Search

This paper investigates resource allocation of simultaneous wireless information and power transfer (SWIPT) in non-orthogonal multiple access (NOMA) system with power splitting (PS) technology. Our goal is to optimize both the harvested energy and the transmission rate subject to the minimum requirements on each user’s harvested energy and transmission rate. Considering the battery is capable of storing power which is converted into throughput in reverse link, we establish the equivalent-sum-rate (ESR) maximazation function by combining the transformed throughput and the transmission rate with a weight coefficient. Since the formulated nonconvex problem is difficult to solve, we develop a deep learning-based approach to obtain an efficient resource allocation strategy. In particular, deep belief network (DBN), which comprises preparing data samples, training and running, has been adopted. The simulation results verify the effectiveness of the proposed DBN-based scheme, and prove that the ESR performance of the considered NOMA-SWIPT is better than that of the OFDMA-SWIPT.

Longitudinal rip of conveyor belts is a serious threat to safety production. Based on the machine vision technology, an algorithm used to find longitudinal rip of belts on-line from gray belt images directly is proposed. A gray image is first translated into a unidimensional vector. The unidimensional vector is further analyzed to obtain rip eigenfunctions. Then, faults of longitudinal rips are diagnosed by using the rip eigenfunction. The calculation of searching from the unidimensional vector is smaller than searching from the gray image. The validity of the proposed algorithm is testified by the testing results with some belt images.

The Back Propagation Neural Network Model has some disadvantages to decrease prediction accuracy. Combining the advantages of the Kalman filter, a new Back Propagation Neural Network Model Based on Kalman Filter is established for the prediction of the water pollutants concentration. The result of the case study shows that the method proposed can effectively improve the prediction accuracy, and the improved model is proved to be a better and more effective method in water quality prediction.

Automatically recognizing a place or landmark attracts increasing attentions in recent years due to its wide applications in mobile terminals. In this paper, we consider the problem of landmark recognition using sparse representation in compressed sensing. After constructing the dictionary with training samples, the recognition of a query landmark image is converted to solving a linear representation problem from an over-complete equation. The recent spatial pyramid kernel based bag-of-words (BoW) method is employed for the landmark image representation. Two representative algorithms, namely, the orthogonal matching pursuit (OMP) and the sparse reconstruction by separable approximation (SpaRSA), are adopted to find the sparse representation coefficients. Experimental results conducted on the Nanyang Technological University (NTU) campus landmark database are given to demonstrate the effectiveness of the propose landmark recognition algorithm.

Landmark recognition attracts great concerns in recent years due to its extensive applications in mobile terminals. An effective recognition system with high recognition accuracy and fast response speed is highly desired by users. In this paper, we propose an ensemble based constrained-optimization extreme learning machine (CO-ELM) combining with the spatial pyramid kernel based bag-of-words (SPK-BoW) method for landmark recognition. The recent SPK-BoW method is employed for feature extraction and representation due to its effectiveness in exploiting the spatial layout information for landmark images. To enhance the recognition performance and accelerate the data training and testing speed, the voting based CO-ELM (VCO-ELM) with multiple network ensembles is proposed as the classifier. Experiments on two real-world landmark datasets show that the proposed VCO-ELM algorithm outperforms the original CO-ELM and support vector machine (SVM) in general.

With the continuous development of science and technology, more and more database and information systems connect with the network. That is to say how to discover the required information from complex network data has become a more and more important concern problem. Data mining refers to the practical application of data from which implicit information and knowledge are extracted to analysis and use. Data mining from Web-Oriented is more complex than that from a single data warehouse, XML technology provides a convenient way for the Web data mining. Web-oriented data mining and it's types, XML technology, the transforming from HTML into a model of XML and the application of XML in Web Data Mining are described in this paper. and then an example is adopted to illustrate the application of the model.

A data center network solution was designed to improve the network performance in processing the search traffic. The design is based on the analysis of the switching network search traffic model. According to the search traffic features, two technology revolutions are explained in this paper. The solution is able to improve data center network performance in processing the search traffic obviously.

IEEE Std 802.15.4, as an widespread wireless network standard, defines the protocol and compatible interconnection for data communication devices using low-power and low-complexity short-range radio frequency (RF) transmissions in a wireless personal area network (WPAN). It presents the advantage to fit different requirements of potential applications by adequately setting its parameters. For time critical applications, the protocol can provide timeliness guarantees by using its Guaranteed Time Slot (GTS) mechanism in beacon-enabled mode. Deterministic performance evaluation methods are inevitable for the validation of systems that must guarantee hard delay bounds and timeliness of information processing. One recent deterministic modeling approach is Network Calculus, which allows determining worst case transmission times. Based on GTS allocation mechanism, we generate appropriate modeling elements for the Network Calculus as arrival curves and service curves. The results of this work may pave the way for a time efficient management of the GTS mechanism in an IEEE 802.15.4-based network.