Loading...

Table of Content

    The Invited Paper of the Editorial Board
    The calculation method of absolute assets and liabilities of water resource
    Shengle CAO,Cuisong YU
    Journal of Shandong University(Engineering Science). 2018, 48(5):  1-8.  doi:10.6040/j.issn.1672-3961.0.2018.272
    Abstract ( 669 )   HTML ( 334 )   PDF (1873KB) ( 133 )   Save
    Figures and Tables | References | Related Articles | Metrics

    In order to comprehensively reflect the quantity, quality and efficiency of regional water resource development and utilization, a framework of absolute balance sheet of water resource was proposed.The concepts and the associated determination methods for resource coefficient, quality coefficient and efficiency coefficient were proposed, and the quantification methods of the absolute assets and liabilities of water resource were given. Taking Jinan City of Shandong Province as an example, based on the proposed method, the resource coefficient, quality coefficient and efficiency coefficient, which could reflect the quantity, quality and utilization efficiency of local water resource, were calculated. The calculated absolute assets from 2011 to 2015 were 0.28×108, 0.37×108, 0.54×108, 0.26×108 and 0.25×108 m3 respectively, and the absolute liabilities were 0.64×108, 0.42×108, 0.71×108, 0.19×108 and 0.64×108 m3 respectively. This research could be considered as a further in-depth innovation on the existing relative balance sheet of water resource, and had theoretical significance and practical values on the establishment of absolute balance sheet and regional sustainable development of water resource.

    Machine Learning & Data Mining
    An unconstrained optimization EMD approach in 2D based on Delaunay triangulation
    Jianping HU,Xin LI,Qi XIE,Ling LI,Daochang ZHANG
    Journal of Shandong University(Engineering Science). 2018, 48(5):  9-15, 37.  doi:10.6040/j.issn.1672-3961.0.2018.245
    Abstract ( 682 )   HTML ( 27 )   PDF (11187KB) ( 301 )   Save
    Figures and Tables | References | Related Articles | Metrics

    An improved unconstrained optimization empirical mode decomposition (EMD) approach in two-dimensional (2D) based on Delaunay triangulation was presented. It firstly redefined the extremum of 2D images, and then constructed an optimization model to decompose the input image iteratively based on the Delaunay triangulation of the image extrema. The proposed approach could adaptively decompose the input image into several intrinsic mode images with fine-coarse scales and a residue. Experiment results demonstrated the proposed method had more powerful capabilities in capturing the multi-scale details and image features than the original 2D unconstrained optimization EMD approach.

    Fast scene recognition based on LDB descriptor and local spatial structure matching
    Dongbo ZHANG,Tao KOU,Haixia XU
    Journal of Shandong University(Engineering Science). 2018, 48(5):  16-23.  doi:10.6040/j.issn.1672-3961.0.2017.409
    Abstract ( 1128 )   HTML ( 30 )   PDF (11270KB) ( 213 )   Save
    Figures and Tables | References | Related Articles | Metrics

    A new local difference binary (LDB) descriptor and local spatial structure matching method was proposed to implement fast scene recognition. The multi-grid dense sampling method was used to obtain grayscale and gradient information of the image area, and the binary description was performed by comparing the grayscale and gradient size between the grids, which inherited the advantages of fast and low storage of binary feature extraction. The multi-point matching was adopted to replace the original single point of matching technology, which removed a large number of mismatches, thus the match accuracy was improved. The experiment showed that the efficiency of this method was about 2.7 times of SIFT and 1.9 times of SURF. The validity and recognition performance of the method were fully verified.

    Solar cell defect images fusion based on empirical wavelet
    Haiyong CHEN,Li YU,Hui LIU,Jiabo YANG,Qidi HU
    Journal of Shandong University(Engineering Science). 2018, 48(5):  24-31.  doi:10.6040/j.issn.1672-3961.0.2018.249
    Abstract ( 625 )   HTML ( 19 )   PDF (8253KB) ( 161 )   Save
    Figures and Tables | References | Related Articles | Metrics

    To solve the problem of the weak defect detection of solar cells, a multispectral image fusion algorithm based on 2D tensor empirical wavelet transform was proposed. The image information of solar cells was collected by using a set of specific wavelengths lights, and the noise was suppressed by using top-hat transformation. The preprocessed images were decomposed using empirical wavelet transform, and the obtained subband images of high and low frequency were fused using the saliency rules based on maximum value. The fused subband images of high and low frequency were transformed into the final image through inverse empirical wavelet transform. Cell images of five types of chromatic aberrations were acquired under the same acquisition conditions for testing algorithm, and were compared with other algorithms from two aspects of image visual effect and objective evaluation indexes. The experimental results showed that the proposed algorithm had good adaptability and good performance in the aspects of maintaining spectral information and suppressing noise.

    Weighted k sub-convex-hull classifier based on adaptive feature selection
    Lianming MOU
    Journal of Shandong University(Engineering Science). 2018, 48(5):  32-37.  doi:10.6040/j.issn.1672-3961.0.2017.415
    Abstract ( 631 )   HTML ( 10 )   PDF (1002KB) ( 279 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Because of the increase of the dimension of the problem and the effect of different features on classifier, the performance of the k sub-convex-hull classifier was seriously reduced. An adaptive feature selection weighted k sub-convex-hull classifier was designed (AWCH). A weighted k sub-convex-hull classifier was designed according to the shortcomings of conventional convex hull distance. By applying the distance metric learning and regularization technique in the k neighborhood of the test sample, an adaptive feature selection method was designed and seamlessly integrated into the optimization model on the weighted k sub-convex-hull. Through these efforts, for different test samples, an adaptive feature space in different categories could be extracted, and a valid weighted k sub-convex-hull distance could be obtained. Experimental results showed that the AWCH not only reduced the dimension of the problem, but also was significantly superior to similar classifiers.

    Cross-media retrieval model based on choosing key canonical correlated vectors
    Guangli LI,Bin LIU,Tao ZHU,Yi YIN,Hongbin ZHANG
    Journal of Shandong University(Engineering Science). 2018, 48(5):  38-46.  doi:10.6040/j.issn.1672-3961.0.2017.552
    Abstract ( 644 )   HTML ( 6 )   PDF (1693KB) ( 189 )   Save
    Figures and Tables | References | Related Articles | Metrics

    It is one of the most important factors which affect final retrieval performance effectively by acquiring the core semantic correlations between heterogeneous media in cross-media retrieval. To improve retrieval performance, a modified kernel canonical correlation analysis (MKCCA) model was presented: image features like SIFT (scale invariant feature transform) and GIST were extracted respectively to better characterize the key visual content of images. Meanwhile TF (term frequency) feature was extracted to depict the key characteristics of texts. Then the extracted features were mapped into a high-dimensional space by mapping kernels. As the results, two kernel matrixes were acquired to describe the mapped features. Based on the kernel matrixes, the non-linear semantic correlations between images and texts were fully mined by canonical correlation analysis (CCA) model. More importantly, with the help of a semantic correlation threshold, those core canonical correlation vectors were chosen to suppress semantic noises and depict the key semantic correlations between images and texts more robustly. Experimental results showed that the best overall retrieval performance was obtained by using the feature combination SIFT-TF. Moreover the highest retrieval performance was obtained by MKCCA model combined with gauss kernel. Compared to the best competitor, the MAP value of the "images retrieve texts (I_R_T)" task was improved about 3.06% while the MAP value of the "texts retrieve image (T_R_I)" task was improved about 1.18%.

    Suggestion sentence classification model based on feature fusion and ensemble learning
    Pu ZHANG,Chang LIU,Yong WANG
    Journal of Shandong University(Engineering Science). 2018, 48(5):  47-54.  doi:10.6040/j.issn.1672-3961.0.2018.207
    Abstract ( 847 )   HTML ( 8 )   PDF (1579KB) ( 267 )   Save
    Figures and Tables | References | Related Articles | Metrics

    As an emerging research task, suggestion mining has gradually attracted attention of researchers in recent years. Compared with English language suggestion expression forms, those of Chinese were more abundant, and many different characteristics were present. It was necessary to carry out the research on suggestion mining in the Chinese environment. As suggestion sentence detection was the core task of suggestion mining, this research proposed an ensemble learning model that integrated the Stacking and Bagging methods to classify the reviews for the detection of suggestion sentence. The model firstly used Stacking to combine classifiers and constructed probabilistic feature space. Then, the convolution neural network (CNN) and paragraph vector (PV) model were used to construct the CNN feature space and paragraph vector feature space of the reviews respectively. Finally, the above features were fused and the Bagging classifier was trained to classify suggestion sentences. Experimental results on Chinese dataset verified the effectiveness of the model.

    Feature extraction method of color pseudo-random coded structured light
    Guoxin WANG,Fengdong CHEN,Guodong LIU
    Journal of Shandong University(Engineering Science). 2018, 48(5):  55-60.  doi:10.6040/j.issn.1672-3961.0.2018.246
    Abstract ( 719 )   HTML ( 8 )   PDF (12883KB) ( 92 )   Save
    Figures and Tables | References | Related Articles | Metrics

    In order to enhance the feature information of weak texture target in three-dimensional reconstruction, a feature extraction method of structured light based on color square pseudo-random code was proposed. A pseudo-random coded structured light pattern composed of five kinds of color squares was designed and projected onto the target object. A gradient operator template was established to coarsely locate the corners of the down-sampled image. The local non-maximum was suppressed. The Harris algorithm was extended to color multi-channel images, corner detection was carried out on the coarse locating area of the original image, and then the precise position of the corner point was determined in the color image. The experiment results indicated that the proposed method could effectively guarantee the accuracy of feature extraction and had strong robustness with poor surface color and texture.

    Finite-time flocking behavior of leader-following Cucker-Smale system
    Youquan LIU,Chenguang WANG,Hongjun SHI
    Journal of Shandong University(Engineering Science). 2018, 48(5):  61-68.  doi:10.6040/j.issn.1672-3961.0.2018.031
    Abstract ( 746 )   HTML ( 17 )   PDF (2039KB) ( 109 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Based on the finite-time stability theory, the finite-time flocking behavior of leader-following Cucker-Smale systems was studied. By using Lyapunov function approach, sufficient conditions were provided to ensure the finite-time flocking. It was shown that the convergence time depended on the group size and the coupling strength between agents and the leader. The convergence time decreased with the increasing of the group size and the coupling strength. The state trajectories of velocity and velocity error were provided to confirm the theoretical results with simulation examples.

    Active driving behavior analysis algorithm based on monocular camera
    Chenmou WU,Zhijun FANG,Jenqneng HWANG
    Journal of Shandong University(Engineering Science). 2018, 48(5):  69-76.  doi:10.6040/j.issn.1672-3961.0.2017.424
    Abstract ( 880 )   HTML ( 11 )   PDF (9086KB) ( 314 )   Save
    Figures and Tables | References | Related Articles | Metrics

    In order to prevent accidents, an algorithm for recognizing and monitoring the driver′s behavior based on the three-dimensional pose estimation of the human body was proposed. A monocular camera was used to capture the video stream of the driver in motion, the two-dimensional contour features of each frame of the image was extracted, and the two-dimensional projection of the pre-established three-dimensional human body model was matched to estimate the attitude of the driver′s upper body in real time. Based on the three-dimensional coordinates of the driver′s eight skeletal nodes, the driver′s behavior was identified and analyzed. Four driving states of driver′s normal, one-handed, answering calls and fatigue/drunk driving were simulated. Through the coordinate changes of the skeletal nodes, the gesture behavior of the driver could be detected and recognized, and the driver could be given reminders. When the light was enough, the algorithm could reduce the false detection rate by 24.24% compared with the PRECLOSE algorithm.

    Control Science & Engineering
    Lung tumor images recognition based on PSO-ConvK convolutional neural network
    Mengmeng LIANG,Tao ZHOU,Yong XIA,Feifei ZHANG,Jian YANG
    Journal of Shandong University(Engineering Science). 2018, 48(5):  77-84.  doi:10.6040/j.issn.1672-3961.0.2018.191
    Abstract ( 771 )   HTML ( 8 )   PDF (3246KB) ( 473 )   Save
    Figures and Tables | References | Related Articles | Metrics

    In order to solve problems that convolution kernel was random initialization and the gradient descent method to train convolution neural network was easy to fall into local minimum, an image recognition method based on particle swarm optimization for convolution kernel was proposed. CNN(convolution neural network) was constructed by using the parameter migration method, and convolution kernel was extracted. The particle swarm algorithm was used to update the velocity and position of particles constantly and find the global optimal value to initialize convolution kernels. Convolution kernels were transferred to convolution neural network, and lung tumor images were used to train them. CNN model was trained by lung tumor images, and gradient descent method was used to modify network weights, hence global optimization ability of PSO algorithm was combined with local search ability of gradient descent method. The experiments verified effectiveness of method through three perspectives: batch sizes, iteration numbers, and network layer numbers. The particle swarm algorithm was compared with gauss function. The recognition rates of PSO optimized convolution kernel were always higher than that of randomized convolution kernel and gauss convolution kernel, its recognition rate reached 98.3%, which had certain feasibility and superiority.

    Two methods for sliding mode synchronization of five-dimensional fractional-order chaotic systems with entanglement iterms
    Dongxiao WANG
    Journal of Shandong University(Engineering Science). 2018, 48(5):  85-90.  doi:10.6040/j.issn.1672-3961.0.2018.139
    Abstract ( 610 )   HTML ( 0 )   PDF (1637KB) ( 154 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Sliding mode synchronization of five-dimensional fractional-order chaotic systems with three entanglement iterms was studied based on classical and integral sliding mode methods. Sliding mode surfaces and controllers were designed in two methods and two sufficient conditions were arrived for entanglement chaotic systems to acquire sliding mode synchronization. The research conclusion illustrated that five-dimensional fractional-order entanglement chaotic systems were sliding mode synchronization under certain conditions. Numerical simulation showed the correctness and the effectiveness of the designed controller.

    Synchronization control of fractional-order multi-scroll chaotic system based on reduced-order method
    Chunyan WANG,Jinhong DI
    Journal of Shandong University(Engineering Science). 2018, 48(5):  91-94, 123.  doi:10.6040/j.issn.1672-3961.0.2017.614
    Abstract ( 648 )   HTML ( 3 )   PDF (1037KB) ( 151 )   Save
    Figures and Tables | References | Related Articles | Metrics

    The problem of synchronization control of intergal-order and fractional-order multi-scroll chaotic systems were studied based on reduced-order method. Third fractional-order multi-scroll system was transferred into a first-order system. The chaotic synchronization sufficient conditions were arrived for the drive-response systems of fractional-order multi-scroll system which acquired synchronization using fractional-order Lyapunov. The strict proof in mathematics was given out, and the simulations examples demonstrated the efficient of the proposed method.

    Indoor wireless positioning based on ensemble deep neural network
    Dongdong SHEN,Fengyu ZHOU,Mengyuan LI,Shuqian WANG,Renhe GUO
    Journal of Shandong University(Engineering Science). 2018, 48(5):  95-102.  doi:10.6040/j.issn.1672-3961.0.2018.169
    Abstract ( 954 )   HTML ( 23 )   PDF (6449KB) ( 157 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Because of the low fault tolerance and weak anti-noise ability of fingerprint database in traditional wireless positioning model, an ensemble deep neural network wireless positioning method based on data fusion was proposed. This method could effectively overcome the interference caused by abnormal samples and noisy data on the wireless positioning system by sampling from the original fingerprint database randomly to generate train data for each base learner. During the process of fingerprint database construction, the Gauss-Occupied (G-O) data expansion method was proposed to solve the limitation of the small sample size of the wireless fingerprint database and decrease the cost of manual acquisition sharply, which increased the scope of the sample′s characterization. The results of the experiment showed that the proposed ensemble deep neural network wireless positioning model could not only improve the average positioning accuracy and the anti-noise ability of the wireless positioning system, but also reduce the maximum single point error in the positioning process.

    Intelligent interaction method for power distribution robot based on Kinect
    Mian ZHANG,Ying HUANG,Haiyi MEI,Yu GUO
    Journal of Shandong University(Engineering Science). 2018, 48(5):  103-108.  doi:10.6040/j.issn.1672-3961.0.2018.228
    Abstract ( 673 )   HTML ( 5 )   PDF (3940KB) ( 213 )   Save
    Figures and Tables | References | Related Articles | Metrics

    In order to realize natural interaction between the operator and the live-line working robot, an intelligent man-machine interaction method based on the Kinect gesture recognition was proposed. Based on the Kinect's depth information and skeleton information, the operator's gesture was segmented, the geometric moment Hu moment was selected as the gesture feature, and the machine learning method of SVM was used to classify and identify the operator's gesture. The gestures were mapped to the motion of the robot, and the motion control of the robot was realized by the gesture. The experimental results verified the feasibility of the intelligent human-computer interaction method of the power distribution robot.

    Civil Engineering
    The effect of hydrochemical conditions on compression characteristics of kaolinite
    Zhechao WANG,Xinyu WANG,Changfu WEI,Wei LI,Guangping DUAN,Shuai LI,Chunyu ZHANG
    Journal of Shandong University(Engineering Science). 2018, 48(5):  109-117.  doi:10.6040/j.issn.1672-3961.0.2017.442
    Abstract ( 796 )   HTML ( 3 )   PDF (4513KB) ( 132 )   Save
    Figures and Tables | References | Related Articles | Metrics

    In order to investigate the compression characteristics of kaolinite in various hydrochemical conditions, oedometer tests on kaolinite specimens saturated with acidic, alkaline and saline solutions were performed. The results indicated that Na+ and Ca2+ induced the compressibility of specimens significantly in low pressure level, while the increase of ion concentration made a growing trend in the compressibility of kaolinite; in the same concentration, the effect of Ca2+ on the compressibility of specimens was more obvious than Na+; in acidic or alkaline conditions, the compressibility of kaolinite was improved; hydrochemical condition also had effect on the rebound curve. Then the mechanism of the test was analyzed and it was considered that the effect of variation in hydrochemical conditions on compressibility of kaolinite included both mechanical model and physical-chemical model. Cation exchange and adsorption, dissolution and sedimentation were important influential factors of the compressibility of soil. The basis was provided for further revealing the mechanical mechanism of water-soil chemical interaction.

    Experimental study on compaction properties of tire derived aggregate-weathered rock material mixtures
    Lei ZHANG,Ming XIAO,Lei WANG,Xinzhuang CUI,Lianyong SUN,Dan HUANG,Junwei SU
    Journal of Shandong University(Engineering Science). 2018, 48(5):  118-123.  doi:10.6040/j.issn.1672-3961.0.2017.487
    Abstract ( 641 )   HTML ( 5 )   PDF (1140KB) ( 94 )   Save
    Figures and Tables | References | Related Articles | Metrics

    To promote the usage of scrap tires in civil engineering, the 0~60%content of tire derived aggregates by weight were mixed with widely distributed and low price weathered rock materials, and the compaction properties of tire derived aggregate-weathered rock material mixtures were studied based on heavy compaction tests performed by the large size compaction equipment. The experimental results showed that the compaction curves of mixtures were obviously different from that of pure weathered rock materials. As the content of tire derived aggregates increased, the maximum dry density of mixtures effectively decreased and the optimum water content of mixtures reduced. Tire derived aggregate-weathered rock material mixtures could be used as the lightweight backfill with good properties. According to the results of laboratory tests, the maximum dry density and optimum moisture content of mixtures were 1.865 g/cm3 and 6.25% when the TDA content was 20%, and the maximum dry density and the optimum moisture content of mixtures were 1.600 g/cm3 and 4.90% when the TDA content was 40%. Compaction parameters of mixtures could be proposed for design based on laboratory test results.

    Electrical Engineering
    Multi-scale assessment of wind-solar generation resources based on continuous wavelet transform
    Fei WANG,Shizhan SONG,Yongji CAO,Hongtao XIE,Xinhua ZHANG,Jian ZHANG,Tian XIAO,Yawen ZHAO
    Journal of Shandong University(Engineering Science). 2018, 48(5):  124-130.  doi:10.6040/j.issn.1672-3961.0.2018.172
    Abstract ( 632 )   HTML ( 2 )   PDF (1849KB) ( 161 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Taken into account the assessment of areal wind and solar generation resources, a multi-scale assessment approach using the continuous wavelet transform was proposed. Based on the National Aeronautics and Space Administration (NASA), the wind speed and solar irradiation data were obtained and then preprocessed into capacity factors via virtual generation systems. From the viewpoint of time and space, the quantitative indices of energy potential, variability and complementarity were established to capture the attributes of areal wind and solar resources. The multi-scale variabilities and complementarities were extracted by the continuous wavelet transform to analyze the damping effect on output power and estimate the optimal scale. Zaozhuang City was taken as a case study to validate the effectiveness of proposed approach, of which the results indicated that there were inherent variability and complementary characteristics of wind and solar resources and the reasonable planning of hybrid generation systems in optimal scale could damp the power fluctuation.

    PV installed capacity planning for power distribution network based on time series production simulation
    Shizhan SONG,Chuanyong WANG,Wenwen KANG,Jian ZHANG,Honghua YAN,Peng LI
    Journal of Shandong University(Engineering Science). 2018, 48(5):  131-136.  doi:10.6040/j.issn.1672-3961.0.2018.270
    Abstract ( 660 )   HTML ( 5 )   PDF (3797KB) ( 270 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Based on time series production simulation, an optimization model was built to optimize PV installed capacity for distribution network with integration of wind and solar power. The optimal installed capacity of the photovoltaic system was given according to the different wind/PV curtailment ratios. Simulations revealed that the proposed planning method guaranteed the reasonable revenue of wind power/PV and maximized the integration of PV generation with a certain level of wind/PV curtailment ratio, which improved utilization level of renewable energy generation.