Despite years of research, there are still some unsolved problems on semantic attribute learning. First, real-world applications usually involve hundreds of attributes which requires great effort to acquire sufficient amount of labeled data for model learning. Second, existing attribute learning work for visual objects focuses primarily on images, with semantic analysis on videos left largely unexplored.
In this dissertation I conduct innovative research and propose novel approaches to tackling the aforementioned problems. In particular, I propose robust and accurate learning frameworks on both attribute ranking and prediction by exploring the correlation among multiple attributes and utilizing various types of label information. Furthermore, I propose a video-based skill coaching framework by extending attribute learning to the video domain for robust motion skill analysis. Experiments on various types of applications and datasets and comparisons with multiple state-of-the-art baseline approaches confirm that my proposed approaches can achieve significant performance improvements for the general attribute learning problem.
Trees serve as a natural umbrella to mitigate insolation absorbed by features of the urban environment, especially building structures and pavements. For a desert community, trees are a particularly valuable asset because they contribute to energy conservation efforts, improve home values, allow for cost savings, and promote enhanced health and well-being. The main obstacle in creating a sustainable urban community in a desert city with trees is the scarceness and cost of irrigation water. Thus, strategically located and arranged desert trees with the fewest tree numbers possible potentially translate into significant energy, water and long-term cost savings as well as conservation, economic, and health benefits. The objective of this dissertation is to achieve this research goal with integrated methods from both theoretical and empirical perspectives.
This dissertation includes three main parts. The first part proposes a spatial optimization method to optimize the tree locations with the objective to maximize shade coverage on building facades and open structures and minimize shade coverage on building rooftops in a 3-dimensional environment. Second, an outdoor urban physical scale model with field measurement is presented to understand the cooling and locational benefits of tree shade. The third part implements a microclimate numerical simulation model to analyze how the specific tree locations and arrangements influence outdoor microclimates and improve human thermal comfort. These three parts of the dissertation attempt to fill the research gap of how to strategically locate trees at the building to neighborhood scale, and quantifying the impact of such arrangements.
Results highlight the significance of arranging residential shade trees across different geographical scales. In both the building and neighborhood scales, research results recommend that trees should be arranged in the central part of the building south front yard. More cooling benefits are provided to the building structures and outdoor microclimates with a cluster tree arrangement without canopy overlap; however, if residents are interested in creating a better outdoor thermal environment, open space between trees is needed to enhance the wind environment for better human thermal comfort. Considering the rapid urbanization process, limited water resources supply, and the severe heat stress in the urban areas, judicious design and planning of trees is of increasing importance for improving the life quality and sustaining the urban environment.
the ability to accurately edit genomes at scale has remained elusive. Novel techniques
have been introduced recently to aid in the writing of DNA sequences. While writing
DNA is more accessible, it still remains expensive, justifying the increased interest in
in silico predictions of cell behavior. In order to accurately predict the behavior of
cells it is necessary to extensively model the cell environment, including gene-to-gene
interactions as completely as possible.
Significant algorithmic advances have been made for identifying these interactions,
but despite these improvements current techniques fail to infer some edges, and
fail to capture some complexities in the network. Much of this limitation is due to
heavily underdetermined problems, whereby tens of thousands of variables are to be
inferred using datasets with the power to resolve only a small fraction of the variables.
Additionally, failure to correctly resolve gene isoforms using short reads contributes
significantly to noise in gene quantification measures.
This dissertation introduces novel mathematical models, machine learning techniques,
and biological techniques to solve the problems described above. Mathematical
models are proposed for simulation of gene network motifs, and raw read simulation.
Machine learning techniques are shown for DNA sequence matching, and DNA
sequence correction.
Results provide novel insights into the low level functionality of gene networks. Also
shown is the ability to use normalization techniques to aggregate data for gene network
inference leading to larger data sets while minimizing increases in inter-experimental
noise. Results also demonstrate that high error rates experienced by third generation
sequencing are significantly different than previous error profiles, and that these errors can be modeled, simulated, and rectified. Finally, techniques are provided for amending this DNA error that preserve the benefits of third generation sequencing.
This thesis develops a classification method to investigate the performance of FDG-PET as an effective biomarker for Alzheimer's clinical group classification. This involves dimensionality reduction using Probabilistic Principal Component Analysis on max-pooled data and mean-pooled data, followed by a Multilayer Feed Forward Neural Network which performs binary classification. Max pooled features result into better classification performance compared to results on mean pooled features. Additionally, experiments are done to investigate if the addition of important demographic features such as Functional Activities Questionnaire(FAQ), gene information helps improve performance. Classification results indicate that our designed classifiers achieve competitive results, and better with the additional of demographic features.
In this dissertation, I carry out the research along the direction with particular focuses on scaling up the optimization of sparse learning for supervised and unsupervised learning problems. For the supervised learning, I firstly propose an asynchronous parallel solver to optimize the large-scale sparse learning model in a multithreading environment. Moreover, I propose a distributed framework to conduct the learning process when the dataset is distributed stored among different machines. Then the proposed model is further extended to the studies of risk genetic factors for Alzheimer's Disease (AD) among different research institutions, integrating a group feature selection framework to rank the top risk SNPs for AD. For the unsupervised learning problem, I propose a highly efficient solver, termed Stochastic Coordinate Coding (SCC), scaling up the optimization of dictionary learning and sparse coding problems. The common issue for the medical imaging research is that the longitudinal features of patients among different time points are beneficial to study together. To further improve the dictionary learning model, I propose a multi-task dictionary learning method, learning the different task simultaneously and utilizing shared and individual dictionary to encode both consistent and changing imaging features.