Earticle

Most existing calculations of similarities suffer from data sparsity and poor prediction quality problems. For this issue, we proposed a similarity measurement algorithm based on entropy. The entropy is computed by the difference of two users’ ratings, and we also consider the size of their common rated items, the size is bigger, the weight of their similarity is higher. Experiments show that the algorithm effectively solves the problem of the inaccuracy of similarities in data sparsity or small size neighborhood environments, and outperforms other state-of-the-art CF algorithms and it is more robust against data sparsity.

Moving object detection is an important fundamental process in intelligent vision systems and an essential preprocessing step in high-level machine vision applications such as object tracking and moving analysis. This technique helps to detect suspicious events in video monitoring and is a key process for concentration estimation in traffic management. It is also one of the methods used in advanced vehicle control systems to keep vehicle in path and prevent accidents.In this paper, an effective weighted background moving object detection is presented,which is optimized for scenes with dynamic background. The proposed detection is based on real time background subtracting with high accuracy, low computational complexity and a short processing time, which makes it a good candidate for hardware implementation. The proposed algorithm is simulated in MATLAB software. The simulation results in MATLAB on various image sequences and comparison with mixture Gaussian method and median filter algorithm shows the effective weighted background method has better performance in different evaluation criteria that approves its efficiency in dynamic scenes.

In order to ensure the safe operation of offshore platform, we need response to the platform motion and forecast mooring force. The prediction method based on numerical calculation and model experiment, has certain limitation. A new principle and method of ship’s mooring load measurements based on indirect measurement is presented in order to achieve the short-term and high-precision mooring load prediction, and an algorithm is proposed through which predictions are made by comb the wavelet multi-scale decomposition and reconstruction method with BP neural networks. This paper, by putting a prototype data as learning samples, using the neural network algorithm for forecasting of mooring force, overcomes the traditional B P neural network faults, gets a higher precision. Through comparing the measured data, it demonstrates the feasibility of this method in engineering application.

Multicore has long been considered an attractive platform for string matching. However, some existing traditional algorithms of string matching do not adapt to multicore platform, which pose new challenges to parallelism designs. In this paper, we introduce a multicore architecture with message passing interface to address these challenges. We exploit the popular Aho-Corasick algorithm for the string matching engine. Data parallelism is utilized to design optimization technique of string matching. The experiments show that an implementation of the 8-core system achieves up to 10.5 Gbps throughput on the average.

This study evaluates the use of Multi-Layer Perceptron (MLP) neural network models to forecast water levels of a gauging station located at the Kuala Lumpur city centre in Malaysia using records of upstream multiple stations. Cross correlation analysis of water level data was performed to determine the input vectors which include the current and antecedent water level data of the upstream stations to ensure that of the data available, the most influential values corresponding to different lags are selected for analysis. Twelve well recorded storm events were used to train, test and validate the MLP models. The best performance based on MSE, MAE and R² was achieved with a model of 15 input vectors of upstream current and antecedent water levels, 7 hidden nodes and an output vector for the station at Kuala Lumpur centre. The R² values for training, testing and validation datasets are 0.81,0.85 and 0.85 respectively.

In today’s information age, how to effectively integrate the information resources of tourism and leisure has received widespread attention in the tourism and leisure industry. This article analyzes platform user requirement for the current situation of single function of information service platform, and simple interactive as well as limited contents. The structure and function of hotel information platform based on cloud computing is brought forward in this paper, the framework and required key technologies of platform customization service implementation are also offered.

The research put forward the concept of parasitic system for the first time and studied distribution rules of N, P and K nutrients of different soil areas and different plant tissues in the system along with changes in the tomato growth period, as well as relevance between rhizosphere soil and nutrient contents in different plant tissues. It is found in the results that when Orobanche aegyptiaca was parasitized in tomatoes and joined nutrient transmission via a certain channel, the nutrients in tomato rhizosphere soil would firstly be transported into aboveground parts and Orobanche aegyptiaca by its transfusion tissue; content changes of rapidly-available N, P and K in Orobanche aegyptiaca rhizosphere soil, tomato rhizosphere soil and non-rhizosphere soil showed certain high-low complementarity; content changing trends of N, P and K in different organs of tomatoes and Orobanche aegyptiaca had certain relations, but would differ along with variation of tomato growth period; contents of rapidly-available N and K in Orobanche aegyptiaca rhizosphere soil showed significant correlation with total contents of N and K in organs of tomato and Orobanche aegyptiaca.

In order to improve the optimum speed, crease the diversity of the population and overcome the premature convergence problem in differential evolution(DE) algorithm for solving the complex optimization problems, the chaotic optimization algorithm with powerful local searching capacity and multi- strategy are introduced into the DE algorithm in order to propose an improved adaptive differential evolution(COMSIADE) algorithm in solving function optimization problems. In the COMSIADE algorithm, the ergodicity, regularity and internal randomness of the chaotic sequence are used to overcome the shortcoming of premature local optimum to improve the global searching capacity of the DE algorithm. The multi-population with parallel evolution is used to preserve the diversity of the population at the initial generation. The self-adaptive crossover operator probability is used to improve the global convergence ability, the stability and robustness. Finally, in order to test and verify the effectiveness of the COMSIADE algorithm, several benchmark functions are selected in this paper. The experimental results indicate that the proposed COMSIADE algorithm can improve the global searching capacity and avoid falling into local optimum. And it takes on the higher searching precision and faster convergence speed in solving the complex optimization problem.

Design a nonlinear controller for second order nonlinear uncertain dynamical systems is one of the most important challenging works. This research focuses on the design, and analysis of a model-reference sliding mode controller for first order delay system, in presence of uncertainties. In order to provide high performance nonlinear methodology, model-reference sliding mode controller is selected. Pure sliding mode controller can be used to control of partly known nonlinear dynamic parameters. Conversely, pure sliding mode controller is used in many applications; it has an important drawback namely; chattering phenomenon. To attenuation the chattering, new filter based high speed control technique is introduced. In this technique, two type derivative techniques are used to improve the rate of delay as well stability, robustness and chattering attenuation. This technique cased to improve the rate of delay compare with conventional PID controller and conventional sliding mode controller.

Based on detailed analysis of computational principles of the grey relational analysis method and a series of the relevant researches, this paper proposes a web service selection method based on Grey Relational Analysis to improve the shortcomings caused by personal assignment, so as to improve the usability of the algorithm and reduce the limitation of service selection. At the same time, this paper gives the detailed description of execution steps and complexity analysis of the algorithm. Then, the validity, applicability and efficiency of the algorithm are verified through some comparison experiments.

In this paper, chaos theory and the traditional multi-objective optimization evolutionary algorithm is put forward, "Chaos-based multi-objective evolutionary algorithm", combines a variety of optimization strategies. The traditional multi-objective evolutionary algorithm for repeating individual causes of variation is based on chaotic analysis of multi-objective evolutionary algorithm and demonstration. According to the characteristics of chaotic map tent, NSGA-II algorithm in this paper on the basis of chaotic map was proposed based on chaotic tent initialization and chaotic mutation multi-objective evolutionary algorithm. The original NSGA-II algorithm is improved, and the introduction of adaptive mutation operator and a new crowding distance is calculated and applied to the design of the algorithm. Analysis and experimental results show that these methods can better improve the distribution of population performance.

Carbon nanotubes (CNTs) are being used extensively as reinforcing materials in polymer matrix composites because of their high strength, stiffness and resilience, as well as superior mechanical, electrical and thermal properties. Incorporating CNTs in polymer matrix composites can potentially enhance the strength and stiffness of composites significantly. In this paper, the effective elastic properties of nanocomposites (CNTs/Epoxy) at different volume fractions of CNTs and multiscale composites (Glass/CNTs/Epoxy) at 5% volume fraction of CNTs are evaluated using finite element method (FEM). 3-D finite element models using square representative volume element (RVE) incorporating necessary boundary conditions are developed. For validity the obtained results are compared with that of classical theories of equivalent material properties. Good agreement between them has been observed. Further the effect of CNT-integration in fiber-reinforced composites (three-phase) is also studied.

With the prevalence of ubiquitous computing, big data, and Internet of things in cloud computing environment, it’s important to consider both of collaboration, heterogeneity, isolation of multi-tenant applications and information security and privacy in service composition. Current methods need to be readdressed to cope with cross-organizational, multi-roles participated and knowledge-intensive service composition in an integrated way. Based on the modeling and verification theories of hierarchical colored petri-net, a resource-oriented collaborative workflow model, its resource control model and the joint modeling and verification method are proposed which present a unified solution bridging the gap between traditional structure-oriented workflow execution model and resource-oriented workflow domain model taking into account the underlying roles, tasks, resources and their association and coordination in design-time and runtime as well. In our approach, a business process is divided into three layers: the backbone top-level process, the task fulfillment sub-process and the task execution sub-process in order to reduce the complexity of model verification. In addition this paper gives in-depth discussions on the fine control of implicit parallel and multi-threaded process executions. Finally, the case studies show that the proposed methods are not only applicable to modeling and verification of traditional task-oriented workflows, but also suited for knowledge or data-intensive workflows which involve

VLSI designers are being motivated to explore the opportunities in low power design at different levels of abstraction in the fast growing mobile and battery power devices market. Research of the past few decades has been resulted in efficient electronic design automation tools which can be applied at several circuit and device level techniques to reduce power consumption. Research is being conducted to explore new techniques to utilize the application of specific signaling characteristics to reduce the power consumption. Few types of clock gating based power reduction techniques are established in present day EDA tools. The proposed research work presents novel sub word partitioned signal range based clock gating technique, which can be very efficient in signal processing applications. A scalable VHDL model is developed for the Correlator architecture with the proposed clock gating scheme. MATLAB script generated test data is used for functional verification. Xilinx FPGA based synthesis and power analysis tools are employed to analyze the power optimization of proposed architecture. The simulation results demonstrate power optimization without compromising on the performance. The results show power saving up to 31% for narrow band signal input conditions.

Rapid Propagation of malicious program has caused great harm to the security of user information, the traditional way of killing methods, which is lagging behind and non-intelligent, has been unable to meet the demand of current detection. Studying the new malicious detection method on Windows Platform, screening out intelligent detection rules model feature of malicious executable and extracting the new malicious program detection methods based on data mining. Introducing the sample data processing and feature selection process, analyzing and simulating the new classification method, the result shows that the malicious program model can effectively improve the detection accuracy and reduce the rate of false negatives and false positives.

A plethora of big data applications are emerging and being researched in the computer science community which require online classification and pattern recognition of huge data pools collected from sensor networks, image and video systems, online forum platforms, medical agencies etc. However, as an NP hard issue data mining techniques are facing with lots of difficulties. To deal with the hardship, we conduct research on the novel algorithm for data mining and knowledge discovery through network entropy. We firstly introduce necessary data analysis techniques such as support vector machine, neural network and decision tree methods. Later, we analyze the organizational structure of network graphical pattern with the knowledge of machine learning methodology and graph theory. Eventually, our modified method is finalized with decision and validation implementation. The simulation results of our approach on different databases show the feasibility and effectiveness of our proposed framework. As the final part, we provide our conclusion and prospect.

With the fast development of information technology made people eager to get access the convenient implementations of modern technology in every walk of life. Online handwritten recognition technology for Uyghur is also receiving great need, too. Precious work form researchers for this technology has been gifted many gains. This paper observe the classifiers used in previous work on this field in order to see their adaptabilities for Uyghur online handwritten recognition, and acquire clues for classifier implementation in future work.

Android smart phones often carry personal sensitive information, which makes Android a tempting target for malwares. Recent studies have showed that Android applications frequently are over privileged and the risk of personal privacy leakage is very high. With known Android statics security analysis techniques in literatures, due to lack of considering the control flow between components, the static analysis of sensitive data transmission paths often costs a larger computation overheads, static analysis methods have to make a trade-off between computing time and the precision of analysis results. In this work, we propose a static analysis framework to discovery the sensitive data propagation paths and extract execution conditions (including data inputs and events inputs) of these paths. Our approach first extract a asynchronously executing events sequence graph that directly handles inter-components control flows, it then can be used to archive higher efficient taint analysis when the data propagation path asynchronously cross the boundaries of multiply components. The represented analysis results (data and events inputs) will make the analyst easier to determine if the sensitive data transmission is really a privacy leakage. We present an evaluation with a typical Android malicious app. The result of case study shows that our scheme can effectively help discover the privacy leakage behaviors in the malicious apps.

For solar thermal power generation system with fast time-varying, strong interference and uncertainty characteristics, combined with compensatory of the feedforward compensation to measurable disturbance, strong robustness of sliding mode control and the advantages of predictive control to handle obvious constraints effectively a method of feedforward sliding mode predictive controller is put forward to apply in solar thermal power generation heat collecting system. First of all, ignoring the heat loss in heat transfer process mathematical model of solar thermal power generation heat collecting system is established as prediction model of controller design. Progressive stable sliding surface was designed through the pole placement method, which effectively overcame the chattering phenomenon and reduced interference caused by uncertainty at the same time. Feedforward compensator was designed to compensate the effect of measured interference signal which is solar radiation to collector output. Simulation results show that feedforward sliding mode predictive control has strong anti-interference ability and improves the control accuracy compared with sliding mode predictive control.

In last few years, vehicular networks (or moving objects) are gaining more and more attraction from the researchers and the automobile industries. In that, Location-Based Services (LBSs) become more feature-rich and versatile due to the explosion of mobile devices and the advances of positioning technologies. Trust and Privacy are the two key parts of security and it is undoubtedly a necessity to develop (or maintain) trust for moving objects (or vehicular users). The main aim of this paper is to propose a trust model for vehicular environment with desired level of privacy protection. The proposed model contains two different modules. First, this paper analyzed the merit and demerit of exiting location privacy protection method.Then a perceived k-value location privacy protection algorithmdiscussed to provide desired level of privacy protection. Hereafter the protocol (or procedure) of this algorithm; simulation result are discussed in detail.Second,it provides a model to maintain trust for vehicle Ad-hoc Network (VANET) users in LBSs. The results show that proposed method outperforms the existing privacy preservation method by effectively enhances privacy and trust against various adversaries. Hence,the purpose of this work is to maintain trust and certain level of privacy among vehicular users without revealing her identity in LBSs.

In this paper, we conduct a novel research on assembling paper fragments with kernel sparse representation and regular edge geometry analysis using the traditional example of rectangular pieces. At the initial stage, we adopt the methodology of image sparse presentation technique to overcome the influence of noise. During the process of assembling, we make good use of MATLAB and C++ to extract the core visual information from the fragments’ digitally to capture the matrix in the grey value scale. Edge characteristics are derived and regarded as the basic unit to find out fragments which belong in the first column. According to the similarity characteristic, adjacent rows are found and matched accordingly, annealing algorithm is used to gather the fragments. From the perspective of practical use, we find out the robustness and effectiveness of our proposed approach. Compare with some state-of-the-art algorithms, our methodology shows the better accuracy, it’s of great importance to the community of fragment assembly.

Combining with the requirements of the development of the smart grid, we raised the research of distribution network monitoring system based on wireless sensor networks. In analysis of the status quo and deficiencies of the existing cable communication system of the distribution network, combining with the structure and characteristics of the wireless sensor networks, we built a new construction strategy of distribution network data monitoring system and discussed it in details regarding both the overall structure itself and the key technologies involved.

Soft computing models like Artificial Neural Network (ANN) have been widely used to model complex hydrological processes, such as rainfall-runoff and have been reported to be one of the promising tools in hydrology. In this paper, the influences of back propagation algorithm and their efficiencies which affect the input dimensions on rainfall runoff model have been demonstrated. The capability of the Artificial Neural Network with different input dimensions have been attempted and demonstrated with a case study on Sarada River Basin. The developed ANN models were able to map relationship between input and output data sets used. The developed model on rainfall and runoff pattern have been calibrated and validated. The significant input variables for training of ANN models were selected based on statistical parameters viz. cross-correlation, autocorrelation, and partial autocorrelation function. Various combinations were attempted and six combinations were selected based on the statistics of these functions. It was found those models considering rainfall lag rainfall and lag discharge as inputs were performing better than those considering rainfall alone. It was found that the neural network model developed is performing well. It can be inferred from the developed model, Neural Network model was able to predict runoff from rain fall data fairly well for a small semi-arid catchment area considered in the present study.

Coverage is a key and fundamental problem in wireless sensor networks. To provide high quality of service, high coverage ratio of sensor nodes in monitored area should be assured. Coverage holes may lead to routing failure and degrade the quality of service. A novel coverage hole discovery algorithm, VCHDA, is proposed for wireless sensor networks in this paper. The proposed algorithm is based on the well-known Voronoi diagram. It can recognize coverage holes and label the border nodes of coverage holes effectively. Simulations are conducted and the results show that the proposed algorithm is effective and with high accuracy.

As the increasing usage of data generating devices like cameras, mobile phones, Auto-ID technologies, and so on, huge amount of data are created. Data compression is very important. In order to use the suitable compression methods on reducing the data volume, this paper uses iceberg-cubes to compress the data based on the entropy query mechanism. Using the definition of iceberg-cubes, this paper uses the entropy query principle for getting the key value from the original datasets. The iceberg-cubes are then used for generating the compressed data which should be stored in the hardware devices. It is observed that these proposed algorithms could achieve 32.46% compression ratio averagely.

The image retrieval performance based on single feature is limited. For different kinds of images, it can not a better retrieval result. This paper raises image retrieval method based on weighted multi feature. In each kind of images, each feature precision is the weight evidence. On this basis, we research the existing semantic retrieval technology. Choosing the SVM classification theory which is more mature. Selecting parts of images as training set. Doing the training classification. From the research of different characteristics priority, it raises the image retrieval technology which synthesizes SVM and multi feature. From that, it can get a higher retrieval efficiency.

Driving speed is a key parameter for building the traffic state identification model, its precision directly affects the model reliability and the traffic state identification accuracy. Aiming at the standard normal deviation method’s defects in dealing with the extreme noise data, an anomaly driving speed detection algorithm based on quantiles is proposed, use historical data to establish the exception borders which are used to detect whether an unknown data is abnormal; on the basis of the abnormal data detection, a driving speed prediction algorithm based on improved KNN is proposed, use K-means algorithm to clustering the historical data, and predict the next moment’s speed according to the distance between the data to be predicted and the clusters, the predicted speed can be used to correct the abnormal speed. Experimental results show that the detection rate of the proposed anomaly detection algorithm has improved about 4.25% compared with the standard normal deviation method, and the false detection rate has reduced about 25.51%; the mean relative error of the proposed speed prediction algorithm is 13.69%, it can predict the driving speed well, namely, the anomaly driving speed detection and correction algorithm based on quantiles and KNN is feasible and effective.

As a carrier of artificial intelligence research, computer game can establish a sound theoretical foundation for the research of non-zero-sum card games with imperfect information. In this paper, we first propose a game model based on the finite Moore automaton, which illustrates the implementation of the model for Niujiu card. At the same time, a novel search strategy combining IMP-minimax and Monte Carlo algorithm is presented in this model. Through the given algorithm, this paper accomplishes the simulation, including not only the process of minimal and optimal occupancy for the first player, but the available frequency of special card type. Experiments show that our model and algorithm are feasible and effective.

In a three-dimensional laser scanning system, the measurement accuracy of the entire system is determined by the optical system. To improve the accuracy, this paper designs a three-dimensional laser scanning optical system. In order to improve the performance of scanning, to reduce the influence of stray light and the imaging geometric distortion is required, as far as possible to improve the distribution uniformity of the image illumination. In this paper, the semiconductor laser is chosen as the light source which is suitable for laser triangulation measurement. This system ensures accuracy in the first place, and obtain larger working distance later. The volume of the measuring system is reduced by introducing layout that the beam splitter and the normal are coaxial. The Scheimpflug conditions are deduced under this structure, and the experimental results of the laser triangulation optical system are analyzed finally.