Table of Content

10 January 2019, Volume 39 Issue 1

Previous Issue    Next Issue

2018 CCF Annual Conference on Distributed and Parallel Computing Systems (DPCS 2018)

Cloud resource scheduling method based on combinatorial double auction

MAO Yingchi, HAO Shuai, PING Ping, QI Rongzhi

2019, 39(1):  1-7.  DOI: 10.11772/j.issn.1001-9081.2018071614

Asbtract ( )   PDF (1103KB) ( )  

References | Related Articles | Metrics

Aiming at the resource scheduling problem across data centers, a Priority Combinatorial Double Auction (PCDA) resource scheduling scheme was proposed. Firstly, cloud resource auction was divided into three parts:cloud user agent bidding, cloud resource provider bid, auction agent organization auction. Secondly, on the basis of defining user priority and task urgency, the violation of Service Level Agreement (SLA) of each job during auction was estimated and the revenue of cloud provider was calculated. At the same time, a number of transactions were allowed in each round of bidders. Finally, reasonable allocation of cloud resource scheduling according to user level could be achieved. The simulation results show that the algorithm guarantees the success rate of auction. Compared with traditional auction, PCDA reduces energy consumption by 35.00% and the profit of auction cloud provider is about 38.84%.

Task assignment method based on cloud-fog cooperative model

LIU Pengfei, MAO Yingchi, WANG Longbao

2019, 39(1):  8-14.  DOI: 10.11772/j.issn.1001-9081.2018071642

Asbtract ( )   PDF (1133KB) ( )  

References | Related Articles | Metrics

To realize reasonable allocation and scheduling of mobile user task requests under cloud and fog collaboration, a task assignment algorithm based on cloud-fog collaboration model, named IGA (Improved Genetic Algorithm), was proposed. Firstly, individuals were coded in the way of mixed coding, and initial population was generated randomly. Secondly, the objective function was set as the cost of service providers. Then select, cross, and mutate were used to produce new qualified individuals. Finally, the request type in a chromosome was assigned to the corresponding resource node and iteration counter was updated until the iteration was completed. The simulation results show that compared with traditional cloud model, cloud-frog collaboration model reduces the time delay by nearly 30 seconds, reduces Service Level Objective (SLO) violation rate by nearly 10%, and reduces the cost of service providers.

Mobile crowdsensing task distribution mechanism based on compressed sensing

SONG Zihui, LI Zhuo, CHEN Xin

2019, 39(1):  15-21.  DOI: 10.11772/j.issn.1001-9081.2018071595

Asbtract ( )   PDF (1085KB) ( )  

References | Related Articles | Metrics

Since the cost of mobile crowdsensing in full coverage of area is excessively high, a Compressive Sensing-based mobile crowdsensing Task Distribution (CS-TD) mechanism was proposed. Firstly, an overall cost model of perceived task was proposed. In this model, the number of nodes participating in a perceived task, the number of nodes perceived and data uploaded were comprehensively considered. Then based on cost model, the daily movement trajectory of sensory node was analyzed, by combining with the compressed sensing data acquisition technology, a compressed sensing sampling method based on perceived node trajectory was proposed. Secondly, the optimal node set was selected by the Region Covers Least Nodes (RCLN) algorithm, the tasks were assigned to the nodes, and then the compressed sensing technology was used to recover node data. Finally, the trustworthiness of perceived node was evaluated in iteration of multiple perceived tasks to ensure the optimality of task plan. The CS-TD distribution model was tested several times. Compared with the existing CrowdTasker algorithm, the average cost of CS-TD algorithm is reduced by more than 30%. CS-TD model can effectively reduce consumption of sensing node and reduce overall perceived cost in full coverage sensing task.

Resource allocation optimization method for augment reality applications based on mobile edge computing

YU Yun, LIAN Xiaocan, ZHU Yuhang, TAN Guoping

2019, 39(1):  22-25.  DOI: 10.11772/j.issn.1001-9081.2018071615

Asbtract ( )   PDF (656KB) ( )  

References | Related Articles | Metrics

Considering the time delay and the energy consumption of terminal equipment caused by high-speed data transmission and calculation, a transmission scheme with equal power allocation in uplink was proposed. Firstly, based on collaborative properties of Augment Reality (AR) services, a system model for AR characteristics was established. Secondly, system frame structure was analyzed in detail, and the constraints to minimize total energy consumption of system were established. Finally, with the time delay and energy consumption constraints satisfied, a mathematical model of Mobile Edge Computing (MEC) resource optimization based on convex optimization was established to obtain an optimal communication and computing resource allocation scheme. Compared with user independent transmission scheme, the total energy consumption of the proposed scheme with a maximum time delay of 0.1 s and 0.15 s was both 14.6%. The simulation results show that under the same conditions, compared with the optimization scheme based on user independent transmission, the equal power MEC optimization scheme considering cooperative transmission between users can significantly reduce the total energy consumption of system.

ERC²: DTN Epidemic Routing method with Congestion Control strategy

TAN Jing, DONG Chengfeng, WANG Huiqiang, WANG Hezhe, FENG Guangsheng, LYU Hongwu, YUAN Quan, CHEN Shijun

2019, 39(1):  26-32.  DOI: 10.11772/j.issn.1001-9081.2018071752

Asbtract ( )   PDF (1110KB) ( )  

References | Related Articles | Metrics

Delay Tolerant Network (DTN) has characteristics of dynamic topology changes and limited node storage space. A DTN Epidemic Routing with Congestion Control strategy (ERC²) method was proposed. The method was based on a Dynamic Storage State Model (DSSM). According to sensing network conditions, the threshold of node's semi-congested state was dynamically adjusted to reduce the possibility of network congestion by nodes. The ACK index and message management queue were added to make node storage state change randomly with network load, dynamically update and actively delete redundant packages. Single or mixed mode was selected for message forwarding according to different congestion states combining with advantages of Epidemic and Prophet routing, so as to achieve the purpose of preventing, avoiding and canceling congestion, realizing adaptive buffer management of nodes and dynamically controlling congestion of network. Simulations were conducted on the ONE(Opportunistic Networking Environment) platform using Working Day Movement (WDM) model. In the simulation, ERC² was 66.18% higher than Prophet in message delivery rate. The average latency of ERC² was decreased by 48.36%, and the forwarding number was increased by 22.83%. The simulation results show that ERC² has better network performance than Epidemic and Prophet routing algorithms in scenarios with different levels of congestion.

Multi-cell uplink joint power control algorithm for LTE system

ZHANG Roujia, ZHAN Qingxiang, ZHU Yuhang, TAN Guoping

2019, 39(1):  33-38.  DOI: 10.11772/j.issn.1001-9081.2018071624

Asbtract ( )   PDF (866KB) ( )  

References | Related Articles | Metrics

Focusing on the issue that traditional open-loop power control algorithm normally aims to increase the throughput and ignores the interference to other cells, to achieve a tradeoff between edge users and whole system performance, an Uplink Joint Power Control algorithm of LTE system (UJPC), was proposed. In the algorithm, single base station and three sectors were adopted as system model, which aimed to maximize proportional fair index of system throughput. Firstly, the corresponding mathematical optimization model was obtained according to two constraints of the minimum Signal-to-Interference plus Noise Ratio (SINR) and the maximum transmit power of users. Then continuous convex approximation method was used to solve optimization problem to get optimal transmission power of all users in each cell. The simulation results show that, compared with open-loop scheme, UJPC can greatly improve spectrum utilization of cell edge while ensuring average spectrum utilization of system and its best performance gain can reach 50%.

Research progress of index-based subgraph query technology

SHI Weijie, DONG Yihong, WANG Xiong, PAN Jianfei

2019, 39(1):  39-45.  DOI: 10.11772/j.issn.1001-9081.2018071593

Asbtract ( )   PDF (1121KB) ( )  

References | Related Articles | Metrics

As a type of data structure representing entities, graphs are widely used in fields that have high requirements on data relevance, such as community data discovery, biochemical analysis and social security analysis. Focusing on the issue of real-time graph query operation under large-scale data, building a suitable index can effectively reduce query response time and improve query accuracy. The basic structure of index-based subgraph query algorithm was firstly introduced and then state-of-the-art algorithms were divided into two categories by construction method of index:enumeration construction and frequent pattern mining construction. Then these algorithms were introduced and analyzed from three aspects:index features, index structures and application datasets. Finally, main problems toward index-based subgraph query algorithm were summarized and analyzed, the latest query technology based on the distributed system was briefly described, and the future trend was forecasted.

SQM: subgraph matching algorithm for single large-scale graphs under Spark

LI Longyang, DONG Yihong, SHI Weijie, PAN Jianfei

2019, 39(1):  46-50.  DOI: 10.11772/j.issn.1001-9081.2018071594

Asbtract ( )   PDF (859KB) ( )  

References | Related Articles | Metrics

Focusing on low accuracy and high costs of backtracking-based subgraph query algorithm applied to large-scale graphs, a Spark-based Subgraph Query Matching (SQM) algorithm was proposed to improve query accuracy and reduce query overhead for large graphs. The data graph was firstly filtered according to structure information, and the query graph was divided into basic query units. Then each basic query unit was matched and joined together. Finally, the algorithm's efficiency was improved and search space was reduced by parallelization. The experimental results show that compared with Stwig (Sub twig) algorithm and TurboISO algorithm, SQM algorithm can increase the speed by 50% while ensuring the same query results.

New NVM storage system supporting high concurrent access

CAI Tao, CHEN Zhipeng, NIU Dejiao, WANG Jie, ZHAN Bisheng

2019, 39(1):  51-56.  DOI: 10.11772/j.issn.1001-9081.2018071644

Asbtract ( )   PDF (1057KB) ( )  

References | Related Articles | Metrics

I/O system software stack is an important factor that affects the efficiency of NVM (Non-Volatile Memory) storage system. For NVM storage systems with unbalanced read/write speeds and limited writing lifetimes, new synchronous and asynchronous converged access management strategy was designed. While an asynchronous write cache was implemented by DRAM for the write access to large data, synchronous management strategy was still used for the read access and the write access to small data. Addressing large time overhead of address translation for NVM storage systems by conflict among cores in a computer with multi-core processor, a new address translation cache was designed for multi-core processor to reduce time overhead of address translation. Finally, a prototype of Concurrent NVM Storage system (CNVMS) was implemented, and the universal testing tools were used to test performance of random reads writes, sequential reads writes, mixed reads/writes and with actual application workload. The experimental results show that the proposed strategy increases read and write speed by 1%-22% and IOPS (Input/Output operations Per Second) by 9%-15% compared with PMBD (Persistent Memory Block Driver), which verifies that CNVMS strategy can provide higher I/O performance and better access request processing speed.

Multi-source data parallel preprocessing method based on similar connection

GUO Fangfang, CHAO Luomeng, ZHU Jianwen

2019, 39(1):  57-60.  DOI: 10.11772/j.issn.1001-9081.2018071869

Asbtract ( )   PDF (587KB) ( )  

References | Related Articles | Metrics

With the development of large-scale network environments and big data-related technologies, traditional data fusion analysis technology faces new challenges. Focusing on poor flexibility and low processing efficiency in current multi-source data fusion analysis process, a multi-source data parallel preprocessing method based on similar connection was proposed, in which the idea of dividing and conquering and paralleling was adopted. Firstly, the preprocessing method was improved to increase the flexibility by unifying similar semantics in multi-source data and retaining personality semantics. Secondly, an improved parallel MapReduce framework was proposed to improve the efficiency of similar connections. The experimental results show that the proposed method reduces total data volume by 32% while ensuring data integrity. Compared with traditional MapReduce framework, the improved framework decreases 43.91% of time consumed; therefore, the proposed method can effectively improve the efficiency of multi-source data fusion analysis.

Data race detection approach in concurrent programs

ZHANG Yang, LIANG Yanan, ZHANG Dongwen, SUN Shixin

2019, 39(1):  61-65.  DOI: 10.11772/j.issn.1001-9081.2018071605

Asbtract ( )   PDF (857KB) ( )  

References | Related Articles | Metrics

Aiming at the problems of false positive and false negatives in data race detection, a novel static data race detection approach was proposed. Firstly, intra-thread and inter-thread function call graphs were automatically constructed via control flow analysis. Secondly, the information of variable-access events within thread were collected, and possible races were detected based on the defined data race conditions. Then, in order to improve the detection accuracy, alias variables and alias locks were analyzed to reduce false negatives and false positives, respectively. Finally, the sequential relationship between access events was abstracted through control flow analysis, and program slicing was used to determine the happens-before relationship of access events, thereby reducing false positives caused by ignoring thread interactions. A data race detection tool was implemented by Java and Soot framework based on this approach. In the experimentation, several benchmarks from JGF and IBM Contest benchmark suites, such as raytracer and airline, were selected for evaluation, and the results were compared with existing data race detection algorithm and tool (HB (Happens-Before) and RVPredict). The experimental results show that, compared with algorithm HB and tool RVPredict, total number of data races detected by the proposed approach are increased by 81% and 16% respectively, the accuracy of this approach for data race detection are respectively increased by 14% and 19%, which effectively avoids false negatives and false positives.

Parallel algorithm of Markov clustering for large-scale biological networks

SUN Jiamin, ZHU Jiafu, YANG Fuzhang, XIE Jiang

2019, 39(1):  66-71.  DOI: 10.11772/j.issn.1001-9081.2018071660

Asbtract ( )   PDF (936KB) ( )  

References | Related Articles | Metrics

Markov Clustering Algorithm (MCL) is an effective method to find modules in large-scale biological networks. It can mine modules that have significant influence on network structure and function. The algorithm involves large-scale matrix calculations, so its complexity can reach cubic orders. For the problem of high complexity, a parallel algorithm of Markov clustering based on Message Passing Interface (MPI) was proposed to improve computational performance of algorithm. Firstly, a biological network was transformed into an adjacency matrix. Secondly, according to the characteristics of the algorithm, the matrix size was judged and a new matrix was regenerated to handle the calculation of non-square multiple matrix. Thirdly, the algorithm was calculated in parallel by means of block allocation, which could effectively implement the operation of matrix of any size. Finally, the loop was parallelized until the matrix was converged to obtain network clustering results. The experimental results on simulated network and real biological network datasets show that compared with Full-block Collective Communication (FCC) parallel method, the average parallel efficiency is improved by more than 10 percentage points, so the optimization algorithm can be applied in different types of large-scale biological networks.

Parallel algorithm of biological complex network motifs discovery

YANG Fuzhang, ZHU Jiafu, SUN Jiamin, XIE Jiang

2019, 39(1):  72-77.  DOI: 10.11772/j.issn.1001-9081.2018071655

Asbtract ( )   PDF (889KB) ( )  

References | Related Articles | Metrics

Biological complex network motifs discovery, based on theoretical research of complex networks, is an important method for studying biological networks, which provides a new perspective on life phenomena and life mechanisms. However, it computes inefficiently when dealing with large networks or mining big motifs. On the basis of existing serial ESU (Enumerate SUbgraph) algorithm of network motifs discovery, a parallelized ESU algorithm based on Message Passing Interface (MPI) was proposed. The node values in ESU algorithm were optimized to solve the problem of node value dependency, the number of subgraphs was counted by using subgraph discovery strategy of ESU algorithm, and a dynamic programming method was used to determine optimal node allocation strategy to satisfy load balancing. The experiments on simulated and biological networks show that the parallelized ESU algorithm addresses node value dependency and realizes a load balancing strategy, which saves more than 90% running time compared to serial algorithm. Furthermore, the parallel algorithm is suitable for different types and different scales of networks, and effectively improves computation efficiency of network motifs discovery.

Classification method and updating mechanism of hierarchical 3D indoor map

FENG Guangsheng, ZHANG Xiaoxue, WANG Huiqiang, LI Bingyang, YUAN Quan, CHEN Shijun, CHEN Dawei

2019, 39(1):  78-81.  DOI: 10.11772/j.issn.1001-9081.2018071657

Asbtract ( )   PDF (713KB) ( )  

References | Related Articles | Metrics

For the fact that existing map updating methods are not good at map updating in indoor map environments, a hierarchical indoor map updating method was proposed. Firstly, the activity of indoor objects was taken as a parameter. Then, the division of hierarchy was performed to reduce the amount of updated data. Finally, a Convolutional Neural Network (CNN) was used to determine the attribution level of indoor data in network. The experimental results show that compared with the version update method, the update time of the proposed method is reduced by 27 percentage points, and the update time is gradually reduced compared with the incremental update method after the update item number is greater than 100. Compared with the incremental update method, the update package size of the proposed method is reduced by 6.2 percentage points, and its update package is always smaller than that of the version update method before the data item number is less than 200. Therefore, the proposed method can significantly improve the updating efficiency of indoor maps.

Fast retrieval method of three-dimensional indoor map data based on octree

LYU Hongwu, FU Junqiang, WANG Huiqiang, LI Bingyang, YUAN Quan, CHEN Shijun, CHEN Dawei

2019, 39(1):  82-86.  DOI: 10.11772/j.issn.1001-9081.2018071646

Asbtract ( )   PDF (741KB) ( )  

References | Related Articles | Metrics

To solve the low efficiency problem of data retrieval in indoor three-dimensional (3D) maps, an indoor 3D map data retrieval method based on octree was proposed. Firstly, the data was stored according to the octree segmentation method. Secondly, the data was encoded to facilitate addressing. Thirdly, the search data was filtered by adding a room interval constraint to the data. Finally, the indoor map data was retrieved. Compared with the search method without constraints, the search cost of the proposed method was reduced by 25 percentage points on average, and the search time was more stable. Therefore, the proposed method can significantly improve the application efficiency of indoor 3D map data.

Short-term traffic prediction method on big data in highway domain

WANG Xuefei, DING Weilong

2019, 39(1):  87-92.  DOI: 10.11772/j.issn.1001-9081.2018071665

Asbtract ( )   PDF (1092KB) ( )  

References | Related Articles | Metrics

Aiming at the problems that traditional short-time traffic flow prediction method in highway domain is suitable for small scale data, which limits the efficiency on massive data, and the spatio-temporal relationship of data is neglected, a short-term traffic flow prediction method for big data with combining K-Nearest Neighbors (KNN) in highway domain was proposed. Firstly, the K value and distance metric of model were tuned, and the model parameters were compared by using cross validation. Secondly, considering inherent spatio-temporal association of data, feature vectors based on spatio-temporal characteristics were modeled. Finally, a regression prediction model was established under big data environment, and the prediction was realized with the model of optimal parameters. The experimental results show that compared with traditional time series model, the proposed model works on all toll stations at one time, has high speed of single running and improves the efficiency by 77%. The method significantly reduces Mean Absolute Percentage Error (MAPE) and Median Absolute Percentage Error (MDAPE) and it also has good horizontal expansibility.

Road vehicle congestion analysis model based on YOLO

ZHANG Jiachen, CHEN Qingkui

2019, 39(1):  93-97.  DOI: 10.11772/j.issn.1001-9081.2018071656

Asbtract ( )   PDF (775KB) ( )  

References | Related Articles | Metrics

To solve traffic congestion problems, a new road condition judgment model was proposed. Firstly, the model was based on YOLOv3 target detection algorithm. Then, according to the eigenvalue matrix corresponding to the picture, the difference between adjacent frames was made by the eigenvalue matrix, and the difference value was compared with preset value to determine whether the current road was in a congested state or a normal traffic state. Secondly, the current calculated road state was compared with previous two calculated road states. Finally, the state statistics method in the model was used to calculate the duration of a state (congestion or patency) of road. The proposed model could analyze the states of three lanes of a road at the same time. Through experiments, the average accuracy of model to judge the state of single lane could reach 80% or more, and it was applicable to both day and night roads.

Forecasting model of pollen concentration based on particle swarm optimization and support vector machine

ZHAO Wenfang, WANG Jingli, SHANG Min, LIU Yanan

2019, 39(1):  98-104.  DOI: 10.11772/j.issn.1001-9081.2018071626

Asbtract ( )   PDF (1158KB) ( )  

References | Related Articles | Metrics

To improve the accuracy of pollen concentration forecast and resolve low accuracy of current pollen concentration forecast model, a model for daily pollen concentration forecasting based on Particle Swarm Optimization (PSO) algorithm and Support Vector Machine (SVM) was proposed. Firstly, the feature vector extraction was carried out by using correlation analysis technique to select meteorological data with strong correlation with pollen concentration, such as temperature, daily temperature difference, relative humidity, precipitation, wind, sunshine hours. Secondly, an SVM prediction model based on this vector and pollen concentration observation data was established. The PSO algorithm was designed to optimize the parameters in SVM algorithm, and then the optimal parameters were used to construct daily pollen concentration prediction model. Finally, the forecast of pollen concentration in 24 hours in advance was made by using the optimized SVM model. The comparison among the accuracy of the optimized SVM model, Multiple Linear Regression (MLR) model and Back Propagation Neural Network (BPNN) model was performed to evaluate their performances. In addition, the optimized model was also applied for the forecast of pollen concentration in 24 hours in advance at Nanjiao and Miyun meteorological observation stations. The experimental results show that the proposed method performs better than MLR and BPNN methods. Meanwhile, it also provides promising results for forecast of pollen concentration in 24 hours in advance and also has good generalization ability.

Extraction method of marine lane boundary from exploiting trajectory big data

XU Yao, LI Zhuoran, MENG Jinlong, ZHAO Lipo, WEN Jianxin, WANG Guiling

2019, 39(1):  105-112.  DOI: 10.11772/j.issn.1001-9081.2018071739

Asbtract ( )   PDF (1324KB) ( )  

References | Related Articles | Metrics

The traditional road information extraction method is high-cost and slow-update. Compared with it, road or marine lane information extraction from crowdsourcing trajectory data is low-cost and easier to update. However, it is difficult to extract lane boundary due to vessel trajectory data with high noise, large data volume and uneven distribution across different regions. To solve this problem, an extraction method of marine lane boundary from exploiting trajectory big data was proposed. Firstly, the parallelized denoising, interpolation and trajectory segmentation for trajectory big data was conducted. Then, based on parallelization and Geohash-encoded spatial clustering, trajectory data was simplified into multiple square regions. The regions were divided and the NiBlack method was extended as SpatialNiBlack algorithm to recognize regions on lane. Finally, based on the filtering results, del-alpha-shape algorithm was proposed to construct a Delaunay triangulation network and obtain marine lane boundary. The theoretical analysis and experimental results show that the proposed method can achieve an accuracy of 86.7% and a recall rate of 79.4% when the maximum density value is 200, minimum density value is 10, length and width of window are 5 and 5 respectively. The experimental results show that the proposed method is effective to extract valuable marine lane boundaries from large-scale trajectory data.

Ship trajectory extraction method for port parking area identification

ZHENG Zhentao, ZHAO Zhuofeng, WANG Guiling, XU Yao

2019, 39(1):  113-117.  DOI: 10.11772/j.issn.1001-9081.2018071625

Asbtract ( )   PDF (942KB) ( )  

References | Related Articles | Metrics

Ship trajectory data shows the characteristics of low precision, sparseness and trajectory drift for the port parking area recognition. To improve the accuracy of port parking area recognition based on ship trajectory big data, a Multi-constrained and Parallel Track Stay Segment Extraction (MPTSSE) method was proposed. Firstly, the definition of stay segment based on ship trajectory data was given as a basic concept for parking area identification. Secondly, a stay segment extraction model based on multiple constraints, such as speed, time difference, dwell time and distance, was introduced. Furthermore, a parallel trajectory stay segment extraction algorithm was proposed. Finally, Hadoop framework was adopted to implement the proposed algorithm. In comparison experiments with the trajectory stay segment extraction method based on Stop/Move model based on real ship trajectory big dataset, the accuracy of MPTSSE is increased by 22% in berth recognition of three ports. The MPTSSE method can effectively avoid misdivision of track stay segment and has better execution efficiency under large-scale ship trajectory dataset.

Ultra-lightweight RFID mutual authentication protocol based on regeneration transformation

HUANG Keke, LIU Yali, YIN Xinchun

2019, 39(1):  118-125.  DOI: 10.11772/j.issn.1001-9081.2018071738

Asbtract ( )   PDF (1360KB) ( )  

References | Related Articles | Metrics

Focusing on the problem that open and insecure wireless channel between reader and tag in Radio Frequency IDentification (RFID) system is vulnerable to multiple malicious attacks, a new ultra-lightweight RFID Mutual Authentication Protocol based on Regeneration (RRMAP) was proposed. Firstly, the regeneration transformation of the first-stage reverse sequence self-combination transformation on two binary arrays was performed to achieve its own bit confusion effect. Secondly, the result of first-stage was used for the second-stage parity adjacent crossover-XOR operation, thus whole regeneration transformation was completed. Finally, through new definition of regeneration transformation, the left circular shift operation and modular 2^m addition operation were combined to construct secret communication messages during authentication process, which could effectively solve security problems existing in RFID system currently. The BAN (Burrows-Abadi-Needham) logic formal proof was given to show the availability of protocol. The security analysis and performance comparison show that RRMAP has strong security and privacy protection attributes which can resist some common malicious attacks.

Forensics algorithm of various operations for digital speech

XIANG Li, YAN Diqun, WANG Rangding, LI Xiaowen

2019, 39(1):  126-130.  DOI: 10.11772/j.issn.1001-9081.2018071596

Asbtract ( )   PDF (728KB) ( )  

References | Related Articles | Metrics

Most existing forensic methods for digital speech aim at detecting a specific operation, which means that these methods can not identify various operations at a time. To solve the problem, a universal forensic algorithm for simultaneously detecting various operations, such as pitch modification, low-pass filtering, high-pass filtering, and noise adding was proposed. Firstly, the statistical moments of Mel-Frequency Cepstral Coefficients (MFCC) were calculated, and cepstrum mean and variance normalization were applied to the moments. Then, a multi-class classifier based on multiple two-class classifiers was constructed. Finally, the classifier was used to identify various types of speech operations. The experimental results on TIMIT and UME speech datasets show that the proposed universal features achieve detection accuracy over 97% for various speech operations. And the detection accuracy in the test of MP3 compression robustness is still above 96%.

Risk assessment method of Android application based on permission

BU Tongtong, CAO Tianjie

2019, 39(1):  131-135.  DOI: 10.11772/j.issn.1001-9081.2018071643

Asbtract ( )   PDF (874KB) ( )  

References | Related Articles | Metrics

Focusing on the problems existing in Android permission mechanism and poor capability of traditional measurement methods of Android software security, a risk assessment method of Android APP based on permission was proposed. Firstly, the system permissions declared by application, the permissions obtained through static analysis and custom permissions were extracted by reverse-engineering analysis of application. At the same time, the permissions used by executing application were extracted through dynamic detection. Secondly, quantitative risk assessment of applications was performed from three aspects:permission combination of hiding malicious intent, "over-privilege" problem and custom permission vulnerability. Finally, the Analytic Hierarchy Process (AHP) evaluation model was adopted to calculate the weights of three aspects above for estimating risk value of application. In addition, custom permission data set and permissions combination dataset with hiding malicious intent were built by training 6245 software samples collected from application store and VirusShare. The experimental results show that the proposed method can assess risk value of application software more accurately compared with Androguard.

Image retrieval algorithm based on saliency semantic region weighting

CHEN Hongyu, DENG Dexiang, YAN Jia, FAN Ci'en

2019, 39(1):  136-142.  DOI: 10.11772/j.issn.1001-9081.2018051150

Asbtract ( )   PDF (1175KB) ( )  

References | Related Articles | Metrics

For image instance retrieval in the field of computational vision, a semantic region weighted aggregation method based on significance guidance of deep convolution features was proposed. Firstly, a tensor after full convolutional layer of deep convolutional network was extracted as deep feature. A feature saliency map was obtained by using Inverse Document Frequency (IDF) method to weight deep feature, and then it was used as a constraint to guide deep feature channel importance ordering to extract different special semantic region deep feature, which excluded interference from background and noise information. Finally, global average pooling was used to perform feature aggregation, and global feature representation of image was obtained by using Principal Component Analysis (PCA) to reduce the dimension and whitening for distance metric retrieval. The experimental results show that the proposed image retrieval algorithm based on significant semantic region weighting is more accurate and robust than the current mainstream algorithms on four standard databases, because the image feature vector extracted by the proposed algorithm is richer and more discerning.

Saliency detection algorithm of deep guidance

ZHAO Heng, AN Weisheng, FU Weigang

2019, 39(1):  143-147.  DOI: 10.11772/j.issn.1001-9081.2018061194

Asbtract ( )   PDF (869KB) ( )  

References | Related Articles | Metrics

As current saliency detection algorithms based on deep convolutional network have problems of incomplete target and noisy background detected from complex scene images, a new algorithm of deep feature-oriented saliency detection composed with basic feature extraction and high-level feature which guided cross-level aggregating delivery was proposed. It was based on the improvement of an extant Encoded Low level distance map with Deep features (ELD) model. Firstly, according to the characteristics of convolutional features at different levels, a cross-level feature fusion network model of high-level feature guidance was established. Then, saliency clustering propagation by using high-level feature guidance on initial saliency map that generated by improved neural network was implemented. Finally, final saliency map with more details and less noise was generated by using fully-connected conditional random field after saliency propagation. The experimental results on ECSSD and DUT-ORMON data sets show that, the Precision-Recall (PR) performance of the proposed algorithm is better than ELD algorithms, and F-measure(F) is increased by 7.5% and 11%, respectively, while its Mean Average Errors (MAE) are decreased by 16% and 15%, respectively,which also can obtain more robust results in complex image scene fields of target recognition, pattern recognition, image indexing, and so on.

Improved particle swarm optimization algorithm based on hierarchical autonomous learning

YUAN Xiaoping, JIANG Shuo

2019, 39(1):  148-153.  DOI: 10.11772/j.issn.1001-9081.2018061342

Asbtract ( )   PDF (853KB) ( )  

References | Related Articles | Metrics

Focusing on the shortages of easily falling into local optimal, low convergence accuracy and slow convergence speed in Particle Swarm Optimization (PSO) algorithm, an improved Particle Swarm Optimization based on HierarChical autonomous learning (HCPSO) algorithm was proposed. Firstly, according to the particle fitness value and the number of iterations, the population was dynamically divided into three different classes. Then, according to characteristics of different classes of particles, local learning model, standard learning model and global learning model were respectively adopted to increase particle diversity and reflect the effect of individual difference cognition on performance of algorithm and improve the convergence speed and convergence precision of algorithm. Finally, HCPSO algorithm was compared with PSO algorithm, Self-adaptive Multi-Swarm PSO algorithm (PSO-SMS) and Dynamic Multi-Swarm PSO (DMS-PSO) algorithm on 6 typical test functions respectively. The simulation results show that the convergence speed and convergence accuracy of HCPSO algorithm are obviously higher than these of the given algorithms, and the execution time difference of the proposed algorithm and basic PSO algorithm is within 0.001 orders of magnitude. The performance of the proposed algorithm is improved without increasing complexity.

Base station traffic prediction model based on spatial collaboration

PENG Duo, ZHOU Jianguo, YI Shuwen, JIANG Hao

2019, 39(1):  154-159.  DOI: 10.11772/j.issn.1001-9081.2018061330

Asbtract ( )   PDF (962KB) ( )  

References | Related Articles | Metrics

Concerning the problem that AutoRegressive Integrated Moving Average (ARIMA) model and Long Short-Term Memory (LSTM) unit do not utilize the collaboration between Base Stations (BSs) in traffic prediction, a new method called Traffic Prediction based on Space Collaboration (TPBC) which uses the collaboration between BSs produced by users was proposed. Firstly, a BS cooperative network was constructed based on the collaboration between BSs and then divided into multiple communities. Next, the cooperative BSs, which have the closest relationships with the target BS in the same community, were found via Granger causality test. Finally, a hybrid neural network was constructed by LSTM and Embedding layer, and the historial traffic of target BS and each cooperative BS was utilized for traffic prediction of target BS. The experimental results show that the Root Mean Square Error (RMSE) of TPBC is reduced by 29.19% and 27.47% compared with ARIMA and LSTM respectively. It shows that TPBC has the capability of improving the accuracy of BS traffic prediction effectively, which benefits traffic offloading and energy saving.

Sentiment analysis of entity aspects based on multi-attention long short-term memory

ZHI Shuting, LI Xiaoge, WANG Jingbo, WANG Penghua

2019, 39(1):  160-167.  DOI: 10.11772/j.issn.1001-9081.2018061232

Asbtract ( )   PDF (1273KB) ( )  

References | Related Articles | Metrics

Aspect sentiment analysis is a fine-grained task in sentiment classification. Concerning the problem that traditional neural network model can not accurately construct sentiment features of aspects, a Long Short-Term Memory with Multi-ATTention and Aspect Context (LSTM-MATT-AC) neural network model was proposed. Different types of attention mechanisms were added in different positions of bidirectional Long Short-Term Memory (LSTM), and the advantage of multi-attention mechanism was fully utilized to allow the model to focus on sentiment information of specific aspects in sentence from different perspectives, which could compensate the deficiency of single attention mechanism. At the same time, combining aspect context information of bidirectional LSTM independent coding, the model could capture deeper level sentiment information and effectively distinguish sentiment polarity of different aspects. Experiments on SemEval2014 Task4 and Twitter datasets were carried out to verify the effectiveness of different attention mechanisms and independent context processing on aspect sentiment analysis. The experimental results show that the accuracy of the proposed model reaches 80.6%, 75.1% and 71.1% respectively for datasets in domain Restaurant, Laptop and Twitter. Compared with previous neural network-based sentiment analysis models, the accuracy has been further improved.

Identification method of depressive tendency with multiple feature fusion

ZHOU Ying, WANG Hong, REN Yanju, HU Xiaohong

2019, 39(1):  168-175.  DOI: 10.11772/j.issn.1001-9081.2018051180

Asbtract ( )   PDF (1395KB) ( )  

References | Related Articles | Metrics

In recent years, the tendency of depression tends to occur at a younger age and affects more people. Although research on the topic has achieved some results, it still lacks a more objective and accurate method for identifying depressive tendencies, and research on depressive tendencies from multiple perspectives is lacking. Therefore, the combination of mental health self-check table and eye-tracking was proposed as a method for identifying depressive tendencies and was studied from multiple perspectives. The innovative features of eye movement, memory, cognitive style, and network behaviors were incorporated. In order to address complex feature relationship and extract more useful information, a scanning process with combining a stacking method was proposed to form a proposed recognition model for depressive tendencies called scanning stacking model. To comprehensively and objectively evaluate the performance of scanning and stacking model, the independent contributions of both scanning process and stacking method were evaluated in the experiment. The experimental results show that the independent contribution of scanning process is 0.03, and the independent contribution of stacking method is 0.02. In addition, the scanning stacking model was compared with several models from parameter R-squared, Mean Square Error (MSE) and average absolute error, and the results show that the scanning stacking model has better prediction effect.

Personalized recommendation algorithm based on graph entropy in trust social network

CAI Yongjia, LI Guanyu, GUAN Haoyuan

2019, 39(1):  176-180.  DOI: 10.11772/j.issn.1001-9081.2018061202

Asbtract ( )   PDF (861KB) ( )  

References | Related Articles | Metrics

Widespread attentions have been drawn to Recommendation Systems (RS) as rapid development of social networks. To solve the cold-start problem and neglect to user's social network information in current recommendation algorithms, a novel Personalized Recommend Algorithm based on Graph Entropy (PRAGE) in trust social network was proposed. Firstly, a weighted User-Item Graph (UIG) was built based on feedback information, and a trust mechanism was introduced to establish a User Trust Graph (UTG). Secondly, by using random walk algorithm on two graphs, the initial similarity of user and item and new user-item similarity based on trust mechanism were obtained; the above algorithm process was repeated until the similarity value reaches convergence value. Then, a method to weight two sets of similarity values with graph entropies of both UIG and UTG was proposed and final recommendation list was accordingly created. The experimental results on two real-world datasets named as Epinions and FilmTrust reveal that, compared with classical Random Walk algorithm, the accuracy of PRAGE is increased by about 34.7%and 19.4% respectively, and its recall is increased by 28.9% and 21.1% respectively, which can alleviate cold start problem effectively and has better performance in accuracy and coverage.

Assessment method of credibility on online product reviews

LI Chao, XIANG Jing, XIANG Jun

2019, 39(1):  181-185.  DOI: 10.11772/j.issn.1001-9081.2018051154

Asbtract ( )   PDF (760KB) ( )  

References | Related Articles | Metrics

Since there are many troubles such as large quantity, uneven quality and poor credibility in getting helpful information and making effective decision for stakeholders, and the existing research work on credibility assessment mainly considers the sources of reviews and the support of reviews in form of votes, an assessment method on review credibility from perspective of intrinsic quality was proposed. That is, the credibility assessment of reviews was realized by integrating the ratings of reviewers, the support degree of reviews and the consistency in reviews, etc. Firstly, the pre-processing of review data was completed based on rule and method libraries. Then, the feature recognition and the feature value extraction and standardization were completed based on product feature library, generic dictionary, sentiment dictionary and method library. Finally, the credibility assessment of reviews was completed based on the established models. The experimental results verify the feasibility of this method, and it can be applied to assess the credibility of product reviews automatically on other e-commerce platforms.

Pedestrian detection method based on cascade networks

CHEN Guangxi, WANG Jiaxin, HUANG Yong, ZHAN Yijun, ZHAN Baoying

2019, 39(1):  186-191.  DOI: 10.11772/j.issn.1001-9081.2018061351

Asbtract ( )   PDF (967KB) ( )  

References | Related Articles | Metrics

In complex environment, existing pedestrian detection methods can not be very good to achieve high recall rate and efficient detection. To solve this problem, a pedestrian detection method based on Convolutional Neural Network (CNN) was proposed. Firstly, pedestrian locations in input images were initially detected with single step detection upgrade network (YOLOv2) derived from CNN. Secondly, a network with target classification and bounding box regression was designed to cascade with YOLOv2 network, which made reclassification and regression of pedestrian location initially detected by YOLOv2, to reduce error detections and increase recall rate. Finally, a Non-Maximum Suppression (NMS) method was used to remove redundant bounding boxes. The experimental results show that, in INRIA and Caltech dataset, the proposed method increases recall rate by 3.3 percentage points, and the accuracy is increased by 5.1 percentage points compared with original YOLOv2. It also reached a speed of 11.6FPS (Frames Per Second) to realize real-time detection. Compared with the existing six popular pedestrian detection methods, the proposed method has better overall performance.

Real-time implementation of improved TINY YOLO vehicle detection algorithm based on Zynq SoC hardware acceleration

ZHANG Yunke, LIU Dan

2019, 39(1):  192-198.  DOI: 10.11772/j.issn.1001-9081.2018051134

Asbtract ( )   PDF (1135KB) ( )  

References | Related Articles | Metrics

TINY YOLO (TINY You Only Look Once) vehicle detection algorithm requires much amount of calculation which makes it difficult to achieve real-time detection in small embedded systems. Because plenty of zero values exist in a network weight matrix which makes the network a sparse structure, an improved version of TINY YOLO vehicle detection algorithm, called Xerantic-TINY YOLO (X-TINY YOLO), was proposed and accelerated in parallel way using architectural advantages of small Zynq SoC system. Original network structure of TINY YOLO was compressed and the operations of convolution steps were accelerated in parallel by using high efficient multistage pipeline. All multiply-add operations were concurrently executed within each stage of pipeline. By matching network structure, a method of data segmentation and transfer was also proposed. The experimental results show that, X-TINY YOLO only consumes 50% hardware resources on chip, and it can be implemented on small Zynq SoC systems which have higher performance-price ratio than GPU and CPU and is suitable for embedded implementation scenes. Its detection speed reaches 24 frames per second, which meets the requirement of real-time vehicle detection.

Crowd counting using multi-scale multi-task convolutional neural network

CAO Jinmeng, NI Rongrong, YANG Biao

2019, 39(1):  199-204.  DOI: 10.11772/j.issn.1001-9081.2018051132

Asbtract ( )   PDF (1063KB) ( )  

References | Related Articles | Metrics

Crowd counting has played a significant role in the field of intelligent surveillance. Concerning the problem of scale variation, non-uniform density distribution and partial occlusion of crowds, a method of crowd counting using Multi-scale Multi-task Convolutional Neural Network (MMCNN) was proposed to solve existing challenges in crowd counting. Initially, a novel adaptive human-shaped kernel was used to generate a density map which described the population information, and the partial occlusion was eliminated. Then, scale variation was handled through constructing a multi-scale convolutional neural network and non-uniform density distribution was resolved by the multi-task learning mechanism, which simultaneously estimate the density map and density level of crowds. Further, a weighted loss function was proposed to improve the accuracy of crowd counting. Evaluations in UCF_CC_50 and World Expo'10 datasets revealed the effectiveness of the proposed adaptive human-shaped kernel. The experimental results show that, compared with the method proposed by Sindagi et al. (SINDAGI V A, PATEL V M. CNN-based cascaded multi-task learning of high-level prior and density estimation for crowd counting. Proceedings of the 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance. Piscataway, NJ:IEEE, 2017:1-6), the Mean Absolute Error (MAE) and Mean Squared Error (MSE) of the proposed method in UCF_CC_50 dataset is decreased by 1.7 and 45 respectively. Compared with the method proposed by Zhang et al. (ZHANG Y, ZHOU D, CHEN S, et al. Single-image crowd counting via multi-column convolutional neural network. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:589-597), the MAE of the proposed method in World Expo'10 dataset is decreased by 1.5. Simultaneously, evaluations in practical bus videos with an error of approximately 0-3, which verifies the practicability of the proposed counting approach.

SQL energy consumption perception model for database load based on SSD

LI Shu, YU Jiong, GUO Binglei, PU Yonglin, YANG Dexian, LIU Su

2019, 39(1):  205-212.  DOI: 10.11772/j.issn.1001-9081.2018051055

Asbtract ( )   PDF (1350KB) ( )  

References | Related Articles | Metrics

For energy consumption and severe environmental problems brought by big data, building an energy-efficient green database system has become a key requirement and an important challenge. To solve the problem that traditional database systems mainly focus on performance, and are lack of energy consumption perception and optimization, an energy consumption perception model based on database workload was proposed and applied to the database system based on Solid-State Drive (SSD). Firstly, the consumption of major system resources (CPU, SSD) during database workload execution was quantified as time overhead and power consumption overhead. Based on basic I/O type of SSD database workload, a time cost model and a power consumption overhead model were built, and an energy consumption perception model with uniform resource unit was implemented. Then, multi-variable linear regression mathematical tools were used to solve the model, and in the exclusive environment and competitive environment, the energy estimation accuracy of the model for different I/O types of database workload was verified. Finally, the experimental results were analyzed and the factors that affect the model accuracy were discussed. The experimental results show that the model accuracy is relatively high. Under ideal conditions that DBMS monopolized system resources, the average error is 5.15% and the absolute error is no more than 9.8%. Although the accuracy in competitive environment is reduced, the average error is less than 12.21%.The model can effectively build an energy-aware green database system.

User influence analysis algorithm for Weibo topics

LIU Wei, ZHANG Mingxin, AN Dezhi

2019, 39(1):  213-219.  DOI: 10.11772/j.issn.1001-9081.2018061321

Asbtract ( )   PDF (1163KB) ( )  

References | Related Articles | Metrics

As an important part of social network analysis, Weibo user influence analysis has been concerned by researchers all the time. Concerning the timeliness shortage and neglect of the relevance between users and topics when analyzing user behaviors, a user influence analysis algorithm for Weibo topics, named Topic and Spread user Rank (TSRank), was proposed. Firstly, based on Weibo topics, the timeliness of user's forwarding behavior was analyzed to construct two topic forwarding networks, user forwarding and user blog forwarding, in order to predict the user's topic information dissemination capability. Secondly, the text contents of user's personal history Weibo and background topic Weibo were analyzed to mine the relevance between user and background topic. Finally, the influence of Weibo user was calculated by comprehensively considering user's topic information dissemination capability and relevance between user and background topic. The experiments on crawled real topic data of Sina Weibo were conducted. The experimental results show that the topic forwarding number of users with higher topic correlation is significantly greater than that of users with lower topic correlation. Compared with no forwarding timeliness, the Catch Ratio (CR) of TSRank algorithm is increased by 18.7%, which is further compared with typical influence analysis algorithms, such as WBRank, TwitterRank and PageRank, TSRank algorithm improves the precision and recall by 5.9%, 8.7%, 13.1% and 6.7%, 9.1%, 14.2% respectively, which verifies the effectiveness of TSRank algorithm. The research results can support theoretical research of social attributes and topic forwarding of social networks as well as the application research of friend recommendation and public opinion monitoring.

Spatio-temporal trajectory retrieval and group discovery in shared transportation

DUAN Zongtao, GONG Xuehui, TANG Lei, CHEN Zhe

2019, 39(1):  220-226.  DOI: 10.11772/j.issn.1001-9081.2018061291

Asbtract ( )   PDF (1102KB) ( )  

References | Related Articles | Metrics

Concerning low efficiency and accuracy of the ridesharing user group discovery in shared transportation environment, a GeoOD-Tree index was established based on R-tree principle, and a group discovery strategy to maximize the multiplying rate was proposed. Firstly, the feature extraction and calibration processing of original spatio-temporal trajectory data was carried out to mine effective Origin-Destination (OD) trajectory. Secondly, a data structure termed GeoOD-Tree was established for effective storage management of OD trajectory. Finally, a group discovery model aiming at maximizing ridesharing travel was proposed, and a pruning strategy using by K Nearest Neighbors (KNN) query was introduced to improve the efficiency of group discovery. The proposed method was evaluated with extensive experiments on a real dataset of 12000 taxis in Xi'an, in comparison experiments with Dynamic Time Warping (DTW) algorithm, the accuracy and efficiency of the proposed algorithm was increased by 10.12% and 1500% respectively. The experimental results show that the proposed group discovery strategy can effectively improve the accuracy and efficiency of ridesharing user group discovery, and it can effectively improve the rideshared travel rate.

Fast malicious domain name detection algorithm based on lexical features

ZHAO Hong, CHANG Zhaobin, WANG Le

2019, 39(1):  227-231.  DOI: 10.11772/j.issn.1001-9081.2018051118

Asbtract ( )   PDF (863KB) ( )  

References | Related Articles | Metrics

Aiming at the problem that malicious domain name attacks frequently occur on the Internet and existing detection methods are not effective enough in performance of real time, a fast malicious domain name detection algorithm based on lexical features was proposed. According to characteristics of malicious domain name, all domain names to be tested were firstly normalized according to their lengths and the weights were given to them in the algorithm. Then a clustering algorithm was used to divide domain names to be tested into several groups, and the priority of each domain group was calculated by the improved heap sorting algorithm according to the sum of weights in group, the editing distance between each domain name in each domain name group and the domain name on blacklist was calculated in turn. Finally, malicious domain name was quickly determined according to the editing distance value. The running results of algorithm show that compared with the malicious domain name detection algorithm of only using domain name semantics and the algorithm of only using domain name lexical features, the accuracy of fast malicious domain name detection algorithm based on lexical features is increased by 1.7% and 2.5% respectively, the detection rate is increased by 13.9% and 6.8% respectively. The proposed algorithm has higher accuracy and performance of real-time.

Conformity effect and authoritative effect of rumor spreading in social network

MA Yuhong, ZHAO Yuanyuan, QIANG Yarong

2019, 39(1):  232-238.  DOI: 10.11772/j.issn.1001-9081.2018061302

Asbtract ( )   PDF (1147KB) ( )  

References | Related Articles | Metrics

Since rumor spreading in social network is inevitably affected by social and environmental factors, the influence of two main social effects, conformity effect and authoritative effect, on rumor spreading were discussed by combining theoretical analysis and simulation experiments. Firstly, the population in social network was divided into four types:Susceptible (S), Hesitated (H), Infected (I) and Removed (R), an SHIR rumor spreading model was established based on a new state transition rule. Secondly, the iterative technique and fitting approach were used to reveal the relations between rumor spreading and the density of initial spreaders or initial spreading rate. Finally, two kinds of social effects, conformity effect and authoritative effect, were characterized at individual level, and their influences on rumor spreading were simulated and analyzed. The experimental results show that the spreading peak values of rumor have a linear relation to the density of initial spreader, while the peak time has a sharp decline with the increasing of density of initial spreader. The more initial spreading rate, the higher the spreading peak value and the shorter peak time. The conformity effect and authoritative effect can significantly increase the range and velocity of rumor spreading, and greatly promote the proportion of the removed in steady-state network; the higher the network density, the faster and wider the rumor spreading, but conformity effect is stronger than authoritative effect at same networks, and their difference become smaller and smaller with increasing of network density; the more important the initial spreaders, the faster and wider the rumor spreading, but authoritative effect is more prominent than conformity effect.

Two-dimensional inverse-trigonometric hyperchaotic system and its application in image encryption

GE Jiangxia, QI Wentao, LAN Lin, TIAN Yu, ZHU Hegui

2019, 39(1):  239-244.  DOI: 10.11772/j.issn.1001-9081.2018061317

Asbtract ( )   PDF (978KB) ( )  

References | Related Articles | Metrics

In order to improve chaos complexity and provide more reliable chaotic system for image encryption, and enhance the security of image encryption algorithm, a new image encryption algorithm based on two-dimensional inverse-trigonometric hyperchaotic system was proposed. Firstly, based on one-dimensional triangular function, a two-dimensional inverse-trigonometric hyperchaotic system was constructed. Compared with some two-dimensional chaotic systems, this system had wider chaotic range, more random iteration sequences and better ergodicity by simulation experiments about bifurcation diagram and Lyapunov exponent. Then based on the proposed chaotic system, the "scrambling-diffusion" strategy was designed and different keys were given, which were used to generate different hyperchaotic sequences. The image matrix was scrambled without repetition by hyperchaotic sequences, then the scrambled sequence were shifted and diffused. So the ciphertext was obtained by looping thrice. Finally, histogram analysis, key space analysis, correlation analysis of adjacent pixels, plaintext sensitivity analysis and information entropy analysis were carried out. The test values of Number of Pixels Change Rate (NPCR) and Unified Average Changing Intersity (UACI) of ciphertext images were very close to their ideal expected values. The test results of information entropy were about 7.997, which was also very close to the expected value of 8. The experimental results show that the image encryption system has more reliable security, stronger ability to resist attacks, and had a good application prospect in the field of image security.

Ranked ciphertext retrieval scheme supporting semantic extension of retrieval keyword

LI Yong, XIANG Zhongqi

2019, 39(1):  245-250.  DOI: 10.11772/j.issn.1001-9081.2018061229

Asbtract ( )   PDF (1071KB) ( )  

References | Related Articles | Metrics

Focusing on the shortages of existing ciphertext retrieval schemes in cloud computing, such as not supporting semantic extension of retrieval keyword, low accuracy and not ranking search results, a ranked ciphertext retrieval scheme supporting semantic extension of retrieval keyword was proposed. Firstly, Term Frequency-Inverse Document Frequency (TF-IDF) method was used to calculate the relevance scores between keywords and documents, and different weights were set for keywords in different document domains. The position weight scores of keywords in different document domains were calculated based on domain-weighted scoring method. The value of keyword corresponding position on document index vector was set as the product of position weight score and relevance score. Secondly, according to WordNet semantic Web, semantic extension was performed on retrieval keywords that input by the authorized users, and edit distance formula was used to calculate the similarity among semantic extension keywords, and the value of retrieval keyword corresponding position on document retrieval vector was set as similarity value. Finally, security index and document retrieval trapdoors were generated by encryption, and the inner product operation was performed based on Vector Space Model (VSM), and the result of ciphertext retrieval documents was sorted by the value of inner product operation. The theoretical analysis and experimental simulations show that the proposed scheme is safe under the known ciphertext model and the known background knowledge model, and has the ability to sort the search results. Compared with Multi-keyword Ranked Search over Encrypted cloud data (MRSE) scheme, the proposed scheme supports keyword semantic extension, and is more accurate and reliable than MRSE, while the retrieval time is not much different from MRSE scheme.

Energy-balanced clustering routing algorithm based on ring partition

WANG Hanxin, HONG Siqin

2019, 39(1):  251-255.  DOI: 10.11772/j.issn.1001-9081.2018061311

Asbtract ( )   PDF (772KB) ( )  

References | Related Articles | Metrics

A novel Energy-Balanced Clustering Routing algorithm based on Ring Partition (EBCR-RP) was proposed to solve the network lifetime problem of unbalanced energy consumption and low energy efficiency in Wireless Sensor Network (WSN). Firstly, the one-hop distance with minimize energy consumption was calculated and regarded as ring spacing. Secondly, the number of clusters was optimized and each ring was partitioned uniformly, and the node with highest energy in each block was chosen as cluster header to balance energy consumption. Finally, a cost function was designed to search optimal data transform path to improve energy efficiency. The simulation results show that network lifetime of EBCR-RP is increased by 51.4% and 8.6% compared with Fuzzy Logic Cluster Formation Protocol (FLCFP) and Improved Uneven Clustering Routing (IUCR) algorithms. EBCR-RP can effectively prolong network lifetime, balance energy consumption and improve energy efficiency.

Fast indoor positioning algorithm of airport terminal based on spectral regression kernel discriminant analysis

DING Jianli, MU Tao, WANG Huaichao

2019, 39(1):  256-261.  DOI: 10.11772/j.issn.1001-9081.2018051074

Asbtract ( )   PDF (899KB) ( )  

References | Related Articles | Metrics

Aiming at the characteristics of large passenger flow, complex and variable indoor environment in airport terminals, an indoor positioning algorithm based on Spectral Regression Kernel Discriminant Analysis (SRKDA) was proposed. In the offline phase, the Received Signal Strength (RSS) data of known location was collected, and the non-linear features of the Original Location Fingerprint (OLF) were extracted by SRKDA algorithm to generate a new feature fingerprint database. In the online phase, SRKDA was firstly used to process the RSS data of the point to be positioned, and then Weighted K-Nearest Neighbor (WKNN) algorithm was used to estimate the position. In positioning simulation experiments, the Cumulative Distribution Function (CDF) and positioning accuracies of the proposed algorithm under 1.5 m positioning accuracy are 91.2% and 88.25% respectively in two different localization scenarios, which are 16.7 percentage points and 18.64 percentage points higher than those of the Kernel Principal Component Analysis (KPCA)+WKNN model, 3.5 percentage points and and 9.07 percentage points higher than those of the KDA+WKNN model. In the case of a large number of offline samples (more than 1100), the data processing time of the proposed algorithm is much shorter than that of KPCA and KDA. The experimental results show that, the proposed algorithm can effectively improve the indoor positioning accuracy, save data processing time and enhance the positioning efficiency.

Image matching method with illumination robustness

WANG Yan, LYU Meng, MENG Xiangfu, LI Yuhao

2019, 39(1):  262-266.  DOI: 10.11772/j.issn.1001-9081.2018061210

Asbtract ( )   PDF (774KB) ( )  

References | Related Articles | Metrics

Focusing on the problem that current image matching algorithm based on local feature has low correct rate of illumination change sensitive matching, an image matching algorithm with illumination robustness was proposed. Firstly, a Real-Time Contrast Preserving decolorization (RTCP) algorithm was used for grayscale image, and then a contrast stretching function was used to simulate the influence of different illumination transformation on image to extract feature points of anti-illumination transformation. Finally, a feature point descriptor was established by using local intensity order pattern. According to the Euclidean distance of local feature point descriptor of image to be matched, the Euclidean distance was determined to be a pair matching point. In open dataset, the proposed algorithm was compared with Scale Invariant Feature Transform (SIFT) algorithm, Speeded Up Robust Feature (SURF) algorithm, the "wind" (KAZE) algorithm and ORB (Oriented FAST and Rotated, BRIEF) algorithm in matching speed and accuracy. The experimental results show that with the increase of image brightness difference, SIFT algorithm, SURF algorithm, the "wind" algorithm and ORB algorithm reduce matching accuracy rapidly, and the proposed algorithm decreases matching accuracy slowly and the accuracy is higher than 80%. The proposed algorithm is slower to detect feature points and has a higher descriptor dimension, with an average time of 23.47 s. The matching speed is not as fast as the other four algorithms, but the matching quality is much better than them. The proposed algorithm can overcome the influence of illumination change on image matching.

Image depth estimation model based on atrous convolutional neural network

LIAO Bin, LI Haowen

2019, 39(1):  267-274.  DOI: 10.11772/j.issn.1001-9081.2018061305

Asbtract ( )   PDF (1380KB) ( )  

References | Related Articles | Metrics

Focusing on the issues of poor depth estimation and inaccurate depth value acquisition under traditional machine learning methods, a depth estimation model based on Atrous Convolutional Neural Network (ACNN) was proposed. Firstly, the feature map of original image was extracted layer by layer using Convolutional Neural Network (CNN). Secondly, with the atrous convolution structure, the spatial information in original image and the extracted feature map were fused to obtain initial depth map. Finally, the Conditional Random Field (CRF) with combining three constraints, pixel spatial position, grayscale and gradient information were used to optimize initial depth map and obtain final depth map. The model usability verification and error estimation were completed on objective data set. The experimental results show that the proposed algorithm obtains lower error value and higher accuracy. The Root Mean Square Error (RMS) is averagely reduced by 30.86% compared with machine learning based algorithm, and the accuracy is improved by 14.5% compared with deep learning based algorithm. The proposed algorithm has a significant improvement in error reduction and visual effect, indicating that the model can obtain better results in image depth estimation.

Single image super resolution algorithm based on structural self-similarity and deformation block feature

XIANG Wen, ZHANG Ling, CHEN Yunhua, JI Qiumin

2019, 39(1):  275-280.  DOI: 10.11772/j.issn.1001-9081.2018061230

Asbtract ( )   PDF (1016KB) ( )  

References | Related Articles | Metrics

To solve the problem of insufficient sample resources and poor noise immunity for single image Super Resolution (SR) restoration, a single image super-resolution algorithm based on structural self-similarity and deformation block feature was proposed. Firstly, a scale model was constructed to expand search space as much as possible and overcome the shortcomings of lack of a single image super-resolution training sample. Secondly, the limited internal dictionary size was increased by geometric deformation of sample block. Finally, in order to improve anti-noise performance of reconstructed picture, the group sparse learning dictionary was used to reconstruct image. The experimental results show that compared with the excellent algorithms such as Bicubic, Sparse coding Super Resolution (ScSR) algorithm and Super-Resolution Convolutional Neural Network (SRCNN) algorithm, the super-resolution images with more subjective visual effects and higher objective evaluation can be obtained, the Peak Signal-To-Noise Ratio (PSNR) of the proposed algorithm is increased by about 0.35 dB on average. In addition, the scale of dictionary is expanded and the accuracy of search is increased by means of geometric deformation, and the time consumption of algorithm is averagely reduced by about 80 s.

Crack detection algorithm based on multi-factor decision and percolation model

AN Shiquan, CAO Yuexin, QU Zhong

2019, 39(1):  281-286.  DOI: 10.11772/j.issn.1001-9081.2018061226

Asbtract ( )   PDF (926KB) ( )  

References | Related Articles | Metrics

Concerning the problem that traditional crack detection algorithm based on percolation model has low efficiency and detection results are prone to fracture, a crack detection algorithm based on multi-factor decision and percolation model was proposed. Firstly, an improved algorithm of accelerating crack inspection based on percolation model was proposed, which improves the efficiency of percolation processing by reducing a large number of redundant pixel points involved in percolation processing. Secondly, the extracted percolation points were used to percolation processing. Finally, a multi-factor decision connection algorithm based on crack orientation was proposed. In the algorithm, the rationality of crack connection was analyzed by four decision factors to improve the accuracy of crack connection. Different morphological crack images with different interfering objects in background were used in experiments. Compared with traditional percolation model detection algorithm and original algorithm of accelerating crack inspection based on percolation model and skeleton connection algorithm, the number of percolation points of the proposed algorithm was reduced by an average of 99.7% and 38.1%, respectively. The precision was increased by an average of 60.5% and 6.4%, respectively, and the recall was increased by an average of 10.5% and 4.0%, respectively. The experimental results show that the proposed algorithm can significantly improve the efficiency of percolation processing and improve the accuracy of crack detection.

Automatic recognition method of pointer meter for inspection robots

SUN Ting, MA Lei

2019, 39(1):  287-291.  DOI: 10.11772/j.issn.1001-9081.2018061275

Asbtract ( )   PDF (818KB) ( )  

References | Related Articles | Metrics

In the outdoor working environment of inspection robots, recognizing the number of meter was susceptible to illumination. An adaptive adjustment algorithm for meter images based on 2D-Gamma function was studied. Then an algorithm based on Maximally Stable Extremal Region (MSER) was proposed to extract the pointer. Firstly, the reflection component was extracted by three-scale Gaussian functions, 2D Gamma function was constructed to automatically adjust brightness of the reflected or overshadowed region of image. Secondly, the pointer region was extracted through two MSER detections. Thirdly, on the condition that the pointer passed through the axis of dial, the pointer was precisely positioned by thinning algorithm and Progressive Probabilistic Hough Transform (PPHT) to improve the accuracy of positioning lines. Finally, on basis of comparing the positions of two endpoints by PPHT with axis, the direction of pointer was directly determined, thus calculating the number was more convenient. The experimental results show that the proposed method can deal with different types of meters under different lighting conditions. Moreover, the correct rate of identification reaches over 94%.

Reliability simulation analysis of coal transportation road network

LU Qiuqin, JIN Chao

2019, 39(1):  292-297.  DOI: 10.11772/j.issn.1001-9081.2018061193

Asbtract ( )   PDF (1046KB) ( )  

References | Related Articles | Metrics

Concerning the problem that destruction of nodes or edges in coal transportation road network for emergencies has caused problems in blockage of coal transportation road networks, based on complex network theory, the network models constructed by original method and dual method were established, and their reliability were simulated by Matlab software. Firstly, basic characteristics of two networks were compared and analyzed, and then relative changes of network efficiency were proposed to identify key road segments in network. Based on this, a network reliability evaluation model was established, and three reliability evaluation indexes including network efficiency, maximum connected subgraph relative size and network dispersion were proposed to simulate network reliability under two destruction modes:random destruction and deliberate destruction. The experimental result shows that in deliberate destruction mode, when 10% of nodes fail, three reliability index values are 10%, 20%, and 20, respectively, while the index values in random destruction mode still maintain at a high level. Therefore, the coal transportation network is robust to random destruction and vulnerable to deliberate destruction. The protection of important nodes in network should be strengthened.

Land parcel boundary extraction of UAV remote sensing image in agricultural application

WU Han, LIN Xiaolong, LI Xirong, XU Xin

2019, 39(1):  298-304.  DOI: 10.11772/j.issn.1001-9081.2018051114

Asbtract ( )   PDF (1276KB) ( )  

References | Related Articles | Metrics

Aiming at the over-segmentation problem caused by inconsistency of large-format, high-resolution and inconsistency of parcel size in extraction of Unmanned Aerial Vehicle (UAV) remote sensing image of farmland scene, an automatic extraction process for land boundary based on multi-scale segmentation was proposed. In this process, the block segmentation strategy was adopted under the framework of Multi-scale Combinatorial Grouping (MCG) segmentation method. The optimal ground sampling distance was selected by comparing experimental research and optimal segmentation scale was selected by analyzing the variation curve of boundary extraction accuracy with scale, therefore automatic extraction process of parcel boundaries was achieved. Experiments were conducted on the data collected from Xiantao City, Hubei Province. The experimental results show that the most suitable ground sampling distance for extracting land parcel boundary is about 30 cm and the optimal segmentation scale is[0.2,0.4]. The accuracy of land parcel boundary extraction can be more than 90%. In addition, the proposed method can accurately extract large-scale agricultural parcel boundary and also can provide a reference for later aerial program of agriculture UAV.

Discretization process of coupled Logistic fractional-order differential equation

LIU Shanshan, GAO Fei, LI Wenqin

2019, 39(1):  305-310.  DOI: 10.11772/j.issn.1001-9081.2018040848

Asbtract ( )   PDF (871KB) ( )  

References | Related Articles | Metrics

Focusing on the problem of solving coupled Logistic fractional-order differential equation, a discretization method was introduced to solve it discretly. Firstly, a coupled Logistic integer-order differential equation was introduced into the fields of fractional-order calculus. Secondly, the corresponding coupled Logistic fractional-order differential equation with piecewise constant arguments was analyzed and the proposed discretization method was applied to solve the model numerically. Then, according to the fixed point theory, the stability of the fixed point of the synthetic dynamic system was discussed, and the boundary equation of the first bifurcation of the coupled Logistic fractional-order system in the parameter space was given. Finally, the model was numerically simulated by Matlab, and more complex dynamics phenomena of model were discussed with Lyapunov index, phase diagram, time series diagram and bifurcation diagram. The simulation results show that, the proposed method is successful in discretizing coupled Logistic fractional-order differential equation.