Sökning: "QDA"
Visar resultat 1 - 5 av 14 uppsatser innehållade ordet QDA.
1. Robustness Against Non-Normality : Evaluating LDA and QDA in Simulated Settings Using Multivariate Non-Normal Distributions
Kandidat-uppsats, Uppsala universitet/Statistiska institutionenSammanfattning : Evaluating classifiers in controlled settings is essential for empirical applications, as extensive knowledge on model-behaviour is needed for accurate predictions. This thesis investigates robustness against non-normality of two prominent classifiers, LDA and QDA. LÄS MER
2. A sensory evaluation of swidden rye (Secale cereale) – how the taste of history and geographical location can play part in a sustainable food production
Master-uppsats, Uppsala universitet/Institutionen för geovetenskaperSammanfattning : Due to their resilience, durability, and broad genetic variations, increasing the production and consumption of landrace cereals has been highlighted as a solution to handle increasing environmental variability resulting from climate change. However, the consumption of landrace cereals remains low due to limited production and purchase availability for consumers. LÄS MER
3. Searching for a sensory vocabulary for Swedish vegetables : an exploratory study of the flavour and aroma characteristics of carrot, cabbage and onion
Master-uppsats, SLU/Dept. of Plant Protection BiologySammanfattning : Flavour is an important aspect in the consumption of fruits and vegetables. However, the current regulatory context within EU for the quality of fruit and vegetables involve standards that lay primary emphasis on visual properties but limited focus on flavour and nutrition. LÄS MER
4. En jämförelse analys av linjära och icke-linjära klassificerings metoder LDA och QDA för hjärn-dator gränssnitt
Kandidat-uppsats, KTH/Skolan för teknikvetenskap (SCI)Sammanfattning : Hjärn-dator gränssnitt (BCI) är system, kommunikationsvägar som gör det möjligt för användare att interagera med externa enheter utan att förlita sig på kroppsrörelser. Denna växelverkan mellan människa och maskin är möjlig genom att tillåta systemåtkomst för att läsa hjärnans elektriska aktivitet, ofta via elektroencefalogram (EEG). LÄS MER
5. Evaluation of the Robustness of Different Classifiers under Low- and High-Dimensional Settings
Master-uppsats, Uppsala universitet/Statistiska institutionenSammanfattning : This thesis compares the performance and robustness of five different varities of discriminant analysis, namely linear (LDA), quadratic (QDA), generalized quadratic (GQDA), diagonal linear (DLDA) and diagonal quadratic (DQDA) discriminant analysis, under elliptical distributions and small sample sizes. By means of simulations, the performance of the classifiers are compared against separation of mean vectors, sample size, number of variables, degree of non-normality and covariance structures. LÄS MER