Self-representation subspace clustering based on graphs has the merits of capability and efficiency. However, the graph built by the self-representation methods has two issues: (i) usually lacking conciseness and informativeness due to the negative representation coefficients. (ii) no guarantee of an overall optimal solution due to the separation of representation learning and graph construction. To alleviate these issues, we propose a novel subspace clustering via learning non-negative representation with an adaptive graph. Specifically, we explicitly impose the non-negative constraint on the self-representation learning, ensuring that each data point is approximated from a group of homogeneous samples and enhancing the distinguishability of data representation. Meanwhile, an adaptive graph is developed so that both representation and the geometric structure of data are simultaneously learned in a unified procedure. Moreover, the learned representation is less sensitive to data noise imposed by the$\ell _{2,1}$-norm, so the adaptive graph will be further improved. An efficient optimization procedure is developed to find the optimal solution. Extensive experiments on subspace clustering and the extension application to image segmentation validate the advantages of our method against state-of-the-art methods.

Understanding the feedback loop that links the spatiotemporal spread of infectious diseases and human behavior is an open problem. To study this problem, we develop a multiplex framework that couples epidemic spreading across subpopulations in a metapopulation network (i.e., physical layer) with the spreading of awareness about the epidemic in a communication network (i.e., virtual layer). We explicitly study the interactions between the mobility patterns across subpopulations and the awareness propagation among individuals. We analyze the coupled dynamics using microscopic Markov chains (MMCs) equations and validate the theoretical results via Monte Carlo (MC) simulations. We find that with the spreading of awareness, reducing human mobility becomes more effective in mitigating the large-scale epidemic. We also investigate the influence of varying topological features of the physical and virtual layers and the correlation between the connectivity and local population size per subpopulation. Overall the proposed modeling framework and findings contribute to the growing literature investigating the interplay between the spatiotemporal spread of epidemics and human behavior.

Spectral clustering is a vital clustering method and has been widely applied for data analysis and pattern reorganization. A routine of solving spectral clustering problem consists of two successive stages: (1) solving a relaxed continuous optimization problem to obtain a real-valued indicator solution (2) transform the real-valued indicator into a 0-1 discrete one as the final clustering result. However, we may lose the optimal solution with such a two-stage process. Besides, the spectral clustering has a high time complexity which limits the analysis of large-scale data. To alleviate these problems, this paper proposes an efficient spectral clustering framework that computes spectral embedding and improved spectral rotation simultaneously (SE-ISR). In addition, we also provide a parameter-free method (SE-ISR-PF) to automatically choose the trade-off parameter. Furthermore, with an anchor-based similarity matrix construction, it is scalable to large-scale data. An effective algorithm with a strict convergence proof is provided to solve the corresponding optimization problem. Experimental results on several benchmark datasets demonstrate that the proposed algorithm outperforms the state-of-art methods.

Sentiment classification has gained much attention in big data era. Most existing methods rely on bag-of-words model, which disregard contextual information. In many cases however, the sentiment strength of a word is implicitly associated with its part of speech and context. In this paper, we present a WWE (weighted word embeddings) method that combines word embeddings and part-of-speech (POS) tagging. First, we used a continuous word representations algorithm (Word2Vec) to train a vector model. The algorithm learns the optimal vectors from the context of surrounding words. According to the cosine similarity between the vector of a word and the vectors of seed words, a polarity score of this word can be calculated. The state-of-the-art SyntaxNet was used for POS tagging. We then computed an overall polarity score of the whole sentence by POS weighted polarity scores of words. At the end, majority voting was applied to determine the final polarity. Our experimental results show that the WWE method is performed with promising outcomes. Additionally, the methodology was demonstrated on the 3 Twitter datasets from different domains. The robustness recommends that this method can be applied on other sentiment classification problems or domains. We also compared the performance on various dimensions of the trained models. A higher dimension achieved a better performance.

In this big data era, huge amount data are continuously acquired for a variety of purposes. Advanced computing, imaging, and sensing technologies enable scientists to study natural and physical phenomena at unprecedented precision, resulting in an explosive growth of data. It is a huge challenge to visualize this growing data in static or in dynamic form. Most traditional data visualization approaches and tools can't support at "big" scale. In this paper, we identified the challenges and opportunities in big data visualization and review some current approaches and visualization tools.