Please wait a minute...
, No 8

■ Cover Page (PDF 284 KB)   Table of Contents, August 2019 (PDF 192 KB)

  • Reliability based Maintenance Model to Assess the Condition of Rotor using XLrotor
    Murgayya S B, H N Suresh, Madhusudhan N, and Sarvanabavan B
    2019, 15(8): 2019-2030.  doi:10.23940/ijpe.19.08.p1.20192030
    Abstract    PDF (1575KB)   
    References | Related Articles
    The work carried out is focused on study and behavior of rotors and to check the reliability at the design stage using the advanced XLrotor tool. For the selected rotor, the failures are controlled by shifting critical speeds above the maximum speed in which it is designed for. The rotor is balanced with safe limits of vibration severity criteria as per ISO standards for an optimized model. Sensitivity analysis is carried out on the rotor model by varying factors such as the diameter of shaft, disk configuration, disk offset, and load on rotor model. The results obtained show good agreement with the FEM results. The results obtained are undamped & damped critical speeds, as well as velocity & dynamic load on bearings due to imbalance using XLrotor. The rotor model is balanced for a steel shaft with a steel disk as well as a steel shaft with an aluminum disk (optimized rotor model) as part of the corrective method. The work clearly emphasizes XLrotor for designing a highly reliable rotor that is safe for operating conditions.
    Evaluation Model of the Production System Effectiveness
    Ahmed Bounit, Elhassan Irhirane, Badr Dakkak, Abdelatif Rajji, and Abaida Abdellah
    2019, 15(8): 2031-2039.  doi:10.23940/ijpe.19.08.p2.20312039
    Abstract    PDF (609KB)   
    References | Related Articles
    The valuation of a production system's effectiveness requires a more appropriate decision-making indicator. The absence of this indicator constitutes a disability to give the managers a method to attain performance at the level of their services. In this article, we propose a model based on fuzzy logic that assess system effectiveness of manufacturing production. As a result, this model guides the operational decision-makers (maintenance, production, quality) to make the best decision and to have a more global vision of the production system's performance. A case study was done within an industrial firm to test the offered model. Results show that the model is more realistic, robust and has better stocks compared to the classical method.
    Homogeneous Metal Foam Manufacturing and Impact Test Performance
    Ananthakrishnan Kaimal, Bevin Boban Mathew, and S. Jeyanthi
    2019, 15(8): 2040-2048.  doi:10.23940/ijpe.19.08.p3.20402048
    Abstract    PDF (589KB)   
    References | Related Articles
    In this investigation, metal foam was produced by casting aluminum around intersecting ceramic cylinders. Through this study, an attempt was made to propose the use of homogeneous metal foams in impact attenuation. The metal foam in this investigation was made using a novel casting method. The testing was done on a UTM and subsequent simulations on an explicit dynamic solver in an ABAQUS environment. The crash simulation is initiated after a certain level of similarity between results of the UTM compression test and FEM compression analysis. The results demonstrate that a compact and cheap impact energy absorption unit can be made using the described method. The simulation compares a solid block to the obtained foam in terms of "Energy absorption per unit volume" and total kinetic energy of the impact test set-up.
    Proposed Hybrid Approach to Predict Software Fault Detection
    Manu Banga, Abhay Bansal, and Archana Singh
    2019, 15(8): 2049-2061.  doi:10.23940/ijpe.19.08.p4.20492061
    Abstract    PDF (1012KB)   
    References | Related Articles
    The major challenge is to validate software failure dataset by finding unknown model parameters used. Previously, many attempts for software assurance were made using classical classifiers as Decision Tree, Naïve Bayes, and k-NN for software fault prediction. But the accuracy of fault prediction is very low as defect prone modules are very small as compared to defect-free modules. So, for solving modules fault classification problems and enhancing reliability accuracy, a hybrid algorithm proposed on Particle Swarm Optimization (PSO) & Modified Genetic Algorithm (MGA) for feature selection and Bagging for effective classification of defective or non-defective modules in a dataset. This paper presents an empirical study on NASA Metric Data Program (MDP) datasets, using the proposed hybrid algorithm. Results showed that our proposed hybrid approach enhances the classification accuracy compared with existing methods.
    Reliability Analysis of Cold Standby Systems based on Supplement Events using Multiple-Valued Decision Diagrams
    Ting Zeng
    2019, 15(8): 2062-2070.  doi:10.23940/ijpe.19.08.p5.20622070
    Abstract    PDF (311KB)   
    References | Related Articles
    Multiple-valued decision diagrams (MDDs) have been widely used in reliability analysis for non-repairable fault-tolerant systems. Typically, multiple-valued decision diagrams are used to analyze the static fault tree (SFT) model since basic events in the SFT are non-sequence-dependent. However, a cold standby system belongs to the dynamic fault tree model; the traditional MDD cannot be directly applied in this system. Hence, a novel analytical method based on conditional events using multiple-valued decision diagrams for combinatorial reliability analysis of non-repairable cold standby systems is proposed. In the proposed method, a set of fault events with specific supplement events replaces cut sequences for qualitative analysis. The sets are converted to algebraic structure-based models for quantitative analysis. Additionally, the system MDD model and reliability evaluation expression can be reused for reliability analysis with different component failure parameters.
    Bug Report Classification based on Vector Space Model
    Lele Chen, Song Huang, Jinlei Sun, Zhanwei Hui, and Sen Yang
    2019, 15(8): 2071-2080.  doi:10.23940/ijpe.19.08.p6.20712080
    Abstract    PDF (539KB)   
    References | Related Articles
    As a vehicle for recording and tracking defects, bug reports provide a basis for solving software quality problems. Currently, software testing is often carried out in a multi-person and parallel state. The integration process of numerous bug reports, such as moving fake or duplication bug reports, is facing severe challenges. Therefore, this paper proposes an automatic detection modus for bug reports based on the vector space model. After pre-processing the bug report, a matching library is created according to the test requirements and test report samples. The vector space model is used to calculate the similarity between the two, and the correctness of the bug report is detected based on this. Experiments with the data of a software test contest show that the modus proposed in this paper can correctly judge most bug reports, effectively improving the efficiency of de-false and de-duplication.
    Scheduling Algorithm for a Task under Cloud Computing
    Yan Li and Yao Yao
    2019, 15(8): 2081-2090.  doi:10.23940/ijpe.19.08.p7.20812090
    Abstract    PDF (631KB)   
    References | Related Articles
    Aiming at the problem of low efficiency of task scheduling in cloud computing, this paper first analyzes the task of cloud computing task scheduling. Secondly, the pheromone setting quality function of the ant colony algorithm and the empirical feedback factor of selection probability are improved. The new method is adopted for the colonial calculation method and boundary value processing in the imperial competition algorithm. Finally, the two algorithms are merged to obtain a cloud computing task scheduling algorithm based on the ant colony algorithm-empire competition algorithm. In the simulation experiment, the algorithm demonstrates certain advantages in terms of task execution time, execution cost, and load rate.
    Models with Memory for RF Power Amplifier Behavioral Modeling
    Xiang Chen, Yihan Xiao, Hui Han, Jie Chang, and Nan Tang
    2019, 15(8): 2091-2099.  doi:10.23940/ijpe.19.08.p8.20912099
    Abstract    PDF (3822KB)   
    References | Related Articles
    Power amplifiers are used to amplify signals to the required power and then transmit the signals through antennas. They are the key component of modern wireless communication systems. However, the power amplifier itself has non-linear characteristics and memory effect, especially when the input signal is a broadband signal and high frequency signal, which seriously affects the normal transmission of communication systems. In this paper, the RF power amplifier under test is an amplifier using a BLT53A transistor. We collect the input and output signals of the power amplifier for behavioral modeling. The behavior model only considers the input and output of the amplifier. We adopt a memory polynomial model based on the least squares method. In this paper, we evaluate the correctness of the model from many aspects including AM-AM curve, AM-PM curve, spectrum, gain compression, constellation diagram, and normalized mean square error. The results show that the model is effective.
    Symbol Rate Estimation based on Wavelet Transform and Cyclic Spectrum
    Danyang Li, Xiaojun Hao, and Zhaoyue Zhang
    2019, 15(8): 2100-2106.  doi:10.23940/ijpe.19.8.p9.21002106
    Abstract    PDF (533KB)   
    References | Related Articles
    Aiming at the digital modulation signals such as MASK, MPSK, and MQAM in a Gaussian white noise environment, this paper theoretically analyzes the reason and rule of the appearance of the spectrum of wavelet transform and the symbol rate spectrum line of cyclic spectrum. The simulation results show that the method based on wavelet transform is better than that based on cyclic spectrum, and the SNR threshold of the first method is reduced by 8dB compared with the latter.
    Carrier Frequency Estimation based on Frequency Domain and Wavelet Ridge
    Xiang Chen, Wei Zhi, and Yihan Xiao
    2019, 15(8): 2107-2115.  doi:10.23940/ijpe.19.08.p10.21072115
    Abstract    PDF (605KB)   
    References | Related Articles
    To estimate the carrier frequency of digital signals such as MASK, MPSK, and MQAM under the condition of white Gaussian noise, this paper uses the methods based on frequency domain and wavelet ridge, and two corresponding improved methods are proposed. For the method based on frequency domain, aiming at the problem of poor spectral accuracy and applicability, we propose a method using power spectrum instead of spectrum. Compared with the original method, the simulation consequences express that the improved method reduces the signal-to-noise ratio (SNR) threshold by 5dB. For the method based on wavelet ridge, we propose an improved method to identify the problems of initial iteration parameters, accuracy of results, and divergence points. The simulation consequences illustrate that the improved method reduces the signal-to-noise ratio threshold by 2dB compared with the original method.
    Engineering Realization of a Dual-Band Monopulse Antenna
    Fengwei Yao, Wei Liu, and Mei Jiang
    2019, 15(8): 2116-2122.  doi:10.23940/ijpe.19.08.p11.21162122
    Abstract    PDF (425KB)   
    References | Related Articles
    The dual-frequency monopulse antenna is on the front end of the dual-mode seeker, and its geometrical and radiation characteristics both decide the performance of a system. In this paper, a new dual-frequency monopulse antenna is introduced; it adopts a compact slot radiator, a novel side-feed array, a waveguide feeding network in one dimension to reduce microstrip loss and other novel designs. After second optimization to overcome the engineering problem, an improved antenna is created, and it is divided into two parts to improve weldability and yield. The tested results show that the antenna has good monopulse characteristics in two bands at the same time, with an efficiency of 38% and 45%, respectively. The experimental results demonstrate that this design is effective.
    Position of Fingerprint Location based on Improved Universal Kriging Interpolation Method
    Zhongwen Wang, Xin Ge, Ruizhen Duan, and Mingshan Chi
    2019, 15(8): 2123-2132.  doi:10.23940/ijpe.19.08.p12.21232132
    Abstract    PDF (588KB)   
    References | Related Articles
    The accuracy of fingerprint databases is very important to position fingerprint locations. However, due to the measurement of the received signal strength cost and artificial constraints, the measured RSSI is limited, resulting in insufficient accuracy of fingerprint databases. Therefore, we adopt the spatial interpolation algorithm to obtain a more accurate location fingerprint database and innovatively propose an improved universal Kriging interpolation method, introducing variable parameters, overcoming the shortcomings of large measurement errors in the variation function, and generating an accurate location fingerprint database. The simulation results show that compared with the universal Kriging interpolation method and the inverse distance weighting method, the standard error of prediction is increased by 76.33% and 96.50%, respectively.
    Resource Allocation Optimization of UAVs-Enabled Air-Ground Collaborative Emergency Network in Disaster Area
    Lei Wu and Weijian Wang
    2019, 15(8): 2133-2144.  doi:10.23940/ijpe.19.08.p13.21332144
    Abstract    PDF (879KB)   
    References | Related Articles
    This paper aims to improve the efficiency of UAVs-enabled air-ground collaborative emergency networks through resource allocation optimization. The bandwidth assignment, UAVs' flight trajectories, and transmission power were jointly optimized to maximize the achievable signal rate of all terminal receivers in the downlink. The block coordinate descent method and successive convex approximation were utilized to solve the established mixed-integer non-convex optimization problem. Then, an emergency communication scenario was designed to run different emulation experiments, which were used to verify that the proposed algorithm was effective. Numerous results showed that the proposed algorithm can attain great performances in this scenario. Compared with single factor optimizing strategies, the users' signal rate can be improved by 5%-28% through joint optimization.
    Adaptive Grid Decomposition Algorithm based on Standard Deviation Circle Radius
    Guoqiang Zhou, Xiulian Tang, and Shui Qin
    2019, 15(8): 2145-2152.  doi:10.23940/ijpe.19.08.p14.21452152
    Abstract    PDF (989KB)   
    References | Related Articles
    The differential privacy preservation model based on spatial dataset meshing has been widely concerned, but the distribution characteristics of the dataset and user's query granularity are often ignored or not fully considered in the partitioning of the dataset. Aiming at deficiencies in existing mesh-based algorithms, a standard deviation circle radius adaptive grid decomposition (SDCAG) algorithm is proposed. Firstly, the standard deviation circle radius is introduced to quantitatively represent the distribution characteristics of datasets in order to calculate privacy preservation requirements. Secondly, filtering and bucketing are used to reduce the noise error. Finally, the improved query precision is implemented based on the post-processing. Experiments on the NYC dataset, the Beijing dataset, and the Checkin dataset show that the SDCAG algorithm is superior to similar algorithms in terms of query performance.
    Optimization and Parallelization of MRF Community Detection Algorithm for a Specific Network
    Jun Lu and Yuanzhong Zhang
    2019, 15(8): 2153-2164.  doi:10.23940/ijpe.19.08.p15.21532164
    Abstract    PDF (387KB)   
    References | Related Articles
    Research on the optimization and parallelization of the MRF network community detection algorithm for a specific network is carried out in this paper. Firstly, the principle of the existing algorithm is expounded, the algorithm is analyzed, and some problems are pointed out. Some optimization strategies and rules are proposed, including the extraction of variables and operations from inner loops to outer loops, the merging of related operations in loops, the removal of redundant loops, and the split of loops. In order to achieve better parallelism, OpenMP parallel computing of this method is realized by reversing the order of inner and outer loops. The influence of the density of network edges on the algorithm efficiency is also analyzed in this paper. The optimization and parallel algorithm can be applied to the module partition of Alzheimer's disease gene data, and the efficiency of the algorithm is greatly improved. The optimization strategies and rules proposed in this paper can be further extended to general situations. It is significant in practical applications.
    A Quantum Key-based Mobile Security Payment Scheme
    Dexin Zhu, Xiaohui Li, Jianan Wu, and Lijun Song
    2019, 15(8): 2165-2172.  doi:10.23940/ijpe.19.08.p16.21652172
    Abstract    PDF (310KB)   
    References | Related Articles
    In view of the safety problem of current mobile security payment encryption schemes, this paper proposed a quantum key-based MSP (mobile security payment) scheme. First, this scheme introduced quantum encryption technology to solve the symmetric key problem between the payment platform server and the commercial supermarket server. Then, the quantum key was safely obtained and the QR (quick response) code was generated by using the proposed quantum key gateway. Finally, the mobile device finished the payment according to the one-time pad encryption scheme. Compared with the existing schemes, the proposed scheme can fully employ the advantages of quantum encryption technology. It can also resist multiple security threats by using the quantum key gateway. Under the real quantum key distribution and quantum key gateway environment, the feasibility and effectiveness of this scheme were proven by experimental results.
    Imbalanced Data Optimization Combining K-Means and SMOTE
    Wenjie Li
    2019, 15(8): 2173-2181.  doi:10.23940/ijpe.19.08.p17.21732181
    Abstract    PDF (427KB)   
    References | Related Articles
    With the wide application of imbalanced data processing in various fields, such as credit card fraud identification, network intrusion detection, cancer detection, commodity recommendation, software defect prediction, and customer churn prediction, imbalanced data has become one of the current research hotspots. When classifying imbalanced data sets, aiming at the problems of low classification accuracy of negative class samples in the random forest algorithm and marginalization for selecting new samples in the SMOTE algorithm, a new algorithm, KMS_SMOTE, is proposed to deal with imbalanced data sets. In order to avoid the problem of marginalization of new samples, the K-Means algorithm is used to classify the negative class samples to obtain the centroid of the negative class samples, and then the new data set is obtained by selecting the samples near the centroid. Finally, in order to verify the effect of the KMS_SMOTE algorithm, it is compared with the SMOTE algorithm on the data sets of UCI machine learning. The experimental results show that the KMS_SMOTE algorithm effectively improves the classification performance of the random forest algorithm on the imbalanced data set.
    Deep Convolutional Neural Network and Its Application in Image Recognition of Road Safety Projects
    Lingling Wang, Wenyin Gong, and Xiang Li
    2019, 15(8): 2182-2189.  doi:10.23940/ijpe.19.08.p18.21822189
    Abstract    PDF (1091KB)   
    References | Related Articles
    Road safety projects constitute an important part of road safety facilities. Assessing the safety of these projects is important for assessing the safety of roads. In recent years, road safety problems have caused enormous losses to the country and its people. Traditional inspection and maintenance of road safety projects mainly involve manual inspection and on-site maintenance; however, manual inspection is time-consuming and laborious, and it cannot be used to identify safety issues in large areas. This paper focuses on the application of the deep convolutional neural network algorithm, a deep learning algorithm, for the recognition of road safety projects. Comparative analysis of the experimental results shows that both the convolutional neural network models VGG16 and InceptionV3 can identify the pre-processed data sets of the road safety projects; however, the accuracy of the test set model InceptionV3 is higher than that of VGG16, reaching 93.3%.
    Content-Centric Network Caching Strategy based on Node Situational Degree
    Jianwei Zhang, Chunfeng Du, Zengyu Cai, Wenqian Wang, and Zuodong Wu
    2019, 15(8): 2190-2198.  doi:10.23940/ijpe.19.08.p19.21902198
    Abstract    PDF (457KB)   
    References | Related Articles
    In order to meet the requirement of efficient network utilization and cache data availability of content-centric networks, a content-centric network caching strategy based on the node situational degree is proposed. It considers user preferences, content popularity, and node caching. Specifically, the active nodes in CCN network statistics involve user requests, hit rates, time intervals, and cache statuses of nodes according to the period. Through these data, the user preferences around the active node, the content popularity of each type of content in the node, and the cache degree of the node are calculated. Finally, the situational degree of the node is obtained. In the process of user request data and content packet information interaction with active nodes or content source servers, the situational threshold of nodes is calculated. According to dynamic changes in the node situational degree value and the matching of byte value information contained in the interest package and data package, the best caching node can be judged and selected for content replica. The optimized configuration of cached content can be realized. Simulation results show that, compared with the traditional caching scheme, this caching strategy can effectively improve the average cache hit ratio and reduce the request delay.
    Fast Multipath Jump Algorithms for Security Constraints
    Wanwei Huang, Yang Chen, Jianwei Zhang, Chunfeng Du, Sunan Wang
    2019, 15(8): 2199-2207.  doi:10.23940/ijpe.19.08.p20.21992207
    Abstract    PDF (575KB)   
    References | Related Articles
    Transmission path jump can effectively resist network reconnaissance attacks by fragmented data transmission. However, most of the existing path jump models are based on SMT or game theory, which results in an exponential increase of computing time with network size. An efficient path generation algorithm for active random routing is proposed. Firstly, based on the global view of the network defined by the software, the paths of multiple streams are randomly changed actively and concurrently to resist reconnaissance, eavesdropping, and DoS attacks. Secondly, the traditional path calculation algorithm is re-modelled to satisfy the capacity, security, and QoS constraints of the K path generated, while improving the computational efficiency. Then, the optimal K value is solved, and the security effect of dynamic path is analysed. Finally, simulation results based on typical network topology show that the proposed algorithm can avoid and defend against malicious eavesdropping by attackers and improve the computational efficiency.
    Cloud-OM Patching: A Novel Video Stream Scheduling Scheme based on Hybrid Cloud-Overlay Architecture
    Guangqian Kong, Xun Duan, and Yun Wu
    2019, 15(8): 2208-2216.  doi:10.23940/ijpe.19.08.p21.22082216
    Abstract    PDF (466KB)   
    References | Related Articles
    Patching is an effective multicast video stream scheduling technology that provides "real" VoD services. However, patching streams cannot be shared by other users, resulting in insufficient server scalability. In addition, IP multicast cannot be deployed on the Internet in a large scale; thus, the application of multicast stream scheduling technology is limited. Based on the above problems, this paper first proposes a hybrid cloud-overlay multicast architecture based on overlay network and cloud computing. It consists of three parts: cloud layer, overlay layer, and monitoring layer. Then, based on this architecture, a Cloud-OM patching stream scheduling algorithm is proposed, which combines patching stream sharing and multicast tree level time difference cache sharing technology. The experimental results show that Cloud-OM patching can effectively reduce the server bandwidth requirements and has better performance than standard patching, double patching, and batched patching, especially for popular videos.
    A Scalable Load Balancing Scheme for Software-Defined Datacenter Networks based on Fuzzy Logic
    Guoyan Li, Xinqiang Wang, Zhigang Zhang, Yadong Chen, and Shudong Liu
    2019, 15(8): 2217-2227.  doi:10.23940/ijpe.19.08.p22.22172227
    Abstract    PDF (620KB)   
    References | Related Articles
    In order to solve the problem that traditional load balancing technology lacks sufficient scalability and flexibility, we propose a dynamic and scalable load balancing scheme based on fuzzy logic for datacenter networks using the SDN architecture characteristics of control and forwarding separation, named LBSFL. The main parameters affecting the server load performance are analyzed and used as the input variables of fuzzy logic system to evaluate the server load, and then SDN controller schedules current network requests to achieve server load balancing. Additionally, we take into account the issue of server activation and deactivation under various traffic loads in this scheme. The experimental results show that the response time of the system can be increased by about 15% compared with LBBSRT, and it can also maintain the system load between the lower (30%) and normal (50%) boundaries. The scheme can greatly improve the load balance of servers under the premise of guaranteeing the network performance.
    Auto-Construction of Course Knowledge Graph based on Course Knowledge
    Peng Zhu, Wei Zhong, and Xianming Yao
    2019, 15(8): 2228-2236.  doi:10.23940/ijpe.19.08.p23.22282236
    Abstract    PDF (603KB)   
    References | Related Articles
    Course knowledge informationization increases the difficulties to present intrinsic connections among knowledge points in a visual way. This paper presents research on the auto-construction of course knowledge graphs based on knowledge graphs. Detailed questions regarding the auto-construction of course knowledge graphs are illustrated through a series of mature and reliable technical means. Additionally, this paper studies the application of course knowledge graph visualized navigation, providing new methods of course knowledge information construction and decreasing the learning costs for new knowledge.
    Deep Walk Algorithm based on Improved Random Walk with Equal Probability
    Zhonglin Ye, Haixing Zhao, Ke Zhang, Yanlin Yang, and Lei Meng
    2019, 15(8): 2237-2248.  doi:10.23940/ijpe.19.08.p24.22372248
    Abstract    PDF (879KB)   
    References | Related Articles
    Most of the existing network representation learning algorithms are mainly based on the DeepWalk algorithm. The main improvement is to modify DeepWalk's three-layer neural network to multi-layer neural network or to introduce the network's external attributes into the DeepWalk algorithm for joint representation learning. In network representation learning, the random walk strategy can be considered as network data preprocessing of network representation learning tasks. Learning the random walk sequences, including most of the network structure features, is very important for the network representation learning algorithm, because the subsequent training procedure of neural networks is to continuously adjust the representation of each node in the network based on the co-occurrence of node pairs. Therefore, the purpose of this paper is to improve the random walk strategy of the DeepWalk algorithm. We propose a novel DeepWalk algorithm based on the improved random walk with equal probability (EPDW). Although the next node in the random walk of the DeepWalk algorithm is chosen with equal probability, one of the neighbouring nodes of the current node is chosen as the next node of the random walk by the pseudo-random number. The improvement of EPDW is to choose the next hop node in the random walk using the roulette method of cumulative probability sum of random walk nodes. Although this method also chooses the next hop node with equal probability, it can choose the next hop random walk node more reasonably and effectively.
    A Comparison of Mobile Vehicles for Data Collection and Wireless Charging
    Yu Sheng, Weirong Liu, Yating Li, Ping Zhong, and Guihua Duan
    2019, 15(8): 2249-2257.  doi:10.23940/ijpe.19.08.p25.22492257
    Abstract    PDF (492KB)   
    References | Related Articles
    There are two ways to collect data and charge nodes based on mobile vehicles in wireless rechargeable sensor networks (WRSNs). One involves using single function vehicles, data collection vehicles (DCVs), and wireless charging vehicles (WCVs) to collect data and supply energy to sensors. The other involves using dual function vehicles, simultaneous data collection, and wireless charging vehicles (DC-WCVs) to gather data and supply energy to sensors. In order to compare and analyze the performance difference of these two ways, we classify and summarize related works in the field of mobile vehicles in sensor networks. Furthermore, we validate the network performance differences between the two ways through experimental verification and observe that the network lifetime and collected data amount are higher in networks using single function vehicles. The tour length of dual function vehicles is smaller in networks using dual function vehicles. Finally, we propose suitable vehicles to collect data and charge nodes for different optimization objectives.
    Heterogeneous Knowledge Fusion Algorithm for Minority Cultural Resources based on MapReduce
    Ying Liu, Juxiang Zhou, and Jianhou Gan
    2019, 15(8): 2258-2266.  doi:10.23940/ijpe.19.08.p26.22582266
    Abstract    PDF (624KB)   
    References | Related Articles
    Aiming at the shortcomings of current knowledge fusion methods and understanding the knowledge fusion algorithm in the big data environment, this paper proposes a heterogeneous knowledge fusion algorithm based on MapReduce for minority cultural resources. In order to improve the performance of the fusion algorithm, the algorithm is used in the similarity calculation. It is improved on the basis of the traditional attribute similarity calculation method. Based on the Hadoop platform and MapReduce framework, the experimental platform is validated. The experimental results show that the proposed MapReduce-based heterogeneous knowledge fusion algorithm for ethnic cultural resources is effective and feasible, both in terms of accuracy and effectiveness.
    Collaborative Filtering Algorithm based on Data Mixing and Filtering
    Xiaohui Cheng, Li Feng, and Qiong Gui
    2019, 15(8): 2267-2276.  doi:10.23940/ijpe.19.08.p27.22672276
    Abstract    PDF (562KB)   
    References | Related Articles
    Personalized recommendation systems based on the collaborative filtering algorithm are faced with an excessive user rating data sparseness problem. In order to solve this problem, an improved collaborative filtering algorithm is proposed, which gathers a variety of single numerical filling methods and selects a more appropriate filling method according to the filling rules to fill the vacant positions in the user-item scoring matrix filling. The recommendations are then made on the populated user-item score matrix through a user-based collaborative filtering approach. The method of data mixed filling can effectively reduce the recommended error and numerical singularity caused by fixed filling values such as the mean and median. The improved collaborative filtering algorithm is tested on the Movie Lens data set. The results show that the method of data mixing is adopted to fill the empty positions in the scoring matrix, which effectively alleviates the data sparsity problem in the collaborative filtering algorithm and improves the accuracy of recommendation systems for target users.
    Image Pixel Value Unification Digital Watermarking Embedding Method based on Quantum Key
    Jianan Wu, Di Zhang, Huan Wang, Dexin Zhu, and Lijun Song
    2019, 15(8): 2277-2284.  doi:10.23940/ijpe.19.08.p28.22772284
    Abstract    PDF (585KB)   
    References | Related Articles
    At present, most watermarking algorithms use pseudo-random number sequences as watermarks, and the design of the algorithm is more focused on improving the concealment and robustness. The common problem is poor security of the watermark itself. At the same time, the frequency domain algorithm also has poor concealment. Based on quantum secure communication technology, this paper proposes a new frequency domain watermark embedding and extraction algorithm for secure communication. The algorithm, based on the principle of the BB84 protocol, uses the quantum key with true randomness generated by the mechanism for distributing the quantum key as the data source for preparing watermarks. Simultaneously, the quantum key is combined with the frequency domain wavelet transform watermarking algorithm to embed and extract the watermark. The results indicate that the proposed algorithm has high security, the same robustness as the classical frequency domain watermarking algorithm, and higher concealment than the frequency domain watermarking algorithm.
ISSN 0973-1318