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 7 of 7 for “"Deep Embedded Clustering"”.
-
Explainable Deep Embedded Clustering for Scalable, Equity-conscious Alzheimer’s Disease Phenotyping: From Routine Clinical Data to Biomarker-enriched Precision Prevention
… scalable phenotyping framework for AD using deep embedded clustering (DEC) with SHAP explainability, applied across three aims. Aim 1 (Chapter II) applies DEC to 47 routinely captured clinical features in the Wisconsin Registry for Alzheimer's Prevention (WRAP; n = 1,491), identifying three …
-
SUICIDE SUBTYPING AND RISK PREDICTION USING UNSUPERVISED LEARNING APPROACHES ON HEALTH RECORDS DATA
… data-driven subtypes of suicide decedents using clustering methods applied to electronic health records and hospital discharge data, and to compare alternative approaches. Second, to identify longitudinal patterns by mining administrative claims and discharge data for recurrent ICD-coded clinical …
-
Outcome-driven deep clustering for cardiovascular subtyping
… interventions to improve cardiovascular health. Clustering patients based on both clinical profiles and outcome associations can resolve subpopulations with shared characteristics within heterogeneous samples, focusing on diagnostic and treatment strategies. We propose novel solutions that …
-
Improving Feature Learning Capability and Interpretability of Unsupervised Neural Networks
… Secondly, once such models are developed, a deeper understanding of ML models is necessary for humans to adapt and use such models. Real-world systems generate massive amounts of unlabeled data at rapid speed, limiting the usability of state-of-the-art supervised machine learning approaches. …
-
Advanced AI for Histopathological Whole Slide Image Classification and Captioning
… The redundant patches are removed by using deep embedded clustering to dynamically cluster the images and extracting representative images through a scalar dot attention mechanism. The graph is formed by constructing edges from similarity matrix, ensuring that each node is connected to its …
-
Deep clustering from novel perspectives
Les approches récentes de clustering profond consistent à effectuer conjointement un clustering sur les représentations latentes et un apprentissage profond de descripteurs basé sur deux stratégies d’entraînement : l’auto-supervision et la pseudo-supervision. Cependant, deux problèmes majeurs ont …
-
Investigating brain aging with Magnetic Resonance Imaging and Convolutional Neural Networks
… Previous neuroimaging studies have used deep learning algorithms to investigate structural biomarkers including volumetric, microstructural and focal ones, using both cross-sectional and longitudinal cohorts. In this thesis, I investigate deep learning methods for analysing structural …