Fine-grained urban crime prediction is of great significance to urban management and public safety. Previous crime prediction work has been done at a relatively coarse time granularity, which may suffer from two issues for fine-grained crime prediction. 1)The zero-inflation problemassociated with fine-grained granularity. Crime occurrence is sparse, and when the time granularity becomes finer, it leads to a more sparse prediction label for this problem resulting in the zero inflation problem. 2)Insufficient amount of informationinvolved in crime datasets. When the spatio-temporal granularity becomes smaller, more information from related fields needs to be introduced to extract spatio-temporal features to assist the analysis. To address the first issue, we introduce a classification-labeled continuousization strategy and a weighted loss function for sparse classification problem, making the model more likely to focus on non-zero elements in zero-inflated datasets. For the second issue, we propose a novel deep learning based model, termed attention-based spatio-temporal multi-domain fusion network, which fuses features from multiple datasets in related domains. We evaluate our method on six real-world datasets collected in New York City and experiments on our model show the advantages beyond many competitive baselines.

Multiple domain fusion has been widely used for urban anomalies forecasting problem, as urban anomalies such as traffic accidents or illegal assembly are usually caused by many complex factors and they would affect many fields. Although many efforts have been devoted to fusing multiple datasets for anomalies detection, most of the work is to extract the spatio-temporal features one by one from multiple datasets and then fuse to get the result or anomaly score. However, the correlation between data from multiple domains at each moment is ignored, which is especially important when detecting anomalies by analyzing the impacts from multiple datasets. In this paper, we propose a novel end-to-end deep learning based framework, namely deep spatio-temporal multiple domain fusion network to collect the impacts of urban anomalies on multiple datasets and detect anomalies in each region of the city at next time interval in turn. We formulate the problem on a weighted graph and obtain spatiotemporal features with adaptive graph convolution and temporal convolution. In addition, a cross-domain convolution network is applied to fully obtain connection between multiple domains. We evaluate our method with real-world dataset collected in New York City and experiments on our model show the advantages nearly 10% beyond the state-of-the-art urban anomalies detection methods.

In recent years, Web service discovery has been a hot research topic. In this paper, we propose a novel Web services discovery approach, which can mine the underlying semantic structures of interaction interface parameters to help users find and employ Web services, and can match interfaces with high precision when the parameters of those interfaces contain meaningful synonyms, abbreviations, and combinations of disordered fragments. Our approach is based on mining the underlying semantics. First, we propose a conceptual Web services description model in which we include the type path for the interaction interface parameters in addition to the traditional text description. Then, based on this description model, we mine the underlying semantics of the interaction interface to create index libraries by clustering interaction interface names and fragments under the supervision of co-occurrence probability. This index library can help provide a high-efficiency interface that can match not only synonyms but also abbreviations and fragment combinations. Finally, we propose a Web service Operations Discovery algorithm (OpD). The OpD discovery results include two types of Web services: services with “Single” operations and services with “Composite” operations. The experimental evaluation shows that our approach performs better than other Web service discovery methods in terms of both discovery time and precision/ recall rate.

Community detection is one of the most important problems in social network analysis in the context of the structure of the underlying graphs. Many researchers have proposed their own methods for discovering dense regions in social networks. Such methods are only designed with links of the underlying social network. However, with the development of recent applications, rich edge content can be available to give another view to the community detection process. In this study, we focus on improving community detection with the edge content in social networks. In order to regulate the effect of both linkage structure and edge content, we propose two feature integration strategies. Experiment results illustrate that the presence of edge content provides unprecedented opportunities and flexibility for the community detection process.