15 June 2019, Volume 45 Issue 6
-
Select all|
-
Computer Engineering. 2019, 45(6): 1-5. https://doi.org/10.19678/j.issn.1000-3428.0052120
Due to the fact that the current neural network-based traffic flow forecasting method embeds part of the manually designed features,the feature extracted by the network has single function,bad adaptability,poor robustness and inaccurate characterization of the local features.Therefore,this paper proposes a traffic flow forecasting method based on residual Long Short Term Memory(LSTM).The model uses the idea of ensemble learning to train the spatially distributed data into a residual LSTM network.In addition,dimension weighted units are introduced after each LSTM unit to present the interdependencies between different dimensions of modeling features.Experimental results show that the method can realize adaptive modeling analysis of short term traffic flow data.
-
Computer Engineering. 2019, 45(6): 6-11. https://doi.org/10.19678/j.issn.1000-3428.0052439
In order to improve the tracking precision of the unmanned vehicle steering system to the target path,this paper proposes a new unmanned vehicle path tracking method.It introduces the lateral control scheme of unmanned vehicle based on tracking preview point,and gives the dynamic linearized data model of the system and its multi-step prediction equation.The estimation and prediction model of pseudo-gradient vectors is derived by using the method of least squares.Adopting the advantages of model-free adaptive predictive control,it can perform repeated online calculations through rolling optimization strategies,so as to obtain better dynamic performance.Based on the CarSim/Simulink co-simulation platform,the method is verified when the vehicle speed is 5 m/s and 20 m/s.Results show that compared with the MPC scheme based on vehicle dynamics,this proposed method has better tracking performance.
-
Computer Engineering. 2019, 45(6): 12-20. https://doi.org/10.19678/j.issn.1000-3428.0052284
To address the re-identification problem of different individual vehicles with identical types,a new vehicle re-identification algorithm is proposed.According to the component detection algorithm,the window and the vehicle face region with large differences between different vehicles are obtained,and the vehicle features of the detected vehicle window and the vehicle face region are extracted and merged to generate new fusion features.The distance measurement between image features is calculated for classification and recognition.The test is carried out on the public dataset VRID-1 of Sun Yat-sen university and results show that the Rank1 matching rate of the algorithm reaches 66.67%,which is obviously better than the classical traditional feature representation algorithm,thus verifies the feasibility and validity of the algorithm.
-
Computer Engineering. 2019, 45(6): 21-25. https://doi.org/10.19678/j.issn.1000-3428.0050895
Based on the traffic wave theory and VISSIM software simulation analysis,the critical condition of traffic flow that is appropriate for the intersection to set the Contraflow Left-turn Lanes(CLL) is studied.The critical calculation formula of setting left-turn lane is obtained by wave theory analysis and verified by example calculation and VISSIM simulation analysis.Based on the VISSIM software,the difference between the operational indicators before and after the intersection setting the left-turn lane is analyzed.Simulation results show that when the left-turn traffic flow is small that enters the CLL with unsaturated flow rate,it is not advisable to set the CLL.When the traffic condition which is appropriate to set the CLL,the setting of CLL can effectively improve the left-turn capacity and reduce the average delay,schedule time,length of queue,parking time,etc.The setting of CLL may not increase the number of the parking times,which is related to the left-turn traffic flow.
-
Computer Engineering. 2019, 45(6): 26-31. https://doi.org/10.19678/j.issn.1000-3428.0049450
Aiming at the non-stationary characteristics of traffic trajectory big data,the preprocessing method of traffic trajectory big data is studied.According to the multi-resolution analysis characteristics of it,two-dimensional discrete wavelet,it is selected to denoise and compress the traffic trajectory big data.Building a preprocessing platform for traffic trajectory big data and combining with road traffic congestion state judgment criteria to analyze the real-time traffic situation in important sections.Analysis results show that the method can improve the speed of data processing and the analysis accuracy of congested sections.
-
Computer Engineering. 2019, 45(6): 32-36,44. https://doi.org/10.19678/j.issn.1000-3428.0051022Lidar has a great influence on the detection of ground obstacles due to the point swept to the ground.In order to accurately identify obstacles,it is necessary to accurately separate the obstacle point cloud and the ground point cloud.To address the shortcomings of traditional separation methods such as large computational complexity and poor scene versatility of the scene,a point cloud separation method based on three dimensional Mesh graph is proposed.The method connects the collected point cloud data into a Mesh map,finds the ground reference point according to different attributes of the ground point and other points on the Mesh map,spreads the ground attributes to other points and finally separates all the ground points.Experimental results show that the proposed method has a good ground point cloud separation effect while ensuring operational efficiency of the algorithm.
-
Computer Engineering. 2019, 45(6): 37-44. https://doi.org/10.19678/j.issn.1000-3428.0052552
To address the multi-class Lightill-Whitham-Richards(LWR) traffic flow model on non-uniform roads,a low-dissipation central-upwind scheme is proposed.Based on the 4th-order Central Weighted Essentially Non-Oscillatory(CWENO) reconstruction and the low dissipation central-upwind numerical flux,the dissipative characteristics of the numerical format are optimized by constructing different forms of global smoothing factors and increasing the nonlinear weights corresponding to non-smooth templates.The Runge-Kutta method discretizes the semi-discrete numerical scheme in the time direction to maintain 4th-order precision.The numerical simulation of the lane number change and traffic signal control problem of multi-class LWR traffic flow model on non-uniform roads shows that the scheme has 4th-order solving accuracy and high resolution.
-
Computer Engineering. 2019, 45(6): 45-51. https://doi.org/10.19678/j.issn.1000-3428.0051226
In order to solve discrete memory access problem of unstructured grid in high performance computing,this paper proposes a general multi-core optimization algorithm according to the architecture features of the heterogeneous multi-core processor SW26010.This algorithm takes the Chinese supercomputer,Sunway TaihuLight,as the platform,and is based on a sorting approach.Based on the principle of mesh generation,generated non-zero elements of the sparse matrix are reordered in O(n) time.An internal mapping method is used to extend or transform the computational vectors,and the fine-grained memory access is transformed into the coarse-grained access without writing conflicts.Multi-core optimization is carried out for the flux calculation in several practical examples.Experimental results show that compared with the serial algorithm on the main core,the proposed algorithm can achieve an average acceleration of more than 10 times.
-
Computer Engineering. 2019, 45(6): 52-59. https://doi.org/10.19678/j.issn.1000-3428.0052612The Key-Value(KV) is a storage model widely used in NoSQL systems.To address the problems of limited search function,small memory capacity and downtime of the current mainstream NoSQL system,this paper proposes a KV type of NoSQL system design method.The method designs a persistent hybrid primary index structure to solve range queries and fast restarting,uses data distribution algorithms and internal and external hybrid storage technologies,and implements efficient access and low-cost storage of large-scale data through intelligent scheduling of data between memory and Solid State Disk(SSD).Experimental results show that compared withRedis,the system improves the single-node read/write performance by about 8 times and reduces the configuration cost by about three-fourths when addressing values of typical size.It has obvious advantages in the low-cost and efficient storage of massive data.
-
Computer Engineering. 2019, 45(6): 60-66. https://doi.org/10.19678/j.issn.1000-3428.0050655To reduce the computational cost of multi-attribute non-equi join operation,an non-equi join operation algorithm MIEJoin based on attribute optimization is proposed.The tuples are sorted by join attribute,the candidate set size of each join attribute is calculated,and the final result set is filtered according to the join predicate in the minimal candidate set.On this basis,a cache-sensitive multi-attribute non-equi join algorithm CMIEJoin is proposed to improve the hit rate of the system cache.Based on the MIEJoin algorithm,the array of sorted tuples is established,and the continuousty accessed data is stored in memory in proximity to reduce the number of cache missings and improve the efficiency of the algorithm.Experimental results on the TPC-H dataset show that CMIEJoin algorithm has higher efficiency than BIEJoin algorithm and NLJoin algorithm.
-
Computer Engineering. 2019, 45(6): 67-74. https://doi.org/10.19678/j.issn.1000-3428.0053522
Aiming at online task allocation problem of spatiotemporal crowdsourcing,a task range adjustment algorithm DMRA and an online task allocation algorithm PAMA based on predictive analysis are proposed.The DMRA algorithm takes task location as the center and dynamically adjusts the range of tasks according to worker density.The PAMA algorithm uses Bayesian classifier to predict the distribution of the next timestamp object based on historical statistical probability.On this basis,the weighted bipartite graph optimal matching algorithm is executed to complete the task allocation.Experimental results show that the combination of DMRA algorithm and PAMA algorithm can improve the total utility of task allocation and reduce the travel cost of workers,and the performance of task allocation is better than that of greedy algorithm and random threshold algorithm.
-
Computer Engineering. 2019, 45(6): 75-81. https://doi.org/10.19678/j.issn.1000-3428.0051839
Fuzzy C-Means(FCM) clustering algorithm can only deal with low-dimensional data and is sensitive to the initial center,without considering the interactions between class centers.For this reason,an improved method of initial center selection is designed based on the idea of conditional fuzzy clustering,replacing the Euclidean distance in the traditional FCM algorithm with the cosine distance.A wHFCLM algorithm is proposed and combined with extended incremental clustering algorithms,spFCM,oFCM and rseFCM,to generate their extended incremental fuzzy clustering algorithms,spHF(c+l)M,oHF(c+l)M and rseHF(c+l)M.Experimental results show that compared with spFCM,oFCM and rseFCM,the extended incremental fuzzy clustering algorithms is less sensitive to the selection of initial centers.It can better handle large-scale sparse high-dimensional data sets,and has better clustering performance under blocks of the appropriate size.
-
Computer Engineering. 2019, 45(6): 82-88. https://doi.org/10.19678/j.issn.1000-3428.0050322Based on the VecOp vector algorithm library of ARM V8 architecture,this paper proposes a scheme of implementing and optimizing the basic vector algorithm lobrary on ARM V8 platform.The optimization is implemented from four aspects: memory access optimization,instruction set optimization,basic block optimization,and vector branch optimization,to improve the performance of vector algorithm functions on ARM V8 platform to optimize VecOp algorithm library on ARM V8 platform.Experimental results show that the performance of the vector algorithm library on the ARM V8 computing platform can be improved by 10%~300%.
-
Computer Engineering. 2019, 45(6): 89-95. https://doi.org/10.19678/j.issn.1000-3428.0050835In the development cycle of mobile applications,the use of Graphical User Interface(GUI) automated testing technology can improve the efficiency of the development and test of APP.Still,the GUI automated testing method based on recording playback is not applicable to black box test scenarios,and its recognition accuracy rate is not high.To deal with the advantages,this paper proposes a control recognition algorithm based on text recognition in images and application page layout.Based on the page layout structure of mobile applications and the accurate recognition control for the coordinates of gesture operation,the overlapping problem of page layout in the process of traversing is solved by traversing the control tree.Experiments are carried out on Android and iOS platforms respectively,and results show that the control recognition algorithm has higher accuracy than the control recognition algorithm based on coordinates and source codes.
-
Computer Engineering. 2019, 45(6): 96-102. https://doi.org/10.19678/j.issn.1000-3428.0050787In view of the problems of link congestion and high network communication cost that result from the rapid growth of traffic within the cloud Data Center(DC),this paper proposes an improved network-aware virtual machine placement algorithm.According to the hardware resource requirements of virtual machines,the population initialization is used to improve the convergence speed of the proposed algorithm.Then,discrete differential mutation and crossover operations are used to ensure the diversity of the population.With a comprehensive consideration of 4 evaluating indicators including communication cost,maximum link utilization,hardware resource constraint violation degree and link capacity constraint violation degree,this paper proposes a multiple subgroup elitist selection strategy based on ε relaxation to select the optimal virtual machine placement scheme and enhance the global exploitation ability.Simulation results show that the proposed algorithm can effectively reduce the network communication cost and achieve the load balancing of network.
-
Computer Engineering. 2019, 45(6): 103-107,114. https://doi.org/10.19678/j.issn.1000-3428.0051991
Internet Service Providers(ISP) implement local rerouting by deploying Downstream Path Criterion(DC).To reduce the computational overhead of DC implementation method and balance the relationship between fault protection rate and computational overhead,a DC implementation method DC-iSPF based on incremental Shortest Path First(iSPF) algorithm is proposed.The link cost from computing node to neighboring node is set to 0,and the iSPF algorithm is run on the updated topology to calculate all neighboring nodes that conform to DC.Experimental results show that compared with TBFH algorithm and DMPA algorithm,DC-iSPF method can reduce computational overhead and improve fault protection rate.
-
Computer Engineering. 2019, 45(6): 108-114. https://doi.org/10.19678/j.issn.1000-3428.0050894Aiming at the problem that overload processing consumes high system resources in sporadic real-time systems,an overload control strategy based on Minimum Delay Time and Imprecise Computation(MDTIC) is proposed.Combined with the Earliest Deadline First(EDF) scheduling algorithm,the system load state is dynamically determined by using the maximum stealing time and minimum delay time,then some non-critical tasks are discarded according to the system load state to solve the system overload problem.Experimental results show that the proposed strategy can reduce the overload processing time and improve the utilization rate of the system resource.
-
Computer Engineering. 2019, 45(6): 115-118,126. https://doi.org/10.19678/j.issn.1000-3428.0051185
Hardware data prefetching technology can effectively improve the memory access performance of processors,but the traditional stream prefetching strategy has the problem of untimely prefetching.Therefore,a double step stream prefetching strategy is proposed,and the corresponding prefetching component structure is designed.The prefetching component automatically detects the fixed step size of the data stream and enlarges the step size to twice of the original one to calculate the prefetching address.Experimental results show that the performance of the processor can be improved by 45% and 57% respectively when SPEC2006 test set integer application and floating-point application are run with the prefetching component.For applications with high Cache Miss rate,the prefetch component can effectively hide the memory access latency.
-
Computer Engineering. 2019, 45(6): 119-126. https://doi.org/10.19678/j.issn.1000-3428.0050981Aiming at the problem that sub-domain planning and controller deployment are unreasonable in Software Defined Networking(SDN) multi-domain networks,a new SDN multi-domain adaptive management method is proposed.Based on the improved node clustering idea,the SDN Sub-domain Dividing Optimization Algorithm(DDOA) is designed.The nodes in the network are clustered according to the degree of attraction and attribution,and the sub-domain planning is completed.For the different network costs in the sub-domain,the Controller Adaptive Deployment Algorithm(CADA) is given,and the cost of the sub-domain network is obtained by cost-weighted summation to complete the controller deployment.Simulation results show that compared with the controller adaptive deployment algorithm and load balancing algorithm,the network sub-domain division and controller deployment are more reasonable,which can save 23% backup controller space and improve the overall performance of the network.
-
Computer Engineering. 2019, 45(6): 127-133. https://doi.org/10.19678/j.issn.1000-3428.0052863
In order to improve the sensing ability of sensor nodes to acoustic events under environmental noise interference,a fixed time window cumulative sum method is proposed based on the maximum likelihood cumulative algorithm.The influence law of quaternary positioning parameters on the positioning accuracy is analyzed.According to the principle of achieving the maximum circumradius and most appropriate reference angle, the most reasonable node combination is selected from the sensor nodes that sense the acoustic event, and the positioning result is obtained through multiple iterations. Simulation results show that compared with the existing distributed positioning method, the positioning accuracy of this method is improved by about 30%.
-
Computer Engineering. 2019, 45(6): 134-139,145. https://doi.org/10.19678/j.issn.1000-3428.0050608
In order to decrease the interference between small cells in Ultra Dense Network(UDN),this paper a propose an user-centric semi-dynamic clustering method for Coordinated Multiple Point(CoMP) Joint Transmission(JT) scenarios.It divides small stations into non-overlapping clusters,and takes the small stations in the cluster and the small stations located outside the cluster but having large interference with the cluster as the optional service stations of the user.Zero-forcing precoding is used to eliminate interference to users from non-serving base stations in the optional service stations.Users select a number of candidate service stations from the optional service stations service and selected the cluster heads,with the goal of maximizing the sum of throughput of each user select the station clusters for users from the optional service stations.At the meanwhile a suboptimal method for selecting service station clusters for users is given to reduce the complexity.Simulation results show that compared with the existing scheme in the same scenario the proposed scheme improves the system throughput.
-
Computer Engineering. 2019, 45(6): 140-145. https://doi.org/10.19678/j.issn.1000-3428.0050734
In order to solve the problem that topological communities gotten by community structure detection algorithms are not same with the functional communities,a community structure detection algorithm based on Typed-Edge Similarity Clustering(TESC) is proposed.The algorithm clusters nodes with local topological features and heterogeneous information,and constructs similarity matrices between network nodes based on node neighboring edge types to obtain heterogeneous edge information.On the basis of the similarity matrix,the nodes with large similarity are continuously merged by the idea of traditional hierarchical clustering,and then the number of communities is optimized by using the contour coefficients to obtain the final community division result.Selecting 4 real networks with known community structure and 6 artificial synthetic LFR benchmark networks,comparing with GN,Louvain algorithm of homogeneous network and Hete-SPAEM and Hetero-Attractor algorithms of heterogeneous network,the results show that the community structure obtained by the TESC algorithm are more consistent with the actual community of the network.
-
Computer Engineering. 2019, 45(6): 146-151,159. https://doi.org/10.19678/j.issn.1000-3428.0050434
When Wireless Sensor Network (WSN) performs node positioning in complex mountain environments,sparse node deployment can cause positioning errors.Based on the sparseness degree of nodes,the position of an unknown node can be determined by fusing the three-dimensional Approximate Point-in-triangulation Test(APIT) algorithm and the DV-Hop algorithm.By searching neighboring nodes and connecting them,planes could be formed.Then the algorithm makes perpendiculars from the unknown node to the planes,and the average value of the coordinates of perpendicular feet is the final position of the unknown node.Experimental results show that compared with the APIT algorithm and the DV-Hop algorithm,the algorithm improves the node positioning accuracy.
-
Computer Engineering. 2019, 45(6): 152-159. https://doi.org/10.19678/j.issn.1000-3428.0050735
In order to solve the serious traffic load and network congestion caused by the increasing data traffic to the cellular network,a mobile Data Offloading algorithm based on node Selfishness and Centrality(SCDO) in the opportunistic networks is proposed.The cellular network passe the data directly to the seed node,and the seed node uses the contact brought by the node movement to pass the data to other nodes requesting the data.If a node does not receive data when it arrives at the delay tolerance time,the node can directly download data from the cellular network.This paper compares three methods namcly,the cellular network traffic load without spilt flow,the random network scenario when randomly selecting 10% of the nodes as the seed node,and the cellular network traffic load when the SCDO relecting 10% of the seed nodes.Results show that compared with the cellular scenario and the random scenario,the time delay of SCDO is reduced by about 48% and 30% respectively,and the data traffic volume is increased by about 20% and 12% respectively.
-
Computer Engineering. 2019, 45(6): 160-164,174. https://doi.org/10.19678/j.issn.1000-3428.0050704
In order to improve the energy efficiency and convergence speed of cognitive user channel and power allocation algorithms in distributed cognitive wireless networks,use the average number of bits per unit of energy as a communication efficiency indicator,and balance user communication quality and system energy consumption,this paper proposes a distributed channel and power allocation algorithm based on multi-Agent cooperative reinforcement learning.The collaborative learning is introduced on the basis of multi-agent independent Q-learning is introduced,and users share Q values and fuse after independent Q-learning.Simulation results show that the algorithm can effectively improve the convergence speed of cognitive users in transmitting power and channel allocation compared with energy efficiency-based independent Q-learning algorithm,independent Q-learning algorithm and random power allocation algorithm.
-
Computer Engineering. 2019, 45(6): 165-170. https://doi.org/10.19678/j.issn.1000-3428.0050974
In order to simplify the access structure and ensure that all integer programming have solutions,a scheme is proposed to apply integer programming directly to the secret sharing of general access structure.By constructing integer programming,the secret is hidden in the solution to the objective function,and the constraint condition is sent to the participants as the secret share.Participants can use their shares to reconstruct the integer programming problem,and get the correct solution to the objective function quickly by the method of solving equations,and then the secret is recovered.Analysis results show that,compared with the scheme using (t,n) threshold,this scheme can achieve all the access structures.It doesn’t need to solve integer programming with the classical method or deduce the maximal unauthorized subsets,which reduce its computational complexity.
-
Computer Engineering. 2019, 45(6): 171-174. https://doi.org/10.19678/j.issn.1000-3428.0054123
R-ate is an important bilinear mapping in the Identity-Based Cryptography(IBC) algorithm of China state cryptography standard SM9.Its computational performance is very important to the application of SM9 cryptosystem.To improve the computational efficiency of R-ate bilinear pairing,a fast computational algorithm is proposed.By analyzing the computation process of R-ate bilinear pairing on BN curves and the involved principle of inverse operations,the order in which isomorphic mapping takes effect in computation is changed,and most of the inverse operations are transferred from the large feature domain to small feature domain to reduce the computation loss of inverse element solution.The system parameters of SM9 are taken as an example to carry out experiments.Results show that the running time of the proposed algorithm is only 1.8×105 ms.
-
Computer Engineering. 2019, 45(6): 175-180. https://doi.org/10.19678/j.issn.1000-3428.0050585
In order to improve the efficiency of intrusion detection,it is necessary to extract the features of data to reduce the data dimensions.This paper proposes a network intrusion detection method by combining Information Gain(IG) and Principal Components Analysis(PCA).The method uses IG to extract the attribute features with strong classification ability,uses PCA to reduce the dimension of the feature data,and uses Naive Bayes method for classification and detection.The test results of the data set KDDCUP99 show that the detection rate of the method is 94.5%,which is much higher than those of PCA-LDA,FPCA,and KPCA methods.
-
Computer Engineering. 2019, 45(6): 181-187. https://doi.org/10.19678/j.issn.1000-3428.0051023
The multipath effect and time-varying characteristics of wireless signals cause large fluctuations in the measured values based on the Received Signal Strength Indication(RSSI),resulting in large errors in WLAN authentication and attack location based on RSSI location fingerprinting.Therefore,the network access authentication and attack detection location scheme of the Channel State Information (CSI) location fingerprinting are proposed.The Orthogonal Frequency Division Multiplexing(OFDM) technology is used to obtain fine-grained CSI,and the location signal characteristics are described.The K-means optimized initial clustering point algorithm is used for data processing to enhance the differences between location information,and a CSI-based location map is constructed.The CSI location fingerprinting is used to authenticate the user accessing the WLAN,and the attack detection and location are performed on the user who fails the authentication.In the communication standard test of IEEE 802.11n,the correct positioning rate of the scheme is as high as 98.12%.
-
Computer Engineering. 2019, 45(6): 188-192，198. https://doi.org/10.19678/j.issn.1000-3428.0049815
In order to improve the security and reliability of military Ad Hoc network,this paper proposes a hierarchical network architecture and designs a Shortened Random-based Signcryption (SRS) scheme by using a random number instead of timestamp in Direct Key Exchange Using Timestamp Signcryption (DKEUTS) scheme.According to the security requirements,communication and computing performances of different nodes,this paper chooses the DKEUTS scheme or the SRS schemes with different signcryption parameters.By discriminating whether the network node is a cut-vertex,the network connectivity is predicted.The information of network connectivity can be used to reconstruct network topology and guarantee network reliability.Performance analysis results show that the proposed hierarchical network architecture and security protocol can be applied in node non-homogeneous networks.
-
Computer Engineering. 2019, 45(6): 193-198. https://doi.org/10.19678/j.issn.1000-3428.0051108
In the certificateless cryptography system,there is no authentication relationship between the public key and the holder,which may cause a problem that a malicious user replaces the user’s public key.To This end,this paper improves the definition of certificateless signature,and proposes a provably security certificateless short signature scheme.The security of the scheme is based on the Inv-CDH problem,and the complete security proof is given under the stochastic oracle model,and it is proved that the scheme is anti-existence forgery in the adaptive selection message attack under the new adversary.This scheme is implemented by C language,and its performance is analyzed and compared with those of the classical short signature schemes and the certificateless short signature schemes in recent years.Results show that in the signature phase,the scheme only needs one time of multiple-point operation;in the verification phase,the scheme requires two times of multiple-point operation and two times of bilinear pairing operation.The proposed scheme has a short signature length and a high operation efficiency.
-
Computer Engineering. 2019, 45(6): 199-205. https://doi.org/10.19678/j.issn.1000-3428.0051211
To improve the efficiency and accuracy of community detection,a random parallel local search algorithm is proposed.The complex system is represented by graph model structure,and vertices are divided into clusters.The greedy stochastic adaptive search process and path reconnection process are constructed to solve the module maximization problem of weighted graph.A {0,1} matrix class feature is introduced and the distance function of clustering is defined,so that the neighborhood search of vertices can be carried out to achieve high-precision community detection and recognition.Experimental results show that the F1 value and NMI index value of the proposed algorithm are both high.
-
Computer Engineering. 2019, 45(6): 206-210. https://doi.org/10.19678/j.issn.1000-3428.0050677
To extract the content from a Web page accurately,an algorithm based on Support Vector Machine(SVM) and gravity radius model of DOM is proposed.Extract the node of text block from Web pages by means of SVM.Use the links information from its page and the node above to calculate the gravity radius,and utilize gravity radius model of DOM to accurately extract content again.The process of corresponding formula derivation and hyper parameters selection are presented in this paper.Experimental results show that compared with statistical extraction,FFT extraction and other algorithm,the proposed algorithm has higher accuracy and efficiency as well as better generalization ability.
-
Computer Engineering. 2019, 45(6): 211-217. https://doi.org/10.19678/j.issn.1000-3428.0051060
Sentence alignment is a process mapping sentences in the source text to their counterparts in the target text.Within the framework of neural network,this paper proposes a sentence alignment method,on the basis that the aligned source sentence and target sentence pair contains a large number of aligned words.The Gated Relevance Network (GRN) is used to capture the semantic interaction between the source sentence and the target sentence pair,and the semantic interaction is used to determine whether the source sentence and the target sentence are aligned.The alignment evaluation of non-monotonic text shows that the F1 value of the method reaches 93.8%,which effectively improves the accuracy of sentence alignment.
-
Computer Engineering. 2019, 45(6): 218-224. https://doi.org/10.19678/j.issn.1000-3428.0050618
The removal under-sampling method does not consider much the influence of data distribution changes on the classification results when the unbalanced data sets are classified,an improved under-sampling method based on clustering fusion and redundancy removal is proposed.The clustering algorithm is used to obtain the clustering centers of the high-density distribution regions of most samples.Most of the samples are divided into different subsets.The redundancy coefficients of each subset are calculated to de-redundantly delete most of the samples.After under-sampling the data sets with different balance rates,the cost-sensitive attribute hybrid strategy multi-decision tree prediction model is used for classification.Experimental results show that the proposed method can enable the prediction model to improve the positive rate of a few samples and the G-mean value of the prediction model under the premise of ensuring that the classification accuracy of the unbalanced data sets is not reduced.
-
Computer Engineering. 2019, 45(6): 225-229,236. https://doi.org/10.19678/j.issn.1000-3428.0050304
The possible deviations between user ratings and user preferences in collaborative filtering algorithms result in reduced recommendation accuracy.For this problem,a user preference extraction algorithm based on attribution theory is proposed.User preferences are extracted based on the consensus,distinctiveness,positive and negative preference information of user behaviors.Merge preference similarity and rating similarity to get a better nearest neighbor set,and calculate a user’s predicted rating for unrated items.Experiments are carried on Movies Lens-1M dataset and the results show that under the merging condition of 10% preference similarity and 60% rating similarity,the algorithm achieves the highest recommendation accuracy,which is better than the traditional collaborative filtering algorithm and other improved algorithms,such as HU-FCF、BM/CPT-V.
-
Computer Engineering. 2019, 45(6): 230-236. https://doi.org/10.19678/j.issn.1000-3428.0052565
The method of cross-media retrieval mostly maps the original features of two modalities to the common subspace,and performs cross-media retrieval in the subspace,ignoring the selection of discriminant features and the relationship between modalities.Therefore,a new cross-modal retrieval method based on coupled dictionary learning and graph regularization is proposed.A uniform sparse representation is generated for different modalities by associating and jointly updating dictionaries of different modalities.The sparse representations of the different modalities are then projected into the common subspace defined by the class label information to perform cross-modal matching while applying 21 norm terms to the projection matrix to select the correlation and discriminative features of the feature space.On this basis,the regularization term of the graph is used to preserve the inter-modal and intra-modal similar relationship.Experimental results show that compared with the Canonical Correlation Analysis(CCA) method,the method has higher accuracy in cross-media retrieval.
-
Computer Engineering. 2019, 45(6): 237-241,248. https://doi.org/10.19678/j.issn.1000-3428.0051131
In order to make full use of the historical knowledge and improve the accuracy of rating prediction,a recommendation model based on Lifelong Machine Learning(LML) is proposed to mine both user ratings and comments.The model accumulates knowledge from previous tasks and utilizes it in future tasks to help improve the rating prediction accuracy.Experimental results on real datasets show that compared with models without LML ability,the mean square error of the predicted ratings of this model is reduced by 5.4‰,and with the accumulation of knowledge,its error is continuely dropped.The accuracy of topic word classification results is improved.
-
Computer Engineering. 2019, 45(6): 242-248. https://doi.org/10.19678/j.issn.1000-3428.0050777In the text classification process,the Extreme Learning Machine(ELM) randomly maps the input text features and presents a nonlinear geometric structure.As a result,the least square method cannot solve such nonlinear structures and thus affects the text classification performance.To solve this problem,this paper introduces a new manifold regularization and presents an improved algorithm based on extreme machine learning.The Laplace feature mapping is used to preserve the geometry of input text features.The distance between sample points is modified based on the category information of the sample,and the sample points with the same category are selected first to improve the classification performance.Experimental results on the datasets of Reuters and 20newsgroup show that,compared with the Regularization Extreme Learning Machine(RELM),AdaBELM and other algorithms,the proposed algorithm has better classification performance,and the F1-measure can reach 91.42%.
-
Computer Engineering. 2019, 45(6): 249-253,266. https://doi.org/10.19678/j.issn.1000-3428.0051065The cross-entropy criterion of mainstream neural network training classifies and optimizes each frame of acoustic data, while the continuous speech recognition uses the sequence-level transcription accuracy as the performance measurement.For this difference,an end-to-end speech recognition system based on sequence-level transcription is constructed.The phoneme is used as the basic unit to build the model,and the target function of Connectionist Temporal Classification (CTC) is used to improve the structure of Long Short-Term Memory(LSTM) network.The dictionary and language model are introduced in the decoding process,and the tone feature is added to the front end to enrich the acoustic feature.The modeling effect of CTC is improved by using the sequence discrimination training technique.Experimental results show that the recognition efficiency and accuracy of the proposed system is improved,and the Word Error Rate(WER) can be as low as 19.09%±0.16%.
-
Computer Engineering. 2019, 45(6): 254-258. https://doi.org/10.19678/j.issn.1000-3428.0051800Orbital Angular Momentum (OAM) vortex electromagnetic waves are mostly generated by complex systems.In order to obtain OAM electromagnetic waves easily,a circularly polarized nut-shaped antenna is designed.By controlling the relative positions of two feeding points,a specific mode of circularly polarized vortex electromagnetic waves with OAM is generated.The theoretical deduction and simulation results prove the effectiveness of the nut-shaped patch antenna.Compared with the traditional shaped patch antenna,the proposed antenna is smaller and more compact,with improved spatial radiation phase distribution and resonance characteristics.
-
Computer Engineering. 2019, 45(6): 259-266. https://doi.org/10.19678/j.issn.1000-3428.0050584To address the low accuracy of location in 3D map due to GPS error and digital map error,a map matching algorithm based on an improved Hidden Markov Model(HMM) is introduced.This paper proposes the area overlap method to obtain the candidate road segments.The calculation of the observation probability takes the distance,road width and historical positions into account.The transition probability is computed in terms of road network topology data,the tourist’s behavior characteristics and the correlation between scenic spots and roads.Then the algorithm uses the Viterbi algorithm to get the optimal matching road segments.The presented algorithm enables the 3D visualization of the scenic scene on the Unity3D platform,and is verified by using the campus map.Experimental results show that the matching accuracy of the presented algorithm achieves 95.4%.The presented algorithm has a good performance in 3D scenic spot navigation in both practicability and accuracy.
-
Computer Engineering. 2019, 45(6): 267-272,279. https://doi.org/10.19678/j.issn.1000-3428.0051091Aiming at the problems existing in the traditional recommendation system,such as cold start,sparse data,lack of semantics and relatively low recommendation accuracy,a recommendation algorithm based on event ontology is proposed.By combining the news classification structure and news corpus to build event ontology,the elements of news browsed by users are extracted and user’s interest model is constructed.The similarity between the news events is calculated based on the event ontology structure,the user interest similarity is calculated through user’s interest model,and relevant news events are found according to the semantic radius of the non-hierarchical structure of event ontology.Synthesize the news ontology similarity,the user’s interest similarity,and the non-hierarchical structure similarity to realize a comprehensive news personalized recommendation.Experimental results show that the proposed algorithm has better recommendation than the collaborative filtering recommendation algorithm and the recommendation algorithm based on content.
-
Computer Engineering. 2019, 45(6): 273-279. https://doi.org/10.19678/j.issn.1000-3428.0051598In order to solve the test adequacy problem of the integrated shipboard network system,a network fault injection platform is designed.Based on network fault injection and network attack,the fault impact factor is constructed to form a fault model library.Network fault injection is simulated with the functional modules and tools including tc,netem,and netfilter.Cyberattacks are simulated based on the tfn2k architecture.The data packet carrying the attack command is sent to the Agent according to the fault injection parameters configured by the user,and the performance monitoring data of the local device regularly collected by Agent is received and processed.The example verification result shows that the platform can effectively extend the fault model library,realize automatic generation and injection monitoring of test data,and improve test sufficiency and test efficiency.
-
Computer Engineering. 2019, 45(6): 280-289,296. https://doi.org/10.19678/j.issn.1000-3428.0051781When using linear regression models to predict public building energy consumption data,there are uncertainties and precision deviations.Therefore,a Genetically Optimized Decision Tree(GODT) model is established.The Genetic Algorithm(GA) is used to optimize the subtree generation process of the Gradient Boosting Decision Tree (GBDT).The R-Square value predicted by the model is used as the evaluation criterion of the iteration to achieve the purpose of energy consumption prediction.Experimental results show that the prediction accuracy of this model is higher than that of the traditional regression prediction model.
-
Computer Engineering. 2019, 45(6): 290-296. https://doi.org/10.19678/j.issn.1000-3428.0050649To address the problem that the existing methods of total energy consumption prediction cannot accurately distinguish where the consumption of building energy is consumed and have the low prediction.To this end,according to the use of energy consumption,this paper divides the total energy consumption into four items and proposes a prediction model of itemized building energy consumption.Firstly,based on time sequence Auto-regression(AR) model,the lighting energy consumption of a building is predicted in short term.Secondly,a Deep Belief Network(DBN) model is constructed,which predicts air conditioning energy consumption,power energy consumption and special energy consumption of the building according to the lighting energy consumption prediction results,hourly average outdoor temperature,hourly average outdoor relative humidity,weather feature,holiday,hourly average wind speed,time.Experimental results show that,compared with the total energy consumption prediction models iPSO-BP and BP,the proposed model can predict the itemized energy consumption of a building more accurately and effectively.
-
Computer Engineering. 2019, 45(6): 297-302,309. https://doi.org/10.19678/j.issn.1000-3428.0050714According to the characteristics of the fall among elder,such as high incidence,great injury,and low rescue rate,combining Computer Radio Frequency Identification (CRFID) and pattern recognition technology,this paper designs an improved fall detection system.Firstly,the system collects the state signals by CRFID.Secondly,the state signals are decomposed by Empirical Mode Decomposition(EMD) to obtain the time-frequency features.Thirdly,Principal Component Analysis(PCA) is used to reduce the dimension of the features.Finally,the Random Forest(RF) is used to detect the falling condition.Experimental results show that the recall,precision,transferability and accuracy of the system are 97.75%,97.9%,98%,and 97.8%,respectively.The system can detect the fall behavior of the elderly accurately in real time.
-
Computer Engineering. 2019, 45(6): 303-309. https://doi.org/10.19678/j.issn.1000-3428.0051849Based on the aircraft arrival trajectory model and Required Time of Arrival(RTA) constrained model at the merge point,the multi-objective optimization model is established with the optimization goal of fuel consumption and the Global Warming Potential(GWP).The Artificial Bee Colony (ABC) algorithm is improved by introducing crossover operation and attenuation factor,and the intelligent solution of the model is realized.The A330 aircraft is taken as an example for calculation and analysis.The results show that the improved ABC algorithm can meet the needs of the arrival trajectory optimization under the constraint of RTA.The number of neighborhood search times,the weight of the optimized sub-objectives and the size of the RTA window all have an important effect on the optimization results.
-
Computer Engineering. 2019, 45(6): 310-314. https://doi.org/10.19678/j.issn.1000-3428.0050886To address the problems of low positioning accuracy,unstable positioning results and poor environmental adaptability of indoor fingerprinting localization algorithm based on static-weight,this paper proposes a variable-weight indoor fingerprinting localization algorithm based on Euclidean distance.The algorithm is divided into offline sampling phase and online localization phase.In the offline sampling phase,the algorithm performs Gaussian filter denoising on the Received Signal Strength Indication (RSSI) value to construct a fingerprint library.The weight of indexs,α and β,are introduced in the online localization phase,and the RSSI value and Euclidean distance are referenced as weight to figure out the nearest neighbor points and their weighted centroid.Experimental results show that compared with KNN algorithm and RW algorithm,the proposed algorithm has a higher positioning accuracy with the mean error of 0.965 m,and errors are less volatile.
-
Computer Engineering. 2019, 45(6): 315-320. https://doi.org/10.19678/j.issn.1000-3428.0050818There is a lot of fuzzy and non-monotonic knowledge in the semantic Web,which cannot be expressed by the current description logic.Aiming at the problem,this paper adds weak negative constructor and proposes a fuzzy and non-monotonic description logic f-SHOIQN based on the fuzzy description logic f-SHOIQ.The weak negative is used to mark fuzzy and non-monotonic atomic concepts,and further represent fuzzy and non-monotonic rules,which are then introduced into fuzzy description logic to represent fuzzy and non-monotonic knowledge.The knowledge base of f-SHOIQN is constructed,and the processing methods on fuzzy non-monotonic knowledge and fuzzy monotonic knowledge are given.In order to deal with the problem of rule competition while satisfying the rule inclusion and rule equivalence in the description logic,this paper proposes a priority decision algorithm about competition rules in f-SHOIQN.analyzes the properties of f-SHOIQN and gives relevant proofs.
Volume 50 No 3
Sponsored by：
East-China Institute of Computer Technology Shanghai Computer Society
Edited & Published by：
Editorial Board of Computer Engineering
Chief Editor：Jiang Bo
Executive Chief Editor:
Hu Bing
Tel：021-67092217
E-mail: ecice06@ecict.com.cn
CN: 31-1289/TP
ISSN: 1000-3428