Sökning: "Prediction Of Future Activity"

Visar resultat 1 - 5 av 23 uppsatser innehållade orden Prediction Of Future Activity.

1. 1. Neural Network-Based Residential Water End-Use Disaggregation

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

   Författare :Cajsa Pierrou; [2023]
   Nyckelord :Residential water end-use; Flow disaggregation; Time series classification; Artificial neural network; Smart water meter; Slutanvändning av vatten i hushåll; Flödesdisaggregering; Tidsserieklassificering; Artificiella neurala nätverk; Smart vattenmätare;

   Sammanfattning : Sustainable management of finite resources is vital for ensuring livable conditions for both current and future generations. Measuring the total water consumption of residential households at high temporal resolutions and automatically disaggregating the sole signal into classified end usages (e.g. LÄS MER

3. 2. High tide flooding in near future projections for popular travel destinations

   Master-uppsats, Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskap

   Författare :David Ebert; [2023]
   Nyckelord :Physical Geography and Ecosystem analysis; High tide flooding; Projections; Adaptation and mitigation strategies; Lunar precession; Nodal cycle; Cycle of lunar perigee; Earth and Environmental Sciences;

   Sammanfattning : High tide flooding (HTF) is becoming more common in coastal regions of the United States, although this phenomenon remains largely undocumented in published literature from other parts of the world. No matter the emissions scenario over the next decades, sea level rise (SLR) is projected to continue worldwide until at least the end of the 21st century, continually pushing the frequency and severity of HTF. LÄS MER

4. 3. Anticipating bankruptcies among companies with abnormal credit risk behaviour : Acase study adopting a GBDT model for small Swedish companies

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

   Författare :Simon Heinke; [2022]
   Nyckelord :Bankruptcy prediction; Credit risk analysis; Abnormal credit risk behaviour; Gradient boosted decision trees; SHAP-values.; Konkurs förutsägelse; Kredit riskanalys; Abnomralt kreditbeteende; Gradient baserat beslutsträd; SHAP-värden.;

   Sammanfattning : The field of bankruptcy prediction has experienced a notable increase of interest in recent years. Machine Learning (ML) models have been an essential component of developing more sophisticated models. Previous studies within bankruptcy prediction have not evaluated how well ML techniques adopt for data sets of companies with higher credit risks. LÄS MER

5. 4. Dopamine Waves Lead to a Swift and Adaptive Reinforcement Learning Algorithm

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

   Författare :Gergö Gömöri; [2021]
   Nyckelord :Reinforcement Learning; Dopamine; Basal Ganglia; Successor Representation; förstärkningsinlärning; dopamin; basala ganglierna; successionsrepresentation;

   Sammanfattning : Accumulating evidence suggests that dopaminergic neurons show significant task-related diversity. Curiously, dopamine concentration and dopamine axon activity show spatio-temporal wave patterns in the dorsal striatum. LÄS MER

7. 5. The Grid of Sweden - A Micro-unit Analysis of Vulnerable Neighborhoods

   Master-uppsats, Malmö universitet/Fakulteten för hälsa och samhälle (HS)

   Författare :Mia Puur; [2020]
   Nyckelord :Crime; Geography; Micro-places; Police authorities; Spatial analysis; Socio-demographic; Vulnerable neighborhoods;

   Sammanfattning : Through a national collection, the Swedish Police identify and classify vulnerable neighborhoods. Areas are assessed through police perceptions regarding high concentrations of certain problems and criminal activity, such as public acts of violence with risk of harming third parties, open drug markets and organised crime structures. LÄS MER