Sökning: "Feature analysis"

Visar resultat 1 - 5 av 1082 uppsatser innehållade orden Feature analysis.

1. 1. Feature Selection for Microarray Data via Stochastic Approximation

   Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

   Författare :Erik Rosvall; [2024-03-18]
   Nyckelord :feature selection; feature ranking; microarray data; stochastic approximation; Barzilai and Borwein method; Machine Learning; AI;

   Sammanfattning : This thesis explores the challenge of feature selection (FS) in machine learning, which involves reducing the dimensionality of data. The selection of a relevant subset of features from a larger pool has demonstrated its effectiveness in enhancing the performance of various machine learning algorithms. LÄS MER

3. 2. Data analysis for predictive maintenance and potential challenges associated with the technology integration of steel industry machines.

   Master-uppsats, Högskolan i Gävle/Elektronik

   Författare :Pradip Nath; [2024]
   Nyckelord :Data Science; Data processing; Industrial Manufacturing; System Identification; Predictive maintenance; Conditional monitoring; Statistical Analysis; Signal processing; Hydraulic System; IoT; Sustainable Maintenance; Data vetenskap; Databehandling; Industriell tillverkning; System identifiering; Prediktivt underhåll; Tillståndsövervakning; Statistisk analys; Signal behandling;

   Sammanfattning : The recharge is the focus of data analysis of the different situations with the integration of the system and development of the two-stage 2/2 proportional cartridge valve for the steel industry machine. Using the statistical analysis technique to visualize the valve signal data behavior identify the accuracy of the machine data and apply the statistical feature extracting model using classification and clustering algorithms of real-time data analysis for the manufacturing. LÄS MER

4. 3. Simulation-based discrimination of Crab pulsar models with XL-Calibur

   Master-uppsats, KTH/Fysik

   Författare :Dennis Åkerström; [2024]
   Nyckelord :Astroparticle Physics; Astrophysics; Detector Physics; Simulation; Theoretical Physics; Engineering Physics; Pulsar models; Crab pulsar; Astropartikelfysik; Astropartikelfysik; Detektorfysik; Simulering; Teoretisk Fysik; Teknisk Fysik; Pulsar modeller; Krabbpulsaren;

   Sammanfattning : Polarisation of X-ray light is being investigated with polarimeters to extend the borders of what can be observed. Distant compact objects, such as pulsars, that are to small on the sky to be analysed with imaging can be investigated by analysing the polarisation of the emitted light. This can reveal physics previously hidden by their small nature. LÄS MER

5. 4. Potential and Limitations of the Sketch Map Tool in the International Red Cross Red Crescent Movement

   Master-uppsats, Lunds universitet/Avdelningen för Riskhantering och Samhällssäkerhet

   Författare :Kimon Letzner; [2024]
   Nyckelord :Disaster risk reduction; Participatory action research; Community risk mapping; International Red Cross Red Crescent Movement; Colombia; Technology and Engineering;

   Sammanfattning : In disaster risk management, participatory mapping (PM) closes spatial data gaps in communities by integrating local risk knowledge. The thesis examined the potential and limitations of the Sketch Map Tool (SMT) as a PM tool for community-based disaster risk reduction (DRR) through an International Red Cross Red Crescent Movement case study. LÄS MER

7. 5. Detecting Fraudulent User Behaviour : A Study of User Behaviour and Machine Learning in Fraud Detection

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Analys och partiella differentialekvationer

   Författare :Patrik Gerdelius; Sjönneby Hugo; [2024]
   Nyckelord :Fraud Detection; User Behaviour; Random Forest; PCA; SMOTE;

   Sammanfattning : This study aims to create a Machine Learning model and investigate its performance of detecting fraudulent user behaviour on an e-commerce platform. The user data was analysed to identify and extract critical features distinguishing regular users from fraudulent users. LÄS MER