Loading...

Table of Content

    25 January 2021, Volume 49 Issue 1
    2021, 49(1):  0. 
    Asbtract ( 62 )   PDF (408KB) ( 60 )  
    Related Articles | Metrics
    Computer Science & Technology
    HUANG Ping LIANG Weijie
    2021, 49(1):  1-9.  doi:10.12141/j.issn.1000-565X.200207
    Asbtract ( 397 )   PDF (685KB) ( 151 )  
    Related Articles | Metrics
    The designing thought of verification equations in PGHR protocol is singular,that is,a verification equation targets only one constraint,ignoring their joint effect. In this paper,a new ZK-SNARK protocol——— CPGHR protocol———was obtained by using the indivisible properties of additional constant coefficient factors and the combined effect of verification equations to achieve effective compression of the PGHR protocol. At the same time,a strict verification of the security of the new protocol was given,and the validity of the protocol was theoretically analyzed and experimentally verified. The results show that the amount of evidence of the new protocol is reduced by about 75% ,and the calculation efficiency is improved by about 33% .
    IKA Novita Dewi, CAI Xiaoling, et al
    2021, 49(1):  10-17.  doi:10.12141/j.issn.1000-565X.200506
    Asbtract ( 417 )   PDF (426KB) ( 71 )  
    Related Articles | Metrics
    A drug interaction extraction model combining category key words with attention mechanism was proposed to enhance the discrimination among different categories of data and improve the performance of classifier. Firstly,the keywords of each class were selected based on the chi-square test and document frequency. Then,the position coding of keywords and drug pairs was added into the pre-trained model BERT,in order to make the difference of the samples more salient. The distribution information of keywords and other words in the sentence was learned through the attention mechanism to improve the performance of the model. Aiming at the problem of too much negative samples in the drug interaction extraction experiment,a negative sample filtering method based on rules and patterns was proposed to effectively reduce the proportion of positive and negative samples. Compared with other DDI models based on CNN,LSTM,and BERT,KA-BERT model can better improve performance on DDI data,which proves the effectiveness of KA-BERT model. The results of the test on chemical protein relation extraction show that the precision,recall and F1 score of KA-BERT model are enhanced significantly,which further proves the validity and universality of KA-BERT model.
    LIU Kan, HUANG Zheying
    2021, 49(1):  18-28.  doi:10.12141/j.issn.1000-565X.200489
    Asbtract ( 607 )   PDF (1872KB) ( 108 )  
    Related Articles | Metrics
    Since the outbreak of the covid-19 epidemic,related rumors have spread rampantly. Traditional rumor identification models have difficulties in epidemic rumor identification because the size of epidemic rumors is not large enough to train a good classification and identification model. Therefore,it is an urgent task to build a rumor identification model based on a small amount of epidemic rumor data. To deal with the problem of insufficient training data,text enhancement and generative adversarial networks ( GAN) methods were used to generate a large amount of information similar to epidemic rumors and to improve the identification effect of epidemic rumors. First, the textual characteristics was analyzed to extract keyword of epidemic rumors. Second,epidemic rumor generation model was constructed based on the idea of GAN,and historical rumors which do not contain epidemic rumor features were textually enhanced by the epidemic rumor feature thesaurus,and a large amount of new rumor data containing epidemic rumor features were generated. Finally,the newly generated rumor data are combined with the epidemic rumor data to train a more accurate classification model of the epidemic rumor. Experiment results show that the rumor identification effect is improved by 3% after using the GAN extended training set. The new model is evidently much better than the traditional machine learning and deep learning algorithms,and it provides a new way for the identification of rumors in public health emergency.
    YANG Shenghao, WU Yueyue, et al
    2021, 49(1):  29-38,46.  doi:10.12141/j.issn.1000-565X.200513
    Asbtract ( 425 )   PDF (1190KB) ( 116 )  
    Related Articles | Metrics
    As an important content of judicial information disclosure,case documents should be disclosed to the public after the trial. Some case documents involving juvenile are likely to cause the disclosure of juvenile personal privacy information. In order to conduct targeted privacy protection processing,the first step is to accurately identify documents involving juvenile information from a large number of case documents. At the same time,in order to solve the problem of difficulty in effective supervised learning due to the lack of labeled samples in the real data set,this paper proposed a juvenile case documents recognition method based on semi-supervised learning. Firstly, the corpus text of the case document was pre-processed,and then the features of the text were extracted with Word2Vec and BERT-wwm-ext. After the above processing,the long corpus text was converted into the data format that can be used as the input for the classification model. Then the classification model was trained with the PU learning method,and an effective classifier was constructed with a large number of unlabeled samples under the condition of few positive examples. Then,based on the prediction results of the classification model,active learning method was employed to obtain keywords and screen the prediction results,so as to further improve the prediction effect. Finally,the case documents recognition method proposed in this article achieves a recall of 98. 67% and a precision of 81. 02% on the test set constructed based on the proportion of real scenes.
    WU Qiuxia, LI Lingmin
    2021, 49(1):  39-46.  doi:10.12141/j.issn.1000-565X.200373
    Asbtract ( 595 )   PDF (1263KB) ( 169 )  
    Related Articles | Metrics
    Image and point cloud are the common data formats for 3D object detection,for images have a superior object recognition capability and point clouds contain accurate spatial information. In order to utilize the above mentioned advantages of both images and point clouds,a 3D object detection method named Bird-PointNet based on bird's eye view of point cloud remapping approach was proposed. First,point cloud was encoded into bird's eye view format for object recognition and rough positioning. Then the results from bird's eye view detection was remapped into the point cloud's space for precise detection. Experiments on the BEV detection benchmark and the 3D detection benchmark of KITTI dataset have demonstrated that the proposed Bird-PointNet method has a higher accuracy of 3D detection,compared with the baseline method that only with bird's eye view coding of point cloud.
    GU Wanrong, XIE Xianfen, ZHANG Ziye, et al
    2021, 49(1):  47-57.  doi:10.12141/j.issn.1000-565X.200210
    Asbtract ( 312 )   PDF (786KB) ( 104 )  
    Related Articles | Metrics
    Most score prediction studies are based on the assumption that the missing values are random. However, the missing data of the score matrix of the actual on-line recommendation system is non-random. Incorrect assumptions about the missing data can lead to biased parameter estimation and prediction. In order to improve the accuracy of non-random missing score matrix filling,the internal principle of user and item score matrix was analyzed in this paper. It presents a method to transform the score matrix of user and object into the equivalent bilateral block diagonal matrix by row or column transformation. Then the matrix decomposition method was applied to different blocks to decompose and predict the score,making local data update and decomposition become a reality. The experimental results on the public test dataset show that the proposed method can improve the score filling effect,solve the problem of non-random score missing effectively,and improve the prediction accuracy of the recommendation system. The improved block matrix also has a better speedup ratio in the distributed processing experiment,which shows that the proposed method has better scalability.
    GENG Qinghua, LIU Weiming
    2021, 49(1):  58-64,73.  doi:10.12141/j.issn.1000-565X.200399
    Asbtract ( 645 )   PDF (867KB) ( 82 )  
    Related Articles | Metrics
    For the classic perspective-three-point ( P3P) problem,when the Z-axis coordinates of the three-dimensional control points are randomly distributed in a large range,there are still problems of poor numerical stability, degradation caused by increased image noise,and low computational efficiency. Therefore,a fast and stable algebraic solution method was proposed in this article. Firstly,when the proposed solution directly estimates the rotation and position of a calibrated camera from three 3D to 2D point correspondences,an intermediate coordinate frame is introduced between the world coordinate frame and the camera coordinate frame to reduce the number of unknown parameters,and the rotation matrix is normalized to simplify the calculation process and improve the calculation efficiency. Secondly,the midpoint between the two control points was chosen as the origin point of the intermediate coordinate frame,so as to improve the anti-noise performance of the P3P problem in degenerate configurations. Finally,the P3P problem was transformed into a biquadratic equation with one unknown parameter by using a Grbner basis,then a closed solution to the P3P problem was obtained. Experimental results show that the proposed algorithm can achieve better numerical stability and anti-noise performance compared with other three classic algorithm of the P3P problem.
    Mechanical Engineering
    LUO Yutao, GUO Haiwen
    2021, 49(1):  65-73.  doi:10.12141/j.issn.1000-565X.200012
    Asbtract ( 385 )   PDF (5131KB) ( 72 )  
    Related Articles | Metrics
    When the traditional sliding mode control ( SMC) method is applied to steer-by-wire ( SBW) system,it is necessary to obtain the upper bound value of system disturbance in advance,and the change of system disturbance will lead to poor stability of angle control. In order to improve the wheel angle tracking performance of SBW system,an adaptive neural network sliding mode control ( RBFSMC) method considering system disturbance was proposed. Firstly,the RBF neural network was used to estimate the system uncertainty and motor torque disturbance in real time. Secondly,the wheel angle controller was designed by combining RBF with SMC in order to improve the adaptability and stability of the angle control. The joint simulation results of MATLAB /Simulink and CarSim on SMC and RBFSMC show that,RBFSMC can better maintain 0° wheel angle and realize fast and stable tracking of dynamic wheel angle under the conditions of vehicle maintaining steering,continuous steering and single /double lane changing,and it has better corner response and tracking performance than SMC. The study indicates that RBFSMC has better robustness and stability than SMC.
    ZHANG Jiaxu, WANG Chen, WANG Xinzhi, et al
    2021, 49(1):  74-81.  doi:10.12141/j.issn.1000-565X.200289
    Asbtract ( 425 )   PDF (1043KB) ( 66 )  
    Related Articles | Metrics
    According to the requirement of the fault-tolerant control for the soft speed-sensing technology,a novel self-driving vehicle speed estimation method based on the interacting multiple-model unscented Kalman filter was proposed to adapt to the unknown statistical characteristics of the system noise. Firstly,a nominal model,which includes vehicle kinematic and dynamic characteristics,was established based on the positioning information of the self-driving vehicle,and then it was transformed into a state space nominal model including the unknown statistical characteristics of the system noise by using the forward Euler discretization method. Secondly,a series of typical values were used to describe the unknown statistical characteristics of the system noise,and a series of state space nominal models including different statistical characteristics of the system noise were obtained. For each state space nominal model,unscented Kalman filter was used to estimate the self-driving vehicle speed and all of the outputs were smoothly fused by interactive multiple-model algorithm. Thus,the interacting multiple-model unscented Kalman filter with adaptive ability to the statistical characteristics of the system noise was obtained. Simulation results show that the estimation accuracy of the proposed method for the vehicle longitudinal and lateral speeds is 4 times and 1. 5 times as many as that of the unscented Kalman filter,respectively,which satisfies the requirement of the fault-tolerant control for the self-driving vehicle.
    ZHOU Tao, HE Lin, TIAN Pengfei, et al
    2021, 49(1):  82-92.  doi:10.12141/j.issn.1000-565X.190920
    Asbtract ( 353 )   PDF (1858KB) ( 467 )  
    Related Articles | Metrics
    During the metal cutting process,the intense thermo-mechanical load can cause changes in the microstructure of the chips. In order to reflect the influence of the material microstructure on the mechanical behavior of shear zone,an analytical model of microstructure evolution in shear zone based on dislocation density was proposed. And it was used to model the microstructure evolution process caused by plastic deformation during chip formation. Firstly,the distribution of strain and strain rate in shear zone was calculated through the analytical model of unequal shear zone. Secondly,the Johnson-Cook ( J-C) flow stress model was replaced by the material model based on dislocation density to calculate the temperature field in the shear zone iteratively. Finally,the evolution process of dislocation density and grain size in shear zone of orthogonal cutting oxygen-free copper and aluminum alloy was simulated. The results show that the analytic model for the micro-evolution of the shear zone combined with the dislocation density can better reflect the basic characteristics of the deformation field and microstructure evolution during the cutting process. The predicted values of cutting force and grain size in chips under different cutting parameters are in good agreement with the experimental data.
    WANG Yanzhong, XU Zichun, MA Tao, et al
    2021, 49(1):  93-102.  doi:10.12141/j.issn.1000-565X.200272
    Asbtract ( 499 )   PDF (1097KB) ( 90 )  
    Related Articles | Metrics
    Based on the theory of thermal elastohydrodynamic lubrication ( TEHL) ,the lubrication and friction characteristics of modified herringbone gears were analyzed. Firstly,the variation of instantaneous contact lines on tooth surface of the herringbone gears with the specified structure was analyzed under the specified working condition. The specified number of meshing points along the meshing line were selected as analysis objects and the essential values of contact parameters were obtained. Secondly,the accuracy of the TEHL calculation program was verified and the TEHL calculation was performed. The oil film characteristic values at the meshing points were derived from calculation results to obtain their variations along the meshing line. The influences of input torque, driving gear rotation speed and amount of crowned modification on the film profile curves at the meshing point S1 were analyzed. Finally,the variation law of the friction coefficients at the meshing points was obtained by using the Ree-Eyring model. The calculation results show that the maximum film pressure on tooth surface increases first and then decreases,while the variation trends of the minimum film thickness and the maximum film temperature are opposite to that of the maximum film pressure. In addition,the temperature rise and the thickness of the film are influenced significantly by the rotation speed of driving gear; the increase of input torque or amount of crowned modification will lead to the film temperature rise and the peak value rise of the film pressure; the value of friction coefficient is almost zero at the pitch point while greater at the engaging-in / out side.
    MA Guangying, WANG Guangming, LIU Runchen, et al
    2021, 49(1):  103-112.  doi:10.12141/j.issn.1000-565X.200273
    Asbtract ( 423 )   PDF (1622KB) ( 94 )  
    Related Articles | Metrics
    An R + { 2-UPR + RPR} leg mechanism was designed to improve the mobility and adaptability of quadruped robots in complex environment. The spiral theory analysis showed that the mechanism has 3 freedom degrees of two rotations and one movement. Then,the inverse kinematics solution and the positive solution equation were derived based on the position relationship between the member and the motion pair in space,and the velocity and acceleration of the driving member were solved. Then,with the help of Matlab calculation software and ADAMS simulation software,the accuracy of the positive and negative solution model was verified through the comparison of kinematics positive and negative solution theoretical calculation results and simulation results. Finally,the motion trajectory and velocity changes of the leg mechanism were obtained through the motion simulation of the robot's single leg. And the working space of the leg mechanism was analyzed to obtain the working range and motion characteristics of the foot end. The results show that the proposed leg mechanism with less independent joints has better working adaptability and movement flexibility.
    Traffic & Transportation Engineering
    TONG Fang, LAN Fengchong, CHEN Jiqing, et al
    2021, 49(1):  113-122,152.  doi:10.12141/j.issn.1000-565X.200213
    Asbtract ( 293 )   PDF (4111KB) ( 169 )  
    Related Articles | Metrics

    In traffic accidents,aortic valve dysfunction resulting from blunt thoracic impact of occupant and pedestrians can cause congestive heart failure or death. To investigate the effects of thoracic impact timing related to the cardiac cycle on aortic valve injury,a fluid-structure interaction ( FSI) model of aortic valve and blood was established based on smoothed particle dynamics ( SPH) method,and was validated by the valve movement under normal physiological conditions. To ensure the boundaries of the physiological properties,the dynamic blood pressure of animal tests and physiological pressure of human body were combined to load on the coupling model,and the biomechanical response of the aortic valve in different impact timing was simulated. The results show that different impact moments ( diastolic or systolic period) lead to different valve stress and strain fields,valve opening and closing rates. When the valve is open ( like the middle diastolic period) ,it is less likely to suffer from impact injury; when the valve is closed ( like the middle and late diastolic period) ,it is more vulnerable to injury.

    JIN Wenzhou, HU Weiyang, DENG Jiayi, et al
    2021, 49(1):  123-133.  doi:10.12141/j.issn.1000-565X.200248
    Asbtract ( 1204 )   PDF (1006KB) ( 253 )  
    Related Articles | Metrics

    Demand response transit ( DRT) serves is a new type of public transportation service mode. In order to make DRT theory more suitable for practical application in low-density population areas,a flexible bus scheduling model considering multiple vehicle types and multiple operating modes was proposed. First,dual decision variables for vehicle type and route were set up,and then a flexible bus dispatch model that considers multiple vehicle types as well as multiple operating modes was built. Then,a hybrid genetic ant colony algorithm HGACO,which is composed of nearest neighbor search algorithm,2-opt method,destination dimensionality reduction operator,genetic algorithm and ant colony algorithm,was designed using the hybrid model of“large loop and small loop”. Finally, taking the three sections from the southwest part of the city to the city center as an example for scheduling,the results show that the flexible bus dispatch model considering the multi-vehicle and multi-ple operation mode is practical and operable,and it can make DRT in low-density areas more scientific and economical. The improved hybrid algorithm HGACO is superior to the original algorithm in solution ability,accuracy and stability,and can stably obtain a better solution to the DRT flexible scheduling problem.

    HU Baoyu, AI Yuhao, CHENG Guozhu
    2021, 49(1):  134-141.  doi:10.12141/j.issn.1000-565X.200147
    Asbtract ( 730 )   PDF (601KB) ( 147 )  
    Related Articles | Metrics

    In order to solve the problem of coordination dispatching optimization between metro and bus transit network,the bus transit network associated with the metro was divided into collaborative transfer subnetwork and cooperative transport subnetwork. And based on the idea of achieving bus transit network optimization through optimizing subnetworks,the two-objective coordination dispatching optimal model was established. It takes the maximization of the total coordination times in bus transit network as the first object,and takes the maximization of the coordination opportunity of multiple buses and the metro in the collaborative transfer subnetwork and the minimization of the coordination opportunity of multiple buses and the metro in the cooperative transport subnetwork as the second object. Then a heuristic algorithm was developed to solve the model. The results of example analysis show that the model proposed in this paper is correct and the algorithm is effective. The model can set the bus transit timetable which is coordinated with the metro.

    HAO Xueli, SUN Zhaoyun, GENG Fangyuan, et al
    2021, 49(1):  142-152.  doi:10.12141/j.issn.1000-565X.200251
    Asbtract ( 347 )   PDF (2285KB) ( 58 )  
    Related Articles | Metrics

    The angularity of the aggregate particles is an important factor determining the performance of asphalt mixes for road use. In this paper,firstly,a 3D image acquisition system based on Gocator 3D intelligent sensor was built to obtain 3D point cloud data of 3 aggregate samples of basalt,granite and limestone with particle sizes of 9. 5 mm,13. 2 mm and 16. 0 mm. Then,the Sobel-Feldman convolution method and the aggregate surface normal method was used to evaluate the surface angularity of aggregate particles,and the two methods were compared with the existing AIMS gradient angularity evaluation method. The results show that the quantitative method of aggregate particle surface angularity based on Sobel-Feldman convolution is more accurate. In addition,the sharper the aggregate is,the larger the laggregate angularity index and the number of normal clusters are; the more round the aggregate is,the smaller the aggregate angularity index and the number of normal clusters are.

News
 
Featured Article
Most Read
Most Download
Most Cited