Many real-world applications have to face the problem of diversity in data formats and semantics. Currently, how to deal with heterogeneous data effectively is still a big challenge. With the rise of knowledge graphs, more and more applications are built upon graph-like data models, which benefit from flexible schemas and convenient support for relationship queries. We propose a graph-based unifying system for heterogeneous data unification, which helps to (1) transform data in many other formats into graphs, or conversely, from graph to other formats, (2) integrate graph data based on HAO intelligence, which achieves schema integration and entity consolidation, and (3) explore data at different levels via querying the integrated graphs. In this paper, we introduce the overall system architecture, explain in detail the implementation, and display the usage in two practical scenarios.

We propose a generalized optimization framework for detecting anomalous patterns (subgraphs that are interesting or unexpected) in interdependent networks, such as multi-layer networks, temporal networks, networks of networks, and many others. We frame the problem as a non-convex optimization that has a general nonlinear score function and a set of block-structured and non-convex constraints. We develop an effective, efficient, and parallelizable projection-based algorithm, namely Graph Block-structured Gradient Projection (GBGP), to solve the problem. It is proved that our algorithm 1) runs in nearly-linear time on the network size, and 2) enjoys a theoretical approximation guarantee. Moreover, we demonstrate how our framework can be applied to two very practical applications, and we conduct comprehensive experiments to show the effectiveness and efficiency of our proposed algorithm.

The human brain is an amazingly complex network. Aberrant activities in this network can lead to various neurological disorders such as multiple sclerosis, Parkinson's disease, Alzheimer's disease, and autism. functional magnetic resonance imaging has emerged as an important tool to delineate the neural networks affected by such diseases, particularly autism. In this paper, we propose a special type of mixed-effects model together with an appropriate procedure for controlling false discoveries to detect disrupted connectivities for developing a neural network in whole brain studies. Results are illustrated with a large data set known as autism brain imaging data exchange which includes 361 subjects from eight medical centers.

In order to improve the lack of reality and flexibility of the aim path-planning in traditional approximation method, a new method of formation change based on genetic algorithm was presented. By reducing the entities' sequences difference between initial formation and final formation, the chromosome coding and fitness function were designed. Furthermore, the algorithm was applied to a CGF simulation system. The experimental results showed that the proposed algorithm was indeed an effective way to solve the problem of aim path-planning in formation change. Compared with existing algorithms, this algorithm had more reasonable result and the possibility of collision was significantly reduced.