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

DEGREE

PROGRAMME

FACULTY

YEAR

LANGUAGE

KEYWORDS

Development of Decision Support Tool for Transport Forwarding Company Operating within Netherlands and Italy

This paper investigates the development of a decision support tool for a Latvian transportation company operating in the Dutch and Italian markets. Models and algorithms for optimizing freight routes using Excel and Python are included. Digitalization of logistics processes is recognized as a key to improve efficiency and reduce costs. Two methods for solving the traveling salesman problem were examined and compared: Excel with Solver and Python with the NetworkX library.The methodology involved collecting data from Google My Maps, creating Excel spreadsheets, and developing Python software to automate route optimization. The results showed that both methods improved route planning, reducing time and cost, as well as reducing carbon footprint.The study emphasizes the importance of integrating technologies such as machine learning and big data into logistics to increase flexibility and adaptability. Recommendations were offered to further improve and implement these technologies for sustainable business development and increased competitiveness in international markets.

Author: Anastasija Škaduna

Supervisor: Berdymyrat Ovezmyradov

Degree: Professional Bachelor

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...

Vibration Analysis-Based Fault Diagnosis of Tool Conditions on Electric Motor-Powered Machine Tools Using Convolutional Neural Networks

This thesis explores and evaluates techniques for utilizing vibration analysis and Convolutional Neural Networks (CNNs) to assess the condition of drill bits installed on electric motor-driven drills. By strategically positioning an Inertial Measurement Unit (IMU) sensor to capture acceleration data, a wide range of vibration signals can be gathered in different operational scenarios. The CNN models undergo training and validation utilizing this data to precisely detect various fault conditions and operational states of the drill bits, showcasing the possibility of implementing scalable and reliable fault detection systems in industrial environments. The research attains a Technology Readiness Level (TRL) of 3, as demonstrated by trials that effectively categorize machine conditions using CNNs, hence confirming the critical functions of the proposed technology. The aim of this study is to assess the efficacy of vibration analysis in classifying the operational state of a drilling machine as either good, moderate, or bad.Vibration analysis is a method used to analyze the oscillation patterns of a machine in order to identify problems such as misalignment, imbalance, and wear.

Author: Marawan Mohamed Ahmed Elsayed Youssef

Supervisor: Emmanuel Alejandro Merchan Cruz

Degree: Master

Year: 2024

Work Language: English

CNN-Based pipeline-related artifact and damage recognition in IHC staining as preprocessing step for pathological analysis

This work proposes automated solution for artifact and damage segmentation in biomedical images using machine learning algorithms. The development process includes data preprocessing, label classification using a clustering algorithm and segmentation model. CNN architectures like YOLO and U-NET are utilized for segmentation, and K-Means and DBSC algorithms are evaluated for clustering. The outcomes include a set of data preprocessing precodures, clustering algorithm testing and results analysis, segmentation model and recommendations for further development.

Author: Taisija Kožarina

Supervisor: Jeļena Kijonoka

Degree: Bachelor

Year: 2024

Work Language: English

Study programme: Computer Science

More...

Table View
Text View