Search

In the order picking process of the warehouse center, considering the rapid increase in the volume of orders arriving at the picking center at the time of the promotional festival, a hybrid operation mode with multiple picking tables is used to meet the picking requirements of the huge number of real-time orders. Therefore, in this paper, a hybrid picking mode is proposed, taking into account both the idle degree of picking stations and their order item centers of gravity, and a new reinforcement learning algorithm embedding mechanism (PRL) with placeholder control is designed to solve the problem of a huge number of real-time item orders arriving at the picking center system on promotional holidays and in inconsistent quantities, and numerical simulations are performed for this algorithm. The experimental results show that the PRL algorithm in hybrid picking mode can handle a huge number of orders simultaneously and improve picking efficiency effectively.

Information of highway is the basic element of intelligent transportation system. This study proposes a method for extracting section information of highway based on massive GPS data. The method has the advantages of low time complexity and high accuracy. The method is inspired by the algorithm of Density Based Spatial Clustering of Applications with Noise (DBSCAN). DBSCAN can discover cluster of arbitrary shape. The method calculated neighborhood density of GPS points by algorithm of zone division; therefore this method reduces the computation scale and the time complexity greatly. Taking into account the uneven distribution of GPS data between sections, the method of hierarchical division is adopted in clustering, and iterative clustering is computed from dense to sparse. Finally we find that our method can find the road information efficiently on massive GPS data.

This paper studies financial crisis of listed companies in China Manufacture Industry, and selects 181 companies with financial crisis and 181 normal companies as its research samples, and its research is based on financial indexes three years before the financial crisis happens. Firstly the method of principle component analysis is used to abstract useful information from the training data. Secondly a prediction model of financial crisis is constructed with the method of Support Vector Machine and the accuracy of the model is 78.73% on the training data and the 79.79% on the testing data. Thirdly the advantages of this model are discussed over the other prediction models. Finally the research results show that this model uses the least number of input variables and has the highest prediction accuracy, thus this model can provide the useful information to investors, creditors, financial regulators and etc.

In a real e-commerce website, usually only a small number of users will give ratings to the items they purchased, and this can lead to the very sparse user-item rating data. The data sparsity issue will greatly limit the recommendation performance of most recommendation algorithms. However, a user may register accounts in many e-commerce websites. If such users’ historical purchasing data on these websites can be integrated, the recommendation performance could be improved. But it is difficult to align the users and items between these websites, and thus how to effectively borrow the users’ rating data of one website (source domain) to help improve the recommendation performance of another website (target domain) is very challenging. To this end, this paper extended the traditional one-dimensional psychometrics model to multidimension. The extended model can effectively capture users’ multiple interests. Based on this multidimensional psychometrics model, we further propose a novel transfer learning algorithm. It can effectively transfer users’ rating preferences from the source domain to the target domain. Experimental results show that the proposed method can significantly improve the recommendation performance.

In order to improve the Peer-to-Peer (P2P) network resource locating efficiency and isolate malicious peers, a topology adjustment algorithm for unstructured P2P networks is proposed. TTL (time-to-live) value for each neighbor has been set up and adjusted; specific information on the query path is recorded; a topology adjustment algorithm is given. The topology adjustment algorithm is evaluated by peer shortest path, simulation and analysis show that the topology adjustment algorithm can isolate malicious peers to the network edge, and improve service quality of P2P networks.

In recent years, various applications of Peer-to-Peer (P2P) computing have been widely used because of its unique advantages, which have play ed an important role in commerce, communications and other fields. The P2P system is essentially a distributed system, without central servers. Each peer is both client and server, who have the same status. However, some features of P2P networks, such as autonomy, dynamic, and heterogeneity lead to an important problem, namely unreliable quality of service. Unreliable quality of service is usually presented as providing false or unreliable service, impacting customer satisfaction. The establishment of trust models which evaluate s capabilities of peers can measure the service capacity of a peer, and identify malicious behavior, thereby reducing the risk of interaction and being an effective technique to ensure the overall availability of P2P networks. A trust model named METrust in P2P networks based on the recommendation is proposed. In METrust, a peer selects recommendation peers whose evaluation criteria are similar, and evaluation criteria of peers are determined through the AHP method (Analytic Hierarchy Process). Each peer in the network has a unique credibility of recommendation, and two trust parameters for updating the credibility of recommendation are introduced, namely updating range and updating strength. METrust proposes algorithms to compute the trust of peers. Simulations show that, the trust model METrust can identify malicious peers, and improve the quality of service in P2P networks effectively.

A new method, which assumesϕ'with a function form off(eϕ), is applied to solve the Dodd-Bullough equationϕuv=eϕ-e-2ϕthrough travelling-wave transformation. A new family of explicit travelling wave solutions is derived. The proposed method works efficiently to be applied to solve other forms of Dodd-Bullough equations.

In order to solve the problem of manual operation, low efficiency, high error rate in the process of traditional stocktaking, this paper proposes a counting scheme of storage based on a new wireless RFID sensing equipment. By applying the wireless RFID sensing equipment in the stocktaking, it can solve the problem of processing large quantities of data, improve counting efficiency and accuracy, realize the full automatic counting without paper, save manpower and optimize warehouse management.

With the development of positioning services, an increasing number of people and companies pay attention to the management and protection of the precious goods which they possess, through the determination of its location to achieve the management purpose [1]. At present, the main positioning way is to use the global positioning system (GPS), but many of the valuable items are stored in the indoor, and it's hard to receive a satellite signal in the room, so it cannot be accurate positioning. As a new short distance wireless data recognition technology at present, Radio Frequency Identification (RFID) indoor positioning technology is very suitable for the indoor positioning. Because it has many characteristics: large amount of data storage, readable and writable, strong penetrating power, long recognition distance, fast read-write speed and the use of the characteristics of long service life and good adaptability to the environment, etc. Among the RFID indoor positioning technology of many positioning algorithms, the three sides positioning algorithm is commonly used, and more mature. At the same time, the storage space of most valuable items is simple, and the environmental factors have little influence on the signal interference. So it is feasible to use the three sides positioning algorithm of RFID positioning algorithms to locate the valuables in the indoor.