Sökning: "Probabilistic predictions"

Visar resultat 1 - 5 av 26 uppsatser innehållade orden Probabilistic predictions.

  1. 1. Data-Driven Reachability Analysis of Pedestrians Using Behavior Modes : Reducing the Conservativeness in Data-Driven Pedestrian Predictions by Incorporating Their Behavior

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

    Författare :August Söderlund; [2023]
    Nyckelord :Data-driven reachability analysis; Autonomous vehicles; Automated safety; Autonomous situational awareness; Datadriven nåbarhetsanalys; Autonoma fordon; Automatiserad säkerhet; Autonom situationsmedvetenhet;

    Sammanfattning : Predicting the future state occupancies of pedestrians in urban scenarios is a challenging task, especially considering that conventional methods need an explicit model of the system, hence introducing data-driven reachability analysis. Data-driven reachability analysis uses data, inherently produced by an unknown system, to perform future state predictions using sets, generally represented by zonotopes. LÄS MER

  3. 2. Probabilistic Added Wave Resistance Predictions for Design of RoPax Ferries

    Master-uppsats, KTH/Lättkonstruktioner, marina system, flyg- och rymdteknik, rörelsemekanik

    Författare :Jonathan Viinikka; [2023]
    Nyckelord :Added wave resistance in head waves; Roll-on Roll-off Passenger ferry; Probabilistic wave environment; Semi-empirical method; Adderat vågmotstånd i motsjö; Roll-on Roll-off Passagerar Fartyg; Probabilistiska vågförhållanden; Semiempiriska beräkningsmethoder;

    Sammanfattning : This thesis investigates reasons for significant uncertainties in added wave resistance predictionsand how wave conditions can potentially affect the design of RoPax ferries. The objectiveis to find a suitable prediction method of added wave resistance for the RoPax ferry designapplication. LÄS MER

  4. 3. Constructing and representing a knowledge graph(KG) for Positive Energy Districts (PEDs)

    Master-uppsats, Högskolan Dalarna/Institutionen för information och teknik

    Författare :Mahtab Davari; [2023]
    Nyckelord :Knowledge graph; Positive Energy Districts PEDs ; longest path; Questions and Answers; Community Detection; Node Embedding; t-SNE plots; Edge Prediction;

    Sammanfattning : In recent years, knowledge graphs(KGs) have become essential tools for visualizing concepts and retrieving contextual information. However, constructing KGs for new and specialized domains like Positive Energy Districts (PEDs) presents unique challenges, particularly when dealing with unstructured texts and ambiguous concepts from academic articles. LÄS MER

  5. 4. Clinical Assessment of Deep Learning-Based Uncertainty Maps in Lung Cancer Segmentation

    Master-uppsats, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)

    Författare :Federica Carmen Maruccio; [2023]
    Nyckelord :3D U-Net; Contouring; Clinical validation; Deep learning; Lung cancer; Monte Carlo dropout; Probability map; Reliability diagram; Segmentation; Uncertainty map;

    Sammanfattning : Prior to radiation therapy planning, tumours and organs at risk need to be delineated. In recent years, deep learning models have opened the possibility of automating the contouring process, speeding up the procedures and helping clinicians. LÄS MER

  7. 5. Conform with the Wind : Processing short-term ensemble forecasts with conformal based methods for probabilistic wind-speed forecasting

    Master-uppsats, Lunds universitet/Matematisk statistik

    Författare :Simon Althoff; [2023]
    Nyckelord :wind-speed; probabilistic; forecasts; forecasting; ensemble; post-processing; conformal prediction; conformal predictive systems; quantile regression forest; non-exchangeable; Mathematics and Statistics;

    Sammanfattning : Forecasting wind has always been an interesting subject, and as large parts of the world are relying more on wind for power production it is becoming even more important to have reliable forecasts. Probabilistic forecasts, where distributions are predicted in contrast to deterministic forecasts, are impor- tant for informed decision making. LÄS MER