Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 15 of 15 for “"Data shift"”.
-
A Robust Data-Driven Framework for Artificial Intelligent Systems
… a critical concern, particularly in terms of data and model reliability. This dissertation aims to address the challenges associated with building robust AI systems by focusing on two key aspects: data robustness and model robustness. Data robustness poses significant challenges, including …
-
Development of drift-adaptive machine learning methods to support health desicion making in dynamic data contexts
… is often challenged by the phenomenon of data shift, referring to the deviation between the data distributions used for training and those encountered during real-world deployment. Data shifts may arise from temporal dynamics or from changes in data acquisition conditions, leading to …
-
A Quality Assurance Pipeline for Deep Learning Segmentation Models for Radiotherapy Applications
… outcomes. Due to the rapid growth in patient data and the advanced DL techniques, increased attention has been paid to the clinical application of machine learning (ML) and DL1,2 and commercial software has been integrated into clinical workflows in some applications. However, in a clinical …
-
Indirect effects of fire on the small mammal community of a tallgrass blackland prairie remnant in Texas.
… maintained capture rates similar to pre-burn data. Shift in species composition has occurred from Baiomys taylori and Sigmodon hispidus to Peromyscus maniculatus, suggesting short-term fire response of small mammals in tallgrass prairies. This secondary successional cycle of 7 months suggests …
-
Development and evaluation of various scan-path storage cells
… soft-macro cells which include a multiplexed data shift-register latch, a two-port shift-register latch, a raceless two-port storage flip-flop, and a transmission gate based storage flip flop were mapped into silicon. The transmission gate storage cell's physical layout was also done manually …
-
Classify-normalize-classify : a novel data-driven framework for classifying forest pixels in remote sensing images
… requires the analysis of a large amount of image data, often collected by orbital remote sensing platforms. However, variations in the observed signals due to changing atmospheric conditions often result in a data distribution shift for different dates and locations making it difficult to …
-
Statistical Evaluation of Deep Learning for Event Detection in Time Series: Quantifying Uncertainty, Efficiency, and Adaptation with Applications to Seismic Data
… a few performance metrics computed on benchmark datasets, which ignores important questions about how predictive performance varies with data availability, how uncertainty is communicated in both predictions and aggregate metrics, and how shifting data distributions impact model reliability. …
-
Towards Robust and Generalizable Machine Learning for Real-World Healthcare Data with Heterogeneity
… has enable artificial intelligence with abundant data to train. In return the trained models have shown to lower the uncertainty in clinical decision making. However, as always, with opportunities comes new challenges. We have observed many discrepancies of compatibility between sophisticated …
-
Treemaps: Visualizing Hierarchical and Categorical Data
… visualization of hierarchical and categorical data sets. Treemap presentations of data shift mental workload from the cognitive to the perceptual systems, taking advantage of the human visual processing system to increase the bandwidth of the human-computer interface. Efficient use of display …
-
Domain Adaptation for Remote Sensing Using Deep Learning
… these techniques require sufficient training data to be available for every particular image. Obtaining training samples is challenging, particularly for near real-time applications. Therefore, past knowledge must be utilized to overcome the lack of training data in the current regime. This …
-
Advancing characterization techniques for structure-property determination of in-situ lignocelluloses
… TTS reveals that while all storage modulus data shift smoothly, the thermorheological complexity of solvent-plasticized wood becomes evident in loss component master curves. It is argued that the plasticized lignocellulose TTS is insightful and potentially useful, although it fails to …
-
Low-Resource Neural Adaptation: A Unified Data Adaptation Framework for Neural Networks
… learning (ML) models are trained on specific datasets for specific tasks. While traditional transfer learning can adapt to new datasets when labeled data are adequate, adapting to small datasets is still a challenging task. Researchers have applied multi-task learning, meta-learning, …
-
Estimation of inter-area oscillations in the Nordic power system using dynamic mode decomposition
… ability to recognise known structures in data. Statistical tests were performed to chart the noise-sensitivity of DMD with respect to changes in sampling rate, data shift-stacking, the number of data channels, and the length of the analysis window. DMD was implemented with a randomised …
-
Robust learning to rank models and their biomedical applications
… errors in labeling or annotation, distributional data shift, or adversarial data perturbations. To fill this gap, we develop four LTR frameworks that are robust to various types of perturbations. First, Pairwise Elastic Net Regression Ranking (PENRR) is an elastic-net-based regression method for …
-
Impedance modelling and stability analysis of power grid-connected inverter-based resources
… method using perturbation and observation, a data-driven automation method for clustering and aggregation of multiple operating point impedance models, and a data-driven automation method using a Bayesian optimisation method to determine stability boundary. The two impedance-based modelling …