TSI logo 25 years
LV EN
Home > About Us > Structure and Government > Abstracts

DEGREE

PROGRAMME

FACULTY

YEAR

LANGUAGE

Unsupervised machine learning approach for hierarchical graph-based representation of natural language text collections.

Managing big data efficiently is important in various fields, much so when data consists of human-written documents. Recent advances in Natural Language Processing (NLP), particularly LLMs, allowed to solve many task in this domain, despite the high demand for labelled data, compute resources and specialized skills.To tackle these limitations, current study proposed a NLP pipeline to identify topic hierarchies in collections of scientific publications. The work focused on evaluation of available unsupervised machine learning methods and quality metrics in NLP, and development of visualization techniques to build a prototype of the pipeline.Proposed solution is based on the hARTM approach optimized for interpretability. It demonstrated the capacity to infer human-interpretable topic hierarchies from collections of scientific texts and construct meaningful hierarchy of topic-based document representations. The visualization approaches rely on MDS to present inter-document similarity and Sankey plots to show document cluster relatedness within topic hierarchy.Utility was demonstrated on two datasets, focusing on interpretability and meaning of the topic hierarchy and associated topic definitions. Potential application areas include personal education and scientific writing.

Author: Jevgenijs Bodrenko

Supervisor: Irina Jackiva

Degree: Master

Year: 2024

Work Language: English

Study programme: Computer Sciences

More...

The automated business processes integration and their impact on SMEs in Latvia

This thesis investigates the integration of automated business processes within SMEs (small and medium-sized enterprises) in Latvia's fintech sector, focusing on identifying specific challenges and opportunities. It emphasizes the role of automation in enhancing operational efficiency and enabling SMEs to allocate more resources to strategic and innovative tasks. The research has developed a conceptual framework and provides practical recommendations to assist SMEs in effectively integrating automated processes. The first chapter reviews digital transformation (DT) and business process automation (BPA), including robotic process automation (RPA). The next chapters focus on the survey and interview analysis using the Analytic Hierarchy Process (AHP) and Domain Mapping Matrix (DMM) methods. The fourth chapter presents a business case for integrating BPA in SMEs with examples and discussions on implications. Chapter five introduces a framework for future BPA initiatives and offers practical recommendations for companies integrating BPA.Key findings indicate that while automation offers substantial efficiency and cost-reduction benefits, its practical implementation requires carefully crafted strategies tailored to SMEs' needs.

Author: Jevgeņija Fatunova

Supervisor: Soltani Mohammad

Degree: Master

Year: 2024

Work Language: English

Application of machine learning in decision support system

The aim of the work is to improve the accuracy of predicting wait times in an existing queue management system using machine learning. Client-provided data was analyzed, and models were trained using various machine learning algorithms. Performance measures of the models were collected, and the best one was selected. Additionally, software and a database were developed to manage the training process and evaluate the quality of the models. The quality of the software was assessed using industry-standard methodologies and tested.

Author: Jevgēnijs Nikolajevs

Supervisor: Jeļena Kijonoka

Degree: Bachelor

Year: 2024

Work Language: Latvian

Study programme: Computer Science

More...

The strategic planning features in case of the company's activity change on example of SIA ANTIKS PAINT.

This bachelor thesis analyses the strategic planning of Antiks Paint Ltd. and its impact on the competitiveness and financial stability of the company in the ship repair and construction industry. The thesis provides a theoretical insight into the meaning of strategic planning and its role in the development of the company, as well as analyses different methods of analysis.The study provides an in-depth analysis of the activities of Antiks Paint Ltd., including the company's background information, organisational structure and current strategic planning. The company's financial performance is thoroughly assessed and interviews are conducted with the company's management to gain a deeper understanding of the current challenges and opportunities.The third chapter of the thesis develops a strategic plan, which sets out concrete actions to improve the company's performance and competitiveness. The thesis concludes with conclusions and proposals based on the analysis, proposing solutions for sustainable growth and improvement of the company's market position.The result of this work is a practical strategic planning plan that will help Antiks Paint Ltd to improve its competitiveness and financial performance in a changing business environment.

Author: Jeļena Pavlova

Supervisor: Renāte Indrika

Degree: Bachelor

Year: 2024

Work Language: Latvian

Study programme: Business and Management

More...

Failure Analysis and Enhancements of Cessna-172 Nose Landing Gear Fork

Landing gear provides crucial support for aircraft while on ground. It is fastened to the main structural parts of the plane. The nose landing gear transfers all ground stresses to the aircraft structure, while the aircraft is on ground. Standard airplanes have main gears and the nose gear when taxiing on the ground the nose wheel is essential for both landing safely and guiding the plane. Main landing gear is to facilitate the safe touchdown of the aircraft. When combined, the main landing gear and the nose landing gear allow for landing smooth and jerk-free. The whole weight of the aircraft is supported by the undercarriage during taxiing and landing. Using the modelling program, a design and precise geometry of the existing Cessna 172 nose landing gear fork was created as well as for the proposed model of the nose landing gear. Comparison of four different materials for nose landing gear fork structures and evaluate the equivalent stress, strain and deflection was done. There is comparison of the nose landing gear fork structure with existing and proposed model. Compared to all the cases the titanium alloy material receives the lesser and nearer to the deformation of the steel.

Author: Jithin Thundiyil Appachen

Supervisor: Iyad Alomar

Degree: Bachelor

Year: 2024

Work Language: English

Study programme: Aviation Engineering

More...

Table View
Text View