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 “"dataset collection"”.

  1. Empirical Investigations and Dataset Collection for American Sign Language-aware Personal Assistants

    … recognition technologies. 2. Part II: Dataset Collection With the context that there is a ASL data bottleneck for these technologies, this part investigates remote ASL data collection at scale, creating an online sign language data collection platform and testing its viability. …

    rit Repository record for Empirical Investigations and Dataset Collection for American Sign Language-aware Personal Assistants (opens in a new tab)

  2. Multilingual Spoken Language Understanding: Efficient Speech Dataset Collection, Architectural Exploration, and Zero-Shot SLU

    … Speech Translation (ST), publicly available SLU datasets are limited to 760 hours across multiple languages, with only 300 hours of real human speech. To address this, I developed a multilingual SLU dataset covering 12 languages with human recordings. During crowd-sourced SLU data collection, I …

    trento Repository record for Multilingual Spoken Language Understanding: Efficient Speech Dataset Collection, Architectural Exploration, and Zero-Shot SLU (opens in a new tab)

  3. NLP Crowdsourcing for Predominantly Oral Languages: The Case of Bambara

    … readily available machine learning (ML) datasets. We investigate methods to overcome this data scarcity for Bambara, a Manding language, spoken primarily in Mali, with a rich oral tradition but limited digital presence. The research leverages crowdsourcing and community engagement to …

    rit Repository record for NLP Crowdsourcing for Predominantly Oral Languages: The Case of Bambara (opens in a new tab)

  4. Improved Detection of Recyclable Plastics Using Multi Modal Sensing and Machine Learning

    … images of real-world plastics for plastic image dataset collection. In this thesis, I have split my work into five chapters explaining my contribution in each chapter for plastic classification and sensor development and described my future work in chapter 6 involving development of a prototype …

    buffalo Repository record for Improved Detection of Recyclable Plastics Using Multi Modal Sensing and Machine Learning (opens in a new tab)

  5. Automobilių atpažinimas iš vaizdo srauto /

    … inspection. This work describes vehicle dataset collection, preparation and ways of training image recognition model which gives the impression of needed tools, important facts, training parameters and possible improvements. Noted that it is neccessary to carefully test and remove all …

    vilnius Repository record for Automobilių atpažinimas iš vaizdo srauto / (opens in a new tab)

  6. Experimental Evaluation of Radar-Based Velocity Estimation for Navigation in GNSS-Denied Environments

    … This thesis develops a multi-sensor data collection platform to enable radar-inertial algorithm development. Datasets are collected in various environments and include raw LiDAR, radar, and IMU data along with corresponding ground truth. Using these datasets, this work evaluates …

    vt Repository record for Experimental Evaluation of Radar-Based Velocity Estimation for Navigation in GNSS-Denied Environments (opens in a new tab)

  7. Efficient modularity density heuristics in graph clustering and their applications

    … by using graphs from the “Stanford Large Network Dataset Collection”. The experiments have shown that our eight heuristics found solutions for graphs with hundreds of thousands of nodes. Our results have also shown that five of our heuristics surpassed the current state-of-the-art Modularity …

    brazil-ufrgs Repository record for Efficient modularity density heuristics in graph clustering and their applications (opens in a new tab)

  8. Towards Leveraging Sparse Infrared Datasets for Multiple View Synthesis, Few Shot Learning and Background Invariant Recognition

    … have not been fully addressed. Infrared dataset collection and annotation is both difficult and expensive. What if there is a way we can generate infrared images and diminish the need for collecting data out in the field? Our first research study encompasses an encoder-decoder model that …

    ucf Repository record for Towards Leveraging Sparse Infrared Datasets for Multiple View Synthesis, Few Shot Learning and Background Invariant Recognition (opens in a new tab)

  9. Security and privacy in speaker recognition systems

    … we explore a new method for collecting biometric datasets. We design, implement and evaluate a system for collecting these datasets remotely. This allows researchers to scale their dataset collection more effectively, allowing for the creation of larger and more useful biometric datasets in the …

    oxford Repository record for Security and privacy in speaker recognition systems (opens in a new tab)

  10. Learning Context-sensitive Human Emotions in Categorical and Dimensional Domains

    … cess, however, their dependency on large-scale datasets labeled with (1) emotion, and (2) valence, arousal and dominance, in categorical and dimensional domains respectively, introduce challenges the community tries to tackle. Emotions offer dissimilar semantics when aroused in different con- …

    ucf Repository record for Learning Context-sensitive Human Emotions in Categorical and Dimensional Domains (opens in a new tab)

  11. Towards scalable data model for curation and reusable workflows for porous media image analysis

    … computed tomography, has provided a wealth of datasets that can be used for the characterization of porous media such as rocks and soil. We first introduce image processing techniques commonly used in porous media analysis, including state-of-the-art machine learning (ML) techniques in Section …

    texas Repository record for Towards scalable data model for curation and reusable workflows for porous media image analysis (opens in a new tab)

  12. Label-efficient learning for medical images

    … tasks, the requirement of large-scale annotated datasets hinders many of their real-world applications. In the management of prostate cancer, where segmentation and registration of lower-pelvic imaging play indispensable roles in various stages, automation of these tasks is limited by the …

    oxford Repository record for Label-efficient learning for medical images (opens in a new tab)

  13. Unbiased phishing detection using domain name based features

    … for extracting feature and keeping the dataset updated nor an updated dataset of phishing and legitimate website. The second concern is the large number of features used and the lack of validating arguments for the choice of the features selected to train the machine learning classifier. …

    colostate Repository record for Unbiased phishing detection using domain name based features (opens in a new tab)

  14. Visible Light Positioning for Robotic Navigation

    … the absence of large-scale, high-quality datasets for algorithm development and evaluation, and the lack of evidence demonstrating that VLP can support practical robotic navigation. This thesis addresses both challenges through a set of proposed frameworks supported by experimental …

    auckland-tech Repository record for Visible Light Positioning for Robotic Navigation (opens in a new tab)

  15. From Correlation to Causality: Does Network Information improve Cancer Outcome Prediction?

    … solely tested their methods on a small amount of datasets, questioning the general applicability of network-based methods for outcome prediction. Methods: In this thesis, I provide a comprehensive and systematically evaluation of a network-based outcome prediction approach -- NetRank - a PageRank …

    qucosa-diss

  16. Machine learning powered insights into metamaterial prediction and design

    … and can break down when evaluated on test datasets that violate the i.i.d. assumption. In contrast, out-of-distribution (OOD) generalization approaches assume that the data contained in test environments are allowed to shift. To date, multiple methods have been proposed to improve the OOD …

    bu Repository record for Machine learning powered insights into metamaterial prediction and design (opens in a new tab)

  17. Design and Development of Tactile Robot Hands for Enhanced Dexterous Manipulation

    … the sensor eliminates the need for extensive dataset collection and can be utilized immediately after a simple calibration process. <br/><br/>This thesis focuses on the electromechanical system design of tactile robotic hands. It proposes a new classification method and a novel 3D printing …

    bristol Repository record for Design and Development of Tactile Robot Hands for Enhanced Dexterous Manipulation (opens in a new tab) Download PDF for Design and Development of Tactile Robot Hands for Enhanced Dexterous Manipulation (opens in a new tab)

  18. Electromyography-based Biometrics for Secure and Robust Personal Identification and Authentication

    … study (Chapter 5) a multi-day and large-sample dataset collection was performed to address these limitations. For the research study, EMG data was collected from 43 participants over three different days with long separation (Days 1, 8, and 29) while performing 16 different static hand/wrist …

    waterloo Repository record for Electromyography-based Biometrics for Secure and Robust Personal Identification and Authentication (opens in a new tab)

  19. Towards Open Energy System Modelling Infrastructure for the Australian National Electricity Market

    … – the network of people, software, and datasets which supports energy system modelling tasks – remains reliant on closed-source, expensive, proprietary software. This thesis aims to further the development of open modelling infrastructure for the NEM – an infrastructure based on open …

    unsw Repository record for Towards Open Energy System Modelling Infrastructure for the Australian National Electricity Market (opens in a new tab)

Page 1 of 2