Loading...

Table of Content

      
    20 February 2014
    Volume 44 Issue 1
    Articles
    Protein sequence identification based on improved TIGA-S4VM algorithm
    WANG Xiao-feng, SUI Ting-ting
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  1-6.  doi:10.6040/j.issn.1672-3961.1.2013.029
    Abstract ( 783 )   PDF (1465KB) ( 1714 )   Save
    Related Articles | Metrics

    In order to effectively deal with the choice blindness of parameters and unbalanced class sizes, TIGA-S4VM, a protein sequence identification model was developed and trained using safe semi-supervised support vector machine (S4VM) based on improved TF-IDF algorithm and Genetic Algorithm (GA). LBTF-IDF, the improved TF-IDF algorithm, was put forward in this model for extracting the protein sequences′  features. After the normalization of features′  frequencies, the results were taken as the characteristic values for classifier. Combining LBTF-IDF, GA and S4VM, the mixed strategy was used to identify the protein sequences. Experiment results showed that the method was superior to other five classification methods and could get good classification performance with reduced training set.

    Adaptive hot topic tracking model based on relevance feedback
    ZHAI Dong-hai1,2, YU Jiang1, NIE Hong-yu1, CUI Jing-jing1, DU Jia1
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  7-12.  doi:10.6040/j.issn.1672-3961.0.2013.141
    Abstract ( 923 )   PDF (1288KB) ( 1128 )   Save
    Related Articles | Metrics

     To solve the topic excursion problem in hot topic tracking process, an adaptive hot topic tracking model based on relevance feedback was proposed. To obtain the topic dynamic evolution procedure accurately, firstly, a correlation factor was introduced into TF-IDF (term frequency—inverse document frequency) for extracting feature words. Secondly, a formula for computing relevance degree between story and topic was constructed, and a discriminant function for determining whether the new feature word could be added into the topic lexicon was also constructed. At the same time, the methods for dynamically computing adaptive updating threshold and adaptive correlation threshold were given. Finally, in the updated topic lexicon, our approach gave the new weight to each feature word according to its contribution to the topic. The experimental results showed that the proposed method could reduce the false alarm rate 0018 and the miss alarm rate 0.063 compared with the other 3 trackers in the hot topic tracking process, which concluded that this proposed technique was more suitable for solving the problem of topic drift.

    A method of gender discrimination based on character feature of Chinese names
    YU Jiang-de1, ZHAO Hong-dan1, ZHENG Bo-ju1, YU Zheng-tao2
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  13-18.  doi:10.6040/j.issn.1672-3961.2.2013.274
    Abstract ( 927 )   PDF (1046KB) ( 2104 )   Save
    Related Articles | Metrics

    Based on the strong gender discrimination of Chinese names, a method of gender discrimination based on character feature of Chinese names using nave Bayes classifier was presented. In this method, the first character of each Chinese name (Zi1), the second character (Zi2), the first and the second characters (Zi1Zi2) were regarded as distinguishing features. The nave Bayes classification method was used for gender discrimination of Chinese names. Training and testing were done on 412775 Chinese names corpus using 10 fold cross validation method, and comparative experiments were done according to the different feature combinations, they were  Zi1, Zi2, Zi1+Zi2, Zi1+Zi1Zi2, Zi2+Zi1Zi2, Zi1+Zi2+Zi1Zi2(all the distinguishing features). The average accuracy were as followings in turn, 72.75%,86.92%, 88.84%, 87.37%, 89.35%, 90.06%, of which the best average accuracy was 90.06%.

    TE mode analysis based on a new Padé approximant BPM algrorithm
    LIU Yang, GE Lian-sheng*
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  19-23.  doi:10.6040/j.issn.1672-3961.0.2013.223
    Abstract ( 904 )   PDF (1493KB) ( 903 )   Save
    Related Articles | Metrics

    The most common method used in the wideangle BPM(beam propagation method)was the (p, p) Padé approximant formalism, which could not damp the evanescent modes for the algorithm itself. A new BPM based on a direct approximation to the propagator using (p-1, p) Padé approximant was applied to tapered waveguide for TE polarized waves. Based on the results of the new method, it was found that the new method of (p-1, p)  Padé approximant could obviously suppress the evanescent modes in TE mode, and could be more accurate to the propagating modes with the increase of p.

    Research on imagine attention of lowlevel features  based on fMRI
    BAO Shu-zhe1,2, ZHU Yue-huan1, WANG Chun-li1*
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  24-28.  doi:10.6040/j.issn.1672-3961.1.2013.233
    Abstract ( 793 )   PDF (1823KB) ( 1161 )   Save
    Related Articles | Metrics

    The cognitive mechanisms of human brain based on fMRI were studied to get the image features that the subjects paied attention to when they saw the images. The shape, texture and color perception regions were located in the brain for every subject through one fMRI experiment, and these regions were defined as interest regions. The mean percent bold signal changed in interest regions was calculated when the subjects were watching face, bus, dinosaur and mountain images through another fMRI experiment. The image features that the subjects pay attention to were different when they saw different images.

    Intrusion detection scheme based on traffic scenarios in vehicular adhoc networks
    LI Chun-yan, LIU Yi-liang, WANG Liang-min*
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  29-34.  doi:10.6040/j.issn.1672-3961.0.2013.192
    Abstract ( 823 )   PDF (1293KB) ( 1615 )   Save
    Related Articles | Metrics

    To reduce various intrusion behaviors   that might damage  the drivers and passengers in vehicular ad-hoc networks (VANETs), a mixed intrusion detection scheme (MIDS) based on different traffic scenarios was proposed. While the vehicles were running on the same road, message integrity method (MIM) was used, otherwise VOTE method was chosen. When the network condition was allowed, the corresponding scenario information could be requested to prove the reality of alert messages. The simulation results showed that the proposed method outperformed the existing intrusion detection methods in terms of communication delay and detection rate. Meanwhile, this method could overcome the limitations of existing schemes and could detect many intrusion behaviors efficiently.

    Color smoke image recognition based on differential box-counting fractal dimension algorithm
    YU Hai-jing1,2, LI Gui-ju1*
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  35-40.  doi:10.6040/j.issn.1672-3961.1.2013.292
    Abstract ( 884 )   PDF (2050KB) ( 1223 )   Save
    Related Articles | Metrics

    The smoke recognition method was proposed which used the differential box-counting fractal dimension combined with the color feature, in order to effectively identify the smoke from the forest background in color image. First, differential box dimension algorithm was used to calculate the fractal dimension value of the whole image. Second, based on the value of the image segmentation and smoke color characteristics in RGB color space, smoke region was recognized according to the split of differential box counting method regional discrimination. The algorithm reduced the number of sub-window within the coverage of the box to improve the accuracy of algorithm calculation and the speed of arithmetic operation. The changed gradation within the sub-window was proposed. The results showed that the improved differential box counting method, combined with color feature technique could accurately identify the smoke. The surface texture information was better reflected in the image and the speed of calculation is increased by nearly 50%.This method can be used for early warning of forest fires.

    An improved induction algorithm based on ordinal decision tree
    PAN Pan1, WANG Xi-zhao2, ZHAI Jun-hai2
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  41-44.  doi:10.6040/j.issn.1672-3961.1.2013.256
    Abstract ( 815 )   PDF (1189KB) ( 878 )   Save
    Related Articles | Metrics

    An improved ordinal decision tree algorithm was proposed. The extended attributes selected with the proposed algorithm maximized the ranking mutual information between the candidate attributes and the decision attribute, and also minimized the ranking mutual information between the candidate attributes and the selected conditional attributes on the same branch. The experimental results showed that  the correlation to be taken account among the conditional attributes could  avoid to  selecte  the same one, and the ideas of the proposed method could really reflect the nature of the ranking mutual information. The proposed algorithm could improve the test accuracy compared with the existing algorithms.

    Facial expression recognition based on adaptive dictionary learning and sparse representation
    XIA Hai-ying1, DU Hai-ming2,XU Lu-hui1, YAN Yuan-hui1
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  45-48.  doi:10.6040/j.issn.1672-3961.1.2013.009
    Abstract ( 813 )   PDF (1496KB) ( 1283 )   Save
    Related Articles | Metrics

    A facial expression recognition method based on adaptive dictionary learning and sparse representation was proposed. Eyes and mouth were located by Haar-like features and the geometric structure of face. For learning dictionaries, random blocks near facial salient points were extracted, and those blocks were trained from the same kind of expression to form one expression dictionary. Then, all expression dictionaries were arranged into a learned dictionary. The test expressions were classified by sparse decomposition. The good performance was verified by the experiments on standard JAFFE and Cohn-kanade expression database. Good robustness was obtained even if the image had noise corruption or under occlusion.

    H∞-controller design for a class of nonlinear Hamilton networked contol systems with actuator saturation
    HONG Xiao-fang1,2, WANG Yu-zhen1*, WEI Ai-rong1
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  49-56.  doi:10.6040/j.issn.1672-3961.0.2013.142
    Abstract ( 854 )   PDF (1421KB) ( 832 )   Save
    Related Articles | Metrics

    The H∞ state-feedback controller design problem for a class of nonlinear Hamilton networked control systems with actuator saturation was investigated. Subject to actuator saturation, uncertain networkinduced delays and data packet dropout were included in the networked control systems. The disturbances of the systems studied have unknown statistical characteristics but bounded norm. First, according to the structural characteristics of Hamilton systems and the bound of networkinduced delays and data packet dropout, networkinduced delays and data packet dropout were changed into time-varying time-delay. Then, by using the stability theorem of Lyapunov-Krasovskii,  the H∞ controller was designed and which also satisfied the requirements in  H∞ performance. The unknown parameters of the controller were obtained by solving a special kind of inequalities. Finally, a example was given to illustrate the efficiency of the proposed method.

    Gait planning and control of a biped robot walking up and down stairs
    WANG Hai-yan, LI Yi-bin*
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  57-62.  doi:10.6040/j.issn.1672-3961.0.2013.147
    Abstract ( 973 )   PDF (2649KB) ( 1374 )   Save
    Related Articles | Metrics

    Focusing on the walking stability of humanoid robot going up and down stairs, according to the restrains condition of the stairs, the gait for the biped robot climbing up and down stairs dynamically and the corresponding control policy for the biped robot walking stably were proposed. The gait planning method which kept the COM (Center of Mass) of the biped robot in the dynamic balance was proposed and the maximum displacement of the trunk was used to realize the stability of the biped robot in the lateral plane. Cubic polynomial fitting was used in the gait generation of the forward motion and gravity directions. In order to keep the motion stability of the biped robot in the frontal plane, the stairs information combining with the trunk posture angles and the corresponding angular velocity which were obtained from VG (Vertical Gyro), were used to adjust the COM position in the forward motion and the gravity directions. The validity of the proposed methods was verified by the simulations of the biped robot climbing up and down stairs dynamically.

    Refining of the membership function in cross fuzzy entropy and its influence
    HE Si-yan1, LI Peng2, LIU Cheng-yu2, WU Xue-qian2, CHEN Qi-jun3
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  63-68.  doi:10.6040/j.issn.1672-3961.0.2013.278
    Abstract ( 822 )   PDF (1352KB) ( 792 )   Save
    Related Articles | Metrics

    To further improve the statistical performances of cross fuzzy entropy (X-FuzzyEn) algorithm, an adjustable factor  λ  was introduced and a refined X-FuzzyEn method was developed accordingly. Its statistical stability and relative consistency was tested by coupled noise and coupled MIX(p) models. Then it was validated by the coupling analysis of heart rate and cardiac diastolic period series between heart failure patients and healthy subjects. Results indicated that the refined algorithm had significantly improved performances and it was capable to tell the differences between heart failure patients and healthy subjects.

    In-situ measurement study on deformation and internal force of pile-anchor retaining excavation
    ZHAN Yong-liang1, SHU Ji-cheng2, SHAO Guang-biao2, SUN Jian-ping2
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  69-74.  doi:10.6040/j.issn.1672-3961.0.2013.254
    Abstract ( 675 )   PDF (2349KB) ( 907 )   Save
    Related Articles | Metrics

     Based on the monitoring data of pulling and arching supporting structure of deep foundation pit in Jinan, the correlations of  cable stress, displacement and internal force of the pile were studied. The factors that influence the displacement of excavations and the settlement of surrounding buildings were discussed.Some useful conclusions were drawn, which could help the pit design and construction. First,the monitoring data of foundation pit anchor cable tension analysis showed that the loss of prestress was bigger with the improper measures when the cable was stretched. Second, by setting the inclinometer pipe and steel bar stress gauge monitoring of pile displacement and internal force analysis, the point of inflection of displacement and internal force of pile appeared when the pit was bottomed, and the displacement and internal force of pile could be effectively controlled by combined action of top beam and anchor cable. Third, based on the observation and analysis of settlement of surrounding buildings, it was found that the distance to pit edge and dewatering were the key factors of surrounding building settlement. The settlement of building surroundings pit could be ignored with better soil conditions.

    Experiment research on unconfined compressive strength of cement soil under small age
    ZHOU Hai-long, SHEN Xiang-dong, XUE Hui-jun
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  75-79.  doi:10.6040/j.issn.1672-3961.0.2013.276
    Abstract ( 817 )   PDF (1137KB) ( 1411 )   Save
    Related Articles | Metrics

     The cement mixing ratio  was respectively selected as 5%, 10%, 15%, 20%, and the curing age was respectively selected as 7, 14, 21, 28d to put forth the uniaxial compression test. The value of unconfined compressive strength and the change law of stressstrain curve for cement soil was obtained. Finally, the influence of cement mixing ratio and small age on mechanical behavior of cement soil were quantitatively analyzed, and the mathematical expression of stressstrain relation curve was granted, which could  provide science foundation for applying cement soil into irrigation channel liner impervious engineering and civil construction engineering in the middle area of Inner Mongolian Autonomous Region.

    Anti-reflective property of Ni-P/cicada microstructure composites
    CHEN Ting, QIN Ji-ning, FAN Tong-xiang*
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  80-84.  doi:10.6040/j.issn.1672-3961.0.2013.320
    Abstract ( 729 )   PDF (2926KB) ( 2086 )   Save
    Related Articles | Metrics

    The Ni-P/cicada  wing composites with nano-array structure were prepared by utilizing Pomponia imperatoria wing as the substrates of electroless plating. The microstructures of the samples were characterized by scanning electron microscope (SEM) and transmission electron microscope (TEM), and the component as well as the optical property was respectively tested by X-ray photoelectron spectrometer (XPS) and UV-VIS-NIR spectrophotometer. Moreover, in order to investigate the effect of the nano-array structure on the antireflection property of the Ni-P coating, the 3D finite difference time domain (3D-FDTD) method was used to calculate the reflectance spectra of the synthesized composites based on the experimental data. Result showed that the reflectance of Ni-P/cicada  wing composites with nano-array structure was 70% lower than that of the one without the surface structure, which was ascribed to the interaction between the nanoarray structure and the incident light. This work could provide inspirations for the  antireflective Ni-P surface structure design.

    Wind power prediction based on time-series and BP-ANN
    MA Chang-hui1, FENG Jiang-xia2, JIANG Zhe1, WU Nai-hu1, L Xiao-lu3
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  85-89.  doi:10.6040/j.issn.1672-3961.0.2012.261
    Abstract ( 859 )   PDF (1768KB) ( 1325 )   Save
    Related Articles | Metrics

    To solve the problem that non-linear relationship between wind speed and wind power could amplify prediction error, the improved model for wind speed and wind power forecasting in short term was proposed based on time series and back propagation artificial neural network (BPANN). First, the time series model was built to forecast wind speed. Then the BP-ANN model of wind speed-to-power was set up and the predicted wind speed was input into the model to obtain wind power. Taking a wind power plant as an example, mean absolute error and correlation index of the improved model and the conventional model were compared, and the result showed that the improved model could improve wind power forecasting accuracy.

    Experimental analysis of condensation heat transfer characteristics under vacuum condition of Nickel based implanted tube bundle
    CHENG Shen, SUN Feng-zhong*
    JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(1):  90-94.  doi:10.6040/j.issn.1672-3961.0.2013.182
    Abstract ( 693 )   PDF (1398KB) ( 1293 )   Save
    Related Articles | Metrics

    The steam condensation heat transfer characteristics of Nickel based implanted tube bundle was studied though comparative experiments and theoretical analysis for exploring effect mechanism on steam condensation heat transfer by surface material characteristics. The results showed that the Nickel based implanted tube bundle had a better performance than common copper tube, especially in a higher vacuum state, the maximum enhance rate was up to 77%. The theoretical research was carried on by analyzing the flow of steam, noncondensed gas thermal resistance and solidliquid interfacial energy, it turned out that dropwise condensation was easily generated under lower pressure and its heat transfer coefficient increased with a rising vacuum, consistent with the subsequent experimental results.