• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 3
  • Tagged with
  • 4
  • 4
  • 4
  • 4
  • 3
  • 3
  • 2
  • 2
  • 2
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Machine Learning for Beam Based Mobility Optimization in NR

Ekman, Björn January 2017 (has links)
One option for enabling mobility between 5G nodes is to use a set of area-fixed reference beams in the downlink direction from each node. To save power these reference beams should be turned on only on demand, i.e. only if a mobile needs it. An User Equipment (UE) moving out of a beam's coverage will require a switch from one beam to another, preferably without having to turn on all possible beams to find out which one is the best. This thesis investigates how to transform the beam selection problem into a format suitable for machine learning and how good such solutions are compared to baseline models. The baseline models considered were beam overlap and average Reference Signal Received Power (RSRP), both building beam-to-beam maps. Emphasis in the thesis was on handovers between nodes and finding the beam with the highest RSRP. Beam-hit-rate and RSRP-difference (selected minus best) were key performance indicators and were compared for different numbers of activated beams. The problem was modeled as a Multiple Output Regression (MOR) problem and as a Multi-Class Classification (MCC) problem. Both problems are possible to solve with the random forest model, which was the learning model of choice during this work. An Ericsson simulator was used to simulate and collect data from a seven-site scenario with 40 UEs. Primary features available were the current serving beam index and its RSRP. Additional features, like position and distance, were suggested, though many ended up being limited either by the simulated scenario or by the cost of acquiring the feature in a real-world scenario. Using primary features only, learned models' performance were equal to or worse than the baseline models' performance. Adding distance improved the performance considerably, beating the baseline models, but still leaving room for more improvements.
2

Contributions to Computational Methods for Association Extraction from Biomedical Data: Applications to Text Mining and In Silico Toxicology

Raies, Arwa B. 29 November 2018 (has links)
The task of association extraction involves identifying links between different entities. Here, we make contributions to two applications related to the biomedical field. The first application is in the domain of text mining aiming at extracting associations between methylated genes and diseases from biomedical literature. Gathering such associations can benefit disease diagnosis and treatment decisions. We developed the DDMGD database to provide a comprehensive repository of information related to genes methylated in diseases, gene expression, and disease progression. Using DEMGD, a text mining system that we developed, and with an additional post-processing, we extracted ~100,000 of such associations from free-text. The accuracy of extracted associations is 82% as estimated on 2,500 hand-curated entries. The second application is in the domain of computational toxicology that aims at identifying relationships between chemical compounds and toxicity effects. Identifying toxicity effects of chemicals is a necessary step in many processes including drug design. To extract these associations, we propose using multi-label classification (MLC) methods. These methods have not undergone comprehensive benchmarking in the domain of predictive toxicology that could help in identifying guidelines for overcoming the existing deficiencies of these methods. Therefore, we performed extensive benchmarking and analysis of ~19,000 MLC models. We demonstrated variability in the performance of these models under several conditions and determined the best performing model that achieves accuracy of 91% on an independent testing set. Finally, we propose a novel framework, LDR (learning from dense regions), for developing MLC and multi-target regression (MTR) models from datasets with missing labels. The framework is generic, so it can be applied to predict associations between samples and discrete or continuous labels. Our assessment shows that LDR performed better than the baseline approach (i.e., the binary relevance algorithm) when evaluated using four MLC and five MTR datasets. LDR achieved accuracy scores of up to 97% using testing MLC datasets, and R2 scores up to 88% for testing MTR datasets. Additionally, we developed a novel method for minority oversampling to tackle the problem of imbalanced MLC datasets. Our method improved the precision score of LDR by 10%.
3

Novel Support Vector Machines for Diverse Learning Paradigms

Melki, Gabriella A 01 January 2018 (has links)
This dissertation introduces novel support vector machines (SVM) for the following traditional and non-traditional learning paradigms: Online classification, Multi-Target Regression, Multiple-Instance classification, and Data Stream classification. Three multi-target support vector regression (SVR) models are first presented. The first involves building independent, single-target SVR models for each target. The second builds an ensemble of randomly chained models using the first single-target method as a base model. The third calculates the targets' correlations and forms a maximum correlation chain, which is used to build a single chained SVR model, improving the model's prediction performance, while reducing computational complexity. Under the multi-instance paradigm, a novel SVM multiple-instance formulation and an algorithm with a bag-representative selector, named Multi-Instance Representative SVM (MIRSVM), are presented. The contribution trains the SVM based on bag-level information and is able to identify instances that highly impact classification, i.e. bag-representatives, for both positive and negative bags, while finding the optimal class separation hyperplane. Unlike other multi-instance SVM methods, this approach eliminates possible class imbalance issues by allowing both positive and negative bags to have at most one representative, which constitute as the most contributing instances to the model. Due to the shortcomings of current popular SVM solvers, especially in the context of large-scale learning, the third contribution presents a novel stochastic, i.e. online, learning algorithm for solving the L1-SVM problem in the primal domain, dubbed OnLine Learning Algorithm using Worst-Violators (OLLAWV). This algorithm, unlike other stochastic methods, provides a novel stopping criteria and eliminates the need for using a regularization term. It instead uses early stopping. Because of these characteristics, OLLAWV was proven to efficiently produce sparse models, while maintaining a competitive accuracy. OLLAWV's online nature and success for traditional classification inspired its implementation, as well as its predecessor named OnLine Learning Algorithm - List 2 (OLLA-L2), under the batch data stream classification setting. Unlike other existing methods, these two algorithms were chosen because their properties are a natural remedy for the time and memory constraints that arise from the data stream problem. OLLA-L2's low spacial complexity deals with memory constraints imposed by the data stream setting, and OLLAWV's fast run time, early self-stopping capability, as well as the ability to produce sparse models, agrees with both memory and time constraints. The preliminary results for OLLAWV showed a superior performance to its predecessor and was chosen to be used in the final set of experiments against current popular data stream methods. Rigorous experimental studies and statistical analyses over various metrics and datasets were conducted in order to comprehensively compare the proposed solutions against modern, widely-used methods from all paradigms. The experimental studies and analyses confirm that the proposals achieve better performances and more scalable solutions than the methods compared, making them competitive in their respected fields.
4

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.

Page generated in 0.0981 seconds