Loading...

Table of Content

      
    20 April 2015
    Volume 45 Issue 2
    A clustering ensemble algorithm based on co-evolution
    DONG Hongbin, ZHANG Guangjiang, PANG Jinwei, HAN Qilong
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  1-9.  doi:10.6040/j.issn.1672-3961.1.2014.095
    Abstract ( 921 )   PDF (2562KB) ( 476 )   Save
    References | Related Articles | Metrics
    Since clustering could not solve the problem of generalization, the integration technology was introduced into clustering algorithm, which could significantly improve the generalization ability of learning systems. A co-evolutionary clustering ensemble algorithm based on particle swarm optimization and genetic algorithm (CEGPCE) was proposed. PSO (particle swarm optimization) ensured the algorithm with fast convergence, and GA (genetic algorithm) expanded the search scope with its global search capability, which improved the performance of the algorithm and the convergence speed. Experiments on the UCI data sets verified the effectiveness of CEGPCE.
    A Mean-Shift target tracking algorithm fused multi technology
    GUO Zhibo, DONG Jian, PANG Cheng
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  10-16.  doi:10.6040/j.issn.1672-3961.2.2014.069
    Abstract ( 918 )   PDF (2758KB) ( 480 )   Save
    References | Related Articles | Metrics
    Based on the study of classic algorithm, a Mean-Shift target tracking algorithm fused multi-technology was proposed, and the defects of the classic Mean-Shift tracking algorithm were solved. The center position of target was estimated by the Kalman algorithm. The space information of the target area was extracted using the block color histogram. The combination approach of the background weighted and nuclear weighted was used to suppress the interference of background pixels on the target. The experiments resulted on several video data showed that the new method fused three kinds of technology effectively overcame the barrier and background pixel sensitive problem, and had more accurate tracking than classic Mean-Shift target tracking algorithm under complex environment.
    Improved quantum crossover immune clonal algorithm and its application
    DAI Hongwei, YANG Yu, ZHONG Zhaoman, LI Cunhua
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  17-21.  doi:10.6040/j.issn.1672-3961.2.2014.211
    Abstract ( 793 )   PDF (1073KB) ( 473 )   Save
    References | Related Articles | Metrics
    An improved quantum crossover immune clonal algorithm (IQCICA) was proposed based on two crossovers with complementary characteristics. The hybrid crossover consists of two crossovers with exploitation and exploration characteristics respectively. A user-defined parameter was used to select the crossover. The improved algorithm was used to solve the famous combinatorial optimization problems-Traveling Salesman Problems (TSP). Comparison was also performed with other algorithms. Simulation results showed that the improved algorithm had better convergence and stability, and could effectively balance the global and local search capabilities.
    A semi-supervised method based on tree kernel for relationship extraction
    LIU Xiaoyong
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  22-26.  doi:10.6040/j.issn.1672-3961.1.2014.259
    Abstract ( 862 )   PDF (1287KB) ( 535 )   Save
    References | Related Articles | Metrics
    It was difficult for traditional semi-supervised relation extraction methods to solve "semantic variation" problem. A new semi-supervised relation extraction algorithm based on ensemble learning was prorosed and named L-EC-RE, which used two strategies, one was tree kernel and the other was constrained extension seed set. Experimental study on PopBank benchmark data sets showed that L-EC-RE had better performance than two usual relation extraction algorithms in four assessment criteria, which were Precision, Recall, F-measure and Accuracy.
    Network simplification method for reliability analysis of infrastructure networks
    LIU Xuan, PAN Zhusheng, ZHONG Farong, MO Yuchang, CHEN Zhongyu
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  27-32.  doi:10.6040/j.issn.1672-3961.1.2014.024
    Abstract ( 791 )   PDF (2529KB) ( 668 )   Save
    References | Related Articles | Metrics
    A redundant subnetwork reducing technique was presented for the reliability analysis of infrastructure networks containning articulate nodes. This simplification technique could identify and delete the redundant subnetwork based on articulate nodes, and thus the network reliability could be calculated very quickly based on a reduced network. According to the experimental results on some selected networks from USAir97 benchmark, the redundant subnetwork reducing method could achieve a great reduction on computing time for reliability calculation. Thus the performance of infrastructure networks reliability analysis could be greatly enhanced.
    Quantum ant colony algorithm based on the game theory
    WANG Qiming, LI Zhanguo, FAN Aiwan
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  33-36.  doi:10.6040/j.issn.1672-3961.2.2014.045
    Abstract ( 883 )   PDF (990KB) ( 569 )   Save
    References | Related Articles | Metrics
    Local optimum and low convergence rate were the main problems when used Quantum ant colony algorithm to solve combinatorial optimization, a quantum ant colony algorithm based on game theory (GQACA) was put forward. The algorithm generated a game sequence by the repeated game model, which made every game produce maximum benefit and get Nash equilibrium of the corresponding game process. Five typical test functions were used to make experiment test on the optimal performance of the GQACA algorithm.The experiments showed that the convergence precision and stability of the GQACA algorithm were superior to QACA algorithm and ACA algorithm.
    Tag optimization based on semantic similarity
    QIAN Suchi, PENG Furong, LU Jianfeng
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  37-42.  doi:10.6040/j.issn.1672-3961.2.2014.125
    Abstract ( 979 )   PDF (877KB) ( 786 )   Save
    References | Related Articles | Metrics
    To effectively solve those problems such as lack and misuse of tags in the social media, a tag optimization method based on content similarity and semantic similarity was proposed. Firstly, TF-IDF(term frequency—inverse document frequency) was used to calculate the text similarity. Afterwards, the objective function was defined by the consistency between text similarity and tag similarity. Finally, correction term was added in optimization process to reduce the deviation of tags provided by users. The objective function was applied to Douban Movie to optimize movie tags and the results were compared and analyzed with the original tags. The accuracy of the optimized tags was improved by comparison. Experimental results showed that the method could effectively optimize tags and solve those problems such as lack and misuse of tags.
    Performance comparison between breadth-first ordering and priority ordering in network reliability analysis
    WU Huan, ZHONG Farong, MO Yuchang, PAN Zhusheng, ZENG Lingguo
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  43-48.  doi:10.6040/j.issn.1672-3961.1.2014.011
    Abstract ( 716 )   PDF (1432KB) ( 400 )   Save
    References | Related Articles | Metrics
    In order to explore the correlation between edge ordering heuristics and characteristics of network structure, and to build the method of selecting heuristic relied on network structure, the performances of breadth-first search and priority ordering search were studied based on four kinds of regular network models. Some performance data, such as binary decision diagram size and runtime under two heuristics, were compared emphatically through the experiments. The experimental results showed that different ordering heuristics fitted different network structures: BFS was generally better than POS in the networks of Torus and Square, and POS was generally better than BFS in the De Bruijn and Nearest-neighbor networks. These results could provide reference for choosing the optimal or suboptimal edge ordering heuristic for the particular regular network.
    Maximum likelihood identification method for a multivariable controlled autoregressive moving average system
    GAO Yanpu, WANG Xiangdong, WANG Dongqing
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  49-55.  doi:10.6040/j.issn.1672-3961.0.2014.359
    Abstract ( 687 )   PDF (1094KB) ( 377 )   Save
    References | Related Articles | Metrics
    An algorithm of maximum likelihood method for parameters estimate was presented aimed at multivariable controlled autoregressive moving average (CARMA-like). The algorithm transform the CARMA-like system into m identification models (m is the output numbers), each of which only had a parameter vector which needed to be estimated, and then through maximum likelihood method for estimating parameter vectors of each identification model, and all parameters estimate of the system were obtained. Simulation results verified the effectiveness of the proposed algorithm.
    Model of contact angle of hydrophobic surface based on minimum Gibbs free energy
    SONG Hao, LIU Zhanqiang, SHI Zhenyu, CAI Yukui
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  56-61.  doi:10.6040/j.issn.1672-3961.0.2014.272
    Abstract ( 1068 )   PDF (1432KB) ( 1302 )   Save
    References | Related Articles | Metrics
    Based on the function of Young used for smooth surface and the model of Cassie-Baxter used for rough surface, the prediction model for contact angle of hydrophobic surface based on minimum Gibbs free energy was proposed. The model for contact angle prediction was then modified by considering the influence of skew walls on the contact line between gas-liquid. The effects of hydrophobic surface material properties and geometric parameters on contact angle were analyzed based on the modified model. The results showed that, under the same condition of machined micro-surface, the contract angle on the hydrophobic surface root was larger than that on the hydrophilic one. Besides, for the Cassie-Baxter model, the larger radio between the width of groove and the width of convex was, the larger contract angle was.
    CFD-DEM simulation of bubbling and particle mixing properties in pulsed jet fluidized bed
    REN Libo, SHANG Libao, YAN Rixiong, HE Hailan, ZHAO Hongxia, HAN Jitian
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  62-66.  doi:10.6040/j.issn.1672-3961.0.2014.235
    Abstract ( 860 )   PDF (1970KB) ( 509 )   Save
    References | Related Articles | Metrics
    Based on the MPI (Message Passing Interface) platform of FLUENT software, the parallel simulation technique for pseudo three-dimension computational fluid dynamics-discrete element method (CFD-DEM) coupling model was developed through the user-defined functions (UDFs). Numerical simulation of the gas-solid flow in pulsed jet fluidized bed was conducted by the developed parallel CFD-DEM coupling model, and the bubbling properties for the gas phase and particle mixing properties were revealed. Simulation results showed that the developed parallel CFD-DEM coupling model could have good scalability and speeded-up performance with increase in the number of computing nodes. Small-scale vortices on both sides of the mainstream gradually evolved into two main vortices in the bubbling processes. The particle mixing only occurred in the jet-influenced region after a single bubble had passed through the bed. The simulation results accorded well with the related experimental and simulation results, which showed that this model could well simulate the bubbling and particle mixing properties in dense particulate flows, laying the foundation for the implementation of the model in massively cluster systems.
    Evaluation on the bearing degree of soil acid deposition in Qingdao City
    DU Jinhui, ZHANG Cheng, ZHANG Jian, MU Jinbo
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  67-74.  doi:10.6040/j.issn.1672-3961.0.2014.149
    Abstract ( 822 )   PDF (2066KB) ( 469 )   Save
    References | Related Articles | Metrics
    To solve the soil ecosystem damage problems caused by the atmospheric acid deposition, a method for evaluating the carrying capacity of acid deposition on soils was proposed. With the support of geographic information system, the acid deposition flux was used as a pressure from outside of soils using OMI data and the ground observation data, the critical load of acid deposition was used as a max buffer capacity, and the bearing degree was used as an index for evaluating the carrying capacity status of acid deposition. The proposed method was applied to evaluate the carrying capacity of acid deposition on soils in Qingdao City and the results showed that the carrying capacity levels of acid deposition on the soils on a regional scale could be evaluated, the constraints such as lack of the ground monitoring data could be avoided, and the spatial needs for the study of the atmospheric acid deposition could be met. Compared with the traditional methods, with the atmospheric remote sensing data products be used, the proposed method could provide the supplementary basis for the control of atmospheric acid deposition and the reference for similar researches.
    Adsorption of Pb(II) and Ni(II) by pine sawdust
    YU Meiqiong, YANG Jinbei, CHEN Xiuyu, DENG Shu
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  75-81.  doi:10.6040/j.issn.1672-3961.0.2014.217
    Abstract ( 756 )   PDF (1662KB) ( 704 )   Save
    References | Related Articles | Metrics
    Sawdust was used to remove Pb(II) and Ni(II) from water as an absorbent. Effects of sawdust dosage, stirring speed and pH on the adsorption capacity, adsorption kinetics and thermodynamics were discussed. The results showed that sawdust had a good adsorption capacity for Pb(II) and Ni(II). The adsorption process corresponded with pseudo-second-order kinetic model (R2≥0.997 7), the activation energy were 9.808 7 kJ/mol for Pb(II) and 2.859 4 kJ/mol for Ni(II), respectively. The adsorption isotherms of Pb(II) and Ni(II) were consistent well with the Langmuir isotherm (R2≥0.999 2). Thermodynamics analysis showed that the adsorption process was spontaneous and exothermic.
    Efficiency and mechanism of ferric salt enhanced biological phosphorus removal
    SUN Cuiping, ZHOU Weizhi, ZHAO Haixia
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  82-88.  doi:10.6040/j.issn.1672-3961.0.2014.299
    Abstract ( 854 )   PDF (2369KB) ( 615 )   Save
    References | Related Articles | Metrics
    An efficient phosphorus (P) removal bacterium strain was screened from deep-sea bacteria, and phosphorus removal efficiency and mechanism by iron enhanced biological treatment were studied in the high salinity synthetic wastewater. The effects of molar ratio Fe(III)/P, initial pH on phosphorus removal and kinetics of iron enhanced biological phosphorus removal were investigated by batch tests, and the surface morphology of bacteria was studied by SEM-EDS (scanning electron microscopy-energy dispersive X-ray spectroscopy). Results showed that the phosphorus removal efficiency of iron enhanced biological treatment was high and stable at more than 95% compared to those of independent iron and biological treatment. Removal efficiency of phosphorus reached the maximum of 98.5% with molar ratio of Fe(III) and P being 1, which increased 30% than that of the biological treatment, whereas the maximum phosphorus removal was 90% with molar ratio of Fe(III) and P ranging from 2 to 3 by independent iron treatment. Phosphorus removal was mainly ascribed to bacterial growth and aided by iron, and pH was kept stable at about 7.2 when molar ratio of Fe(III) and P being not more than 1. Phosphorus removal was mainly by chemical precipitation with molar ratio of Fe(III) and P being more than 1 because that the pH reduced to 5.5 or even lower by Fe(III) hydrolysis and significantly influenced bacterial growth. Phosphorus removal was kept at above 95% at pH of 6~9 with molar ratio ofFe(III) and P being 1. The dynamic pseudo-first-order model could fit the biological phosphorus removal process well, and the pseudo-second-order model could well describe the iron enhanced biological phosphorus removal without phosphorus releasing for a long time. Except the uptake of part of the phosphorus by bacterial growth and bio-sorption by extracellular polymeric substance, the hydroxyl phosphate iron complex compound and iron phosphorus precipitation induced by bacterium also contributed to the phosphorus removal.
    Emulsion stability of simulated polymer/surfactant flooding produced water
    MIAO Ling, LI Yujiang, LI Feng
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2015, 45(2):  89-94.  doi:10.6040/j.issn.1672-3961.0.2014.226
    Abstract ( 628 )   PDF (1691KB) ( 433 )   Save
    References | Related Articles | Metrics
    The mechanism of oil-displacing agent for the emulsion stability of polymer/surfactant produced water was studied in detail by preparing the simulated polymer/surfactant flooding produced water with light oil (V(petroleum ether):V(benzene)=9:1), which had a comparatively simple component instead of crude oil with complex component. The interfacial tension, Zeta potential of oil droplets and the rheology of oil-water interface were investigated by spinning drop inferface tensiometer, Zeta potential analyzer and surface rheology analyzer.The effects of WPS (petroleum sulfonate), HPAM (partially hydrolyzed polyacrylamide)and salinity on oil-water separation were studied. The results showed that WPS could reduce the interfacial tension and enhance the stability of produced water.With the concentration of HPAM increasing, the bulk phase viscosity increased, which had little effects on final emulsion stability. The increasing salinity could greatly enhance the stability of produced water, which could provide reference for the study of emulsion stability of produced water.