NOC was considered moderate to substantial. The most prescribed NIC nursing interventions were: PAIN Control, FALL Prevention and POSITIONING, considered as Process variables. The Nursing outcomes NOC (Body Positioning: self-initiated, Mobility, Knowledge: prescribed activity and Pain Level) included in the Outcome dimension from NREM, had significant changes (P <0.001) during the follow-up. The scales showed internal consistency (α> 0.7). It is concluded that the Structure, Process and Outcomes variables are related and according to the effects it generates on the outcomes achieved, it has repercussions on the Advanced Nursing Process quality based on the Standardized Language Systems NANDA- I, NIC and NOC for patients submitted to Hip Arthroplasty.
Prinz, Ralf. "Vom CAD-Modell über die Simulation zum 3D-Druck und zurück : Simulationsansätze in einer, durch den 3D-Druck entfesselten, neuen Gestaltungsfreiheit." Universitätsbibliothek Chemnitz, 2016. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-qucosa-206799.
Повний текст джерелаKoch, Thomas. "Ein Beitrag zur Optimierung klinischer Patientenpfade und deren Anwendung auf komplexe Behandlungsfälle am Beispiel der Station Mund-, Kiefer- und Gesichtschirurgie am Universitätsklinikum Dresden." Bachelor's thesis, Dresden International University, 2014. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-147883.
Повний текст джерелаTo meet the cost pressures in medical care facillities, driven by the demands of the volume V of the German Social Code and DRG, while patient satisfaction and quality of care in complex organizational requirements, the identification of optimization potentials and its realization is an essential lever for the survival of hospitals on the medical market. The patient pathway, which is the core process of the value added chain of medical services at the hospital, froms the "Logistical chain for medical and social services" at the same time. To illustrate the complexity of the interaction of processes and interfacesthe author develops the phase madel "Health Care Process" (HCP) consisting of its three madical and care main processes pre-clinical; clinical and post-clinical process, characterized by their medical, logistical, economic and human social interdisciplinary. This model proves to be a viable approach for the analysis for the optimization of tretment pathways in the clinical field of oral and maxillofacial surgery (OMS). As a result a proposal is being developed which converts 7 elective medical pattern and the heterogeneous processstructures in a standardized treatment pathway OMS. Based on the derivation of standardized treatment pathways and the definition of so-called "Standard Operating Procedures" (SOPs) a modular system for medical treatment is provided which guarantees a configurable individualization of the treatmet process for the patient. Based on the detailed analysis and derivation of target structures for clinical pathways on the example of OMS at the University Medical Center Dresden and their linkage to interdisciplinarities under the procedural aspect this bachelor graduation paper-work makes a contribution to process optimization in the hospital and at the same time forms a contribution to the modeling of a model-aided, evidence-based process management
Oliveira, Daniele Adelaide BrandÃo de. "Risco de insustentabilidade financeira dos beneficiÃrios de uma operadora de planos de saÃde: uma comparaÃÃo de modelos de classificaÃÃo." Universidade Federal do CearÃ, 2014. http://www.teses.ufc.br/tde_busca/arquivo.php?codArquivo=14472.
Повний текст джерелаEste trabalho teve por objetivo realizar um estudo analÃtico relativo à sustentabilidade financeira dos beneficiÃrios da carteira de uma operadora de planos de saÃde. A amostra investigada no estudo à de uma operadora de plano de saÃde vinculada ao Banco do Nordeste do Brasil S.A. (BNB) e à composta por 38.875 usuÃrios, ativos, entre os anos de 2011 e 2013. Especificamente, buscou-se nesse trabalho aplicar tÃcnicas de classificaÃÃo de insustentabilidade financeira de beneficiÃrios de uma operadora de planos de saÃde, identificando o modelo de melhor ajustamento e os principais determinantes de insustentabilidade. As tÃcnicas estatÃsticas de classificaÃÃo supervisionada empregadas foram a regressÃo logÃstica, as Ãrvores de classificaÃÃo e o classificador de vizinhos mais prÃximos. AlÃm disso, foi empregada a curva ROC para comparar os desempenhos das tÃcnicas utilizadas, sendo a Ãrea abaixo da curva (AUC), a principal medida observada. Os resultados obtidos mostraram que a maior parte da amostra à composta por beneficiÃrios sustentÃveis. O modelo de regressÃo logÃstica obteve precisÃo de 68,43% com AUC de 0,7501, as Ãrvores obtiveram 67,76% e AUC de 0,6855, enquanto o classificador dos vizinhos mais prÃximos teve uma precisÃo de 67,22% e AUC de 0,7258. As variÃveis apontadas como mais importantes pelos dois primeiros modelos, considerando uma anÃlise conjunta, sÃo a Idade e o Tipo de Plano, dentre aquelas que definem o perfil do usuÃrio e a Receita, Consulta e Odontologia, daquelas que definem o histÃrico de utilizaÃÃo do usuÃrio
This study aimed to carry out an analytical study on the financial sustainability of the beneficiaries of the portfolio of managed care plans. The sample investigated in the study is a health plan operator linked to the Banco do Nordeste do Brazil SA (BNB) and consists of 38,875 members, assets, between the years 2011 and 2013. Specifically, we sought to apply techniques that work financial unsustainability classification of beneficiaries of a managed care plans, identifying the model best fit and the main determinants of unsustainability. The technical classification statistics were supervised employed logistic regression, classification trees and the classifier closest neighbors. Furthermore, the ROC curve was used to compare the performance of the techniques used, and the area under the curve (AUC), the main extent observed. The results showed that most of the sample is composed of organic recipients. The logistic regression model obtained precision of 68.43% with AUC of 0.7501, the trees obtained 67.76% and AUC of 0.6855, while the classifier of the closest neighbors had an accuracy of 67.22% and AUC of 0.7258. The variables identified as most important by the first two models, considering a joint analysis, are the Middle and the Plan type, among those that define the user profile and the Revenue Consultation and Dentistry, those that define the user use history
Argenta, Carla. "Modelo multidimensional de cuidado ao idoso associado aos sistemas de linguagens padronizadas de enfermagem NANDA-I, NIC E NOC." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2018. http://hdl.handle.net/10183/186134.
Повний текст джерелаComprehensive care for the elderly can be guaranteed through the use of the Nursing Process (PE), together with a theoretical framework such as the Multidimensional Model of Successful Aging (MMSA), which has a proposal for the evaluation of the elderly. There is, however, a gap to its use, since there are no studies that prove its effectiveness in the clinical practice of Nursing associated with the application of discipline classification systems such as NANDA-I, NIC and NOC. The objective of this study is to build an elderly care multidimensional model associated with the standardized NANDA-I, NIC and NOC Nursing language systems, applicable to the nursing consultation. The study was conducted in two different methodological steps. The first comprised a content validation study while the second a results research, which included a quasi-experimental study. The samples consisted of 15 specialists in Gerontology Nursing and 28 elderly people in a first consultation in the City of the Elderly, place of study, with age equal to or greater than 60 years, of both sexes, who presented the diagnosis of Nursing Risk of Syndrome of the Elderly (RSIF) or Fragile Elderly Syndrome (SIF), from May to October 2017. After the validation of the multidimensional model content, with the opinion of the specialists, it was applied to the elderly in four every elderly person. During the consultations the diagnoses were established, the results were measured and the Nursing interventions were implemented, according to the multidimensional model and the clinical evaluation. The specialists validated information about the anamnesis and the physical examination referring to the defining characteristics, related and risk factors of the two diagnoses and the physiological, psychological and social dimensions, as proposed by the MMSA. Validation also confirmed that of the 13 different validated Nursing outcomes, 10 were common in both diagnoses. The results validated for the two diagnoses evaluated: Equilibrium (0202), Cognition (0900), Nutritional status (1004), Self-control of chronic disease (3102), Knowledge: pain control (1843), Knowledge: control of chronic disease (1847), Knowledge: prevention of falls (1828), Knowledge: weight control (1841) and Comfort state (2008). Only two of the 13 results were validated for SIF diagnosis, being: Fatigue level (0007) and Self-care: activities of daily living (0300), and a result, Knowledge: medicine (1808), was validated only for the diagnosis RSIF. The Nursing interventions of the NIC, validated for the two Nursing diagnoses, were practically the same. Of the eight different validated interventions, only Self-care Assistance (1800) was validated exclusively for SIF diagnosis and the other seven were validated for both diagnoses. The interventions emphasize the importance of Promoting Exercise (0200), Nutrition Counseling (5246), Medication Control (2380), Cognitive Stimulation (4720), Improving Socialization (5100), Fall Prevention (6490) and Teaching the Process of the disease (5602). The second stage showed that of the 28 elderly, the majority were female (17-60.7%), with a mean age of 65.6 ± 6.3 years, and of these, 23 elderly were diagnosed with RSIF and five with SIF. Nursing results used to evaluate the elderly with RSIF and SIF showed a significant improvement in the mean of the scores of their indicators: Knowledge: control of chronic disease; Self-control of chronic disease; Knowledge: prevention of falls; Weight control; State of comfort and Participation in physical exercise program. The results Knowledge: pain control and nutritional status had significant improvement in the scores of indicators only for the elderly with RSIF, as well as the self-care evaluation: daily life activities for elderly with 9 SIF. The interventions that presented a statistically significant reduction in the use of their activities in the elderly, with both diagnoses, were Teaching: disease process and Exercise promotion, while the intervention Prevention of falls was found only in the elderly with RSIF. It is concluded that the seven nursing interventions validated by the specialists were implemented to the elderly with a diagnosis of RSIF Nursing and were considered effective, based on the evaluation of nine results that indicated a significant improvement in the comparison between the means of the first and fourth visits. Among the eight Nursing interventions implemented to the elderly with SIF Nursing diagnosis, seven were considered effective, based on the evaluation of 11 results that indicated a significant improvement in the comparison between the means of the first and fourth visits. Thus, it can be concluded that the multidimensional model of elderly care associated with standardized Nursing language systems contributes to the nurses practice in the nursing consultation, with a view to successful aging. Among the important implications and contributions of the results of this research is the possibility of supporting the link between results and validated interventions with the RSIF and SIF, facilitating nursing assessment and nursing care for the elderly in clinical practice. In addition, it is recommended to construct operational definitions for indicators of nursing outcomes. One limitation of the study was the fact that we conducted the research with specialists from the same country.
Mühlstedt, Jens, Christian Hentschel, Doreen Bartel, Isabell Grundmann, and Birgit Spanner-Ulmer. "Bewertungsmodell muskulärer dynamischer Beanspruchungen." Universitätsbibliothek Chemnitz, 2011. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-qucosa-68034.
Повний текст джерелаWang, Gubing, Armagan Albayrak, and der Cammen Tischa J. M. van. "Converting wandering behaviour into a guided activity: a case study of co-designing with People Living with Dementia based on theoretical models." TUDpress, 2019. https://tud.qucosa.de/id/qucosa%3A36598.
Повний текст джерелаAntonio, Marie de. "Statistiques et modèles de survie pour améliorer la connaissance d’une maladie rare, la dystrophie myotonique The DM-Scope registry: a rare disease innovative framework bridging the gap between research and medical care Unraveling the myotonic dystrophy type 1 clinical spectrum: a systematic registry-based study - Implications for disease classification." Thesis, Sorbonne université, 2020. http://www.theses.fr/2020SORUS096.
Повний текст джерелаMyotonic dystrophy (DM) is considered one of the most complex neuromuscular diseases. Although research work over the past 30 years has permitted a better understanding of its underlying molecular mechanisms, the unusual nature of its genetic anomalies, its multisystemic expression and its broad clinical spectrum do not allow, at the moment, optimal patient management. The purpose of my work was to deepen our knowledge of this rare disease and to clarify its natural history. The first part of my manuscript is dedicated to the presentation of the DM-Scope Registry, on which all my thesis work is based. After the description of the concept, the functioning and the data collection platform, the manuscript features the characteristics of the DM1 cohort, from which our analyses were conducted : the clinical spectrum covered, multisystemic impairment, genotype/phenotype correlations, interrelations between symptoms and comparison to myotonic dystrophy type II (DM2). In the second part, we focus on the major progress achieved through the existence of DM-Scope and the analyses conducted during my thesis: (i) detailing the natural history of the disease, in particular proposing a new classification; (ii) highlighting the phenotype’s determining factors such as gender, mutation size, interrelations between symptoms. This work has led to recommendations for care, in particular for the transition from child to adult, but also the validation of important inclusion criteria for clinical trials such as gender. DM-Scope provides access to available biological samples for basic research studies and validates new therapeutic approaches. DM-Scope is now a worldwide leader and an essential tool in translational research in DM. The DM-Scope concept can be transferred to any other population and can be used for care management in other rare diseases. Finally, we present the development of a survival model built from the DM-Scope cohort. This model has three specificities: (i) it is applicable to high dimensional data, in such cases as DM-Scope, where there is a large number of measurements; (ii) it takes into account competitive risks, when patients are simultaneously exposed to several events. In our registry, the study of respiratory-related deaths is biased if competing events such as heart disease deaths are not taken into account ; (iii) it models the heterogeneity between patient groups probably due to divergent care, called \og centres effects \fg{}. DM-Scope data analysis requires such specificity of frailty models due to its multicentric coverage (55 centres). This model can be transferred and applied to other data, considering the following : more and more large-scaled registries are being used ; a majority of survival analyses includes censorship caused by the occurrence of the event of interest ; multicentre studies have become increasingly common
Neumann, Anne, Enno Swart, Dennis Häckl, Roman Kliemt, Stefanie March, Denise Küster, Katrin Arnold, et al. "The influence of cross-sectoral treatment models on patients with mental disorders in Germany: study protocol of a nationwide long-term evaluation study (EVA64)." BioMed Central, 2018. https://tud.qucosa.de/id/qucosa%3A33821.
Повний текст джерелаRau, Alex. "Altersarmut." Universität Leipzig, 2019. https://ul.qucosa.de/id/qucosa%3A34804.
Повний текст джерелаMenke, Katrin. "Familienpolitik." Universität Leipzig, 2018. https://ul.qucosa.de/id/qucosa%3A23360.
Повний текст джерелаJakel, Roland. "Berechnung von Schockspektren und praktische Anwendung der dynamischen Stoßanalyse in Creo Elements / Pro Mechanica." Universitätsbibliothek Chemnitz, 2011. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-qucosa-68407.
Повний текст джерелаThe presentation explains idea and fundamentals of shock response spectra analysis. With help of the PTC FEM-software Creo Elements / Pro Mechanica the shock response spectra (SRS) for an exemplary half sine shock is calculated. The shock response of a one-mass and a two-mass oscillator are analyzed per dynamic time as well as per dynamic shock analysis. The modal superposition methods "absolute sum" and "SRSS" (Square Root of the Sum of the Squares) are explained. The method is applied for different half sine shocks on a realistic example: A thermal imaging system of the company Carl Zeiss Optronics GmbH. Finally, the creation of response spectra for global-local analysis is explained
Chen, Mei-Yun, and 陳美雲. "Using Decision Tree to Construct the Classification Model of Car Consumer Purchasing Intention." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/41526648277873686138.
Повний текст джерела大葉大學
國際企業管理學系碩士在職專班
104
With the rapid development of the automotive industry and the increasing emphasis on the convenient life, cars have become indispensable vehicles of daily life. In recent years, the competition of the car marketing in Taiwan is increasingly fierce. Therefore, if car operators want to the fore of the competitive market, understanding the purchasing intention of customers and mastering the right consumer group are very important. The basis of this thesis is to study the relevant literatures of the car purchasing and summed 11 important factors of the purchasing intention. Then, we use populace in Taiwan had a car purchasing intention or idea as the sampling targets to do the decision tree analysis by R statistical software to construct the classification model of the car consumer purchasing intention. This classification model provides car operators an easier way to understand the customer's choices and decisions and master the right consumer group to make a better marketing strategy. The classification model of the car consumer purchasing intention constructed by this study has the accuracy as follow: the car category is 74.23%, the domestic car brand is 60.26%, the imported car brand is 39.53%. According to results of the study, the prediction of the car category and the domestic car brand is credible. But the prediction of the imported car brand is not ideal.
Hu, Qichang. "Dynamic Scene Understanding with Applications to Traffic Monitoring." Thesis, 2017. http://hdl.handle.net/2440/119678.
Повний текст джерелаThesis (Ph.D.) -- University of Adelaide, School of Computer Science, 2017
Lin, Wen-Chin, and 林玟妗. "Using convolutional neural network to construct classification models of bus drivers\' car-following behavior." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/eya368.
Повний текст джерела國立交通大學
運輸與物流管理學系
107
Safety is one of the issues in public transportation that the government emphasizes. If bus companies are able to comprehend the driving behavior of bus drivers, then companies can effectively adopt appropriate management measures for drivers. The purpose of this study is to develop classification models of bus drivers' car-following behavior using convolutional neural networks (CNN). The headway data recorded by Mobileye systems were used as the input data to build and train the CNN classification models. The proposed classification models would facilitate determining the car-following types of bus drivers based on Mobileye headway data. We firstly processed the Mobile headway data and then considered three major factors that may affect the car-following behavior of drivers, including weather, speed and day-or-night. According to the three factors, we designed seven different scenarios and filtered the data by scenario. The filtered data were used to generate headway matrices for each driver. The matrices were the input data of the CNNs for training and classification. The trained models can be used to determine the car-following type of the input headway matrix of a driver. The experimental results show that the proposed CNN models have accurate prediction in most of the scenarios. The average accuracy is 97%. The results of this study can be used as a reference in classifying and determining the car-following types of drivers. Bus companies can utilize the classification results to take actions on the driving behavior of drivers.
Harmeyer, Gary R. "A prototype model for automating nursing diagnosis, nurse care planning and patient classification." Thesis, 1986. http://hdl.handle.net/10945/22052.
Повний текст джерелаPeng, Shao-Hsuan, and 彭紹軒. "Using Card Sorting and Edit Distance to Analyze the Consistency between User Mental Models and Product Classifications on Different Shopping Websites." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/wh69nv.
Повний текст джерела國立臺北科技大學
工業工程與管理研究所
98
As the rapid development of electronic commerce and information technology, the population of online shopping is getting more and more. Everyone can buy products on the shopping websites through internet at any time. The benefits and conveniences of online shopping are huge that traditional auction is hard to achieve. This research was based on the biggest shopping website in Taiwan, Yahoo, to discuss related issues. There are various commodities can be chosen on the shopping website, however, how consumers find their needs rapidly and correctly among a huge set of commodities is the objective of this research. The product classification of shopping website is always different from the cognition of consumers, which leads to the difficulty for consumers to search the products they want. Therefore, the main issue of this research is to find out the consumers’ cognition of product classification. This research used card sorting to find out the categorization structure of consumer on shopping websites. After comparing the structure with two shopping websites, we used the edit distance to come up with the differences of categorization structure and design a product search experiment. Results showed that, compared to original web structures, subjects had a shorter product esearch time, less number of clicks on web-pages when they searched products on the web designed based on their mental models. The findings of this study should be helpful for the product classification of shopping websites.
Basiouni, Shereen. "The modulating effects of polyunsaturated fatty acids on membrane composition and phospholipase D in a canine mast cell line as a model for atopic dermatitis." Doctoral thesis, 2013. https://ul.qucosa.de/id/qucosa%3A11383.
Повний текст джерелаMehrfach ungesättigte Fettsäuren (PUFA) können mit einigem Erfolg zur Behandlung der caninen atopischen Dermatitis (CAD) eingesetzt werden. In vitro-Studien zeigten, dass PUFA eine entscheidende Rolle in der Exozytose von Mastzellen spielen. N-3-PUFA wie α-Linolensäure (LNA), Eicosapentaensäure (EPA), Docosahexaensäure (DHA) sowie die n-6-PUFA Linolsäure (LA) können die Sekretion von Entzündungsmediatoren vermindern. Arachidonsäure (AA) als n-6 mehrfach ungesättigte Fettsäure hingegen fördert die Entzündungsmediatoren-Freisetzung aus den Mastzellen. Eine vollständige Aufklärung der Wirkungsweise fehlt aber weiterhin. Das Ziel dieser Arbeit war eine weitergehende Charakterisierung der modulierenden Effekte einer PUFA-Supplementierung auf die Lipidzusammensetzung der Plasmamembran von Mastzellen. Darüber hinaus wurden die Auswirkungen von PUFA auf die Lokalisation und Aktivität des Membran-gebundenen Enzyms Phospholipase D (PLD) untersucht. Canine Mastozytom-Zellen (C2) wurden mit einer der folgenden PUFA kultiviert: LNA, EPA, DHA, LA oder AA. Um den Einfluss von PUFA auf die Lipidzusammensetzung der Membran-Mikrodomänen zu untersuchen, konnten sowohl Lipid Raft als auch Nicht-Raft Plasmamembran-Anteile von Mastzellen zum ersten Mal mittels einer Detergenzien-freien Isolationsmethode getrennt werden. Hervorzuheben ist, dass PUFA signifikant vermehrt in Raft- sowie in Nicht-Raft Membranmikrodomänen eingelagert werden (Publikation 1). Die Integration von PUFA in die Membran geht mit einer Steigerung der Doppelbindungsanzahl und der Fluidität der Membran einher. Diese Erhöhung der Membranfluidität kann zu einer Reorganisation von membranären Signalmolekülen und Enzymen wie der PLD führen. Um die Auswirkungen einer PUFA-Supplementierung auf den intrazellulären Transport der PLD in C2 zu bestimmen, wurden die Zellen mit PLD1- oder PLD2-codierenden grün fluoreszierenden Protein-(GFP-)Fusionsplasmiden transfiziert. Da die Transfektionsfähigkeit der Suspensions-Zelllinie C2 begrenzt ist, wurde ein für nicht-adhärente Zelllinien geeignetes Transfektionsprotokoll etabliert. Mit Hühnereiweiß als Beschichtungsmaterial für die Zellkultur-Platten stieg die Transfektionseffizienz auf 50% im Vergleich zu 5% bei unbeschichteten Platten. Neben der deutlichen Erhöhung der Transfektionseffizienz ist die neu etablierte Technik einfach durchzuführen sowie wirtschaftlich und kann für eine Vielzahl von Suspension-Zelllinien geeignet sein (Publikation 2). Unter Verwendung dieses optimierten Protokolls wurde der Einfluss von PUFA auf die Translokation der PLD-Isoformen untersucht. LNA, EPA, DHA und LA, nicht aber AA verhindern die stimulationsinduzierte Translokation der PLD1 an die Plasmamembran. Die Translokation der PLD1 ist wichtig für die Mastzell-Exozytose. LNA, EPA, DHA und LA haben hier eine hemmende Wirkung auf die stimulationsinduzierte Freisetzung von proinflammatorischen Mediatoren. Alle getesteten PUFA verstärken die Gesamt-PLD-Aktivität. Um zu unterscheiden, welche PLD-Isoform durch PUFA beeinflusst ist, wurden die Mastzellen mit DHA oder AA in Gegenwart von PLD-Isoform-Inhibitoren supplementiert. DHA hebt die inhibitorische Wirkung des PLD1-Inhibitors vollständig auf, zeigte aber keinen Einfluss auf die hemmende Wirkung des PLD2-Inhibitors. Andererseits unterdrückt AA die hemmende Wirkung des PLD1- als auch des PLD2-Inhibitors (Publikation 3). Zusammenfassend bietet die Studie eine mechanistische Basis für die Rolle von PUFA bei Exozytose-Prozessen von Mastzellen. PUFA der n-3- und n-6-Familie beeinflussen die Lipidzusammensetzung von membranären Mikrodomänen, was wiederum zu einer Modulation der physikalisch-chemischen Eigenschaften der Membran führt. LNA, EPA, DHA und LA verhindern die Freisetzung von Entzündungsmediatoren durch ihre hemmende Wirkung auf die stimulationsinduzierte Translokation der PLD1. Umgekehrt erlaubt AA eine stimulationsinduzierte Migration der PLD1 zur Plasmamembran und steigert die Aktivität der beiden Isoformen der PLD. Somit hemmen LNA, EPA, DHA und LA, aber nicht AA die Freisetzung von Mastzell-Entzündungsmediatoren nach Stimulation.
Sembdner, Philipp. "Rechnergestützte Planung und Rekonstruktion für individuelle Langzeit-Knochenimplantate am Beispiel des Unterkiefers." Doctoral thesis, 2016. https://tud.qucosa.de/id/qucosa%3A30198.
Повний текст джерелаGonçalves, João Manuel de Campos. "Utilização de técnicas de data mining na previsão do plano terapêutico em medicina intensiva." Master's thesis, 2012. http://hdl.handle.net/1822/25883.
Повний текст джерелаUm dos principais dilemas existentes na medicina intensiva prende-se com o plano terapêutico, mais concretamente, que medicamentos e quando é que estes devem ser administrados a um doente. No plano terapêutico, a interpretação rápida e avaliação precisa de dados fisiológicos, são cruciais para uma tomada de decisão mais eficiente e eficaz por parte dos médicos. No sentido de apoiar a decisão dos médicos, este trabalho tem como objetivo prever o nível de sépsis e a melhor terapêutica para doentes com problemas microbiológicos, baseados nos níveis de sépsis. Para isso, foi desenvolvido um conjunto de modelos de Data Mining (DM), utilizando técnicas de previsão e modelos classificação, que irão possibilitar o médico decidir qual a terapêutica adequada a aplicar, bem como aquela que apresente uma elevada taxa de sucesso. Os dados utilizados nos modelos de DM foram recolhidos no Serviço de Cuidados Intensivos do Hospital de Santo António, Porto, Portugal. Nesta dissertação, foi utilizada a tarefa de previsão, o modelo de classificação, o método de aprendizagem supervisionada e os algoritmos: Árvores de Decisão, Máquinas de Vetores de Suporte e o classificador Naïve Bayes, para prever o nível de sépsis e o plano terapêutico de doentes com sépsis. Relativamente à avaliação, utilizaram-se a Matriz de Confusão, incluindo as métricas associadas e a Cross-validation. De entre as métricas associadas na análise, foram utilizadas: a taxa de erro total, a sensibilidade, a especificidade e a acuidade, que permitiram identificar quais as medidas mais relevantes para a previsão do nível da sépsis e do plano terapêutico em estudo. Concluindo, foi possível prever com grande acuidade o nível de sépsis, no entanto, o mesmo já não é possível dizer no que diz respeito à medicação. Apesar de os modelos da sépsis terem bons resultados, o plano terapêutico não apresenta o mesmo nível de acuidade. Os resultados provam que de uma forma geral existe uma fraca correlação entre o nível de sépsis e o plano terapêutico, referente ao grupo de medicamentos. No entanto, é de salientar que para alguns grupos de medicamentos, os modelos tiveram uma bom desempenho (nível de acertos em algumas classes foi superior a 80%).
One of the main problems existing in intensive medicine is related to the therapeutic plan, particularly what and when drugs must be administered to a patient. In the therapeutic plan it is crucial to make a rapid interpretation and accurate assessment of physiological data for efficient and effective decisionmaking by doctors. The present investigation aims to support doctor’s decision-making on predicting sepsis level and the best treatment for patients with microbiological problems based on sepsis levels. Thus, a set of Data Mining (DM) models was developed using forecasting techniques and classification models which will enable a doctor’s decision about appropriate therapy to apply, as well as the most successful one. The data used in DM models were collected at the Department of Intensive Care of the Hospital de Santo António, in Oporto, Portugal. Classification DM models where considered to predict sepsis level and therapeutic plan for patients with sepsis in a supervised learning approach. Models were induced making use of the following algorithms: Decision Trees, Support Vector Machines and Naïve Bayes classifier. Confusion Matrix, including associated metrics, and Cross-validation were used for the evaluation. Analysis of the total error rate, sensitivity, specificity and accuracy were the associated metrics used to identify the most relevant measures to predict sepsis level and treatment plan under study. In conclusion, it was possible to predict with great accuracy the sepsis level, but not the medication. Although the good sepsis models results attained, therapeutic plan does not present the same level of accuracy. The results have showed that in general there is a small correlation between sepsis level and therapeutic plan, considering the drugs group. However, for some drugs groups models the results are interesting (some classes exceeded 80% in terms of the accuracy level).