This collection includes most of the ASU Theses and Dissertations from 2011 to present. ASU Theses and Dissertations are available in downloadable PDF format; however, a small percentage of items are under embargo. Information about the dissertations/theses includes degree information, committee members, an abstract, supporting data or media.
In addition to the electronic theses found in the ASU Digital Repository, ASU Theses and Dissertations can be found in the ASU Library Catalog.
Dissertations and Theses granted by Arizona State University are archived and made available through a joint effort of the ASU Graduate College and the ASU Libraries. For more information or questions about this collection contact or visit the Digital Repository ETD Library Guide or contact the ASU Graduate College at gradformat@asu.edu.
The theme for this work is the development of fast numerical algorithms for sparse optimization as well as their applications in medical imaging and source localization using sensor array processing. Due to the recently proposed theory of Compressive Sensing (CS), the $\ell_1$ minimization problem attracts more attention for its ability…
The theme for this work is the development of fast numerical algorithms for sparse optimization as well as their applications in medical imaging and source localization using sensor array processing. Due to the recently proposed theory of Compressive Sensing (CS), the $\ell_1$ minimization problem attracts more attention for its ability to exploit sparsity. Traditional interior point methods encounter difficulties in computation for solving the CS applications. In the first part of this work, a fast algorithm based on the augmented Lagrangian method for solving the large-scale TV-$\ell_1$ regularized inverse problem is proposed. Specifically, by taking advantage of the separable structure, the original problem can be approximated via the sum of a series of simple functions with closed form solutions. A preconditioner for solving the block Toeplitz with Toeplitz block (BTTB) linear system is proposed to accelerate the computation. An in-depth discussion on the rate of convergence and the optimal parameter selection criteria is given. Numerical experiments are used to test the performance and the robustness of the proposed algorithm to a wide range of parameter values. Applications of the algorithm in magnetic resonance (MR) imaging and a comparison with other existing methods are included. The second part of this work is the application of the TV-$\ell_1$ model in source localization using sensor arrays. The array output is reformulated into a sparse waveform via an over-complete basis and study the $\ell_p$-norm properties in detecting the sparsity. An algorithm is proposed for minimizing a non-convex problem. According to the results of numerical experiments, the proposed algorithm with the aid of the $\ell_p$-norm can resolve closely distributed sources with higher accuracy than other existing methods.
With the continuous development of the Chinese capital market over the past thirty years, the securities analyst industry has experienced a process of transformation from a reckless period to a golden time. One of the most important signals is that securities analysts are increasingly conducting research report providing long-term earnings…
With the continuous development of the Chinese capital market over the past thirty years, the securities analyst industry has experienced a process of transformation from a reckless period to a golden time. One of the most important signals is that securities analysts are increasingly conducting research report providing long-term earnings forecasts for the company. However, current research on analysts is limited to their short-term forecasting behavior, and there is little on analysts' long-term earnings forecasts. Therefore, this article takes the research on analysts' long-term forecast reports issued by analysts on A-share listed companies, and conducts an empirical study on the analysts' forecasts accuracy and its influencing factors. First, the author combed the research literature related to analyst forecasts and selected variables from three dimensions, including company characteristics (financial indicators and non-financial indicators), analyst characteristics and affiliated institution characteristics; secondly, considering the high-dimensionality of the influencing factors, this paper uses the method of combining machine learning and traditional regression to conduct empirical research; finally, the research tested the heterogeneity of influencing factors from two perspectives, including time and industry.The results of this article show that the long-term profit forecasts of analysts in China have advantages over traditional statistical models. More than 60% of analysts
provide profit forecasts that are better than statistical models. Afterwards, when examining the factors that affected the accuracy of analysts’ forecasts, it found that although analyst and institutional characteristics affected analysts’ predictions to a certain extent, company characteristics are the most important variables among them all. As the time goes by, the influence of non-financial factors on forecast accuracy gradually decreasing, but analyst characteristics continue to strengthen. In addition, cyclical industries are more difficult to predict than companies in non-cyclical industries, and the difficulty of prediction will not be reduced with the analyst efforts. This research can help analysts optimizing their forecasting behavior and prompts investors to understand analysts' reports more deeply, which makes them using analyst forecast data to make investment decisions in a rationally ways, and it can also help to promote the securities pricing efficiency and development of Chinese capital market.