Advanced search

Showing result 1 - 5 of 78 essays matching the above criteria.

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

    University essay from Karlstads universitet/Institutionen för matematik och datavetenskap (from 2013)

    Author : Alexander Florean; [2024]
    Keywords : 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;

    Abstract : 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. READ MORE

  2. 2. Virtual H&E Staining Using PLS Microscopy and Neural Networks

    University essay from Lunds universitet/Matematik LTH

    Author : Sally Vizins; Hanna Råhnängen; [2024]
    Keywords : Deep learning; Virtual staining; Skin tissue; Hematoxylin Eosin; H E; Pathology; Carcinoma; Point light source illumination; Neural Networks; GANs; Generative adversarial networks; CNNs; Convolutional neural networks; Relativistic generative adversarial network; Unet; Digital microscopy; Attention-Unet; Dense-Unet; Mathematics and Statistics;

    Abstract : Histopathological examination, crucial in diagnosing diseases such as cancer, traditionally relies on time- and resource-consuming, poorly standardized chemical staining for tissue visualization. This thesis presents a novel digital alternative using generative neural networks and a point light source (PLS) microscope to transform unstained skin tissue images into their stained counterparts. READ MORE

  3. 3. Leveraging CNN for Automated Peak Picking in Untargeted Metabolomics without Parameter Dependencies

    University essay from Göteborgs universitet/Institutionen för data- och informationsteknik

    Author : Vivian Wang; Lidia Yalew; [2023-10-19]
    Keywords : Deep learning; Convolutional neural network; LC-MS; Peak Detection; Metabolomics; Faster R-CNN;

    Abstract : Metabolomics is a scientific discipline that involves the thorough analysis of small molecules, known as metabolites, found within a biological system. Furthermore, liquid chromatography-mass spectrometry (LC-MS) is a commonly used analytical technique in metabolomics for analysing biological samples due to its broad coverage of the measurable metabolome. READ MORE

  4. 4. Secondary level EFL teachers’ perceptions, practices, and challenges of implementing CAS in public schools in Nepal. A Narrative Inquiry

    University essay from Göteborgs universitet/Institutionen för pedagogik och specialpedagogik

    Author : Dil Kumar Sijali Magar; [2023-09-11]
    Keywords : Continuous Assessment System; CAS; perceptions; experiences; practices; challenges; implementation;

    Abstract : Aim: The objective of my study was to explore the EFL teachers’ perceptions and experiences of using CAS in Nepalese public schools. It was further aimed to explore their current practice of CAS and the potential challenges they have faced in implementing CAS in language teaching. READ MORE

  5. 5. Investigating the Accuracy of Metric-Based versus Machine Learning Approaches in Detecting Design Patterns

    University essay from Göteborgs universitet/Institutionen för data- och informationsteknik

    Author : Nils Dunlop; [2023-08-03]
    Keywords : Design Pattern Detection; Metrics; Thresholds; Machine Learning;

    Abstract : Design pattern detection approaches have evolved, with machine-learning methods gaining prominence. However, implementing machine-learning models can be challenging due to extensive training requirements and the need for large labeled design pattern datasets. READ MORE