Sökning: "Canonical Correlation Analysis CCA"
Visar resultat 1 - 5 av 8 uppsatser innehållade orden Canonical Correlation Analysis CCA.
1. Transfer learning applied to a deep learning system for cardiac abnormality classification in electrocardiograms
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Cardiovascular diseases are a leading cause of death globally. Early diagnosis and treatment is of prime importance to prevent or mitigate health complications. Electrocardiogram (ECG) is a standard test modality used for early diagnosis of arrhythmias. The standard ECG uses 12 leads (i. LÄS MER
2. Avläsning av EEG-data från Emotiv Epoc X för ett SSVEP-baserat braincomputer interface för att spela Snake
Kandidat-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : Denna rapport beskriver arbetet med att utforma ett BCI som kan styra datorspelet Snake i realtid. Spelet styrs genom att inducera steady state visually evoked potentials i hjärnan via flimrande stimuli av vissa frekvenser. Den resulterande elektriska aktiviteten i hjärnan läses sedan ut med hjälp av elektroencefalografi via Emotiv Epoc X. LÄS MER
3. Decoding Steady-State VisualEvoked Potentials(SSVEPs)- Implementation and Performance Analysis
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces(BCIs) have been widely investigated. Algorithms from the canonical correlation analysis(CCA) family perform extremely well in detecting stimulus targets by analyzing the relationship of frequency features between electroencephalogram (EEG) signals and stimulus targets. LÄS MER
4. A canonical correlation analysis- based approach to identify causal genes in atherosclerosis
Magister-uppsats, Högskolan i Skövde/Institutionen för biovetenskapSammanfattning : Genome-wide associations studies (GWASs) have identified hundreds of loci that are strongly associated with coronary artery disease and its risk factors. However, the causal variants and genes remain unknown for the vast majority of the identified loci. LÄS MER
5. Random Subspace Analysis on Canonical Correlation of High Dimensional Data
Kandidat-uppsats, Uppsala universitet/Statistiska institutionenSammanfattning : High dimensional, low sample, data have singular sample covariance matrices,rendering them impossible to analyse by regular canonical correlation (CC). Byusing random subspace method (RSM) calculation of canonical correlation be-comes possible, and a Monte Carlo analysis shows resulting maximal CC canreliably distinguish between data with true correlation (above 0. LÄS MER