21 |
Patient simulation. : Generation of a machine learning “inverse” digital twin. / Patientsimulering. : Generering av en digital tvilling med hjälp av maskininlärning.Calderaro, Paolo January 2022 (has links)
In the medtech industry models of the cardiiovascular systems and simulations are valuable tools for the development of new products ad therapies. The simulator Aplysia has been developed over several decade and is able to replicate a wide range of phenomena involved in the physiology and pathophysiology of breathing and circulation. Aplysia is also able to simulate the hemodynamics phenomena starting from a set of patient model parameters enhancing the idea of a "digital twin", i.e. a patient-specific representative simulation. Having a good starting estimate of the patient model parameters is a crucial aspect to start the simulation. A first estimate can be given by looking at patient monitoring data but medical expertise is required. The goal of this thesis is to address the parameter estimation task by developing machine learning and deep learning model to give an estimate of the patient model parameter starting from a set of time-varying data that we will refers as state variables. Those state variables are descriptive of a specific patient and for our project we will generate them through Aplysia starting from the simulation presets already available in the framework. Those presets simulates different physiologies, from healthy cases to different cardiovascular diseases. The thesis propose a comparison between a machine learning pipeline and more complex deep learning architecture to simultaneously predicting all the model parameters. This task is referred as Multi Target Regression (MTR) so the performances will be assessed in terms of MTR performance metrics. The results shows that a gradient boosting regressor with a regressor-stacking approach achieve overall good performances, still it shows some lack of performances on some target model parameters. The deep learning architectures did not produced any valuable results because of the amount of our data: to deploy deep architectures such as ResNet or more complex Convolutional Neural Network (CNN) we need more simulations then the one that were done for this thesis work. / Simulatorn Aplysia har under flera decennier utvecklats för forskning och FoU inom området kardiovaskulära systemmodeller och simuleringar och kan idag replikera ett brett spektrum av fenomen involverade i andningens och cirkulationens fysiologi och patofysiologi. Aplysia kan också simulera hemodynamiska fenomen med utgångspunkt från en uppsättning patientmodellparametrar och detta förstärker idén om en digital tvilling", det vill säga en patientspecifik representativ simulering. Att ha en bra startuppskattning av patientmodellens parametrar är en avgörande aspekt för att starta simuleringen. En första uppskattning kan ges genom att titta på patientövervakningsdata men medicinsk expertis krävs för tolkningen av sådana data. Målet med denna mastersuppsats är att addressera parameteruppskattningsuppgiften genom att utveckla maskininlärnings-och djupinlärningsmodeller för att erhålla en uppskattning av patientmodellparametrar utgående från en uppsättning tidsvarierande data som vi kommer att referera till som tillståndsvariabler. Dessa tillståndsvariabler är beskrivande för en specifik patient och för vårt projekt kommer vi att generera dem med hjälp av Aplysia med utgångspunkt från de modellförinställningar som redan finns tillgängliga i ramverket. Dessa förinställningar simulerar olika fysiologier, från friska fall till olika hjärt-kärlsjukdomar. Uppsatsen presenterar en jämförelse mellan en maskininlärningspipeline och en mer komplex djupinlärningsarkitektur för att samtidigt förutsäga alla modellparametrar. Denna uppgift bygger på MTR så resulterande prestanda kommer att bedömas i termer av MTR prestationsmått. Resultaten visar att en gradientförstärkande regressor med en regressor-stacking-metod uppnår överlag goda resultat, ändå visar den en viss brist på prestanda på vissa målmodellparametrar. Deep learning-arkitekturerna gav inga värdefulla resultat på grund av den begränsade mängden av data vi kunde generera. För att träna djupa arkitekturer som ResNet eller mer komplexa CNN behöver vi fler simuleringar än den som gjordes för detta examensarbete.
|
22 |
Random Finite Set Methods for Multitarget TrackingDunne, Darcy 04 1900 (has links)
<p>Multiple target tracking (MTT) is a major area that occurs in a variety of real world systems. The problem involves the detection and estimation of an unknown number of targets within a scenario space given a sequence of noisy, incomplete measurements. The classic approach to MTT performs data association between individual measurements, however, this step is a computationally complex problem. Recently, a series of algorithms based on Random Finite Set (RFS) theory, that do not require data association, have been introduced. This thesis addresses some of the main deficiencies involved with RFS methods and derives key extensions to improve them for use in real world systems.\\</p> <p>The first contribution is the Weight Partitioned PHD filter. It separates the Probability Hypothesis Density (PHD) surface into partitions that represent the individual state estimates both spatially and proportionally. The partitions are labeled and propagated over several time steps to form continuous track estimates. Multiple variants of the filter are presented. Next, the Multitarget Multi-Bernoulli (MeMBer) filter is extended to allow the tracking of manoeuvring targets. A model state variable is incorporated into the filter framework to estimate the probability of each motion model. The standard implementations are derived. Finally, a new linear variant of the Intensity filter (iFilter) is presented. A Gaussian Mixture approximation provides more computationally efficient implementation of the iFilter.</p> <p>Each of the new algorithms are validated on simulated data using standard multitarget tracking metrics. In each case, the methods improve on several aspects of multitarget tracking in the real world.</p> / Doctor of Engineering (DEng)
|
23 |
B-Spline Based Multitarget TrackingSithiravel, Rajiv January 2014 (has links)
Multitarget tracking in the presence of false alarm is a difficult problem to consider. The objective of multitarget tracking is to estimate the number of targets and their states recursively from available observations. At any given time, targets can be born, die and spawn from already existing targets. Sensors can detect these targets with a defined threshold, where normally the observation is influenced by false alarm. Also if the targets are with low signal to noise ratio (SNR) then the targets may not be detected.
The Random Finite Set (RFS) filters can be used to solve such multitarget problem efficiently. Specially, one of the best and most widely used RFS based filter is the Probability Hypothesis Density (PHD) filter. The PHD filter approximates the posterior probability density function (PDF) by the first order moment only, where the targets SNR assumed to be much higher. The PHD filter supports targets die, born, spawn and missed-detection by using the well known implementations including Sequential Monte Carlo Probability Hypothesis Density (SMC-PHD) and Gaussian Mixture Probability Hypothesis Density (GM-PHD) methods. The SMC-PHD filter suffers from the well known degeneracy problems while GM-PHD filter may not be suitable for nonlinear and non-Gaussian target tracking problems.
It is desirable to have a filter that can provide continuous estimates for any distribution. This is the motivation for the use of B-Splines in this thesis. One of the main focus of the thesis is the B-Spline based PHD (SPHD) filters. The Spline is a well developed theory and been used in academia and industry for more than five decades. The B-Spline can represent any numerical, geometrical and statistical functions and models including the PDF and PHD. The SPHD filter can be applied to linear, nonlinear, Gaussian and non-Gaussian multitarget tracking applications. The SPHD continuity can be maintained by selecting splines with order of three or more, which avoids the degeneracy-related problem. Another important characteristic of the SPHD filter is that the SPHD can be locally controlled, which allow the manipulations of the SPHD and its natural tendency for handling the nonlinear problems. The SPHD filter can be further extended to support maneuvering multitarget tracking, where it can be an alternative to any available PHD filter implementations.
The PHD filter does not work well for very low observable (VLO) target tracking problems, where the targets SNR is normally very low. For very low SNR scenarios the PDF must be approximated by higher order moments. Therefore the PHD implementations may not be suitable for the problem considered in this thesis. One of the best estimator to use in VLO target tracking problem is the Maximum-Likelihood Probability Data Association (ML-PDA) algorithm. The standard ML-PDA algorithm is widely used in single target initialization or geolocation problems with high false alarm. The B-Spline is also used in the ML-PDA (SML-PDA) implementations. The SML-PDA algorithm has the capability to determine the global maximum of ML-PDA log-likelihood ratio with high efficiency in terms of state estimates and low computational complexity. For fast passive track initialization, search and rescue operations the SML-PDA algorithm can be used more efficiently compared to the standard ML-PDA algorithm. Also the SML-PDA algorithm with the extension supports the multitarget tracking. / Thesis / Doctor of Philosophy (PhD)
|
Page generated in 0.0339 seconds