Sökning: "Kontextmedveten"

Visar resultat 1 - 5 av 19 uppsatser innehållade ordet Kontextmedveten.

1. 1. 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

3. 2. Context-aware security testing of Android applications : Detecting exploitable vulnerabilities through Android model-based security testing

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

   Författare :Ivan Baheux; [2023]
   Nyckelord :Android Application Security; Vulnerability Detection; Context-Awareness; Model-Based Security Testing; Domain Specific Language; Sécurité des Applications Android; Détection de Vulnérabilités; Sensibilité au Contexte; Tests de Sécurité Basés sur les Modèles; Langage Dédiés; Android-applikationssäkerhet; Upptäckt av sårbarheter; Kontextmedvetenhet; Modellbaserad säkerhetstestning; Domänspecifikt språk;

   Sammanfattning : This master’s thesis explores ways to uncover and exploit vulnerabilities in Android applications by introducing a novel approach to security testing. The research question focuses on discovering an effective method for detecting vulnerabilities related to the context of an application. LÄS MER

4. 3. Context-aware Swedish Lexical Simplification : Using pre-trained language models to propose contextually fitting synonyms

   Kandidat-uppsats, Linköpings universitet/Institutionen för datavetenskap

   Författare :Emil Graichen; [2023]
   Nyckelord :automatic text simplification; lexical simplification; Swedish; BERT; GPT-3; evaluation dataset; synonymy;

   Sammanfattning : This thesis presents the development and evaluation of context-aware Lexical Simplification (LS) systems for the Swedish language. In total three versions of LS models, LäsBERT, LäsBERT-baseline, and LäsGPT, were created and evaluated on a newly constructed Swedish LS evaluation dataset. LÄS MER

5. 4. Mockup - Kontextmedvetet resestöd vid oväntade trafikstörningar i kollektivtrafiken

   Kandidat-uppsats, Malmö universitet/Fakulteten för teknik och samhälle (TS)

   Författare :Arvid Steen; Ali Zreim; [2022]
   Nyckelord :Mockup; context; context-aware; public transport; survey; Demonstrationsmodell; kontext; kontextmedveten; kollektivtrafik; enkät;

   Sammanfattning : In this paper, a mockup application is created to examine how the commuter’s context, with a focus on the train the commuter is on, can be used to suggest individual alternative travel routes to support the commuter in arriving at the requested destination based on minimal delay with consideration of an uncertainty factor. Based on investigations of various travel applications, four different concepts are created that are used in a user survey where commuters can answer questions regarding, alternative travel routes, uncertainty factors and guidance to the requested destination. LÄS MER

7. 5. Context-aware Data Plausibility Check Using Machine Learning

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

   Författare :Mohaddeseh Basiri; [2021]
   Nyckelord :Artificial intelligence; Machine learning; Plausibility check; Anomaly detection; Konstgjord intelligens; Maskininlärning; Rimlighetskontroll; Avvikelse upptäckt;

   Sammanfattning : In the last two decades, computing and storage technologies have experienced enormous advances. Leveraging these recent advances, AI is making the leap from traditional classification use cases to automation of complex systems through advanced machine learning and reasoning algorithms. LÄS MER