Sökning: "evolutionära algoritmer"

Visar resultat 1 - 5 av 21 uppsatser innehållade orden evolutionära algoritmer.

1. 1. Automated Image Pre-Processing for Optimized Text Extraction Using Reinforcement Learning and Genetic Algorithms

   Kandidat-uppsats,

   Författare :Rahmat Rohoullah; Månsson Joakim; [2023]
   Nyckelord :BRISK; YOLO; Reinforcement learning; Evolutionary algorithm; OCR; Image pre-processing; Computer vision; BRISK; YOLO; Förstärkningslärning; Evolutionär algorithm; OCR; Bildförbehandling; Datorseende;

   Sammanfattning : This project aims to develop an automated image pre-processing chain to extract valuable information from appliance labels before recycling. The primary goal is to improve optical character recognition accuracy by addressing noise issues using reinforcement learning and an evolutionary algorithm. LÄS MER

3. 2. Trajectory Optimisation of a Spacecraft Swarm Maximising Gravitational Signal

   Master-uppsats, KTH/Optimeringslära och systemteori

   Författare :Rasmus Maråk; [2023]
   Nyckelord :Spacecraft Swarms; Trajectory Optimisation; Impulsive Manoeuvres; Evolutionary Algorithms; Polyhedral Gravity Model; Small Body Exploration; Discrete Spherical Grids; Svärmande rymdfarkoster; Banoptimering; Impulsiva manövrar; Evolutionära Algoritmer; Polyhedral gravitationsmodell; Utforksning av små kroppar i solsystemet; Diskreta sfäriska rutnät;

   Sammanfattning : Proper modelling of the gravitational fields of irregularly shaped asteroids and comets is an essential yet challenging part of any spacecraft visit and flyby to these bodies. Accurate density representations provide crucial information for proximity missions, which rely heavily on it to design safe and efficient trajectories. LÄS MER

4. 3. A comparative analysis of database sanitization techniques for privacy-preserving association rule mining

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

   Författare :Charlie Mårtensson; [2023]
   Nyckelord :Association rule hiding; privacy-preserving data mining; evolutionary algorithms; performance evaluation; Associationsregeldöljning; sekretessbevarande datautvinning; evolutionära algoritmer; prestandaevaluering;

   Sammanfattning : Association rule hiding (ARH) is the process of modifying a transaction database to prevent sensitive patterns (association rules) from discovery by data miners. An optimal ARH technique successfully hides all sensitive patterns while leaving all nonsensitive patterns public. LÄS MER

5. 4. Boost Converter Inductor Design for High-Power Fuel Cells Using Pareto Optimisation for Single and Coupled Cores

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

   Författare :Lucas Tunelid; [2022]
   Nyckelord :Fuel Cells; Interface Converters; Inductor Design; Mutiobjective Optimisation; Bränsleceller; Gränsnittsomvandlare; Induktor Design; Multiobektiv Optimering;

   Sammanfattning : Hydrogen has been identified by the European Commission to be a competitive alternative to fossil fuels within the transport sector in the medium to long perspective. Because of this, an increased understanding is required of the electrical power train present within such vehicles. LÄS MER

7. 5. Using Data-Driven Feasible Region Approximations to Handle Nonlinear Constraints When Applying CMA-ES to the Initial Margin Optimization Problem

   Master-uppsats, KTH/Matematisk statistik

   Författare :Karl Wallström; [2021]
   Nyckelord :Optimization; Initial margin; Evolutionary algorithms; CMA-ES; Support vector machines; Boundary constraint handling; Nonlinear constraints; Repair algorithms; Feasible region approximation; Optimering; Initial margin; Evolutionära algoritmer; CMA-ES; Support vector machines; Hantering av bivillkor; Icke-linjära bivillkor; Reparationsalgoritmer; Approximation av tillåtet område;

   Sammanfattning : The introduction of initial margin requirements for non-cleared OTC derivatives has made it possible to optimize initial margin when considering a network of trading participants. Applying CMA-ES, this thesis has explored a new method to handle the nonlinear constraints present in the initial margin optimization problem. LÄS MER