Sökning: "anomalous detection"

Visar resultat 1 - 5 av 29 avhandlingar innehållade orden anomalous detection.

1. 1. Conformal anomaly detection : Detecting abnormal trajectories in surveillance applications

   Författare :Rikard Laxhammar; Göran Falkman; Pontus Svenson; Högskolan i Skövde; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Anomaly detection; conformal prediction; trajectory analysis; video surveillance; maritime surveillance; Technology; Teknik; Skövde Artificial Intelligence Lab SAIL ; Skövde Artificial Intelligence Lab SAIL ;

   Sammanfattning : Human operators of modern surveillance systems are confronted with an increasing amount of trajectory data from moving objects, such as people, vehicles, vessels, and aircraft. A large majority of these trajectories reflect routine traffic and are uninteresting. LÄS MER

3. 2. Resistivity investigation and monitoring for detection of internal erosion and anomalous seepage in embankment dams

   Författare :Pontus Sjödahl; Teknisk geologi; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Hydrogeologi; teknisk geologi; internal erosion; Hydrogeology; geographical and geological engineering; time-lapse inversion; inversion; monitoring; modelling; resistivity; detection; leakage; seepage; teknisk geografi; embankment dam;

   Sammanfattning : Methods for monitoring seepage and detecting internal erosion are essential for the safety evaluation of embankment dams. Internal erosion is one of the major reasons for embankment dam failures, and there are several tenths of thousands of large embankment dams in the world. LÄS MER

4. 3. Data Modeling for Outlier Detection

   Författare :Shahrooz Abghari; Niklas Lavesson; Håkan Grahn; Veselka Boeva; Anders Holst; Blekinge Tekniska Högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; data modeling; cluster analysis; stream data; outlier detection;

   Sammanfattning : This thesis explores the data modeling for outlier detection techniques in three different application domains: maritime surveillance, district heating, and online media and sequence datasets. The proposed models are evaluated and validated under different experimental scenarios, taking into account specific characteristics and setups of the different domains. LÄS MER

5. 4. Visual analytics for maritime anomaly detection

   Författare :Maria Riveiro; Göran Falkman; Tom Ziemke; Dag Stranneby; Mikael Jern; Örebro universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; visual analytics; anomaly detection; maritime traffic monitoring; analytical reasoning; information fusion; TECHNOLOGY; TEKNIKVETENSKAP; Information technology; Informationsteknik; Computer science; Datavetenskap; Datalogi; Computer and Systems Science; Technology;

   Sammanfattning : The surveillance of large sea areas typically involves  the analysis of huge quantities of heterogeneous data.  In order to support the operator while monitoring maritime traffic, the identification of anomalous behavior or situations that might need further investigation may reduce operators' cognitive load. LÄS MER

7. 5. Data Mining Approaches for Outlier Detection Analysis

   Författare :Shahrooz Abghari; Niklas Lavesson; Håkan Grahn; Veselka Boeva; Olga Fink; Blekinge Tekniska Högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; outlier detection; data modelling; machine learning; clustering analysis; data stream mining; Computer Science; Datavetenskap;

   Sammanfattning : Outlier detection is studied and applied in many domains. Outliers arise due to different reasons such as fraudulent activities, structural defects, health problems, and mechanical issues. The detection of outliers is a challenging task that can reveal system faults, fraud, and save people's lives. LÄS MER