Since the release of the digital archives of Defense Meteorological Satellite Program Operational Line Scanner (DMSP/OLS) nighttime light data in 1992, a variety of datasets based on this database have been produced and applied to monitor and analyze human activities and natural phenomena. However, differences among these datasets and how they have been applied may potentially confuse researchers working with these data. In this paper, we review the ways in which data from DMSP/OLS nighttime light images have been applied over the past two decades, focusing on differences in data processing, research trends, and the methods used among the different application areas. Five main datasets extracted from this database have led to many studies in various research areas over the last 20 years, and each dataset has its own strengths and limitations. The number of publications based on this database and the diversity of authors and institutions involved have shown promising growth. In addition, researchers have accumulated vast experience OPEN ACCESS Remote Sens. 2014, 6 6845 retrieving data on the spatial and temporal dynamics of settlement, demographics, and socioeconomic parameters, which are "hotspot" applications in this field. Researchers continue to develop novel ways to extract more information from the DMSP/OLS database and apply the data to interdisciplinary research topics. We believe that DMSP/OLS nighttime light data will play an important role in monitoring and analyzing human activities and natural phenomena from space in the future, particularly over the long term. A transparent platform that encourages data sharing, communication, and discussion of extraction methods and synthesis activities will benefit researchers as well as public and political stakeholders.

Heterogeneous data co-clustering has attracted more and more attention in recent years due to its high impact on various applications. While the co-clustering algorithms for two types of heterogeneous data (denoted by pair-wise co-clustering), such as documents and terms, have been well studied in the literature, the work on more types of heterogeneous data (denoted by high-order co-clustering) is still very limited. As an attempt in this direction, in this paper, we worked on a specific case of high-order coclustering in which there is a central type of objects that connects the other types so as to form a star structure of the interrelationships. Actually, this case could be a very good abstract for many real-world applications, such as the co-clustering of categories, documents and terms in text mining. In our philosophy, we treated such kind of problems as the fusion of multiple pairwise co-clustering sub-problems with the constraint of the star structure. Accordingly, we proposed the concept of consistent bipartite graph co-partitioning, and developed an algorithm based on semi-definite programming (SDP) for efficient computation of the clustering results. Experiments on toy problems and real data both verified the effectiveness of our proposed method.

Image clustering, an important technology for image processing, has been actively researched for a long period of time. Especially in recent years, with the explosive growth of the Web, image clustering has even been a critical technology to help users digest the large amount of online visual information. However, as far as we know, many previous works on image clustering only used either low-level visual features or surrounding texts, but rarely exploited these two kinds of information in the same framework. To tackle this problem, we proposed a novel method named consistent bipartite graph co-partitioning in this paper, which can cluster Web images based on the consistent fusion of the information contained in both low-level features and surrounding texts. In particular, we formulated it as a constrained multiobjective optimization problem, which can be efficiently solved by semi-definite programming (SDP). Experiments on a realworld Web image collection showed that our proposed method outperformed the methods only based on low-level features or surround texts.

The basis of applying deep learning to solve natural language processing tasks is to obtain high-quality distributed representations of words, i.e., word embeddings, from large amounts of text data. However, text itself usually contains incomplete and ambiguous information, which makes necessity to leverage extra knowledge to understand it. Fortunately, text itself already contains well-defined morphological and syntactic knowledge; moreover, the large amount of texts on the Web enable the extraction of plenty of semantic knowledge. Therefore, it makes sense to design novel deep learning algorithms and systems in order to leverage the above knowledge to compute more effective word embeddings. In this paper, we conduct an empirical study on the capacity of leveraging morphological, syntactic, and semantic knowledge to achieve high-quality word embeddings. Our study explores these types of knowledge to define new basis for word representation, provide additional input information, and serve as auxiliary supervision in deep learning, respectively. Experiments on an analogical reasoning task, a word similarity task, and a word completion task have all demonstrated that knowledge-powered deep learning can enhance the effectiveness of word embedding.