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

DEGREE

PROGRAMME

FACULTY

YEAR

LANGUAGE

KEYWORDS

Improvement of machine leaning algorithms performance by data set dimensionality reduction using cellular automata

A significant challenge in Machine Learning is dealing with high-dimensional data. Complexity knowns as the "curse of dimensionality" results in deterioration оf Machine Learning algorithms performance as the dimensionality and dataset size increases. Cellular automata are a dynamical discrete computational system with mathematical functions knows as rules that result in complex global behaviour. We used one-dimensional elementary cellular automata as a tool for dataset size. Model variables were selected for initial status vector generation and its further transformation to format that is suitable for cellular automata rules application known in cellular automata theory as configuration. Then model iterated through all possible cellular automata rules and various epochs variations were applied. Model performance for reduced dataset was compared with benchmark results of original dataset after standard dimensionality reduction technics used. It was concluded that applied cellular automata rules can be used as alternative methods for dataset size reduction without deteriorating model performance.

Author: Alexey Kuchvalskiy

Supervisor: Dmitry Pavlyuk

Degree: Master

Year: 2024

Work Language: English

Study programme: Computer Sciences

More...

Development of an Alternative Mean of Compliance for inspecting passenger door stops on Embraer ERJ - 145 using Fluorescent penetrant Non-destructive Testing method.

This bachelor thesis focused on Development of an Alternative Mean of Compliance (AltMoC) for Inspecting the passenger door stops from Embraer ERJ - 145 aircraft Using Non-Destructive Testing Fluorescent penetrant method. The main goal of this work is to simplify the task with the help of a developed inspection for checking a structural component. A structural component is subject to fatigue and physical stress on it, as well as corrosion. Detailed detection of the smallest damage and metal fatigue. The developed AltMoC is aimed at significantly accelerating work processes, making inspection cheaper as well as having a simplified and clear process using penetrant testing. Having carried out research, the Author, carefully select the appropriate method for inspecting a structural component based on the type of material from which it is made, considering its’ its physical and chemical properties. Develop the correct sequence of actions in the instructions. Thanks to this, the workflow time and the risk of errors occurred due to Employees' misunderstanding significantly reduced.

Author: Deniss Zaharovs

Supervisor: Iyad Alomar

Degree: Bachelor

Year: 2024

Work Language: English

Study programme: Aviation Engineering

More...

Green transport solutions in a medium-sized courier company

This paper produces an analysis of the Latvia-based courier delivery company DPD Latvija to determine its possibilities and evaluate sustainable solutions that it has implemented already. The obtained results are used to select suitable green transport solutions using multi-criteria decision making and cost-benefit analysis methods and to develop appropriate recommendations that help to improve the sustainable solutions already used in the company or to introduce new ones.The main green transport solutions covered by the research are the most impactful ones and include switching to electric vehicles, usage of alternative fuels such as CNG, biodiesel and hydrogen cell, and an innovative model of crowdshipping. There are several more solutions covered in the research that can be used to increase a company's contribution to decarbonization.The resulting framework or action plan, can help the company make best investments in implementing green transportation solutions to reduce greenhouse gas emissions and potentially attract new customers. The added value of the work is the opportunity for another Latvian medium-sized courier company to use the proposed framework as a basis for creating its own plan.

Author: Ernests Grahoļskis

Supervisor: Aleksandrs Kotļars

Degree: Master

Year: 2024

Work Language: Latvian

Alternative energy sources in Latvia and their impact on social well-being.

Rapid climate change as well as the geopolitical situation in the world are encouraging the spread and development of "green" energy sources not only at a national level but also in the household sector. This is why alternative energy sources have become increasingly popular in recent years.This study shows the use of alternative energy sources in Latvia and the Baltic States, their patterns, and development opportunities. The results of the analysis of the statistical databases of the Baltic countries show the trends towards alternative energy sources in recent years.The study has highlighted the importance of improving the energy efficiency of buildings alongside the increasing trend towards alternative energy sources and the support programs that have been set up for this purpose. This Research is based on plans, regulations, and laws to increase the use of alternative energy sources and reduce gas emissions.This study evaluates the impact of the development and deployment of alternative energy sources on households and the benefits they can gain.

Author: Roberts Andrejevs

Supervisor: Veronika Siliņeviča

Degree: Bachelor

Year: 2024

Work Language: English

Study programme: Business and Management

More...

Personal Information Management using Adaptive Information Systems

Nowadays people struggle to handle their personal information in an organized and efficient manner. In average individual consumes around 74Gb per day (Heim, 2017), which contributes to to information overload and limits the amount of information that the human mind can handle.Due to human uniqueness, all people have different information preferences. Adaptive Information Systems (AIS) is a relatively new direction of research on the crossroads of Information Science, Human-Computer Interaction and Artificial Intelligence. It is an alternative to the traditional "one-size-fits-all" approach in the development of Information Systems. Considering that Information overload is a user-personal problem, AIS allow involve an adaption process inside the information system activate reinforcement learning for building knowledge about the user’s behavior in information processing. As a next step collected knowledge AIS is used for performing self-adaptive changes inside the system with the final goal of reducing information overload.This study proposed a new way of handling and control information overload by using AIS, which is supposed to consider and adapt to user's personal experience in personal information processing.

Author: Sergejs Paškovskis

Supervisor: Boriss Mišņevs

Degree: Master

Year: 2024

Work Language: English

Table View
Text View