Search

Daily cash flow forecasting plays a very important role in enterprise development planning and strategic deployment. This paper makes use of a deep recurrent neural network model and applies it to the forecast of daily sales cash flow. This model adopts GRU unit structure. Through analyzing and mining historical payment flow data, the neural network model is used to automatically learn and extract the internal characteristics of information, and finally the daily cash flow prediction results are obtained. This method is the first successful application of artificial intelligence algorithm in the daily cash flow prediction of power grid. Experimental results show that the model is more accurate than ARIMA method.

The large-scale deployment of mobile sensing tasks can be hindered by the lack of effective incentives for users to participate and protection of users' privacy. In this paper, we propose a novel privacy-aware incentive mechanism framework by introducing a third party as an arbitration center to separate the relevance between users and task data, and thus protect users' privacy. Finally, we evaluate the proposed solution by function verification. Extensive experimental results demonstrate the effectiveness of our solution that contribute to user privacy protection.

This paper studies two end-effector modalities for warehouse picking: (i) a recently developed, underactuated three-finger hand and (ii) a custom built, vacuum-based gripper. The two systems differ on how they pick objects. The first tool provides increased flexibility, while the vacuum alternative is simpler and smaller. The aim is to show how the end-effector influences the success rate and speed of robotic picking. For the study, the same planning process is followed for known poses of multiple objects with different geometries and characteristics. The resulting trajectories are executed on a real system showing that, under different conditions, different types of end-effectors can be beneficial. This motivates the development of hybrid solutions.

Precise facial feature points extraction is essential to the high-level face recognition and expression analysis. This paper presents a method which uses Active Appearance Models with Inverse Compositional Lucas-Kanade Image Alignment algorithm for facial feature points extraction. Experimental results show that the presented method is capable of extraction of precise facial feature points from face. The feature points extraction is robust against the expression changes and scale variation.

This paper analyzes the generation of pseudorandom number theory, gives a brief description of the pseudorandom number generation mechanisms in SQL Server 2000,and then proposes a new method to generate pseudo random number in database system. This method converts a GUID code into a random plastic number through hash function,generates a random sequence composed by 0 and 1 according to the parity of the plastic number, and then take further operation to the 0-1 random sequence, in order to enhance its randomness, and ultimately generates the required random number according to the 0-1 sequence. At the end, tests the randomness of the 0-1 sequence with a run test.