Search Results (11)
Smart denoising for recurrent neural network optimization
This thesis introduces a new optimization method based on deep learning, designed for data influenced by random processes. The main contribution of this method is the combination of advanced noise reduction techniques with recurrent neural network models, which helps to prevent the common problem of overfitting seen when there is …
Using machine learning methods for analyzing sequential textual data
This thesis investigates machine learning methods for analyzing sequential textual data. Sequential textual data refers to text collected in a specific order where the sequence is significant. Examples include (1) sentences, where word usage and order must adhere to the rules of grammar, (2) news reporting on events happening at …
Bias prediction in multilingual news reporting
Over the past decade, rapid advancements in natural language processing have opened up new avenues for tackling complex issues such as news bias analysis. This progress has empowered researchers to explore innovative approaches to uncovering the complex biases inherent in news production and coverage processes. News bias, a multifaceted reflection …
Machine learning methodology for automatic metadata assignment in cultural heritage archives
This thesis introduces a novel machine learning methodology for automatically assigning metadata to digitized artifacts in cultural heritage. Cultural heritage is an example of a domain that requires expert labeling, with few pre-existing labeled datasets and where simply getting more labeled data is challenging. The societal importance of cultural heritage …
Pre-processing of heterogeneous data streams for internet of things applications
The rapid evolution of sensor technologies, particularly within the Internet of Things (IoT) domain, has led to an era dominated by massive real-time data flows. This transition resulted in the need for novel data processing methodologies that facilitate the shift from traditional offline batch analytics to agile real-time predictions and …
Information spreading barriers in news
News spreads in many patterns, structures, and dynamics that change throughout time. For a variety of reasons, certain news is only covered in a particular area. Language, economy, geography, politics, time zone, and culture are just a few of the many barriers that prevent news from reaching a larger audience. …
Demand forecasting with machine learning methods
This thesis examines how machine learning can be applied in demand forecasting. In particular, it describes a novel approach toward lumpy and intermittent demand forecasting. It advocates using a two-fold model for forecasting lumpy (irregular demand occurrence, strong demand size variability) and intermittent (irregular demand occurrence, little demand size variability) …
Predicting the dynamics of spatio-temporal systems based on heterogeneous data sources
As urbanisation continues to be a trend, in which centralisation of the population into cities is still growing, the importance of intelligent solutions in mobility is in high demand. Likewise, with the integration of renewable energies into all levels of the electrical grid system and the increasing amount of heavy …
Dynamic composition of communication services
In this thesis, we look at networking functionality as a set of services which can be composed dynamically. We argue that the dynamic composition of communication services can speed up design and experimentation with new protocol stacks. The reference Open Systems Interconnect (OSI) architecture of communication networks splits network functionality …
Ontology Extension Using Text Mining for News Analysis
In computer science, ontologies enable formalized knowledge representation. The goal of ontology extension is to correctly augment the existing ontology with new formalized knowledge (e.g., concepts, relationships etc.). This thesis addresses the ontology extension process based on text mining methods. News analysis is the application of the extended ontology. A …