Sökning: "Artificial neural network ANN"

Visar resultat 1 - 5 av 51 avhandlingar innehållade orden Artificial neural network ANN.

  1. 1. Metamodel-Based Multidisciplinary Design Optimization of Automotive Structures

    Författare :Ann-Britt Ryberg; Larsgunnar Nilsson; Anirban Basudhar; Linköpings universitet; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; multidisciplinary design optimization MDO ; metamodel; artificial neural network ANN ; support vector machine SVM ; sequential sampling; crashworthiness; automotive structure; spot weld optimization;

    Sammanfattning : Multidisciplinary design optimization (MDO) can be used in computer aided engineering (CAE) to efficiently improve and balance performance of automotive structures. However, large-scale MDO is not yet generally integrated within automotive product development due to several challenges, of which excessive computing times is the most important one. LÄS MER

  3. 2. Neural Network Approaches To Survival Analysis

    Författare :Jonas Kalderstam; Beräkningsbiologi och biologisk fysik - Genomgår omorganisation; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Survival Analysis; Artificial Neural Networks; Machine Learning; Genetic Algorithms; Evolutionary Algorithms; Fysicumarkivet:2015:Kalderstam;

    Sammanfattning : Predicting the probable survival for a patient can be very challenging for many diseases. In many forms of cancer, the choice of treatment can be directly impacted by the estimated risk for the patient. This thesis explores different methods to predict the patient's survival chances using artificial neural networks (ANN). LÄS MER

  4. 3. Resource Allocation with Potts Mean Field Neural Network Techniques

    Författare :Martin Lagerholm; Beräkningsbiologi och biologisk fysik - Genomgår omorganisation; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Potts; combinatorial optimization; ANN; mean field; approximation; routing; unicast; multicast; airline crew; scheduling; ECG; NP-complete.; Matematik; Mathematics; algorithm; Systems engineering; computer technology; Data- och systemvetenskap; Fysicumarkivet A:1998:Lagerholm;

    Sammanfattning : Potts mean field artificial neural network techniques are developed and applied to airline crew scheduling problems and routing problems. A propagator formalism in terms of Potts neurons is developed to handle global topological issues. An integrated method for identifying and classifying ECG complexes is presented. LÄS MER

  5. 4. Neural Network Ensembles and Combinatorial Optimization with Applications in Medicine

    Författare :Henrik Haraldsson; Beräkningsbiologi och biologisk fysik - Genomgår omorganisation; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; numerisk analys; machine learning; artificial neural networks; ensemble methods; feature extraction; ECG; combinatorial optimization; mean field annealing; Computer science; numerical analysis; systems; Datalogi; control; system; kontroll; Artificial intelligens; Artificiell intelligens; Fysicumarkivet A:2003:Haraldsson;

    Sammanfattning : Artificial neural network (ANN) and combinatorial optimization algorithms are developed, and applied to the medical domain. A novel method for training an ensemble of ANN is presented, based on random weight updates alternated with replication of networks with low error. LÄS MER

  7. 5. ICU prognostication: Time to re-evaluate? Register-based studies on improving prognostication for patients admitted to the intensive care unit (ICU)

    Författare :Peder Andersson; Anestesiologi och intensivvård; []
    Nyckelord :MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; Intensive Care; Critical Care; Mortality; Cerebral Performance Category; Cardiac arrest; Out-of-hospital cardiac arrest; Sepsis; Lactate; Troponin; Neuron-specific enolase; Neurofilament light; Age; Elderly; Prognostication; Prediction; Scoring system; Neural net; Artificial neural network; Deep learning; Artificial intelligence;

    Sammanfattning : Background: ICU prognostication is difficult because of patients’ prior comorbidities and their varied reasons for admission. The model used for ICU prognostication in Sweden is the Simplified Acute Physiology Score 3 (SAPS 3), which uses information gathered within one hour of ICU admission to predict 30-day mortality. LÄS MER