Kategorie: ‘Theses’
Enhancing Chatbot Performance through Process Mining
This thesis aims to develop a framework for analyzing chatbot conversations using process mining techniques. The framework will allow users to discover process models from chatbot event logs, compare them to the bot models, and enhance them based on the analysis results.
Evaluation of Source Inference Attack and Defenses on Federated Learning
Effects of Generative Replay-based methods on Catastrophic Forgetting in DA on healthcare data
From Simulation to Real Settings: Investigating the Testability of Distributed Analytics Experiments
Establishing Trust in P2P Distributed Analytics Infrastructures
Estimation of Individual Privacy Risk in Data Sharing using Predictive Models
Mastering the Game of Contract Bridge: Strategy Optimization via Deep Reinforcement Learning
This thesis aims to explore Deep Reinforcement Learning based methods for strategy optimization in the Contract Bridge game, such as Multi-agent Reinforcement Learning, Value-based Learning, and Policy-based Learning, as well as Knowledge Representation and Reasoning based methods such as Multi-agent Epistemic Situation Calculus
Improved Bottom-up Deep Learning Approach for Neuronal Cell Instance Segmentation
Offloading of IoT Workloads in Peer-to-Peer Networks using WebAssembly
Edge computing offers a framework for offloading the computational effort required by IoT applications.
However, privacy issues and cost constraints for cloud infrastructures pose substantial difficulties to IoT service deployment. We wish to look at the possibilities of Peer-to-Peer networks and WebAssembly for IoT task offloading. As a result, a comparison of existing offloading tactics and information structures based on peer-to-peer and client-side solutions employing modern Web protocols such as WebRTC and WebAssembly is made.