Sökning: "gaussian mixture model"

Visar resultat 11 - 15 av 79 uppsatser innehållade orden gaussian mixture model.

1. 11. Predicting Quality of Experience from Performance Indicators : Modelling aggregated user survey responses based on telecommunications networks performance indicators

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

   Författare :Christian Vestergaard; [2022]
   Nyckelord :Quality of Experience; Telecommunication; Regression; Long Short Term Memmory; Clustering; K-means; Gaussian Mixture Models; Användarupplevelse; Telekommunikation; Regression; Long Short Term Memmory; Klusteranalys; K-means; Gaussian Mixture Models;

   Sammanfattning : As user experience can be a competitive edge, it lies in the interest of businesses to be aware of how users perceive the services they provide. For telecommunications operators, how network performance influences user experience is critical. To attain this knowledge, one can survey users. LÄS MER

3. 12. Neural Ordinary Differential Equations for Anomaly Detection

   Master-uppsats, KTH/Matematisk statistik

   Författare :Jón Hlöðver Friðriksson; Erik Ågren; [2021]
   Nyckelord :Anomaly detection; Neural ordinary differential equations; Statistical modelling; Autoregression; Variational autoencoder; Multivariate time series; Anomalidetektion; Neurala ordinära differentialekvationer; Statistisk modellering; Autoregression; Variational autoencoder; Multivariat tidsserie;

   Sammanfattning : Today, a large amount of time series data is being produced from a variety of different devices such as smart speakers, cell phones and vehicles. This data can be used to make inferences and predictions. Neural network based methods are among one of the most popular ways to model time series data. LÄS MER

4. 13. Unsupervised Anomaly Detection and Root Cause Analysis in HFC Networks : A Clustering Approach

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

   Författare :Povel Forsare Källman; [2021]
   Nyckelord :Anomaly Detection; Root Cause Analysis; Cluster Analysis; k- means; Self- Organizing Map; Gaussian Mixture Model; Dimensionality Reduction; Principal Component Analysis; Hybrid Fiber- Coaxial Network.; Anomalidetektering; Rotfelsanalys; Klusteranalys; k- means; Self- Organizing Map; Gaussian Mixture Model; Dimensionsreducering; Principal Component Analysis; Hybrid Fiber Coax- nät.;

   Sammanfattning : Following the significant transition from the traditional production industry to an informationbased economy, the telecommunications industry was faced with an explosion of innovation, resulting in a continuous change in user behaviour. The industry has made efforts to adapt to a more datadriven future, which has given rise to larger and more complex systems. LÄS MER

5. 14. Incorporating Metadata Into the Active Learning Cycle for 2D Object Detection

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

   Författare :Karsten Stadler; [2021]
   Nyckelord :Active learning; Deep Learning; Object detection; Metadata; Nuscenes Nuimages; Gaussian mixture model; Rejection sampling; Monte-Carlo methods; Aktiv Inlärning; Djupinlärning; Objektdetektering; metadata; Nuscenes Nuimages; Gaussisk blandingsmodell; Rejection sampling; Monte-Carlo metoder;

   Sammanfattning : In the past years, Deep Convolutional Neural Networks have proven to be very useful for 2D Object Detection in many applications. These types of networks require large amounts of labeled data, which can be increasingly costly for companies deploying these detectors in practice if the data quality is lacking. LÄS MER

7. 15. VePMAD: A Vehicular Platoon Management Anomaly Detection System : A Case Study of Car-following Mode, Middle Join and Exit Maneuvers

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

   Författare :Weaam Bayaa; [2021]
   Nyckelord :MDS; GMMHMM; PMP; Machine Learning; Bayesian information Criterion BIC ; Platoon Behavior Recognition; MDS; GMMHMM; PMP; Maskininlärnings; BIC; Plutonbeteendeigenkänning;

   Sammanfattning : Vehicle communication using sensors and wireless channels plays an important role to allow exchanging information. Adding more components to allow exchanging more information with infrastructure enhanced the capabilities of vehicles and enabled the rise of Cooperative Intelligent Transport Systems (C-ITS). LÄS MER