Search

With the rapid popularity of mobile devices, a vast amount of trajectory-based check-in data are shared in many social network applications, which is an important data source for user location prediction. The location category prediction, a branch of location prediction, is a vital task in a wide range of areas, including urban planning, advertising and recommendation systems. In this paper, we propose a novel two-step Pattern-Based Embedding Model (PBEM) for predicting the next location category that user will go to. Based on the observation that some users behave frequently in a similarity pattern, a new feature termed as user cluster label is defined. In order to mine user's behavior patterns and extract the cluster label, a Category-Importance-Decay learning strategy is proposed and implemented, which provides a quantitative standard for evaluating the importance of each category. Thus, a comprehensive feature set is obtained including user, time, historical location category, text content, and user cluster label, which greatly enhances the robustness of data representation and contains more knowledge. Then the extracted feature set is fed into Recurrent Neural Network (RNN) in a unified framework, which improves the prediction accuracy. We evaluate the performance of PBEM on two real-life trajectory-based check-in datasets. Experimental results demonstrate that the proposed model can outperform the state-of-the-art methods.

Fuzzy clustering algorithm based on multiobjective optimization can achieve accurate and comprehensive clustering results. However, the estimation of objective values for this multiobjective optimization problem (MOP) might be expensive. Offspring’s selection driven by simple evaluation is time consuming. Therefore, we integrate regression techniques to determine the superiority of the offspring solutions in the evolution process. However, it suffers from an issue that it is hard to collect reliable samples to train such a robust regression model. In this paper, an evolutionary multiobjective fuzzy clustering method via self-paced learning is proposed for change detection. In the proposed method, the self-paced learning process is implemented to collect reliable training samples for training a robust regression model, which can help to select promising offspring solutions from the candidate solutions for MOP. Experiments on three remote sensing image datasets demonstrate that the proposed method can significantly outperform those state-of-art methods for change detection in terms of accuracy and robustness.

In order to provide quicker, and more comprehensive network service for users, and to bring more convenience for the development of the SP/CP(Service Provider/Content Provider), we propose an open service system whose architecture and the standardization of the open API(Application Programming Interface) are discussed more in this paper. To design such a system, Firstly, the common services model, which could realize the auto choice of the most appreciate services among the services provided by different SP/CP, needs to be built through extracting the service characteristic from different network services. Secondly, it must be ensured that, through the standardized open API, all the common services in different fields could access the service integration and publishing platform. The advantage is that the users can not only realize the mashup of services they need, but also are able to release the services they have developed on such a platform.

Nano-coned array of Cu were prepared by electroless plating with special crystallization conditioning agent. The morphologies of nano-coned array were observed by FE-SEM. The influences of active time in PdCl 2 , concentration of NiSO 4 ·6H 2 O, crystallization conditioning agent, pH and temperature of plating solution were discussed. Then, the possible reasons of the influence on the growth of nano-coned array were investigated. NiSO 4 ·6H 2 O was proved as catalytic active agent. The optimum preparation conditions were fixed. The crystal crystallographic orientation and elements of the nano-coned array were measured using TEM and EDX. The nano-cones consist of 95.57% copper and 4.43% nickel. The crystal crystallographic orientation of them is typical copper FCC single crystal.

Implementing convenient traveling information service is a crucial task for deploying intelligent transportation system applications and location-based services. Traditional traveling information service systems, such as car navigation systems or web maps, only provide relatively static information which doesn't truly reflect the dynamic changes of traffic situation, and result in very limited practical use. Although there have emerged some car navigation products and other applications involving dynamic traffic information, considering the rapid change of city traffic situation, these applications still face practical difficulties for all the information received real-timely will get outdated within a few minutes, which makes the so called dynamic applications basically time-slice limited static ones. Aiming at such a problem, a short-term traffic prediction approach and a consequent real-time route guidance process are presented in this paper which integrates historical traffic based statistical reasoning, real-time traffic and events processing, with a BP neural network based analytical model, to forecast the situation and evaluate the influence of traffic during the traveling process. Then a collaboration working framework is set forward to implement dynamic route guidance, with the combination of a GIS server, a traffic forecasting server and a database management system. The traffic forecasting server, integrating with historical statistics reckoning continuously receives real-time traffic information obtained from floating vehicles, traffic events described in natural language, and achieves short-term forecasting results for the whole road networks, then fed the results back into the database management system and GIS server, so that a time-dependant optimal routing can be conducted through a dynamic least traveling time algorithm developed in this study. A prototype navigation system fulfilling the above aspects has been developed and the dynamic route choice approach demonstrated on road networks in the downtown area of Beijing city. The approach presented in this paper is argued to provide a practical solution for real-time public traveling information service and dynamic web maps.