Sökning: "Dimension reduction"

Visar resultat 1 - 5 av 126 uppsatser innehållade orden Dimension reduction.

1. 1. Exploring Greenhouse Gas Emissions and socio-economic factors for climate change mitigation: A worldwide clustering analysis

   Magister-uppsats, Lunds universitet/Nationalekonomiska institutionen; Lunds universitet/Statistiska institutionen

   Författare :Anna Pasini; [2023]
   Nyckelord :GHG emissions; Climate Change; Panel Data; Gaussian Mixture Models Cluster Analysis; PCA; Business and Economics;

   Sammanfattning : In response to the pressing need to address climate change and reduce global greenhouse gas (GHG) emissions, this study implemented Gaussian Mixture Models Clustering to detect the levels of GHG emissions and related socio-economic factors in 174 countries. To handle the panel data, Principal Component Analysis was conducted to achieve dimension reduction. LÄS MER

3. 2. Energy audit of a single-family house in a city in the middle of Sweden

   Magister-uppsats, Högskolan i Gävle/Energisystem och byggnadsteknik

   Författare :Daniela Valentina García Gimeno; [2023]
   Nyckelord :energy audit; building energy efficiency; building envelope; renewable sources; windows efficiency; insulation of houses in Sweden;

   Sammanfattning : The world is currently submerged in two big problems: supply energy crisis and climate change. It is clear that society has to do its best to overcome these challenges, and one effective way to mitigate their effects is by conducting an energy audit, which helps to identify the weaknesses and strengths of the buildings, enabling improvements in their thermal efficiency. LÄS MER

4. 3. W2R: an ensemble Anomaly detection model inspired by language models for web application firewalls security

   Magister-uppsats, Högskolan i Halmstad/Akademin för informationsteknologi

   Författare :Zelong Wang; Athira AnilKumar; [2023]
   Nyckelord :web application firewall; anomaly detection; word2vec; BERT; dimension reduction; ensemble model;

   Sammanfattning : Nowadays, web application attacks have increased tremendously due to the large number of users and applications. Thus, industries are paying more attention to using Web application Firewalls and improving their security which acts as a shield between the app and the internet by filtering and monitoring the HTTP traffic. LÄS MER

5. 4. Estimating Poolability of Transport Demand Using Shipment Encoding : Designing and building a tool that estimates different poolability types of shipment groups using dimensionality reduction.

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Marvin Kërçini; [2023]
   Nyckelord :Poolability; Transport networks; Autoencoder; Dimensionality reduction; Vehicle Routing Problem; Raggruppabilità; Reti di trasporto; Autoencoder; Riduzione della dimensionalità; Vehicle Routing Problem; Poolbarhet; Transportnätverk; Autokodare; Dimensionsreduktion; Fordonsdirigeringsproblem;

   Sammanfattning : Dedicating less transport resources by grouping goods to be shipped together, or pooling as we name it, has a very crucial role in saving costs in transport networks. Nonetheless, it is not so easy to estimate pooling among different groups of shipments or understand why these groups are poolable. LÄS MER

7. 5. Evaluating clustering techniques in financial time series

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för systemteknik

   Författare :Johan Millberg; [2023]
   Nyckelord :clustering; machine learning; financial time series; time series; unsupervised learning; cluster validation; cluster evaluation; klustring; klusteranalys; finansiella tidsserier; maskininlärning; klustervalidering; evalueringsteknik;

   Sammanfattning : This degree project aims to investigate different evaluation strategies for clustering methodsused to cluster multivariate financial time series. Clustering is a type of data mining techniquewith the purpose of partitioning a data set based on similarity to data points in the same cluster,and dissimilarity to data points in other clusters. LÄS MER