Sökning: "Detektion av avvikelse"

Visar resultat 1 - 5 av 6 uppsatser innehållade orden Detektion av avvikelse.

  1. 1. Unauthorised Session Detection with RNN-LSTM Models and Topological Data Analysis

    Master-uppsats, KTH/Matematik (Avd.)

    Författare :Nazar Maksymchuk Netterström; [2023]
    Nyckelord :Recurrent Neural Network; Long-Short-Term-Memory; Topological Data Analysis; Session based data; Anomaly detection; Time-series analysis; Imbalanced data; Master thesis; Neurala nätverk; Topologisk data analys; Detektion av avvikelse; Sessionsbaserad data; Tidserieanalys; Inbalancerad data; Masteruppsats;

    Sammanfattning : This thesis explores the possibility of using session-based customers data from Svenska Handelsbanken AB to detect fraudulent sessions. Tools within Topological Data Analysis are employed to analyse customers behavior and examine topological properties such as homology and stable rank at the individual level. LÄS MER

  3. 2. Exogenous Fault Detection in Aerial Swarms of UAVs

    Master-uppsats, KTH/Matematik (Avd.)

    Författare :Maja Westberg; [2023]
    Nyckelord :Exogenous Fault Detection; Local Outlier Factor; Aerial Swarm; Unmanned Aerial Vehicle; Behavioral Feature Vector; Outlier Detection; Cluster Analysis; Exogen Feldetektering; Local Outlier Factor; Drönarsvärm; Obemannad Drönare; Beteendevektor; Avvikelse-Analys; Kluster-Analys;

    Sammanfattning : In this thesis, the main focus is to formulate and test a suitable model forexogenous fault detection in swarms containing unmanned aerial vehicles(UAVs), which are aerial autonomous systems. FOI Swedish DefenseResearch Agency provided the thesis project and research question. LÄS MER

  4. 3. Anomaly detection for prediction of failures in manufacturing environments : Machine learning based semi-supervised anomaly detection for multivariate time series to predict failures in a CNC-machine

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

    Författare :Felix Boltshauser; [2023]
    Nyckelord :Machine learning; Anomaly Detection; DeepAnT; ROCKET; OCSVM; manufacturing; predictive maintenance; Maskin inlärning; Anomali Detektion; DeepAnT; ROCKET; OCSVM; tillverkning; prediktivt underhåll;

    Sammanfattning : For manufacturing enterprises, the potential of collecting large amounts of data from production processes has enabled the usage of machine learning for prediction-based monitoring and maintenance of machines. Yet common maintenance strategies still include reactive handling of machine failures or schedule-based maintenance conducted by experienced personnel. LÄS MER

  5. 4. Software Architecture for Concurrency Analysis on a Virtual Platform

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

    Författare :Brinda Mohan; [2022]
    Nyckelord :;

    Sammanfattning : With the increasing demand for faster processing, a trend of moving towards multi-core and multiprocessor environments for embedded systems is clear. In this context, concurrent programming is also on the rise. LÄS MER

  7. 5. Development of a Method to Measure Residual Stresses in Cast Components with Complex Geometries

    Master-uppsats, KTH/Materialvetenskap

    Författare :Yang Yang; [2020]
    Nyckelord :Residual Stresses; Cast Iron; Engine Components; XRD; Ultrasonic; Cutting;

    Sammanfattning : Cast iron, taking the advantages of the advanced castability forming components of complex geometries and favorable mechanical properties, is employed in engine components in truck industries. Compacted graphite iron (CGI) integrates both merits of lamellar graphite iron (LGI) and spheroidal graphite iron (SGI) such as good machinability and high thermal conductivity from LGI, high ultimate tensile strength (UTS), good fatigue resistance, high elastic modulus, and high ductility from SGI, thus is now becoming a competitive alternative of traditional LGI in cylinder blocks and heads. LÄS MER