Loading...

Table of Content

      
    30 June 2016
    Volume 46 Issue 3
    Automatic recognition method of microscopic image of harmful algae
    QIAO Xiaoyan
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  1-6.  doi:10.6040/j.issn.1672-3961.2.2015.044
    Abstract ( 1585 )   HTML   PDF (1498KB) ( 903 )   Save
    References | Related Articles | Metrics
    At present, the microscopic image identification of harmful algae based on biological morphological features are applied widely. However, there are some challenges, such as limited algae species resources, the difficulty of describing biological detailed features. To solve these problems, the identification of harmful algae was divided into four gradual processes: precise segmentation, feature extraction, feature dimension reduction and classification. First, the method based on projection and integral on multiple directions was proposed to extract cell object, and then the spine and cingulum were extracted. Second, the effective description were proposed after shape features, moment invariants, texture features and domain specific features were extracted. Then, SVM classifier was designed to recognize objects. Experimental results showed that this algorithm could achieve the quicker and better segmentation and recognition of 15 species of algae.
    A new multi-focus image fusion method based on deep neural network model
    LIU Fan, CHEN Zehua, CHAI Jing
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  7-13.  doi:10.6040/j.issn.1672-3961.2.2015.106
    Abstract ( 1532 )   HTML   PDF (2708KB) ( 1218 )   Save
    References | Related Articles | Metrics
    There existed low-frequency information distortion phenomenon in fusing multi-focus images. Aimed to solve the problem, a new fusion strategy based on deep neural network model was proposed for fusing low-frequency subbands. Combined with Wavelet Kernel Filter and traditional fusion strategy for high-frequency subbands, a new fusion method for fusing multi-focus images was given. The method extracted efficient features by using AutoEncoder model. The experimental results showed that proposed method could obtain better images. The edge fusion qualify value of the proposed fusion result was 0.802 7, compared with traditional fusion strategy, contourlet-based multi-focus method and non-sampled contourlet-based multi-focus method, 0.761 4, 0.722 7, and 0.716 4, which could provide an effective method for fusing multi-focus images.
    Object tracking via L1 norm and least soft-threshold square
    WANG Haijun, GE Hongjuan, ZHANG Shengyan
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  14-22.  doi:10.6040/j.issn.1672-3961.0.2015.316
    Abstract ( 1376 )   HTML   PDF (9565KB) ( 898 )   Save
    References | Related Articles | Metrics
    Due to the occlusion and motion blur in the traditional object tracking algorithm, a novel object tracking algorithm via L1 norm and least soft-threshold square was proposed to solve the problem of the failure of object tracking based on sparse representation. Firstly, the appearances of the object were modeled by the PCA(Principal Component Analysis)basis vector and the representation coefficients were constrained by L1 norm. Secondly, the trivial error was solved by the least soft-threshold square and the occlusion factor was taken account in the updation of the observation model. At last, the object tracking algorithm was developed in the Bayesian inference framework. Experiments were conducted on fourteen challenging videos and the experimental results showed that the proposed algorithm could cope well with the occlusion, angle variation, scale variation and illumination variation, with the higher average overlap rate and the lower average center point error, compared with the other tracking algorithm.
    A localization algorithm based on RSSI vector for wireless sensor networks
    LIU Chen, CAI Ting
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  23-30.  doi:10.6040/j.issn.1672-3961.1.2015.099
    Abstract ( 1358 )   HTML   PDF (1900KB) ( 792 )   Save
    References | Related Articles | Metrics
    In order to reduce the edge location error of unknown nodes in the location unit, a quadrilateral region localization algorithm was proposed. Based on the different locations of unknown nodes in the location unit, the algorithm adopted either internal or external location mechanism of the location unit. Then, the vector similarity was introduced to facilitate the search of reference sample nodes closest to unknown nodes. Experimental results demonstrated that the proposed algorithm could reduce up to 50 percent of the location error. With the number of anchor nodes increasing, the location accuracy increased, and the accuracy values tended to be stable. The algorithm could also solve the problem that the location accuracy of unknown nodes.
    Fitting of constrained local model based on manifold
    LIU Dakun, TAN Xiaoyang
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  31-36.  doi:10.6040/j.issn.1672-3961.0.2015.279
    Abstract ( 1411 )   HTML   PDF (3567KB) ( 827 )   Save
    References | Related Articles | Metrics
    For the sake of embedding the manifold of face shape vectors into the models of face alignment efficiently, the research was carried out based on the typical constraint local model in the face location parameter model. According to the theorem of local coordinate coding and sparse constrain, the non-rigid deformations were replaced by the adjacent facial shape vectors which were based on manifold of facial shapes. The local tangent space alignment in manifold learning was mixed with the point distribution model, and a manifold embedded constrained local model was derived. The experimental verification on the toyed dataset and two public facial databases(i.e. labeled face parts in the wild and labeled face in the wild)were fulfilled. Compared with linear reconstruction based on constrained local model method fitting, the manifold embedded constrained local model method had better accuracy.
    Depth perceptual model based on the single image
    MENG Lingheng, DING Shifei
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  37-43.  doi:10.6040/j.issn.1672-3961.2.2015.007
    Abstract ( 1490 )   HTML   PDF (2452KB) ( 1598 )   Save
    References | Related Articles | Metrics
    In order to overcome the expensive cost of stereo vision based on depth perceptual models, the single image based on depth perceptual model which mainly supported by machine learning algorithms was proposed. The formula presentation of the single image based on the depth perceptual model and the selecting of multi-scale image features was studied, and this model was used to predict depth image, furthermore the depth image was utilized to reconstruct the 3D scene. The experiments showed that single image based on depth perceptual model could make well predictive precise, faster predictive speed, and better reconstruction results.
    The method of spot cluster recommendation in location-based social networks
    LI Shuo, SHI Yuliang
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  44-50.  doi:10.6040/j.issn.1672-3961.0.2015.295
    Abstract ( 1485 )   HTML   PDF (1626KB) ( 985 )   Save
    References | Related Articles | Metrics
    In order to solve the data sparse and cold start in spot recommendation in the location-based social networking, an improved spot recommendation method was proposed. Based on the clustering algorithm and the collaborative filtering algorithm, the user preferences, friend relations, semantic location and other factors was taken into account. The advantages of the two methods were complemented. The focus of this research was the calculation of similarity, which included location similarity, friends intimacy measure, term frequency inverse document frequency, cosine similarity.To verify the proposed methods, precision, recall,mean average precision was used as a measure on Foursquare dataset. The results showed that the proposed method could effectively improve the recommendation effect.
    Time series classification using piecewise vector quantized approximation based on Mahalanobis distance
    TAO Zhiwei, ZHANG Li
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  51-57.  doi:10.6040/j.issn.1672-3961.2.2015.050
    Abstract ( 1413 )   HTML   PDF (2595KB) ( 797 )   Save
    References | Related Articles | Metrics
    A Mahalanobis distance-based time series classification using PVQA(MPVQA)algorithm was developed. On the basis of inheriting the time complexity of the traditional algorithm and by exploiting Mahalanobis distance, the algorithm could easily overcome the default that the Euclidean distance was easily influenced by the mode characteristic dimension and improve the accuracy. PVQA was first used to generate a codebook using training samples, and then the Mahalanobis distance was taken as the measure of similarity and used to reconstruct time subsequences. For an unseen time series, the Mahalanobis distance was also adopted to find the most similar one to it. Experimental results on four time series datasets demonstrated that our method was more powerful to classify the time series.
    Neighborhood similarity descriptor used in halftone image
    ZHONG Zhiyan, WEN Zhiqiang, ZHANG Xiaoyun, YE Degang
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  58-64.  doi:10.6040/j.issn.1672-3961.1.2015.092
    Abstract ( 1471 )   HTML   PDF (3648KB) ( 746 )   Save
    References | Related Articles | Metrics
    Local binary pattern was obtained by extracting local features, which was appropriate for unobvious textural features but suffered high feature dimension problem. To solve this problem, the neighborhood similarity descriptor method for halftone image feature extraction was proposed. First, the center pixel was compared with its eight neighborhood pixels. Second, the similarity index was computed for those pixel pairs. The similarity index was taken as textural feature vector after normalizing the statistics. Finally, BP neural network was adopted to classify the extracted image features in experiment. Experimental results showed that the proposed method was better than the local binary pattern algorithm in the computational complexity and recognition accuracy.
    Multi-criteria collaborative filtering algorithm based on probabilistic matrix factorization
    PANG Juntao, ZHANG Hui, YANG Chunming, LI Bo, ZHAO Xujian
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  65-73.  doi:10.6040/j.issn.1672-3961.2.2015.080
    Abstract ( 1279 )   HTML   PDF (1608KB) ( 966 )   Save
    References | Related Articles | Metrics
    In order to solve the problem that the correlation was neglected among the multi-criteria in the recommendation method of the multi-criteria, a multi-criteria collaborative filtering algorithm based on probabilistic matrix factorization(MCPMF)was proposed. The algorithm represented the multi-criteria as a weight-matrix which has influence on all users and items. The latent distribution of the weight-matrix was assumed to follow Gaussian distribution, and the probability density distribution of the matrix was conditional related to the distribution of user and item latent feature matrix. The user and item feature matrix was learned by probability matrix factorization method. Experimental results on two real datasets showed that the proposed method was more accurate in forecasting the user's overall rating compared with methods which only considered single overall rating and could reduce the impact of data sparsity to recommendation algorithms.
    Face recognition based on kernel Bayesian compressive sensing
    ZHOU Kai, YUAN Changan, QIN Xiao, ZHENG Yan, FENG Wenduo
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  74-78.  doi:10.6040/j.issn.1672-3961.2.2015.075
    Abstract ( 1166 )   HTML   PDF (1112KB) ( 948 )   Save
    References | Related Articles | Metrics
    In order to improve the speed and rate of face recognition, Bayesian compressive sensing algorithm was applied and its kernel extension to face recognition was proposed. Combined with the spatial pyramid model, statistical local feature was improved to extract the features of face images. Firstly, the statistical local feature was used as a feature extractor to obtain facial features and a second layer of local statistics was processed based on the former layer. Then the spatial pyramid was used to obtain features in different spatial scales in order to accomplish the final step of face recognition, the features were classified through kernel Bayesian compressive sensing. The experimental results on the basis of the AR and FERET databases demonstrated that this algorithm had better performance than other traditional ones.
    Stabilization and H control for nonlinear switched Hamiltonian systems subject to actuator saturation
    LI Han, WEI Airong
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  79-86.  doi:10.6040/j.issn.1672-3961.0.2015.394
    Abstract ( 1216 )   HTML   PDF (1253KB) ( 889 )   Save
    References | Related Articles | Metrics
    The stabilization and H control problems of nonlinear switched Hamiltonian systems(NSHSs)subject to actuator saturation under arbitrary switching paths was investigated. The stabilization of NSHSs with actuator saturation was studied by designing suitable state feedback and deriving a sufficient condition. Then, an H controller was designed to realize the H control of NSHSs subject to actuator saturation with external disturbances, under the designed controller, γ-dissipation inequality held for the system with external disturbances, moreover, the globally asymptotical stabilization was achieved for the corresponding closed-loop system without external disturbances. A simulation example showed that the proposed method and results were effective.
    System optimal model of evacuation route selection based on partial variable demand
    GAO Jianjie, SHI Chenpeng, CAO Jianjun, OU Jushang
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  87-92.  doi:10.6040/j.issn.1672-3961.0.2015.243
    Abstract ( 1203 )   HTML   PDF (962KB) ( 838 )   Save
    References | Related Articles | Metrics
    The traffic demand after effects of the emergency was divided into two parts: fixed demand and variable demand. One was the evacuation demand and the other was the original traffic demand in non hazardous areas. A system optimal model of evacuation route selection based on partial variable demand was proposed aimed at minimizing the total travel time of traffic network system. The equivalence between the solution of the model and the system optimal condition of varying demand was proved. And the existence and uniqueness of the solution of the model was analyzed. At last an algorithm of the model was designed from the convex combination method.
    Optimized design of cross-wound cable barrier end anchorage
    LEI Zhengbao, LIAO Zhuo, LIU Zhuchun
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  93-98.  doi:10.6040/j.issn.1672-3961.0.2015.322
    Abstract ( 1389 )   HTML   PDF (1932KB) ( 712 )   Save
    References | Related Articles | Metrics
    In order to research the cross type flexible barrier end anchorage system which conformed to Chinese highway environmental conditions, each part of anchorage system's shape and size was designed according to Chinese actual road environment and referred to foreign guardrail end anchor. Anchorage system model was established using ls-dyna finite element software, the external load of anchorage system and reliable finite element model of wire rope was got combined with real vehicle test and finite element simulation. The initial size of anchorage system was optimized using orthogonal test method. Optimal size was got thorough range and variance analysis. And it was validated through simulation test. The result showed that anchorage system was not pulled out and tilted under external load. The maximum stress of soil was 8.2×10-3MPa, far less than the allowable stress which was 1.7×10-1MPa. Thus, this anchorage system could meet the evaluation index well according to above mentioned.
    The influence of SDS on C-343 solubilizing behavior in SB-16 micelle
    BAI Yanyan, CAO Yuexin, ZHANG Xianxi, ZHANG Luge, SUN Dezhi, YAN Hui, ZHANG Chong
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  99-105.  doi:10.6040/j.issn.1672-3961.0.2016.115
    Abstract ( 1561 )   HTML   PDF (3086KB) ( 740 )   Save
    References | Related Articles | Metrics
    In order to explore the dissolutive law of coumarin(C-343)in the SDS(sodium dodecyl sulfate)/SB-16(N-hexadecyl-N,N-dimethylammonio-1-propanesulfonate)synergistic system, the solvation of C-343 in pure SB-16 micelle solution and the additive of SDS surfactant influencing this solvation process were performed based on molecular dynamics method. The results showed that the C-343 could be spontaneously dissolved in the pure SB-16 micelle in equilibrium at 298 K and 101.3 kPa. After addition of SDS, the SB-16 micelle appeared slightly swollen and its outer surface was inserted by the hydrophobic tails of SDS, forming a thinner SDS outshell covering the SB-16 micelle. Simultaneously, migration of C-343 from the inner of SB-16 micelle back to the outsurface of SDS shell took place due to the hydrohobic and electrostatic interactions. This work provided one convincing evidence that adding certain surfactants in some kinds of micelles could effectively control the solubilization or release behaviors of some drugs in these solutions, and thus give one helpful guidance for those corresponding experimental studies accordingly.
    Investigation of the release behavior of methylene blue from silica@octacalcium phosphate as drug carrier
    LI Chengfeng, LIU Qun, WANG Wenhao, WANG Baiwei, YANG Zanzhong
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  106-111.  doi:10.6040/j.issn.1672-3961.0.2015.395
    Abstract ( 1031 )   HTML   PDF (3371KB) ( 774 )   Save
    References | Related Articles | Metrics
    A modified Pechinni method was employed to synthesize the drug carrier of silica-MB@OCP, which was achieved through deposition of octacalcium phosphate(OCP)on MB-loaded silica particle(silica-MB). The influences of reaction conditions on structural evolution of drug carrier, modulation of release behaviors and decomposition of drug vehicle were studied. The phase, chemical constitution and morphology of silica-MB@OCP were significantly influenced by the molecular weight of polyethylene glycol(PEG), adding amount of PEG and citric acid. The variations of the cumulative release and the ratio of monomer versus dimers of MB with time were sensitivity with the structure of silica-MB@OCP and the pH value of culture solution, which influenced the diffusion of MB. In comparison with those of silica-MB, the degradation ratios of silica-MB in phosphate buffered saline and lysosome-like buffer were much higher as a result of the influence of MB diffusion on the destruction of drug carrier.
    A method of reducing the slip in radial direction of the traveling wave type rotary ultrasonic motor
    JI Yuebo, WU Wangxian
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  112-116.  doi:10.6040/j.issn.1672-3961.0.2015.282
    Abstract ( 1627 )   HTML   PDF (1541KB) ( 801 )   Save
    References | Related Articles | Metrics
    In order to reduce the slip in radial direction of the traveling wave type rotary ultrasonic motor(TRUM), a method of increasing the maximum of shear deformation of friction layer of rotor was put forward to achieve the purpose of reducing the slip in radial direction of TRUM. The factors which affect the radial maximum angle of shear deformation of the friction layer were got based on the principle of stick-slip of the contact area between the stator and the rotor in TRUM. The motors three-dimensional finite element contact model was built and simulation analysis was conducted with finite element software ANSYS10.0. The analysis results showed that the value of coefficient of friction and the value of poissons ratio of the friction layer material could be increased to reduce the slip in radial direction of TRUM. And the influence of the variation of poissons ratio was more noticeable than that of coefficient of friction on reducing the slip in radial direction of TRUM.
    Effect of mass flux on onset of nucleate flow boiling of R134a and tube wall temperature characteristics
    LU Guoqiang, HAN Jitian, KONG Lingjian, CHEN Changnian, HU Guiqiu, CHEN Jun, LI Jiangfei
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2016, 46(3):  117-122.  doi:10.6040/j.issn.1672-3961.0.2015.288
    Abstract ( 1521 )   HTML   PDF (1667KB) ( 1070 )   Save
    References | Related Articles | Metrics
    In order to obtain the characteristics of onset of nucleate flow boiling(ONB)and tube wall temperature distributions in helically-coiled tube, an experiment was conducted with the working medium R134a. The ONB was determined by observing the wall temperature changes when the heat flux was increased gradually. Analysis of the experimental results was performed to reveal the related mechanism. The results indicated that the heat flux of ONB increased with increase in the mass flux of R134a, however, the mass flux, centrifugal and gravity forces had different influences on the bubble behavior of detaching and reattaching in some cases, resulting in different trends in some positions measured in the experiment. In single-phase, the wall temperatures in the selected points decreased with increase in the mass flux of R134a; under flow boiling conditions, the increase in the mass flux only resulted in a slight change in the tube wall temperatures. The experimental results can provide a reference for the reliable design and safe operation of helically-coiled tube heat exchangers.