Music recommendation systems are crucial in guiding listeners to the extensive selection of music accessible today. However, these recommendation algorithms frequently encounter challenges such as the cold start problem, including less popular tracks, and comprehending the semantic substance of music. This thesis investigates the incorporation of Large Language Models (LLMs) and embeddings to tackle ...

This thesis explores the effectiveness of Large Language Models (LLMs) in enhancing educational methodologies, particularly focusing on personalized learning experiences in music education. Initially, a comprehensive literature review was conducted to establish the theoretical foundation and identify gaps in the current application of Large Language Models in education. Subsequently, employing a ...

This master’s thesis investigates alternative control methodologies for unmanned aerial vehicles (UAVs), focusing on integrating advanced human-machine interaction techniques. Traditional remote-controlled and sensor-based systems pose limitations, particularly for users with physical disabilities. This study explores the potential of virtual keyboards, hand gesture recognition, and eye movement ...

This thesis assesses the impact of fine-tuning and rag on llms in accurately assigning icd-10 codes to historical causes of death. Using funeral records from Trondheim, Norway (1830-1920), we fine-tuned Llama 3 and Mistral on 2000 records. Twelve experiments were conducted on 2000 additional records to evaluate the accuracy of each knowledge-injection technique, as well as a combination of the ...

3D-printing of polymers come in a large variety of methods and materials, each configuration with its own strengths and weaknesses. To compute and estimate mechanical properties of 3D-printed parts, good knowledge to the geometry of the internal structures is important to obtain. This will vary between different printers and slicers. As 3D-printed parts are anisotropic, it is often challenging to ...

Thanks to technical improvements, drones may now perform more than simply visual inspections of structures and buildings. An Unmanned Aerial Vehicle (UAV) drone can be equipped with a robotic arm or an attachment with sensors to check and test the structures and buildings. Designing a robotic arm with a modular end-effector that can be attached to a drone was the focus of this master's thesis research. ...

This thesis project was commissioned by Cegal and aimed to investigate the potential for demand-side flexibility in the Helgeland region, as well as evaluate forecasting methods for a demand-response system. The future energy situation in the area was analyzed, while the experimental part investigated forecasting methods which can be applied in a demand-response system. Finally, the project i ...

The purpose of this thesis is to set the groundwork for future research on developing a machine-learning based anomaly detection system for hospitalized patients. Our first step was to study and analyze the project’s needs, background, and literature examining similar criteria. In the second step, we interviewed medical experts and researchers. Based on our research and the suggestions received ...

The task is to produce a suitable option for those who go mountain hiking and want the thrill to ride down the hills. The product should be lightweight and foldable, and easy to bring along for a bus ride or other types of public transportation. The final product is a downhill scooter, where the neck is foldable. The deck of the scooter is a sandwich structure where the core is made of aluminum 5052 ...

The additive manufacturing or 3D printing (3DP) technologies have undergone exponential expansion, particularly in the previous couple of decades. Additive manufacturing technologies have paved the way for easy component manufacturing in large-scale and high-performance businesses. The introduction of desktop 3D printers has established 3DP as a reliable technique for generating prototypes and direct ...