Now showing items 1-6 of 6

    • Information Extraction from Radiology Reports for a Population Based Cancer Registry 

      Nguyen, Hoang Minh Dung (University of Sydney Graduate School of Engineering and IT School of Information Technologies, 2013-03-31)
      In a noisy corpus such as in clinical data, the text usually contains a large number of misspell words, abbreviations and acronyms that can be an obstacle to high quality information extraction and classification. Furthermore, ...
    • Large Margin Nearest Neighbors Classification With Privileged Information for Biometric Applications 

      He, Jingwen (University of Sydney Faculty of Engineering and Information Technologies School of Electrical and Information Engineering, 2018-07-02)
      In this thesis, a novel metric learning algorithm is proposed to improve face verification and person re-identification in RGB images by learning from RGB and Depth (RGB-D) training images. We address this problem by ...
    • Robust Multiple-Sensing-Modality Data Fusion for Reliable Perception in Outdoor Scenarios 

      Gerardo-Castro, Marcos Paul (University of Sydney Faculty of Engineering and Information Technologies School of Aerospace, Mechanical & Mechatronic Engineering, 2017-06-30)
      To be reliable in outdoor operations, perception systems should use a combination of sensing modalities, such as laser, radar, visual camera, or IR camera, since they respond differently to distinct environmental conditions. ...
    • Space-time modelling of soil moisture: prediction and forecasting for improved agricultural management 

      Manikku Acharige, Niranjan Sanjeeva Wimalathunge (University of Sydney Faculty of Science School of Life and Environmental Sciences, 2019-09-16)
      Knowledge of soil moisture is crucial in every agricultural system. Accurate soil moisture estimates are valuable guides to management decisions such as crop selection and estimation of yield potential. However, soil ...
    • Unmixing of hyperspectral data by incorporating spectral variability and spatial information 

      Uezato, Tatsumi (University of Sydney Faculty of Agriculture and Environment School of Aerospace, Mechanical & Mechatronic Engineering, 2016-08-15)
      Spectral unmixing enables quantitative information on the abundances of cover types to be estimated within each image pixel. Although many spectral unmixing methods have been developed, many of these cannot consider endmember ...
    • Variational Inference in Generalised Hyperbolic and von Mises-Fisher Distributions 

      Abeywardana, Sachinthaka (University of Sydney Faculty of Engineering and Information Technologies School of Information Technologies, 2015-12-17)
      Most real world data are skewed, contain more than the set of real numbers, and have higher probabilities of extreme events occurring compared to a normal distribution. In this thesis we explore two non-Gaussian distributions, ...