Sökning: "maskininlärningsmodeller"

Visar resultat 1 - 5 av 199 uppsatser innehållade ordet maskininlärningsmodeller.

1. 1. Optimizing Flight Ranking:A Machine Learning Approach : Applying Machine Learning to Upgrade Flight Sorting and User Experience

   M1-uppsats, KTH/Hälsoinformatik och logistik

   Författare :Habib Jabeli; [2024]
   Nyckelord :Machine Learning; Flight Comparison; Flygresor.se; Neural Networks; Flight Ranking; Random Forest; XGBoost;

   Sammanfattning : Flygresor.se, a leading flight comparison platform, uses machine learning to rankflights based on their likelihood of being clicked. The main goal of this project was toimprove this flight sorting to obtain a better user experience. The platform's existingmodel is based on a neural network approach and a limited set of features. LÄS MER

3. 2. Utilizing energy-saving techniques to reduce energy and memory consumption when training machine learning models : Sustainable Machine Learning

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

   Författare :Khalid El Yaacoub; [2024]
   Nyckelord :Sustainable AI; Machine learning; Quantization-Aware Training; Model Distillation; Quantized Distillation; Siamese Neural Networks; Continual Learning; Experience Replay; Data Efficient AI; Energy Consumption; Energy-Savings; Sustainable ML; Computation resources; Hållbar maskin inlärning; Hållbar AI; Maskininlärning; Quantization-Aware Training; Model Distillation; Quantized Distillation; siamesiska neurala nätverk; Continual Learning; Experience Replay; Dataeffektiv AI; Energiförbrukning; Energibesparingar; Beräkningsresurser;

   Sammanfattning : Emerging machine learning (ML) techniques are showing great potential in prediction performance. However, research and development is often conducted in an environment with extensive computational resources and blinded by prediction performance. LÄS MER

4. 3. Design of a 2-D Lattice Flower Constellation for Earth observation applying the twin satellite concept

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

   Författare :Julia Martín-Fuertes Brañas; [2023]
   Nyckelord :2D Lattice Flower Constellation design; number of satellites; number of planes; revisit time; coverage; optimized constellation; target list; twin satellite concept; FreeFlyer; 2D Lattice Flower Constellation design; antal satelliter; antal plan; återbesökstid; täckning; optimerad konstellation; mållista; tvilling-satellit-koncept; FreeFlyer;

   Sammanfattning : Events such as forest fires or floods are a danger to our Earth’s environment and the people living in it. The sooner they can be detected, the less damage they can cause. An idea arises: use satellites to monitor the Earth and relay information to prevention and rescue organizations in a very short time, regardless of accessibility from ground. LÄS MER

5. 4. On The Evaluation of District Heating Load Predictions

   Master-uppsats, Lunds universitet/Institutionen för energivetenskaper

   Författare :Herman Hansson; [2023]
   Nyckelord :Technology and Engineering;

   Sammanfattning : District Heating is a technology with the potential to enable a fossil-free society. However, to realize this potential, some improvements need to be made in order to improve District Heating operation at large, decrease losses in the systems, and thus increase the competitiveness of District Heating as a technology. LÄS MER

7. 5. Machine Learning model applied to Reactor Dynamics

   Master-uppsats, KTH/Fysik

   Författare :Dionysios Dimitrios Nikitopoulos; [2023]
   Nyckelord :Master Thesis; Machine Learning; stability; Energy distribution profiles; Prediction; frequency; decay ratio; Data processing; POLCA-T; Pytorch; testing data; RMSE. ii;

   Sammanfattning : This project’s idea revolved around utilizing the most recent techniques in MachineLearning, Neural Networks, and Data processing to construct a model to be used asa tool to determine stability during core design work. This goal will be achieved bycollecting distribution profiles describing the core state from different steady statesin five burn-up cycles in a reactor to serve as the dataset for training the model. LÄS MER