Sökning: "class ensemble"

Visar resultat 1 - 5 av 25 uppsatser innehållade orden class ensemble.

1. 1. Improving Visibility Forecasts in Denmark Using Machine Learning Post-processing

   Master-uppsats, Uppsala universitet/Luft-, vatten- och landskapslära

   Författare :August Thomasson; [2023]
   Nyckelord :visibility forecast; fog; machine learning; numerical weather predicition; XGBoost; Random Forest; siktprognos; dimma; maskininlärning; numerisk vädermodell; XGBoost; Random Forest;

   Sammanfattning : Accurate fog prediction is an important task facing forecast centers since low visibility can affect anthropogenic systems, such as aviation. Therefore, this study investigates the use of Machine Learning classification algorithms for post-processing the output of the Danish Meteorological Institute’s operational Numerical Weather Prediction (NWP) model to improve visibility prediction. LÄS MER

3. 2. An Ensemble of Difference: : Understanding(s) of Participant Experiences and Learning in a Heterogenous Adult Community Drama Class of First and Second Language Speakers in Sweden

   Master-uppsats, Stockholms universitet/Institutionen för pedagogik och didaktik

   Författare :Julia Ouellette-Seymour; [2023]
   Nyckelord :Adult Education; Lifelong Learning; Drama in Education; Drama in L2; Applied Drama; Adult Learning Education; Applied Theatre; Language Learning; Community Drama; Non-formal Education; Migrant; Integration; Cultural Learning; Heterogenous Learning; SLA; Ethnographic Case Study; Vygotsky; Pragmatism;

   Sammanfattning : This case study research aimed to explore, understand, and compare the experiences of individuals participating in a heterogeneous adult community drama class in Central Sweden. Drawing from classical pragmatism and employing a conceptual framework rooted in sociocultural theory, the study utilized semi-structured interviews, open-questionnaire responses, and participant observations to collect data which was analyzed through reflexive thematic analysis. LÄS MER

4. 3. A Comparative Analysis of Decision Tree Models in Identifying Landslide Susceptibility and Type Classification

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

   Författare :Levi Jan Zuiverloon; [2023]
   Nyckelord :Landslides; landslide susceptibility mapping; Random Forest; Extreme Gradient Boosting; machine learning models; multiclass classification; binary classification; risk assessment; mitigation strategies; Italy; Aosta Valley; infrastructure vulnerability; supervised learning algorithms; Earth and Environmental Sciences;

   Sammanfattning : Landslides pose a significant risk to human life and infrastructure, especially in Italy, which has a high frequency of landslide occurrences. To mitigate these hazards, Landslide Susceptibility Mapping (LSM) is crucial for identifying risk areas and developing appropriate mitigation strategies. LÄS MER

5. 4. Data-Driven Traffic Forecasting for Completed Vehicle Simulation: : A Case Study with Volvo Test Trucks

   Magister-uppsats, Luleå tekniska universitet/Institutionen för system- och rymdteknik

   Författare :Samaneh Shahrokhi; [2023]
   Nyckelord :supervised machine learning; traffic forecasting; vehicle presence prediction; binary classification; ensemble learning; feature engineering; hyperparameter tuning; data-driven analysis;

   Sammanfattning : This thesis offers a thorough investigation into the application of machine learning algorithms for predicting the presence of vehicles in a traffic setting. The research primarily focuses on enhancing vehicle simulation by employing data-driven traffic prediction methods. The study approaches the problem as a binary classification task. LÄS MER

7. 5. CenterPoint-based 3D Object Detection in ONCE Dataset

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

   Författare :Yuwei Du; [2022]
   Nyckelord :3D Object Detection; Keypoint Detector; Class Balance; Self-Calibrated Convolution; IoU-aware Detector; Box Ensembles; 3D-Objektdetektering; Nyckelpunktsdetektor; Klassbalans; Självkalibrerad Faltning; IoU-medveten Detektor; Boxensembler;

   Sammanfattning : High-efficiency point cloud 3D object detection is important for autonomous driving. 3D object detection based on point cloud data is naturally more complex and difficult than the 2D task based on images. Researchers keep working on improving 3D object detection performance in autonomous driving scenarios recently. LÄS MER