Table of Content

  

20 December 2014
Volume 44 Issue 6

Improved genetic algorithm based on the dual-mode mutation strategy

LIANG Xingjian, ZHAN Zhihui

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  1-7.  doi:10.6040/j.issn.1672-3961.2.2014.306

Abstract ( 1575 )   PDF (2523KB) ( 634 )   Save

References | Related Articles | Metrics

Aiming at the defects in the standard genetic algorithm such as slow optimization speed and local optimum, an improved genetic algorithm based on the Dual-Mode Mutation strategy is put forward. On the basis of the standard mutation, the idea of individual linear difference mutation is introduced to form the Dual-Mode Mutation balanced by the controlling parameters. The results of simulation experiments on 10 benchmarking functions shows that this algorithm can greatly improve the optimization speed and global convergence and has application value.

Human contour segmentation in image sequence based on region consolidation and contour model

ZHU Hongjin, FAN Honghui, YE Feiyue, ZANG Haijuan

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  8-14.  doi:10.6040/j.issn.1672-3961.2.2013.333

Abstract ( 1509 )   PDF (1940KB) ( 648 )   Save

References | Related Articles | Metrics

Affected by complexity of image background, it was more difficult to achieve high-precision of human contour tracking in image sequence based on watershed algorithm. In order to improve the detection precision, a region consolidation method based on color space transform and a contour model of head using head position information were proposed. The upper part of the human body template based on contour model of head and Gaussian function was founded. The proposed method could be achieved by human detection and tracking without motion vector and inter-frame difference. Human contour could be segmented correctly in image sequence based on color space transform of region consolidation and contour model of head in changing and complex video background. Experimental results demonstrated that human contour could be segmented effectively. The effectiveness and robustness of the proposed method were indicated by the experiments.

The sentiment mining method based on extended sentiment dictionary and integrated features

XU Xiaodan, DUAN Zhengjie, CHEN Zhongyu

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  15-18.  doi:10.6040/j.issn.1672-3961.1.2014.108

Abstract ( 1885 )   PDF (1466KB) ( 1621 )   Save

References | Related Articles | Metrics

In the traditional classification method, only one feature was considered, that was not good enough for the precision. In order to improve the precision, a classification method based on integrated features was provided. First, the emotional tendency value of one word was calculated according to an extended sentiment dictionary; then after the CHI selection, the weights of the positive and negative emotion word posterior probability in the Bayesian model were adjusted acrodding to its tendency value. In the experiments, four kinds of corpus such as hotel and movie reviews were used, compared with other three methods, the integrated features method was better. The results showed the precision of classification was improved and the dimension of the feature was reduced.

A prediction method of atmospheric PM_2.5 based on DBNs

ZHENG Yi, ZHU Chengzhang

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  19-25.  doi:10.6040/j.issn.1672-3961.1.2014.180

Abstract ( 1971 )   PDF (1805KB) ( 2892 )   Save

References | Related Articles | Metrics

A DBNs-based (deep belief networks) method for forecasting the daily average concentrations of PM_2.5 in Xian was proposed. Besides, the way to select training data set as well as the DBNs parameters was optimized. Then relative experiments and comparison with methods based on BP (back propagation) and RBF (radial basis function) artificial neural network confirmed the feasibility and precision of DBNs. The results showed that the MSE (mean square error) between DBNs simulated PM_2.5 daily average concentrations and observed ones was 8.47×10^-4 mg²/m⁶, while the MSE of RBF and BP was 1.30×10^-3 mg²/m⁶ and 1.96×10^-3 mg²/m⁶ respectively. Therefore the DBNs-based method was fit for prediction of PM_2.5 concentrations and it predicted more accurately than those methods based on RBF and BP artificial neural network.

LDA-based link prediction in social network

LU Wenyang, XU Jiayi, YANG Yubin

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  26-31.  doi:10.6040/j.issn.1672-3961.1.2014.116

Abstract ( 1404 )   PDF (1173KB) ( 2164 )   Save

References | Related Articles | Metrics

To address the problem of ignoring the text contents of nodes in social network link prediction methods, a Latent Dirichlet Allocation(LDA)-based collaborative evolutionary link prediction algorithm was proposed. The algorithm used LDA model to analyze the text content and abstracted a topic distribution vector for each node; The product of the topic distribution vectors was adopted to measure the similarity between the nodes' contents; Afterwards, the content similarity matrix was added to the adjacency matrix and the similarities between the nodes were computed consequently; At last, k most similar nodes were selected as the prediction result. The experimental results showed that the proposed algorithm achieved good prediction performance in sparse networks.

Chinese entity relation extraction based on entity disambiguation

SHAO Fa, HUANG Yinge, ZHOU Lanjiang, GUO Jianyi, YU Zhengtao, ZHANG Jinpeng

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  32-37.  doi:10.6040/j.issn.1672-3961.1.2014.163

Abstract ( 1834 )   PDF (1979KB) ( 1582 )   Save

References | Related Articles | Metrics

To solve the polysemy problem in Chinese Entity Relation Extraction in open text, a Chinese entity relation extraction method based on entity disambiguation was proposed. First, mining entity relation pairs from HowNet,and the entities were mapped from HowNet to Wikipedia by using disambiguation method based on Bayesian classification so as to obtain high-quality relationship instance; Then, extracting the sentence instances in the corresponding context with these relation instances, to construct a basic extraction pattern; Finally, extracting new cases use the new pattern. The experimental results showed that the accuracy of the proposed method was higher than the methods without semantic disambiguation and pattern merging.

AC_SAR: actionable clustering algorithm based on strong association rule

YAO Huachuan, WANG Lizhen, WU Pingping, ZOU Muquan

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  38-46.  doi:10.6040/j.issn.1672-3961.2.2013.284

Abstract ( 1424 )   PDF (1236KB) ( 590 )   Save

References | Related Articles | Metrics

An actionable clustering algorithm based on strong association rules (AC_SAR) was proposed. The AC_SAR algorithm looked for strong associated objects for each object, and then some relevant rules were deleted and merged by the anti-symmetric principle and the connectivity principle. The connected sub-graphs (clusters) related to all objects in transaction database were discovered finally. Compared with the traditional algorithms, the AC_SAR algorithm did not need to set the thresholds by user, and there were not redundant rules in the results. Moreover, the intermediate mined results and the final generated clusters could solve the problems in many fields effectively. A large number of experiments showed that the AC_SAR algorithm had higher efficiency, higher accuracy, and stronger action.

Cloud robotics: concept, architectures and key technologies

TIAN Guohui, XU Yaxiong

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  47-54.  doi:10.6040/j.issn.1672-3961.0.2014.282

Abstract ( 2144 )   PDF (1959KB) ( 2480 )   Save

References | Related Articles | Metrics

The technology of cloud robotics is the combination of cloud computing and robotics. It can bring great advantages in task execution and resource sharing for robots, and has become a hot topic in intelligent robot research field. In this paper, the developments of cloud robotics, key technologies, main platforms, main architectures and application prospects were comprehensively analyzed. Firstly, the concept arose of cloud robotics and its developments were introduced, and also the key technologies were given. Secondly, three main cloud service platforms were horizontally contrasted, and the main architectures of cloud robotics were analyzed. Finally, the application prospects for cloud robotics were comprehensively presented.

Model construction of travel behavior based on static and dynamic fictitious play games

LIU Jianmei, MA Shuaiqi

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  55-62.  doi:10.6040/j.issn.1672-3961.0.2014.079

Abstract ( 1420 )   PDF (872KB) ( 651 )   Save

References | Related Articles | Metrics

Travel fictitious play convergence theorem was proved by games with strategic complementarities in order to broaden the condition when the theorem was tenable, and the convergence result was given under different congestion types. Then the convergence of static and dynamic fictitious play models was discussed based on the conclusion under various strategy combinations. Finally, one numerical example was given. Experimental results showed that numerical results were consistent to theory results, which verifies the rationality of traffic fictitious play models.

Images tamper detection and recovery based on block features and chaotic sequence

ZHANG Junpeng, ZHANG Qingfan, YANG Hongjuan

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  63-69.  doi:10.6040/j.issn.1672-3961.0.2014.098

Abstract ( 1460 )   PDF (2797KB) ( 535 )   Save

References | Related Articles | Metrics

To improve the performance of images tamper detection and recovery, an authentication watermarking scheme based on block features and chaotic sequence was presented. For each block of size 2×2 pixels,discrete cosine transform(DCT)coefficients were used to generate watermarking and embedded into the two least significant bits of its mapping block which was determined by chaotic sequence. The conventional authentication methods were improved by combining parity detection and the tampered region could be self-recovered by extracting characteristic information of the valid block. Experimental results demonstrated that the proposed method not only improved the quality and security of watermarked images, but also could detect tampered regions accurately and reconstruct images while keeping the recognition quality. Additionally, the scheme was not vulnerable to the content-only attack.

An emotion recognition method of multiphysiological information fusion based on PCA-SVM

LI Faquan, YANG Licai, YAN Hongbo

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  70-76.  doi:10.6040/j.issn.1672-3961.0.2014.120

Abstract ( 1858 )   PDF (1898KB) ( 1197 )   Save

References | Related Articles | Metrics

To reduce the complexity of the emotion-recognition algorithm caused by multiphysiological information fusion an emotion recognition method based on Principal Component Analysis (PCA) and Support Vector Machine (SVM) was proposed. The influential weights of emotion recognition were calculated for initial features by the PCA, and the features of which the weights were larger than a certain threshold were selected to compose the new feature set. Thus the dimension of the classifierinputs could be reduced so that the complexity of the algorithm will be simplified. Experimental results showed that the PCA-SVM algorithm for sentiment analysis could effectively improve the efficiency of emotion recognition.

Design of a fractional order IMC-ID^μ controller for high order systems

WANG Huifang, ZHAO Zhicheng, ZHANG Jinggang

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  77-82.  doi:10.6040/j.issn.1672-3961.0.2014.172

Abstract ( 1255 )   PDF (1502KB) ( 681 )   Save

References | Related Articles | Metrics

A method of model reduction and fractional order internal model ID^μ controller design was presented for higher order systems. At first, based on the performance index of integral square error (ISE), particle swarm optimization (PSO) was used to reduce the higher order system model and a fractional order model with time-delay was obtained. Then, according to the principle of internal model control (IMC), a fractional order IMC-ID^μ controller was derived by approximating the time-delay term of the model with the first-order Taylor series. The controller contained only one adjustable parameter. Finally, the robust tuning of the controller parameter was realized using the maximum sensitivity index of the system. The simulation results showed that the proposed method could make the system having a better dynamic response characteristic, disturbance suppression performance and robustness against the parameters perturbation of the system.

Molecular dynamics simulation of zwitterionic surfactant sulfobetaine at the vapor/liquid interface

WANG Lijuan, SHI Jing, ZHAO Fangjian

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  83-89.  doi:10.6040/j.issn.1672-3961.0.2014.058

Abstract ( 1667 )   PDF (2576KB) ( 734 )   Save

References | Related Articles | Metrics

The aggregation morphology of zwitterionic surfactant dodecyl hydroxy-propyl sulfobetaine at the vapor-liquid interface was investigated using molecular dynamics method, and the effect of film stability was discussed. Depending on the interface formation energy, the increasing number of surfactant molecules at the interface helped the stability of liquid membrane. Through the radial distribution functions between the head groups of surfactant and water molecules, the water molecules around surfactant molecules were divided into three types, bound water, trapped water and free water. There were important relationships between the stability of foam and the ability of surfactant binding with water molecules through hydrogen bonding and electrostatic interaction. The results showed that this zwitterionic surfactant had strong binding effect to water molecules in the stability of foam.

Numerical study on the air motion of H-type finned tubes and heat transfer characteristics

WU Yanyan, SUN Fengzhong, LI Fei, CHEN Changxian

JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE). 2014, 44(6):  90-94.  doi:10.6040/j.issn.1672-3961.0.2014.125

Abstract ( 1535 )   PDF (2141KB) ( 1240 )   Save

References | Related Articles | Metrics

In order to analyze H-type finned tubes in different arrangement modes numerically, flow and heat transfer numerical models of H-type finned tubes in different arrangement forms were established. The change rules of flow and heat transfer characteristics of two typical arrangements has been obtained. The result showed that the special groove structure of H-type finned tubes turned leeward side into vertical flushing flow field with obvious three-dimensional flow characteristics which had the functions of automatic cleaning and nearly gathering no dust. The heat transfer coefficient of staggered finned parent tubes was higher than that of the parent tubes arranged in equal interval. Additionally, the difference of heat transfer effect was increasingly obvious with the increase of speed. The influence of array pitch of tubes on the heat transfer coefficient of finned tubes was remarkably greater than that of row pitch. The increase of the array pitch of tubes lowered the average speed of air in flow channel, heat transfer coefficient and the loss of flow channel.