Sökning: "iForest"

Hittade 3 uppsatser innehållade ordet iForest.

  1. 1. A deep learning based anomaly detection pipeline for battery fleets

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

    Författare :Nabakumar Singh Khongbantabam; [2021]
    Nyckelord :Forklift batteries; Battery sensors; Data pipeline; Predictive maintenance; Anomaly detection; Deep learning; Battery failure prediction; Time-series; Variational autoencoder; Long short-term memory; LSTM; Gated recurrent unit; GRU; Isolation nearest neighbor; iNNE; Isolation forest; iForest; kth nearest neighbor; kNN.; Gaffeltruckbatterier; Batterisensorer; Datapipeline; Prediktivt underhåll; Avvikelsedetektering; Deep learning; Batterifelsprediktion; Tidsserier; Variationsautokodare; Långt korttidsminne; LSTM; Gated recurrent unit; GRU; Isolation närmaste granne; iNNE; Isolation skog; iForest; kth närmaste granne; kNN.;

    Sammanfattning : This thesis proposes a deep learning anomaly detection pipeline to detect possible anomalies during the operation of a fleet of batteries and presents its development and evaluation. The pipeline employs sensors that connect to each battery in the fleet to remotely collect real-time measurements of their operating characteristics, such as voltage, current, and temperature. LÄS MER

  3. 2. Unsupervised Anomaly Detection on Time Series Data: An Implementation on Electricity Consumption Series

    Master-uppsats, KTH/Matematisk statistik

    Författare :Amelia Lindroth Henriksson; [2021]
    Nyckelord :Unsupervised learning; machine learning; anomaly detection; time series; electricity consumption; synthetic anomalies; DBSCAN; LOF; iForest; OC-SVM; Oövervakad inlärning; maskininlärning; anomalidetektion; tidsserier; elförbrukning; syntetiska anomalier; DBSCAN; LOF; iForest; OC-SVM;

    Sammanfattning : Digitization of the energy industry, introduction of smart grids and increasing regulation of electricity consumption metering have resulted in vast amounts of electricity data. This data presents a unique opportunity to understand the electricity usage and to make it more efficient, reducing electricity consumption and carbon emissions. LÄS MER

  4. 3. Investigation of anomalies in a RTC system using Machine Learning

    Master-uppsats, Umeå universitet/Institutionen för datavetenskap

    Författare :Rafael Da Alesandro; [2019]
    Nyckelord :;

    Sammanfattning : In a Real Time Clearing System (RTCS) there are several thousands of transactions per second, and even more messages are sent back and forth. Th‘e high volume of messages and transactions being sent within the system eventually leads to some anomalies arising. LÄS MER