Haku
Viitteet 1-7 / 7
Methods for Classifying Excavator Motions in Long-Term Activities
(2022)
Diplomityö
Diplomityö
This thesis describes the research work done for Novatron ltd. during the summer and fall of the year 2021. The purpose of the research was to find and compare methods for automatic motion and activity recognition for ...
Dimensionality reduction in generating decision-based adversarial examples
(2022)
Pro gradu -tutkielma
Pro gradu -tutkielma
As the ever-increasing popularity of machine learning continues to rise, its reliability is of utmost importance. Despite the enormous progress and its excellent performance, it has been discovered that machine learning ...
Smooth Masking Augmentation In Passive Sonar Data Based Ship Type Classification
(2023)
Diplomityö
Diplomityö
In this thesis, a novel data augmentation method for deep neural networks is presented for a ship type classification task. This task is an audio classification task, which utilizes underwater hydrophone recordings.
The ...
Precise detection of fiducials using machine learning
(2023)
Diplomityö
Diplomityö
Machine learning methods, specifically convolutional neural networks, can yield good results in many computer vision tasks. With a suitable model and good training data, machine learning models outperform more traditional ...
Computer Generated Holography : from Analytic to Learning-based Methods
(2023)
Diplomityö
Diplomityö
In the pursuit for an ideal way to display visual 3D information in the natural way, holographic displays emerge as a promising candidate. Generating dynamic content for these displays, however, exhibits a trade-off between ...
Comparison of alarm flood classification methods
(2024)
Diplomityö
Diplomityö
Operators in process industries grapple with challenges of alarm systems due to their increasing complexity. These alarm systems, intended to alert operators to faults and issues, can lead to ‘alarm floods’—periods of ...
Off-puck scoring opportunities: Detection and visualization of ice-hockey scoring opportunities from position data
(2024)
Diplomityö
Diplomityö
The purpose of this thesis was to investigate if off-puck player positions can be utilized to predict goal-scoring in ice hockey. In addition to predicting scoring, the aim was to predict where the goals would be scored ...