Objective: Patient-specific musculoskeletal models have emerged as a reliable method to study how tibiofemoral joint (TFJ) morphology influences anterior cruciate ligament (ACL) injuries. However, there are no such models for adolescent populations that can be scaled to accommodate growth. To serve as the foundation for such models, the objective of this thesis was therefore to i) build a patient-specific model of natural knee motion in an ACL-injured (ACLi) adolescent sample using joint congruency and ii) to attempt to reconstruct patient-specific simplified articular contacts using principal component analysis (PCA). Design: Twelve magnetic resonance images (MRI) of ACi adolescents were segmented and used to generate spheres of simplified TFJ articulations. A congruence-based optimization algorithm was used to determine the envelope of tibiofemoral configurations that optimize joint congruency. Descriptive statistics were used to compare model outputs to existing literature. Combinations of marker trajectories and anthropometrics were used to determine the feasibility of reconstructing articular sphere simplifications using PCA. Root-mean squared error (RMSE) was used to compare predicted sphere contacts to MRI-extracted contacts. Results: Average knee joint anglesof the femur with respect to the tibia was slightly abducted and externally rotated, with a range of motion (ROM) of 1.60º ± 0.66 and 7.64 º ± 2.34 across 102° of flexion respectively. The percent elongation of the posterior cruciate ligament (PCL) varied the most across participants (8.65 ± 6.2%) compared to the ACL (2.34 ± 2.1%), MCL (1.41 ± 0.5%) and LCL (1.75 ± 1.6%) respectively. The combination of femur markers and anthropometrics was able to reconstruct simplified tibiofemoral articulations the best, but not within 5 mm of RMSE. Conclusion: Inter-subject variability in passive kinematic motion derived from patient-specific morphology highlights the need for personalized and accessible musculoskeletal models in growing populations. Furthermore, simplified distal femur morphology can be reconstructed from anthropometrics and marker positions, but proximal tibia morphology requires more information.

This study aims to create a Machine Learning model and investigate its performance of detecting fraudulent user behaviour on an e-commerce platform. The user data was analysed to identify and extract critical features distinguishing regular users from fraudulent users. Two different types of user data were used; Event Data and Screen Data, spanning over four weeks. A Principal Component Analysis (PCA) was applied to the Screen Data to reduce its dimensionality. Feature Engineering was conducted on both Event Data and Screen Data. A Random Forest model, a supervised ensemble method, was used for classification. The data was imbalanced due to a significant difference in number of frauds compared to regular users. Therefore, two different balancing methods were used: Oversampling (SMOTE) and changing the Probability Threshold (PT) for the classification model.  The best result was achieved with the resampled data where the threshold was set to 0,4. The result of this model was a prediction of 80,88% of actual frauds being predicted as such, while 0,73% of the regular users were falsely predicted as frauds. While this result was promising, questions are raised regarding the validity since there is a possibility that the model was over-fitted on the data set. An indication of this was that the result was significantly less accurate without resampling. However, the overall conclusion from the result was that this study shows an indication that it is possible to distinguish frauds from regular users, with or without resampling. For future research, it would be interesting to see data over a more extended period of time and train the model on real-time data to counter changes in fraudulent behaviour.

Because of the vast data volume of hyperspectral imagery, compression becomes a necessary process for hyperspectral data transmission, storage, and analysis. Three-dimensional discrete wavelet transform (DWT) based algorithms are particularly of interest due to their excellent rate-distortion performance. This thesis investigates several issues surrounding efficient compression using JPEG2000. Firstly, the rate-distortion performance is studied when Principal Component Analysis (PCA) replaces DWT for spectral decorrelation with the focus on the use of a subset of principal components (PCs) rather than all the PCs. Secondly, the algorithms are evaluated in terms of data analysis performance, such as anomaly detection and linear unmixing, which is directly related to the useful information preserved. Thirdly, the performance of compressing radiance and reflectance data with or without bad band removal is compared, and instructive suggestions are provided for practical applications. Finally, low-complexity PCA algorithms are presented to reduce the computational complexity and facilitate the future hardware design.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.