Browsing by Author "Hu, Zhihao"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Contributions to Efficient Statistical Modeling of Complex Data with Temporal Structures
    Hu, Zhihao (Virginia Tech, 2022-03-03)
    This dissertation will focus on three research projects: Neighborhood vector auto regression in multivariate time series, uncertainty quantification for agent-based modeling networked anagrams, and a scalable algorithm for multi-class classification. The first project studies the modeling of multivariate time series, with the applications in the environmental sciences and other areas. In this work, a so-called neighborhood vector autoregression (NVAR) model is proposed to efficiently analyze large-dimensional multivariate time series. The time series are assumed to have underlying distances among them based on the inherent setting of the problem. When this distance matrix is available or can be obtained, the proposed NVAR method is demonstrated to provides a computationally efficient and theoretically sound estimation of model parameters. The performance of the proposed method is compared with other existing approaches in both simulation studies and a real application of stream nitrogen study. The second project focuses on the study of group anagram games. In a group anagram game, players are provided letters to form as many words as possible. In this work, the enhanced agent behavior models for networked group anagram games are built, exercised, and evaluated under an uncertainty quantification framework. Specifically, the game data for players is clustered based on their skill levels (forming words, requesting letters, and replying to requests), the multinomial logistic regressions for transition probabilities are performed, and the uncertainty is quantified within each cluster. The result of this process is a model where players are assigned different numbers of neighbors and different skill levels in the game. Simulations of ego agents with neighbors are conducted to demonstrate the efficacy of the proposed methods. The third project aims to develop efficient and scalable algorithms for multi-class classification, which achieve a balance between prediction accuracy and computing efficiency, especially in high dimensional settings. The traditional multinomial logistic regression becomes slow in high dimensional settings where the number of classes (M) and the number of features (p) is large. Our algorithms are computing efficiently and scalable to data with even higher dimensions. The simulation and case study results demonstrate that our algorithms have huge advantage over traditional multinomial logistic regressions, and maintains comparable prediction performance.
  • Thumbnail Image
    Data analysis and modeling pipelines for controlled networked social science experiments
    Cedeno-Mieles, Vanessa; Hu, Zhihao; Ren, Yihui; Deng, Xinwei; Contractor, Noshir; Ekanayake, Saliya; Epstein, Joshua M.; Goode, Brian J.; Korkmaz, Gizem; Kuhlman, Christopher J.; Machi, Dustin; Macy, Michael; Marathe, Madhav V.; Ramakrishnan, Naren; Saraf, Parang; Self, Nathan (PLOS, 2020-11-24)
    There is large interest in networked social science experiments for understanding human behavior at-scale. Significant effort is required to perform data analytics on experimental outputs and for computational modeling of custom experiments. Moreover, experiments and modeling are often performed in a cycle, enabling iterative experimental refinement and data modeling to uncover interesting insights and to generate/refute hypotheses about social behaviors. The current practice for social analysts is to develop tailor-made computer programs and analytical scripts for experiments and modeling. This often leads to inefficiencies and duplication of effort. In this work, we propose a pipeline framework to take a significant step towards overcoming these challenges. Our contribution is to describe the design and implementation of a software system to automate many of the steps involved in analyzing social science experimental data, building models to capture the behavior of human subjects, and providing data to test hypotheses. The proposed pipeline framework consists of formal models, formal algorithms, and theoretical models as the basis for the design and implementation. We propose a formal data model, such that if an experiment can be described in terms of this model, then our pipeline software can be used to analyze data efficiently. The merits of the proposed pipeline framework is elaborated by several case studies of networked social science experiments.
  • Thumbnail Image
    Learning Common Knowledge Networks Via Exponential Random Graph Models
    Liu, Xueying; Hu, Zhihao; Deng, Xinwei; Kuhlman, Chris (ACM, 2023-11-06)
    Common knowledge (CK) is a phenomenon where each individual within a group knows the same information and everyone knows that everyone knows the information, infinitely recursively. CK spreads information as a contagion through social networks in ways different from other models like susceptibleinfectious- recovered (SIR) model. In a model of CK on Facebook, the biclique serves as the characterizing graph substructure for generating CK, as all nodes within a biclique share CK through their walls. To understand the effects of network structure on CKbased contagion, it is necessary to control the numbers and sizes of bicliques in networks. Thus, learning how to generate these CK networks (CKNs) is important. Consequently, we develop an exponential random graph model (ERGM) that constructs networks while controlling for bicliques. Our method offers powerful prediction and inference, reduces computational costs significantly, and has proven its merit in contagion dynamics through numerical experiments.
  • Thumbnail Image
    Potential impact of 5 years of ivermectin mass drug administration on malaria outcomes in high burden countries
    Marathe, Achla; Shi, Ruoding; Mendez-Lopez, Ana; Hu, Zhihao; Lewis, Bryan L.; Rabinovich, Regina; Chaccour, Carlos J.; Rist, Cassidy (2021-11)
    Introduction The global progress against malaria has slowed significantly since 2017. As the current malaria control tools seem insufficient to get the trend back on track, several clinical trials are investigating ivermectin mass drug administration (iMDA) as a potential additional vector control tool; however, the health impacts and cost-effectiveness of this new strategy remain unclear. Methods We developed an analytical tool based on a full factorial experimental design to assess the potential impact of iMDA in nine high burden sub-Saharan African countries. The simulated iMDA regimen was assumed to be delivered monthly to the targeted population for 3 months each year from 2023 to 2027. A broad set of parameters of ivermectin efficacy, uptake levels and global intervention scenarios were used to predict averted malaria cases and deaths. We then explored the potential averted treatment costs, expected implementation costs and cost-effectiveness ratios under different scenarios. Results In the scenario where coverage of malaria interventions was maintained at 2018 levels, we found that iMDA in these nine countries has the potential to reverse the predicted growth of malaria burden by averting 20-50 million cases and 36 000-90 000 deaths with an assumed efficacy of 20%. If iMDA has an efficacy of 40%, we predict between 40-99 million cases and 73 000-179 000 deaths will be averted with an estimated net cost per case averted between US$2 and US$7, and net cost per death averted between US$1460 and US$4374. Conclusion This study measures the potential of iMDA to reverse the increasing number of malaria cases for several sub-Saharan African countries. With additional efficacy information from ongoing clinical trials and country-level modifications, our analytical tool can help determine the appropriate uptake strategies of iMDA by calculating potential marginal gains and costs under different scenarios.
  • Thumbnail Image
    Studies on Sintering Silicon Carbide-Nanostructured Ferritic Alloy Composites for Nuclear Applications
    Hu, Zhihao (Virginia Tech, 2016-07-22)
    Nanostructured ferritic alloy and silicon carbide composite materials (NFA-SiC) were sintered with spark plasma sintering (SPS) method and systematically investigated through X-ray diffraction (XRD), scanning electron microscopy (SEM), as well as density and Vickers hardness tests. Pure NFA, pure SiC, and their composites NFA-SiC with different compositions (2.5 vol% NFA-97.5 vol% SiC, 5 vol% NFA-95 vol% SiC, 97.5 vol% NFA-2.5 vol% SiC, and 95 vol% NFA-5 vol% SiC) were successfully sintered through SPS. In the high-NFA samples, pure NFA and NFA-SiC, minor gamma-Fe phase formation from the main alfa-Fe matrix occurred in pure NFA 950 degree C and 1000 degree C. The densities of the pure NFA and NFA-SiC composites increased with sintering temperature but decreased with SiC content. The Vickers hardness of the pure NFA and NFA-SiC composites was related to density and phase composition. In the high-SiC samples, NFA addition of 2.5 vol% can achieve full densification for the NFA-SiC samples at relative low temperatures. With the increase in sintering temperature, the Vickers hardness of the pure SiC and NFA-SiC composite samples were enhanced. However, the NFA-SiC composites had relative lower hardness than the pure SiC samples. A carbon layer was introduced in the NFA particles to prevent the reaction between NFA and SiC. Results indicated that the carbon layer was effective up to 1050 degree C sintering temperature. Green samples of gradient-structured NFA-SiC composites were successfully fabricated through slip casting of an NFA-SiC co-suspension.