|
|
Fine-Grained Recognition and Re-Identification of Vehicles Using Advanced Feature Extraction
Doseděl, Ondřej ; Hradiš, Michal (oponent) ; Špaňhel, Jakub (vedoucí práce)
The aim of this theses was to analyze and improve methods used for fine-grained vehicle recognition and vehicle re-identification. The proposed method can be used both for recognition and re-identification. It was based on 3D bounding boxes, which were used to detect the vehicle on the image and then the vehicle was normalized by unpacking into 2D. Improvement of this method was done by determining direction of the vehicle and distinguishing between front and rear while unpacking the vehicle. This proposed method improved the existing method based on 3D bounding boxes for recognition, reducing error up to 13 % in single sample accuracy and up to 17 % track accuracy. However, no improvement was gained for vehicle re-identification using LFTD aggregation.
|
|
|
Multi-Agent System for the Prediction of the Effect of Mutations on Protein Stability
Doseděl, Ondřej ; Martínek, Tomáš (oponent) ; Musil, Miloš (vedoucí práce)
Proteins are building blocks of every living organism, as they are responsible for multiple crucial functions. They consist of amino acids chains and these chains can be changed. The change is called mutation. Mutation can happen naturally, or created in laboratory. The~aim of this thesis is to present novel methology for determining protein's stability upon mutations. It consists of two models. The first model is multi-agent system which handles classification into two classes, i.e, stabilizing and destabilizing. The best model gained 0.7~ACC and 0.41 MCC. The second part dealt with predicting exact values of G where an Extreme Gradient Boosting model was created which managed to gain 1.67 RMSE with 0.53 PCC. New datasets for training and validation, which are truly independent, were also introduced in this thesis.
|
|
|
Multi-Agent System for the Prediction of the Effect of Mutations on Protein Stability
Doseděl, Ondřej ; Martínek, Tomáš (oponent) ; Musil, Miloš (vedoucí práce)
Proteins are building blocks of every living organism, as they are responsible for multiple crucial functions. They consist of amino acids chains and these chains can be changed. The change is called mutation. Mutation can happen naturally, or created in laboratory. The~aim of this thesis is to present novel methology for determining protein's stability upon mutations. It consists of two models. The first model is multi-agent system which handles classification into two classes, i.e, stabilizing and destabilizing. The best model gained 0.7~ACC and 0.41 MCC. The second part dealt with predicting exact values of G where an Extreme Gradient Boosting model was created which managed to gain 1.67 RMSE with 0.53 PCC. New datasets for training and validation, which are truly independent, were also introduced in this thesis.
|
|
|
Fine-Grained Recognition and Re-Identification of Vehicles Using Advanced Feature Extraction
Doseděl, Ondřej ; Hradiš, Michal (oponent) ; Špaňhel, Jakub (vedoucí práce)
The aim of this theses was to analyze and improve methods used for fine-grained vehicle recognition and vehicle re-identification. The proposed method can be used both for recognition and re-identification. It was based on 3D bounding boxes, which were used to detect the vehicle on the image and then the vehicle was normalized by unpacking into 2D. Improvement of this method was done by determining direction of the vehicle and distinguishing between front and rear while unpacking the vehicle. This proposed method improved the existing method based on 3D bounding boxes for recognition, reducing error up to 13 % in single sample accuracy and up to 17 % track accuracy. However, no improvement was gained for vehicle re-identification using LFTD aggregation.
|
host ::
RSS.