Journal of Jiangsu University(Natural Science Eidtion)

[an error occurred while processing this directive]

Journal of Jiangsu University(Natural Science Eidtion)

Home | About Journal | Editorial Board | Subscriptions | Instruction | Contacts Us | 中文

　

Office Online

　

　

　

　

　

　

Editor-in-chief

　

Journal Online

　

　

Forthcoming Articles

　

　

　

　

　

Download Articles

　

　

Quick Search

Advanced Search

Journal of Jiangsu University(Natural Science Eidtion)

	2020 Vol.41 Issue.3 Published 2020-05-10

	249	Design and implementation of vulnerability code semantic description language
	Design and implementation of vulnerability code semantic description language [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 249-255>')" href="#">	CHEN Jinfu, CHEN Shujie, ZHANG Qingchen, ZHOU Minmin, ZHANG Lei
		To solve the shortcomings of the current general description language of security vulnerability source code, a formal vulnerability code semantic description language (VCSDL) was proposed and implemented based on eXtensible markup language (XML). From the perspective of vulnerability code, the unified security vulnerability code description language was defined based on the traditional security vulnerability description method to convert the unstructured vulnerability source code into structured XML file. The application of VCSDL was discussed, and the description and release of VCSDL were elaborated with the vulnerability code in Juliet vulnerability suite as example. The performance of VCSDL was compared with the other description languages. The results show that VCSDL has good universality and comprehensiveness with high structure, especially has an advantage in describing the vulnerability code attributes. VCSDL can improve the efficiencies of collection, integration and analysis of security vulnerability information. The unified model can be provided by VCSDL for exchanging information between different security tools and security vulnerability data sources, and the exchange of security vulnerability information between different security tools is facilitated.
		2020 Vol. 41 (3): 249-255 [Abstract] ( 35 ) [HTML 1KB] [ PDF 1212KB] ( 472 )

	256	Face recognition based on structured localityconstrained low rank representation
	Face recognition based on structured localityconstrained low rank representation [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 256-261>')" href="#">	CAI Xiaoyun, YIN Hefeng
		For the method of conventional low rank representation (LRR), the representation coefficients of test samples are calculated based on the learned dictionary, which results in high computational complexity and low correlation of representation coefficients between training and test samples. To solve the problems, a structured localityconstrained low rank representation (SLCLRR) method was proposed for face recognition. An ideal regularization term was introduced in LRR to encourage the representation matrix of training data with blockdiagonal structure. A locality constraint was incorporated to acknowledge the intrinsic manifold structure of training data and make the similar samples with similar representations. Test samples were classified by a simple yet effective linear classifier. The verified experiments were conducted on the four benchmark datasets of AR, Extended Yale B, ORL and LFW. The results show that the proposed method can obtain the representation coefficients of training and test samples simultaneously with good robustness for occlusions, pixel corruptions and illumination variations in the face images.
		2020 Vol. 41 (3): 256-261 [Abstract] ( 36 ) [HTML 1KB] [ PDF 5034KB] ( 581 )

	262	Complex network community detection based on multiobjective adaptive Memetic algorithm
	Complex network community detection based on multiobjective adaptive Memetic algorithm [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 262-267>')" href="#">	LIANG Shijiao, CHAI Zhengyi
		To improve the accuracy of complex network community detection, a multiobjective complex network community detection algorithm was proposed based on the adaptive memetic algorithm. According to the Randomwalker initialization strategy, the Logistic function was combined with the fitness function, and the dynamic adaptive strategy was introduced to adjust the crossover and mutation probability. The network topology was also mined，and the community detection accuracy was improved. The multiobjective optimization was transformed into two functions of the minimum optimization connectivity (MRA) and the segmentation (RC). In the local searching, the two objective functions were used to form a local optimization target by the weighted sum method, and the hill climbing algorithm was used to find individual optimal. The algorithm was verified on the artificial and real datasets. The results show that the proposed algorithm can effectively improve the accuracy of community detection with good optimization effect.
		2020 Vol. 41 (3): 262-267 [Abstract] ( 25 ) [HTML 1KB] [ PDF 1183KB] ( 513 )

	268	An attentionbased PointPillars+3D object detection
		ZHAN Weiqin, NI Rongrong, YANG Biao
		To accurately recognize and locate the surrounding vehicles and pedestrians, an attentionbased PointPillars+ 3D target detection algorithm was proposed. The entire space was uniformly divided into pillars with a given resolution, and a pseudoimage was generated by extracting pointbased features from all pillars. Two attention modules were introduced to highlight and restrain the information in the pseudoimage. A convolution neural network was used to process the output of the attention module, and the single shot multibox detector（SSD） was used for 3D object detection. The evaluation results show that the parallel attentionbased PointPillars achieves good performance. Compared with the traditional PointPillars, the mAPm is increased from 66.19 to 69.95 in the bird′s eye view， and the car mAP is increased from 86.10 to 87.73. In the 3D mode, the mAPm is increased from 59.20 to 62.55, and the car mAP is increased from 74.99 to 76.25.
		2020 Vol. 41 (3): 268-273 [Abstract] ( 96 ) [HTML 1KB] [ PDF 3501KB] ( 702 )

	274	Logistics delivery scheduling method based on clustering algorithm and bipartite graph matching
	Logistics delivery scheduling method based on clustering algorithm and bipartite graph matching [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 274-280>')" href="#">	YING Yi, TANG Li, LIU Dingyi, LIU Yajun
		To solve the problems of unreasonable area partitioning and unbalanced work assignment in delivery scheduling of logistics terminal distribution service, a twostage dispatch scheduling algorithm of area partitioning before scheduling was proposed. Based on GIS technology, Web technology and mobile development technology, an intelligent logistics information system with considering the last 1 km delivery was constructed. Introducing workload balance index with considering actual path distance, the distribution area partitioning method of pointtosurface aggregation with regional clustering was realized based on the kmedoids clustering algorithm. Based on the maximum weight, the bipartite graph matching KM algorithm was proposed to implement delivery scheduling algorithm. The twostage dispatch scheduling algorithm was applied in the distribution activities of SF EXPRESS. The results show that the proposed method can realize more clustered area partitioning performance and more balanced work distribution among express delivery personnels, which effectively improves the service efficiency of logistics network.
		2020 Vol. 41 (3): 274-280 [Abstract] ( 56 ) [HTML 1KB] [ PDF 2861KB] ( 588 )

	281	Multisource fusion localization of unmanned sprayer based on factor graph
	Multisource fusion localization of unmanned sprayer based on factor graph [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 281-287>')" href="#">	SHENG Chenhang， SHEN Yue， LIU Hui， CUI Yemin， LONG Youneng
		To reduce pose estimation error of agricultural machinery by the GPS signal losing in the complex orchard environment, a multisource fusion localization method was proposed based on factor graph. RealSense D435i was integrated with color and depth camera and IMU to sense the surrounding environment of unmanned sprayer. Through the improved extraction method of adaptive threshold uniform Harris corner, the pyramid LK optical flow algorithm was used to match and track corner, and the camera motion was estimated by ICP algorithm. Based on the optimization algorithm，the pose estimation errors were iteratively optimized. The experiment was conducted on a forest road. Compared with inertial integrated navigation, the improved method could effectively estimate the sprayer pose in real time when GPS signal was lost. The experiment distance was 112.39 m in total, and the position update frequency after multisensor fusion was about 50 Hz. The results show that the RMS error of sprayer position is reduced by 0.816 m, and the maximum error is reduced by 4.613 m with the maximum error of attitude reduced by 2.713°.
		2020 Vol. 41 (3): 281-287 [Abstract] ( 60 ) [HTML 1KB] [ PDF 8960KB] ( 508 )

	288	Classification method of corn quality selection based on electromagnetic vibration and convolutional neural network
	Classification method of corn quality selection based on electromagnetic vibration and convolutional neural network [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 288-293>')" href="#">	QUAN Longzhe, WANG Jianyu, WANG Qi, XIAO Yunhan, FENG Huaiqu
		To improve the automation level of corn sorting and solve the problems of the complicated process of feature modeling by traditional methods and the high requirement of deployment of convolution neural network, the corn quality sorting and grading device was designed based on electromagnetic vibration and convolution neural network with several parts of corn kernel community feeding unit, electromagnetic feeding unit, control unit, sorting and collecting unit and constant light intensity visual single. The automatic separation of corn kernels, automatic recognition and sorting of corn kernels could be realized in the designed device. The results of model and prototype tests show that the model size is only 5.83 MB, which requires low computer hardware. The model mAP is 88.03%, and the overall classification and detection performance of the model is good. The model has strong recognition ability for excellent corn kernels, and P, R, FPR and F1 values are 98.75%, 94.84%, 3.78% and 96.85%, respectively. The actual detection accuracy of corn kernel is increased to 96.50% by the prototype, and the actual effective sorting rate is 97.51%.
		2020 Vol. 41 (3): 288-293 [Abstract] ( 60 ) [HTML 1KB] [ PDF 7040KB] ( 454 )

	294	Clustering recognition method of wheat seeds based on deep autoencoder
	Clustering recognition method of wheat seeds based on deep autoencoder [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 294-300>')" href="#">	LIU Saixiong, GENG Xia, LU Hu
		To improve the efficiency of agricultural production by artificial intelligence or machine learning, an autoencoder was constructed based on deep neural network to solve the problems of feature extraction and category identification in agricultural data analysis. The proposed network could not only analyze the features of inherent properties in agricultural data, but also could learn the potential advanced features. Based on the Gaussian kernel fuzzy clustering algorithm (AEKFC), the new autoencoder was realized by adding a Gaussian kernel clustering module into the autoencoder, and a new loss function was used to inversely adjust the whole network training to obtain the clustering results gradually. The proposed clustering method was an endtoend deep neural network learning method based on autoencoder. A great number of experiments were conducted on the dataset of agricultural wheat seeds.The results show that compared with other clustering algorithms,the proposed clustering algorithm has better clustering performance. The new machine learning algorithm can improve the effect of agricultural data analysis and has extensive application value.
		2020 Vol. 41 (3): 294-300 [Abstract] ( 44 ) [HTML 1KB] [ PDF 2274KB] ( 676 )

	301	Grain yield prediction of support vector machine based on hybrid intelligent algorithm
	Grain yield prediction of support vector machine based on hybrid intelligent algorithm [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 301-306>')" href="#">	GAO Xinyi, HAN Fei
		Considering the nonlinearity of grain yield, the prediction model of support vector machine was proposed based on hybrid intelligent algorithm. To solve the problem that particle swarm optimization (PSO) was easy to fall into a local optimum, the hybrid intelligent algorithm (GAPSOAFSA) was proposed by combining the improved PSO and the artificial fish swarm algorithm (AFSA).The objective function value was quickly converged to the global optimal solution by the mutation cross within the swarm and the external competition mechanism. The global search ability of the algorithm was improved to obtain the optimal parameter combination of support vector machine. The support vector machine prediction model was used to predict Chinese grain yield, and the model correctness was verified by the experiments.The results show that the prediction model has good prediction result.
		2020 Vol. 41 (3): 301-306 [Abstract] ( 59 ) [HTML 1KB] [ PDF 1355KB] ( 488 )

	307	Prediction of gasoline engine exhaust emission based on BP neural network
	Prediction of gasoline engine exhaust emission based on BP neural network [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 307-313>')" href="#">	ZUO Fushan, LI Zhengyuan, LYU Xiao, ZHANG Ying
		To accurately predict the emissions of gasoline engine exhaust pollutants, the emissions prediction was performed based on the BP neural network model. Aiming at the characteristics of nonlinear gasoline engine exhaust emission prediction, many characteristic parameters and large sample data, the data flow information of the characteristic parameters were used as input, and the vehicle emission level was used as output. Based on the BP neural network, the gasoline engine emission prediction models of CO, HC and NOx were respectively established, and the real vehicle test verification was completed in three modes of normal state, abnormal fuel pressure and abnormal intake pressure sensor. The test results of the vehicle exhaust gas analyzer were compared with the predicted results. The results show that the prediction system can predict three kinds of gases with high prediction accuracy and fast convergence speed, which can reach the expected results with good reliability.
		2020 Vol. 41 (3): 307-313 [Abstract] ( 38 ) [HTML 1KB] [ PDF 1327KB] ( 572 )

	314	Pig face recognition algorithm based on weighted sparse lowrank component coding
	Pig face recognition algorithm based on weighted sparse lowrank component coding [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 314-320>')" href="#">	CHENG Keyang， SUN Jiaao， MAO Qirong， ZHAN Yongzhao
		To solve the problem that animals were difficult to adapt to ear tags in the breeding industry, the pig face recognition algorithm was proposed based on weighted sparse lowrank component coding by the pig face recognition in nonintrusive recognition method. The Retinex theory and the regional covariance filter were applied to estimate the illumination, and the proposed adaptive gamma correction method was used to enhance the reflection components to reduce the impact of illumination on recognition results. The lowrank components in the training samples were used to construct the dictionary matrix, and the residual function was reconstructed to process the errors and improve the recognition performance of the algorithm in dealing with the images containing dirt. The recognition rate and the timeconsuming situation were calculated based on the light and facial dirt verification experiments on the JDD2017 pig face dataset. The results show that the proposed algorithm is significantly better than the traditional sparse representation method, and it has the advantages of tolerance to illumination changes and dirt with short training time.
		2020 Vol. 41 (3): 314-320 [Abstract] ( 60 ) [HTML 1KB] [ PDF 4882KB] ( 474 )

	321	Selection method of interval spectrum feature wavelength variables based on improved genetic algorithm
	Selection method of interval spectrum feature wavelength variables based on improved genetic algorithm[J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 321-327>')" href="#">	LIU Xin， MAO Zhikang， ZHANG Xiaoming， LI Shaowen， JIN Xiu
		To improve the robustness and prediction accuracy of the soil nutrient nearinfrared spectroscopy prediction model, a near infrared interval spectrum selection method was proposed based on the improved genetic algorithm. According to the positive and negative change times in the NIRS full spectrum wavelength variables purity gradients of the soil available phosphorus, the full spectrum was divided into multiple wavelength intervals. Using the variable projection importance coefficients (VVIP) from partial least squares regression model (PLSR) output greater than one as extraction criteria, the wavelength intervals with stronger interpretability for predicting soil nutrient target amount were extracted, and the wavelength intervals were combined into an interval spectrum. PLSR was modeled with the interval spectrum feature wavelength variable (FWV), and an improved genetic algorithm was used to select the optimal FWV corresponding to PLSR root mean square error minimum. The experimental results show that the proposed method for selecting optimal FWV can improve the robustness and prediction accuracy of regression model with simplified model structure. The improved real coded differential mutation operator can improve the genetic algorithm to expand the search space of global optimal solution and increase the convergence rate.
		2020 Vol. 41 (3): 321-327 [Abstract] ( 53 ) [HTML 1KB] [ PDF 0KB] ( 262 )

	328	Realtime location method of image acquisition for bamboo germplasm resources
	Realtime location method of image acquisition for bamboo germplasm resources [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 328-333>')" href="#">	WU Cuiyun, XU Jing, YUE Xiangxiang, LI Shaowen
		To solve the problems of single collection method and timeconsuming and laborious collection method for bamboo germplasm resources at present, the realtime positioning model and method of bamboo germplasm image acquisition were proposed based on Android platform. A mobile positioning method was selected by combining COO positioning with GPS positioning. The realtime localization algorithm was investigated by the least square method to eliminate outliers in lossless Kalman filtering method, and a new improved algorithm was produced. The realization of data and image integration method was discussed, and EXIF format was used to realize image expression of image, GPS information, azimuth, text, etc. The results show that the improved algorithm can effectively remove outliers and provide technical support for more accurate and effective data collection of bamboo germplasm resources.
		2020 Vol. 41 (3): 328-333 [Abstract] ( 57 ) [HTML 1KB] [ PDF 4429KB] ( 447 )

	334	Estimation model of SPAD value for soybean canopy based on multidimensional spectral characteristic wavelength extraction
	Estimation model of SPAD value for soybean canopy based on multidimensional spectral characteristic wavelength extraction [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 334-338>')" href="#">	WANG Lu, LI Weikai, GUAN Haiou, YU Song, HOU Yulong
		The extraction techniques of multiple spectral characteristic wavelength band were applied, and the nearinfrared spectral characteristics of soybean canopy during the whole growth period were investigated. An estimation model of SPAD value for soybean canopy was proposed based on the multidimensional spectral characteristic wavelength extraction. For the original nearinfrared spectral curve of soybean canopy, the multiple scattering correction preprocessing and the partial least squares regression modeling were preferred. Preprocessed with multiple scattering corrections, the competitive adaptive reweighted sampling algorithm (CARS), the principal component analysis and the successive projections algorithm were applied to extract the spectral characteristic wavelengths of soybean canopy, which were respective 22, 51 and 12. Based on the characteristic wavelengths, the partial least squares regression and the multiple linear regression (MLR) methods were used to establish the estimation models of soybean canopy SPAD values. The results show that the CARSMLR model has good experimental effect, and the root mean square errors of CARSMLR model for corrected and predicted samples are respective 5.67 and 5.94 with the average error of about 5.81.
		2020 Vol. 41 (3): 334-338 [Abstract] ( 36 ) [HTML 1KB] [ PDF 1989KB] ( 524 )

	339	Identifying and counting phyllotreta striolata fabriciuson based on yellow sticky trap
	Identifying and counting phyllotreta striolata fabriciuson based on yellow sticky trap [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 339-345>')" href="#">	ZHANG Liankuan, ZHANG Cheng, CEN Guanjun, GAO Yan
		To grasp the occurrence of phyllotreta striolatas fabricius with serious damage to vegetable growth and the damage extent, a method for identifying and counting phyllotreta striolatas fabricius was proposed based on yellow sticky traps. The maximum interclass variance algorithm（OTSU） algorithm was used to segment yellow sticky traps from the background images. OTSU algorithm, color smooth and active contour model were applied to segment phyllotreta striolatas fabricius from yellow sticky traps. Color feature, textural feature and shape feature of candidate areas were subsequently extracted, and support vector machine was built to identify and count the phyllotreta striolatas fabricius. The results show that the proposed method can achieve high accuracy of 88.16％, precision of 92.00％ and recall of 81.56％, and the information of phyllotreta striolata fabricius can be obtained in realtime.
		2020 Vol. 41 (3): 339-345 [Abstract] ( 39 ) [HTML 1KB] [ PDF 6319KB] ( 469 )

	346	Research and development of wind resistance test system for plant protection UAV
	Research and development of wind resistance test system for plant protection UAV [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 346-352>')" href="#">	LIU Yan， CHEN Bin， ZHANG Jingchao， ZHANG Xiao， CHEN Xiaobing
		With the consideration of the important indicator of wind resistance for measuring flight stability, safety and high quality of spraying operations of plant protection UAV, a wind resistance test system for plant protection UAV was developed based on the variable frequency control technology with four parts of axial fan assembly, hydraulic lifting platform, variable frequency control device and airflow field monitoring device. The airflow field was monitored by the gridded measurement method, and the wind speed sensors were used to measure the wind speed of each node. The wind speed and direction of each point by wind turbine were collected at different frequencies and different heights from ground. The test results show that the wind resistance test system can generate an adjustable cylindrical airflow field in transverse crosswind with length of about 5 m, diameter of about 3 m and height of 3 to 7 m from ground when the natural wind speed is lower than 3 m·s-1. The cylindrical airflow field with the same wind direction can meet the requirements of wind resistance test for the plant protection UAV.
		2020 Vol. 41 (3): 346-352 [Abstract] ( 44 ) [HTML 1KB] [ PDF 4483KB] ( 540 )

	353	Error sensitivity analysis of tandem robot based on differential method
	Error sensitivity analysis of tandem robot based on differential method [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 353-358>')" href="#">	CHEN Hua, LIU Xinyu, ZHAO Xuefeng
		To improve the absolute positioning accuracy of tandem robot, a method of analyzing robot error sources was proposed based on differential method and matrix method. The small errors of the single link attitude matrix were analyzed, and the integral method was used to analyze the pose errors of the ends of multiple links.By the differential method and the modified DenavitHartenberg (MDH) kinematics model, the sensitivity of the end pose error was also analyzed. The Matlab software was used to obtain the influence curve of the twist and rotation angles of the four joints of robot on the end pose and the influence curve of connecting rod length and offset on the end pose. The results show that the kinematic errors of geometric parameters with great influence on the end pose can be analyzed and avoided by the influence curves, and the problem of absolute accuracy of tandem robot can be solved from the source.
		2020 Vol. 41 (3): 353-358 [Abstract] ( 50 ) [HTML 1KB] [ PDF 1601KB] ( 462 )

	359	WSNON access mechanism and protocol under apron awareness environment
	WSNON access mechanism and protocol under apron awareness environment [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 359-365>')" href="#">	CHEN Weixing, SU Jingfang, MENG Meihan
		Aiming at the access problem of WSN(wireless sensor network)ON (opportunistic network), a cluster head election method based on game theory (CEGT) was proposed by the ON bundle protocol. CEGT could effectively improve the network connectivity under the special access environment of apron network. In the WSN node clustering stage, the game model was established by measuring the multiple social attributes of node to elect the cluster head more energyefficiently. Under the bundle protocol, the effectiveness of the communication between cluster head and mobile agent (Magent) was the access quality, which determined the quality of the network. The simulation results show that CEGT control method can reasonably elect the cluster head and reduce the node mortality to 57% for extending the network life cycle. Under the bundle protocol, when the numbers of nodes and buffer size are different, compared with non Magent boundary, the encounter opportunities by Magent can improve the delivery rate of cluster heads and achieve efficient ON access.
		2020 Vol. 41 (3): 359-365 [Abstract] ( 33 ) [HTML 1KB] [ PDF 1829KB] ( 488 )

	366	#br# Surface roughness prediction based on Copula EDA optimization of BP neural network
	#br# Surface roughness prediction based on Copula EDA optimization of BP neural network [J]. Journal of JIangsu University(Natural Science Eidtion), 2020,41(3): 366-372>')" href="#">	PEI Hongjie, CHEN Yuying, LI Gongan, LIU Chengshi, WANG Guicheng
		To improve the prediction accuracy of surface roughness of machined surface, the method of optimizing BP neural network was proposed by Copula estimation of distribution algorithm (EDA). The experiments of milling 45＃ steel were conducted by the control variable method. The main cutting force, axial force, radial force and vibration amplitude were measured on line, and the corresponding average value, standard deviation, RMS values of cutting force and vibration amplitude were obtained. The twodimensional surface roughness Ra, threedimensional roughness average Sa and RMS Sq were measured offline. The correlation analysis was carried out among cutting force component mean value, standard deviation, root mean square value, vibration amplitude and roughness. The average value of main cutting force with the largest Kendall rank correlation coefficient was selected as input variable. The average main cutting force was input into BP neural network and another BP neural network optimized by Copula EDA for training and predicting. The experimental results show that the prediction accuracies of BP neural network based on Copula EDA is higher than that of BP neural network, and the average prediction accuracy of Ra, Sa and Sq are 91.98％, 91.03％ and 89.10％, respectively.
		2020 Vol. 41 (3): 366-372 [Abstract] ( 31 ) [HTML 1KB] [ PDF 1292KB] ( 455 )

江苏大学学报（自然科学版）

　

News

　

·	关于近期网络不稳定情况的说明

·	Our journal has be included in JSTChina Database

·	Our journal has be selected for the 2015-2016 China Science Citation Database (CSCD)

　　　　　　　　　　More

　

Links

　

·	Chinese Library Classification Number

·	Society of China University Journals

·	China National Knowledge Infrastructure

·	Chinese Sciencepaper Online

·	Transactions of the Chinese Society for Agricultural Machinery

·	Journal of Southeast University：Natural Science Edition

　　　　　　　　　　More

Copyright © 2011 Journal of Jiangsu University(Natural Science Eidtion)
Support by Beijing Magtech Co.Ltd E-mail：support@magtech.com.cn