Sökning: "novelty detection"
Visar resultat 1 - 5 av 19 uppsatser innehållade orden novelty detection.
1. Neural Networks for Predictive Maintenance on Highly Imbalanced Industrial Data
Master-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskapSammanfattning : Preventive maintenance plays a vital role in optimizing industrial operations. However, detecting equipment needing such maintenance using available data can be particularly challenging due to the class imbalance prevalent in real-world applications. LÄS MER
2. Phosphorous Precipitation in Source Separated Greywater for Direct Environmental Release.
Master-uppsats, Lunds universitet/Kemiteknik (CI)Sammanfattning : As our understanding of the impact humans have on the environment changes, so too do the mitigation strategies we employ to prevent it. One major source of anthropogenic pollution is wastewater effluent. LÄS MER
3. Anomaly or not Anomaly, that is the Question of Uncertainty : Investigating the relation between model uncertainty and anomalies using a recurrent autoencoder approach to market time series
Master-uppsats, Umeå universitet/Institutionen för datavetenskapSammanfattning : Knowing when one does not know is crucial in decision making. By estimating uncertainties humans can recognize novelty both by intuition and reason, but most AI systems lack this self-reflective ability. In anomaly detection, a common approach is to train a model to learn the distinction between some notion of normal and some notion of anomalies. LÄS MER
4. Enhancing Simulated Sonar Images With CycleGAN for Deep Learning in Autonomous Underwater Vehicles
Master-uppsats, KTH/Matematisk statistikSammanfattning : This thesis addresses the issues of data sparsity in the sonar domain. A data pipeline is set up to generate and enhance sonar data. The possibilities and limitations of using cycleGAN as a tool to enhance simulated sonar images for the purpose of training neural networks for detection and classification is studied. LÄS MER
5. A Real- time Log Correlation System for Security Information and Event Management
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The correlation of several events in a period of time is a necessity for a threat detection platform. In the case of multistep attacks (attacks characterized by a sequence of executed commands), it allows detecting the different steps one by one and correlating them to raise an alert. LÄS MER