Sökning: "syntetiska data"

Visar resultat 1 - 5 av 131 uppsatser innehållade orden syntetiska data.

1. 1. Variational AutoEncoders and Differential Privacy : balancing data synthesis and privacy constraints

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

   Författare :Baptiste Bremond; [2024]
   Nyckelord :TVAE; Differential privacy; Tabular data; Synthetic data; DP-SGD; TVAE; differentiell integritet; tabelldata; syntetiska data; DP-SGD;

   Sammanfattning : This thesis investigates the effectiveness of Tabular Variational Auto Encoders (TVAEs) in generating high-quality synthetic tabular data and assesses their compliance with differential privacy principles. The study shows that while TVAEs are better than VAEs at generating synthetic data that faithfully reproduces the distribution of real data as measured by the Synthetic Data Vault (SDV) metrics, the latter does not guarantee that the synthetic data is up to the task in practical industrial applications. LÄS MER

3. 2. Measuring the Utility of Synthetic Data : An Empirical Evaluation of Population Fidelity Measures as Indicators of Synthetic Data Utility in Classification Tasks

   Master-uppsats, Karlstads universitet/Institutionen för matematik och datavetenskap (from 2013)

   Författare :Alexander Florean; [2024]
   Nyckelord :Synthetic Data; Machine Learning; Population Fidelity Measures; Utility Metrics; Synthetic Data Quality Evaluation; Classification Algorithms; Utility Estimation; Data Privacy; Artificial Intelligence; Experiment Framework; Model Performance Assessment; Syntetisk Data; Maskininlärning; Population Fidelity Mätvärden; Användbarhetsmätvärden; Kvalitetsutvärdering av Syntetisk Data; Klassificeringsalgoritmer; Användbarhetsutvärdering; Dataintegritet; Artificiell Intelligens; AI; Experiment Ramverk; Utvärdering av Modellprestanda;

   Sammanfattning : In the era of data-driven decision-making and innovation, synthetic data serves as a promising tool that bridges the need for vast datasets in machine learning (ML) and the imperative necessity of data privacy. By simulating real-world data while preserving privacy, synthetic data generators have become more prevalent instruments in AI and ML development. LÄS MER

4. 3. Detection and Analysis of Anomalies in Tactical Sensor Systems through Structured Hypothesis Testing

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

   Författare :Fredrik Ohlson; [2023]
   Nyckelord :Tactical sensor systems; Sensor fusion; Model based diagnostics; Hypothesis testing; Taktiska sensor system; Sensor fusion; Modellbaserad diagnostisering; Hypotesprövning;

   Sammanfattning : The project explores the domain of tactical sensor systems, focusing on SAAB Gripen’s sensor technologies such as radar, RWR (Radar Warning Receiver), and IRST (InfraRed Search and Track). The study employs structured hypothesis testing and model based diagnostics to examine the effectiveness of identifying and isolating deviations within these systems. LÄS MER

5. 4. Evaluating the Viability of Synthetic Pre-training Data for Face Recognition Using a CNN-Based Multiclass Classifier

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

   Författare :Lars Bergström; Dag Hjelm; [2023]
   Nyckelord :;

   Sammanfattning : Today, face recognition is becoming increasingly accurate and faster with deep learning methods such as convolutional neural networks (CNNs), and is now widely used in areas such as security and entertainment. Typically, these CNNs are trained using real-face datasets like CASIA-WebFace, which was put together using web-crawling of IMDB. LÄS MER

7. 5. Evaluation of a computational method for natural fiber-reinforced plastics

   Master-uppsats, KTH/Hållfasthetslära

   Författare :Anna Lim; [2023]
   Nyckelord :PPNF; Composite material; fiber orientation; natural fiber; coupled analysis; PPNF; Kompositmaterial; fiberorientering; naturfiber; kopplad analys;

   Sammanfattning : The importance of using natural fiber composites (NFCs) has been addressed as a substitution for synthetic fibers, such as glass and carbon fibers. This substitution contributes significantly to reducing greenhouse gas emissions, aligning with the environmental responsibilities of engineering industries. LÄS MER