Sökning: "event based data analysis"

Visar resultat 1 - 5 av 302 uppsatser innehållade orden event based data analysis.

1. 1. Estimating historic ranges of extinct scavenging birds from North America during the late Pleistocene using co-occurrence data from the fossil record

   Master-uppsats, Göteborgs universitet / Institutionen för biologi och miljövetenskap

   Författare :Melissa Miranda; [2023-06-30]
   Nyckelord :Scavenging birds; Vultures; Co-occurrence Data; Range Estimates; Spatial Autoregressive Models; Co-extinction;

   Sammanfattning : The aim of my study was to estimate and compare the historic range of nine scavenging birds from North America that went jointly extinct with their mammalian megafaunal prey in the Late Pleistocene. Although the severity and timing of their co-extinction are strongly correlated, there has been little analytical support in providing estimates for the possible geographic distribution of scavenging birds prior to the extinction event. LÄS MER

3. 2. KVINNORS UPPLEVELSE AV ATT LEVA MED POLYCYSTISKT OVARIESYNDROM - svåra symtom och avvisande bemötande från vården

   Kandidat-uppsats,

   Författare :Almqvist Kajsa; Amanda Ankarhem; [2023-03-15]
   Nyckelord :PCOS; polycystic ovary syndrome; hirsutism; experience; diagnosis; life change event; management; coping strategy; peer-support; distress; mental health; nurse; review; knowledge;

   Sammanfattning : Background: Polycystic ovary syndrome (PCOS) is a common endocrine disorder, affecting up to one of five females in reproductive age. Common symptoms are hirsutism, overweight and infertility. Today's treatment options consist of life-style changes, and various medications for symptom relief. LÄS MER

4. 3. Hydraulic Modelling of Eurasian Beaver Structural Modifications: Implications for Evaluating their Contributions to Natural Flood Management in Scotland

   Master-uppsats, Lunds universitet/Avdelningen för Riskhantering och Samhällssäkerhet

   Författare :Maja Christina Pitcairn; [2023]
   Nyckelord :Beaver reintroduction; Scotland; Flood risk; Natural flood management; Hydraulic modelling.; Technology and Engineering;

   Sammanfattning : The concurrent climate and biodiversity crises in Scotland necessitate the exploration of ecosystem-based adaptation to simultaneously address increased flood risk and the loss of native species. This research investigated the contributions of Eurasian beaver reintroductions to natural flood management in Scotland. LÄS MER

5. 4. AI/ML Development for RAN Applications : Deep Learning in Log Event Prediction

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

   Författare :Yuxin Sun; [2023]
   Nyckelord :LSTM; Anomaly Detection; Failure Prediction; Log Mining; Deep Learning; LSTM; Anomali Detection; Failure Prediction; Log Mining; Deep Learning;

   Sammanfattning : Since many log tracing application and diagnostic commands are now available on nodes at base station, event log can easily be collected, parsed and structured for network performance analysis. In order to improve In Service Performance of customer network, a sequential machine learning model can be trained, test, and deployed on each node to learn from the past events to predict future crashes or a failure. LÄS MER

7. 5. 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