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 20 of 153 for “"Data heterogeneity"”.
-
PENS: Leveraging Data Heterogeneity in Federated Learning
… weights or gradients instead of sharing the raw data between the cooperating devices (clients). Classical FL algorithms such as federated averaging work best in the special case when the data is IID over clients. In this work, we address the problem of data heterogeneity in federated learning. We …
-
Healthcare data heterogeneity and its contribution to machine learning performance
[EN] The data quality assessment has many dimensions, from those so obvious as the data completeness and consistency to other less evident such as the correctness or the ability to represent the target population. In general, it is possible to classify them as those produced by an external effect, …
-
AEBS Event Classification Under Data Heterogeneity and Limited Trusted Labels
… and privacy-sensitive. In addition, event data may exhibit distributional heterogeneity across operating contexts. This thesis investigates AEBS full-braking event classification under these challenges of data heterogeneity and limited trusted labels. The study uses logged full-braking …
-
Addressing data heterogeneity, scarcity, and training efficiency in privacy-preserving federated learning
… (DNNs) relies heavily on access to large-scale datasets, which can be difficult for individual organizations to acquire. The reasons behind are the complexities and costs for data collection and annotation at large scale. A straightforward solution is to centralize data from multiple …
-
TACKLING MODERN CHALLENGES IN STATISTICS: INTEGRATING PRIVACY, DISTRIBUTED LEARNING, AND DATA HETEROGENEITY
In modern statistical applications, data are increasingly distributed across multiple sources, such as hospitals, mobile devices, and research institutions, and often contain sensitive information subject to privacy constraints. This decentralized and privacy-sensitive landscape poses fundamental …
-
DATA HETEROGENEITY IN SINGLE PARTICLE IMAGING EXPERIMENT WITH X-RAY FREE ELECTRON LASER
… particle imaging (SPI). The difficulty in SPI data analysis mainly comes from two kinds of latent unmeasured variables in datasets: orientational heterogeneity caused by randomly oriented particles and structural heterogeneity within an ensemble. While the missing-orientation problem can be …
-
Mitigating effects of data heterogeneity in decentralized learning and addressing challenges of adapting foundation models
… two main topics: Chapters 2 and 3 address data heterogeneity in decentralized and federated learning, while Chapters 4 and 5 focus on the adaptation and optimization of the Segment Anything Model (SAM), a foundation model for image segmentation. We begin by tackling the challenges …
-
Contributions for Handling Big Data Heterogeneity. Using Intuitionistic Fuzzy Set Theory and Similarity Measures for Classifying Heterogeneous Data
A huge amount of data is generated daily by digital technologies such as social media, web logs, traffic sensors, on-line transactions, tracking data, videos, and so on. This has led to the archiving and storage of larger and larger datasets, many of which are multi-modal, or contain different …
-
Contributions for Handling Big Data Heterogeneity. Using Intuitionistic Fuzzy Set Theory and Similarity Measures for Classifying Heterogeneous Data
A huge amount of data is generated daily by digital technologies such as social media, web logs, traffic sensors, on-line transactions, tracking data, videos, and so on. This has led to the archiving and storage of larger and larger datasets, many of which are multi-modal, or contain different …
-
Learning From Heterogeneous Data
Data with both heterogeneity and homogeneity is now ubiquitous due to the development of multitudinous data collection techniques. To encode the data heterogeneity and homogeneity, we focus on unsupervised and supervised learning approaches. In unsupervised learning, to consider both data …
-
Domain Adaptation Using Temporal Relation Knowledge in Cross-user Sensor-based Human Activity Recognition
… state-of-the-art sensor-based HAR methods assume data homogeneity, meaning all data are considered independent and identically distributed (i.i.d.). However, practical sensor data of human activity are often heterogeneous or out-of-distribution (o.o.d.), violating this assumption. Addressing data …
-
Exploring heterogeneity and resource constraints in federated learning
… deep learning models is having abundant training data. This often requires collecting data from multiple sources (clients), which may violate data protection regulations. Federated learning (FL) provides a training paradigm where clients collaboratively train a global model while keeping data …
-
Flexible Models for Heterogeneous Biomedical Data
… development of biomedical sensing techniques and data storage, machine learning has been widely applied to many healthcare applications from the abundance of data resources. However, biomedical data, from real-world applications, has the nature of heterogeneity, and this heterogeneity has not been …
-
Flexible Models for Heterogeneous Biomedical Data
… development of biomedical sensing techniques and data storage, machine learning has been widely applied to many healthcare applications from the abundance of data resources. However, biomedical data, from real-world applications, has the nature of heterogeneity, and this heterogeneity has not been …
-
ADAPTIVE COMMUNICATION-EFFICIENT FEDERATED LEARNING ON REAL-WORLD DATA
… intelligent services while addressing data isolation and user privacy issues. The key idea is that clients can collaboratively train machine learning models without sharing data. As federated learning achieves collaborative learning in a privacy-preserving manner, it attracts …
-
Integrating horizontal borehole imagery and cluster analysis with microseismic data for Niobrara/Codell reservoir characterization, Wattenberg field, Colorado, USA
… multi-variate problems requiring integration of data across multiple disciplines. Integration of multi-scale data to solve shale plays has become increasingly more common (\citet{roth2010}, \citet{norton2011}, \citet{quirein2012}, \citet{xie2012}, \citet{close2012}). In this thesis I examine …
-
Enabling trustworthy and scalable collaborative learning systems
… and smart home devices, produce vast amounts of data that can be used to train machine learning models for various prediction and inference tasks. As the computational capabilities of these devices grow, and due to increasing concerns about privacy, there has been growing interest in locally …
Page 1 of 8