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 22 for “"Data pipeline"”.
-
Data pipeline refactoring for Dohop
… providers. Dohop utilizes Looker Studio for data visualization and business analytics, however, due to experiencing limitations in the creation and deployment of dashboards for data visualization, they have started to consider whether a better alternative exists. Thus, they are tasking us …
-
Accelerating deep learning training : a storage perspective
… new ways, moving the training bottleneck to the data pipeline (fetching, pre-processing data, and writing checkpoints), rather than computation at the GPUs; this leaves the expensive accelerator devices stalled for data. While prior research has explored different ways of accelerating DNN …
-
Uncertainty Quantification in Security Aware Data Pipelines
… systems, the diversity and volume of data have expanded. Proper management of sensitive information collected and processed through data pipelines is crucial. Traditional data pipelines usually perform error analysis of the final pipeline output after a detection model. As a result, …
-
The Applications of Raman Spectroscopy Assisted Urinalysis: Hematuria and Bladder Cancer Detection
… wide-ranging applicability due to the holistic data capturing nature of the scanning technique. Each Raman scan can be considered a 'snapshot' of the molecular makeup of the sample, and, through proper applications of algorithmic transformation and statistical analysis, many types of assessments …
-
Modeling the Performance and Resource Requirements for Gamma-Ray Telescope Signal Processing
… investigates the buffering requirements of the data pipeline for the Advanced Particle-astrophysics Telescope gamma-ray telescope. Given the importance and stochastic arrivals of astronomical signals, it is crucial to ensure that each gamma-ray signal is fully buffered to prevent data loss. To …
-
Energy load prediction for Open Charge Point Protocol - compliant electric vehicle charging stations
… Station Management System (CSMS) and end-to-end data pipeline to enable short-term energy forecasting for individual EV charging stations. The system captures and processes OCPP transactions in PostgreSQL, deriving per-session energy for consistent forecasting targets. Using this platform, four …
-
Algorithmically supported moderation in children's online communities
… the first of its kind. To produce the corpus of data, we introduce a comment moderation website that allows for the review and label of comments. The web-tool acts as a data-pipeline, designed to keep the machine learning models up to date with new forms of inappropriate content and to reduce the …
-
SUPPORTING COMPANIES IN THEIR DIGITAL TRANSITION TO SMART MANUFACTURING SYSTEMS
… to keep not only design, but also production data in-house, to protect industrial secrets, prevents the export of production or design data to external cloud services. Second, the need to keep using specially tailored legacy machines, which are not I4.0 compliant by design, leads to the lack …
-
Development of an End-to-End Pipeline for Custom Key-Value Extraction from Commercial Invoices
… in accomplishing tasks unique to a particular dataset and its associated complications. Using sample documents provided by a leading electronic component distributor, we researched different approaches capable of extracting key-value information from a complex dataset of invoices. The thesis …
-
A Bidirectional Pipeline for Semantic Interaction in Visual Analytics
Semantic interaction in visual data analytics allows users to indirectly adjust model parameters by directly manipulating the output of the models. This is accomplished using an underlying bidirectional pipeline that first uses statistical models to visualize the raw data. When a user interacts …
-
Fast and Scalable Subgraph Learning
… powerful framework for learning over structured data, enabling predictive modeling across domains such as bioinformatics, recommendation systems, and financial fraud detection. While scalable systems like SALIENT++ have advanced the training of node-level GNN tasks at industrial scale, they do …
-
A Framework for Generalizing Uncertainty in Mobile Network Traffic Prediction
… sub-behaviors within aggregates of network data. This method produces distributions that are more robust towards changes in the spatio-temporal environment. The ensemble of time-series prediction models trained on these distributions posses a greater affinity towards accurate network …
-
How Enhanced Data Availability Affects Multi-Channel Marketing Attribution
… analyze the results of these channels. However, data is not always entered in these applications as cleanly as possible and work to integrate the data from these tools is not always prioritized. In order to support prioritization efforts, management would need an example case study to prove how …
-
Autonomous wireless smart sensor for monitoring of railroad bridges
… the need for a human-in-the-loop for remote data retrieval and post-processing. An adaptive strategy combining an event-based scheme, scheduled rendezvous framework, and preemptive multitasking operation is implemented in the proposed system. The robust monitoring strategy is designed to …
-
The Development and Deployment of Sensors and Algorithms for the Mobile Monitoring of Urban Surface Water Quality
… quality within the Amsterdam canal network. The data provide encouraging evidence that opportunistic measurements from a small number of mobile platforms can enable high-resolution mapping and can be used to improve modeling and control of water quality across the city. In the second and third …
-
Assisting Technology: Disability Expertise and Labor in Artificial Intelligence (AI) Data Work in China
… and NGOs to classify and label training data for AI systems. This thesis offers an ethnographic account of one of these programs, combining insights from science and technology studies (STS), critical disability studies, and digital labor scholarship. Run by a disabled persons’ …
-
Probing diffuse galactic synchrotron emission using meerkat single dish data
… experiment, from the L-band (900-1670 MHz) data the 21 cm signal was probed using the single dish mode. However, initially the RFI and the most dominant foreground in our Galaxy which is the synchrotron emission had to be investigated, so they could be removed. This process also provided …
-
Membership Diversity and Tactical Adaptation within Violent Non-State Organizations
… measure tactical adaptation, employing a text as data pipeline to classify and numerically compare descriptions of violent events. It then argues develops a theory of membership diversity as an internal driver of tactical adaptation. The theory emphasizes the stochastic elements that underpin …
-
From data to model behaviour: A causal and empirical analysis of how data shapes the behaviour of language models
… algorithms, but fundamentally by their training data---what examples they see, how those examples are represented, when they encounter them, and how much influence individual examples (or batches of examples) exert. Despite the critical role of training data, a systematic understanding of how …
-
A clinical role for fluid dynamics modelling of arteriovenous fistulae
… 3D geometry scanning methodology, as well as a data pipeline for generation of PS-CFD models. A diverse range of patients with AVFs were scanned during a one year period, from which eight different patient cases were formed, capturing events across multiple scans over varying timelines. …
Page 1 of 2