Sökning: "cluster analysis"
Visar resultat 1 - 5 av 410 uppsatser innehållade orden cluster analysis.
- Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik
Sammanfattning : The aim of this thesis is to predict dierent mechanisms of toxicity from the metabolomic response of HepG2 liver cells. In order to utilize the metabolomic data the a semisupervised machine learning approach is investigated, namely the cluster-then-label approach. The research focuses on the unsupervised part due to the centrality to this method. LÄS MER
- Master-uppsats, Institutionen för tillämpad informationsteknologi
Sammanfattning : With its sudden outbreak in October 2017, the anti-harassment movement #MeToo quickly created avast, worldwide impact on social media, in the traditional press as well as in everyday lives. In Swedenespecially, a country with a long history in fighting for gender equality, women in their thousandsshared their stories of sexual harassment and came together both as individuals and as occupationalgroups to raise a collective voice. LÄS MER
- Kandidat-uppsats, Göteborgs universitet/Institutionen för matematiska vetenskaper
Sammanfattning : As new extreme high throughput DNA sequencing methods continue to develop thelarge amounts of information that they give rise to in terms of metagenomic data opensthe way for completely novel approaches to the study of microbial ecosystems. In thisproject we have investigated how relationships and connections between microbial genesand species that carry them can be found based entirely on their appearance in twoseparate datasets accumulated from the same samples using metagenomic analysis. LÄS MER
4. Hierarchical Clustering of Time Series using Gaussian Mixture Models and Variational AutoencodersMaster-uppsats, Lunds universitet/Matematisk statistik
Sammanfattning : This thesis proposes a hierarchical clustering algorithm for time series, comprised of a variational autoencoder to compress the series and a Gaussian mixture model to merge them into an appropriate cluster hierarchy. This approach is motivated by the autoencoders good results in dimensionality reduction tasks and by the likelihood framework given by the Gaussian mixture model. LÄS MER
- Kandidat-uppsats, KTH/Matematisk statistik; KTH/Matematisk statistik
Sammanfattning : This thesis investigates the possibilities of creating an investment strategy by performing a cluster analysis on stock returns. This to provide a diversified portfolio, which has multiple advantages, for instance that the risk of the investment decreases. LÄS MER