Browsing by Author "Xia, Long"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Design and Synthesis of Doxorubicin Conjugated Gold Nanoparticles as Anticancer Drug Delivery System
    Xia, Long (Virginia Tech, 2016-06-24)
    Doxorubicin is one of the most widely used and effective anticancer agents to treat a wide spectrum of tumors. But its success in cancer therapy is greatly compromised by its cumulative dose-dependent side effects of cardiotoxicity and tumor cell resistance. For the purpose of addressing these side effects, a gold nanoparticles-based anticancer drug delivery system was designed. Five novel thiolated doxorubicin analogs were designed and synthesized and their biological activities have been evaluated. These doxorubicin analogs and the poly(ethylene glycol) (PEG) stabilizing ligands were conjugated to gold nanoparticles via formation of a gold-thiol bond. The systems were evaluated in vitro and in vivo, and the results show that controlled drug release can be achieved either by acidic conditions or by reducing agents in cancer cells, depending on the design of the thiolated drug construct. The overall drug delivery system should achieve enhanced drug accumulation and retention in cancer cells and favorable drug release kinetics, and should demonstrate therapeutic potential and the ability to address some of the current problems of doxorubicin in cancer therapy.
  • Thumbnail Image
    Human Learning-Augmented Machine Learning Frameworks for Text Analytics
    Xia, Long (Virginia Tech, 2020-05-18)
    Artificial intelligence (AI) has made astonishing breakthroughs in recent years and achieved comparable or even better performance compared to humans on many real-world tasks and applications. However, it is still far from reaching human-level intelligence in many ways. Specifically, although AI may take inspiration from neuroscience and cognitive psychology, it is dramatically different from humans in both what it learns and how it learns. Given that current AI cannot learn as effectively and efficiently as humans do, a natural solution is analyzing human learning processes and projecting them into AI design. This dissertation presents three studies that examined cognitive theories and established frameworks to integrate crucial human cognitive learning elements into AI algorithms to build human learning–augmented AI in the context of text analytics. The first study examined compositionality—how information is decomposed into small pieces, which are then recomposed to generate larger pieces of information. Compositionality is considered as a fundamental cognitive process, and also one of the best explanations for humans' quick learning abilities. Thus, integrating compositionality, which AI has not yet mastered, could potentially improve its learning performance. By focusing on text analytics, we first examined three levels of compositionality that can be captured in language. We then adopted design science paradigms to integrate these three types of compositionality into a deep learning model to build a unified learning framework. Lastly, we extensively evaluated the design on a series of text analytics tasks and confirmed its superiority in improving AI's learning effectiveness and efficiency. The second study focused on transfer learning, a core process in human learning. People can efficiently and effectively use knowledge learned previously to solve new problems. Although transfer learning has been extensively studied in AI research and is often a standard procedure in building machine learning models, existing techniques are not able to transfer knowledge as effectively and efficiently as humans. To solve this problem, we first drew on the theory of transfer learning to analyze the human transfer learning process and identify the key elements that elude AI. Then, following the design science paradigm, a novel transfer learning framework was proposed to explicitly capture these cognitive elements. Finally, we assessed the design artifact's capability to improve transfer learning performance and validated that our proposed framework outperforms state-of-the-art approaches on a broad set of text analytics tasks. The two studies above researched knowledge composition and knowledge transfer, while the third study directly addressed knowledge itself by focusing on knowledge structure, retrieval, and utilization processes. We identified that despite the great progress achieved by current knowledge-aware AI algorithms, they are not dealing with complex knowledge in a way that is consistent with how humans manage knowledge. Grounded in schema theory, we proposed a new design framework to enable AI-based text analytics algorithms to retrieve and utilize knowledge in a more human-like way. We confirmed that our framework outperformed current knowledge-based algorithms by large margins with strong robustness. In addition, we evaluated more intricately the efficacy of each of the key design elements.
  • Thumbnail Image
    Solr Project with IDEAL, in CS5604 (Information Storage and Retrieval)
    Xia, Long; Jiang, Tingting; Galad, Andrej; Maharshi, Shivam (2016-05-04)
    This submission describes the work of the Solr team as part of the IDEAL project with the main goal of designing and developing a distributed search infrastructure. It includes the project reports, final presentations, as well as the solutions (configuration files & Java code) developed. The main responsibility of our team was to configure Near Real Time Indexing and implement Custom Ranking for tweets and web page collections. The idea behind NRT Indexing is to help perform incremental updates from an HBase table into the Solr index, thereby optimizing time utilized and compute resources. The main motivation behind the Custom Ranking solution is to improve system precision and recall by transforming user queries with the use of the metadata provided by the other teams. The implementation leverages these three techniques: Query Expansion, Psuedo Relevance Feedback and Query Boosting. Throughout the semester we closely collaborated with several other teams both in getting requirements and the input data.
  • Thumbnail Image
    A Surrogate-based Generic Classifier for Chinese TV Series Reviews
    Ma, Yufeng; Xia, Long; Shen, Wenqi; Zhou, Mi; Fan, Weiguo (2016-11-21)
    With the emerging of various online video platforms like Youtube, Youku and LeTV, online TV series' reviews become more and more important both for viewers and producers. Customers rely heavily on these reviews before selecting TV series, while producers use them to improve the quality. As a result, automatically classifying reviews according to different requirements evolves as a popular research topic and is essential in our daily life. In this paper, we focused on reviews of hot TV series in China and successfully trained generic classifiers based on eight predefined categories. The experimental results showed promising performance and effectiveness of its generalization to different TV series.