Current Issue

26 April 2019, Volume 30 Issue 2
Electronics Technology
No-reference image quality assessment based on AdaBoost BP neural network in wavelet domain
Junhua YAN, Xuehan BAI, Wanyi ZHANG, Yongqi XIAO, Chris CHATWIN, Rupert YOUNG, Phil BIRCH
2019, 30(2):  223-237.  doi:10.21629/JSEE.2019.02.01
Abstract ( )   HTML ( )   PDF (5219KB) ( )  
Figures and Tables | References | Related Articles | Metrics

Considering the relatively poor robustness of quality scores for different types of distortion and the lack of mechanism for determining distortion types, a no-reference image quality assessment (NR-IQA) method based on the AdaBoost BP neural network in the wavelet domain (WABNN) is proposed. A 36-dimensional image feature vector is constructed by extracting natural scene statistics (NSS) features and local information entropy features of the distorted image wavelet sub-band coefficients in three scales. The ABNN classifier is obtained by learning the relationship between image features and distortion types. The ABNN scorer is obtained by learning the relationship between image features and image quality scores. A series of contrast experiments are carried out in the laboratory of image and video engineering (LIVE) database and TID2013 database. Experimental results show the high accuracy of the distinguishing distortion type, the high consistency with subjective scores and the high robustness of the method for distorted images. Experiment results also show the independence of the database and the relatively high operation efficiency of this method.

Effective distributed convolutional neural network architecture for remote sensing images target classification with a pre-training approach
Binquan LI, Xiaohui HU
2019, 30(2):  238-244.  doi:10.21629/JSEE.2019.02.02
Abstract ( )   HTML ( )   PDF (627KB) ( )  
Figures and Tables | References | Related Articles | Metrics

How to recognize targets with similar appearances from remote sensing images (RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network (CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However, the training and testing of CNN mainly rely on single machine. Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure. When a model is complex or the training data is relatively small, overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore, Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Naïve Bayes classifier, a distributed Naïve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.

Closed-form algorithms for computing the intersection of two subspaces
Fenggang YAN, Shuai LIU, Jun WANG, Ming JIN
2019, 30(2):  245-250.  doi:10.21629/JSEE.2019.02.03
Abstract ( )   HTML ( )   PDF (385KB) ( )  
Figures and Tables | References | Related Articles | Metrics

Finding the intersection of two subspaces is of great interest in many fields of signal processing. Over several decades, there have been numerous formulas discovered to solve this problem, among which the alternate projection method (APM) is the most popular one. However, APM suffers from high computational complexity, especially for real-time applications. Moreover, APM only gives the projection instead of the orthogonal basis of two given subspaces. This paper presents two alternate algorithms which have a closed form and reduced complexity as compared to the APM technique. Numerical simulations are conducted to verify the correctness and the effectiveness of the proposed methods.

Two-channel model based adaptive schlieren detection algorithm for BOS system
Han LIU, Yanmei ZHANG, Baojun ZHAO, Haichao GUO, Boya ZHAO
2019, 30(2):  251-258.  doi:10.21629/JSEE.2019.02.04
Abstract ( )   HTML ( )   PDF (1008KB) ( )  
Figures and Tables | References | Related Articles | Metrics

A schlieren detection algorithm is proposed for the ground-to-air background oriented schlieren (BOS) system to achieve high-speed airplane shock waves visualization. The proposed method consists of three steps. Firstly, image registration is incorporated for reducing errors caused by the camera motion. Then, the background subtraction dual-model single Gaussian model (BS-DSGM) is proposed to build a precise background model. The BS-DSGM could prevent the background model from being contaminated by the shock waves. Finally, the twodimensional orthogonal discrete wavelet transformation is used to extract schlieren information and averaging schlieren data. Experimental results show our proposed algorithm is able to detect the aircraft in-flight and to extract the schlieren information. The precision of schlieren detection algorithm is 0.96. Three image quality evaluation indices are chosen for quantitative analysis of the shock waves visualization. The white Gaussian noise is added in the frames to validate the robustness of the proposed algorithm. Moreover, we adopt two times and four times down sampling to simulate different imaging distances for revealing how the imaging distance affects the schlieren information in the BOS system.

New normalized LMS adaptive filter with a variable regularization factor
Zhoufan LI, Dan LI, Xinlong XU, Jianqiu ZHANG
2019, 30(2):  259-269.  doi:10.21629/JSEE.2019.02.05
Abstract ( )   HTML ( )   PDF (386KB) ( )  
Figures and Tables | References | Related Articles | Metrics

A new normalized least mean square (NLMS) adaptive filter is first derived from a cost function, which incorporates the conventional one of the NLMS with a minimum-disturbance (MD) constraint. A variable regularization factor (RF) is then employed to control the contribution made by the MD constraint in the cost function. Analysis results show that the RF can be taken as a combination of the step size and regularization parameter in the conventional NLMS. This implies that these parameters can be jointly controlled by simply tuning the RF as the proposed algorithm does. It also demonstrates that the RF can accelerate the convergence rate of the proposed algorithm and its optimal value can be obtained by minimizing the squared noise-free posteriori error. A method for automatically determining the value of the RF is also presented, which is free of any prior knowledge of the noise. While simulation results verify the analytical ones, it is also illustrated that the performance of the proposed algorithm is superior to the state-of-art ones in both the steady-state misalignment and the convergence rate. A novel algorithm is proposed to solve some problems. Simulation results show the effectiveness of the proposed algorithm.

Defence Electronics Technology
Modified version of three-component model-based decomposition for polarimetric SAR data
Shuang ZHANG, Xiangchuan YU, Lu WANG
2019, 30(2):  270-277.  doi:10.21629/JSEE.2019.02.06
Abstract ( )   HTML ( )   PDF (827KB) ( )  
Figures and Tables | References | Related Articles | Metrics

A new hybrid Freeman/eigenvalue decomposition based on the orientation angle compensation and the various extended volume models for polarimetric synthetic aperture radar (PolSAR) data are presented. There are three steps in the novel version of the three-component model-based decomposition. Firstly, two special unitary transform matrices are applied on the coherency matrix for deorientation to decrease the correlation between the co-polarized term and the cross-polarized term. Secondly, two new conditions are proposed to distinguish the manmade structures and the nature media after the orientation angle compensation. Finally, in order to adapt to the scattering properties of different media, five different volume scattering models are used to decompose the coherency matrix. These new conditions pre-resolves man-made structures, which is beneficial to the subsequent selection of a more suitable volume scattering model. Fully PolSAR data on San Francisco are used in the experiments to prove the efficiency of the proposed hybrid Freeman/eigenvalue decomposition.

Performance gain bounds of coherently combining multiple radars in a target-based calibration manner
Xinghua LIU, Zhenhai XU, Shunping XIAO
2019, 30(2):  278-287.  doi:10.21629/JSEE.2019.02.07
Abstract ( )   HTML ( )   PDF (547KB) ( )  
Figures and Tables | References | Related Articles | Metrics

To achieve a high signal-to-noise ratio (SNR) while maintaining moderate radar antenna, a target-based calibration manner is available to coherently combine multiple radars. The key to this calibration manner is to estimate coherence parameters (CPs), i.e., time and phase calibration values in transmission and reception estimation, by separating the target returns into monostatic and bistatic echoes. However, CPs estimations exist uncertainties, which will affect the performance gain after multiradar coherent combination. The principle of coherently combining multiple radars is elaborated and the signal probability model for CPs estimation is established. On this basis, CPs Cramer-Rao bound (CRB) is derived in the closed-form, according to which the non-tight and tight upper bounds for multiple radars coherent combination performance gain are derived in the closed-form and via Monte Carlo (MC) simulations, respectively. Simulations validate the correctness of the derived CRB and gain bounds.

Systems Engineering
Modeling and solution based on stochastic games for development of COA under uncertainty
Chao CHEN, Zhengjun DU, Xingxing LIANG, Jianmai SHI, Hao ZHANG
2019, 30(2):  288-296.  doi:10.21629/JSEE.2019.02.08
Abstract ( )   HTML ( )   PDF (332KB) ( )  
Figures and Tables | References | Related Articles | Metrics

Developing a course of action (COA) is a key step in military planning. In most extant studies on the COA development, only the unilateral actions of friendly forces are considered. Based on stochastic games, we propose models that could deal with the complexities and uncertainties of wars. By analyzing the equilibrium state of both opponent sides, outcomes preferable to one side could be achieved by adopting the methods obtained from the proposed models. This research could help decision makers take the right COA in a state of uncertainty.

Threat evaluation method of warships formation air defense based on AR(p)-DITOPSIS
Haiwen SUN, Xiaofang XIE
2019, 30(2):  297-307.  doi:10.21629/JSEE.2019.02.09
Abstract ( )   HTML ( )   PDF (448KB) ( )  
Figures and Tables | References | Related Articles | Metrics

For the target threat evaluation of warships formation air defense, the sample data are frequently insufficient and even incomplete. The existing evaluation methods rely too much on expertise and are difficult to carry out for the dynamic evaluation on time series. In order to solve these problems, a threat evaluation method based on the AR(p) (auto regressive (AR))-dynamic improved technique for order preference by similarity to ideal solution (DITOPSIS) method is proposed. The AR(p) model is adopted to predict the missing data on the time series. Then, the entropy weight method is applied to solve each index weight at the objective point. Kullback-Leibler divergence (KLD) is used to improve the traditional TOPSIS, and to carry out the target threat evaluation. The Poisson distribution is used to assign the weight value. Simulation results show that the improved AR(p)-DITOPSIS threat evaluation method can synthetically take into account the target threat degree in time series and is more suitable for the threat evaluation under the condition of missing the target data than the traditional TOPSIS method.

Response surface methodology-based hybrid robust design optimization for complex product under mixed uncertainties
Liangqi WAN, Hongzhuan CHEN, Linhan OUYANG
2019, 30(2):  308-318.  doi:10.21629/JSEE.2019.02.10
Abstract ( )   HTML ( )   PDF (1594KB) ( )  
Figures and Tables | References | Related Articles | Metrics

Minimizing the impact of the mixed uncertainties (i.e., the aleatory uncertainty and the epistemic uncertainty) for a complex product of compliant mechanism (CPCM) quality improvement signifies a fascinating research topic to enhance the robustness. However, most of the existing works in the CPCM robust design optimization neglect the mixed uncertainties, which might result in an unstable design or even an infeasible design. To solve this issue, a response surface methodology-based hybrid robust design optimization (RSM-based HRDO) approach is proposed to improve the robustness of the quality characteristic for the CPCM via considering the mixed uncertainties in the robust design optimization. A bridge-type amplification mechanism is used to manifest the effectiveness of the proposed approach. The comparison results prove that the proposed approach can not only keep its superiority in the robustness, but also provide a robust scheme for optimizing the design parameters.

Evolutionary many objective optimization based on bidirectional decomposition
Chengzhong LYU, Weimin LI
2019, 30(2):  319-326.  doi:10.21629/JSEE.2019.02.11
Abstract ( )   HTML ( )   PDF (747KB) ( )  
Figures and Tables | References | Related Articles | Metrics

The decomposition based approach decomposes a multi-objective problem into a series of single objective subproblems, which are optimized along contours towards the ideal point. But non-dominated solutions cannot spread uniformly, since the Pareto front shows different features, such as concave and convex. To improve the distribution uniformity of non-dominated solutions, a bidirectional decomposition based approach that constructs two search directions is proposed to provide a uniform distribution no matter what features problems have. Since two populations along two search directions show differently on diversity and convergence, an adaptive neighborhood selection approach is presented to choose suitable parents for the offspring generation. In order to avoid the problem of the shrinking search region caused by the close distance of the ideal and nadir points, a reference point update approach is presented. The performance of the proposed algorithm is validated with four state-of-the-art algorithms. Experimental results demonstrate the superiority of the proposed algorithm on all considered test problems.

Hybrid heuristic algorithm for multi-objective scheduling problem
Jian'gang PENG, Mingzhou LIU, Xi ZHANG, Lin LING
2019, 30(2):  327-342.  doi:10.21629/JSEE.2019.02.12
Abstract ( )   HTML ( )   PDF (1317KB) ( )  
Figures and Tables | References | Related Articles | Metrics

This research provides academic and practical contributions. From a theoretical standpoint, a hybrid harmony search (HS) algorithm, namely the oppositional global-based HS (OGHS), is proposed for solving the multi-objective flexible job-shop scheduling problems (MOFJSPs) to minimize makespan, total machine workload and critical machine workload. An initialization program embedded in opposition-based learning (OBL) is developed for enabling the individuals to scatter in a well-distributed manner in the initial harmony memory (HM). In addition, the recursive halving technique based on opposite number is employed for shrinking the neighbourhood space in the searching phase of the OGHS. From a practice-related standpoint, a type of dual vector code technique is introduced for allowing the OGHS algorithm to adapt the discrete nature of the MOFJSP. Two practical techniques, namely Pareto optimality and technique for order preference by similarity to an ideal solution (TOPSIS), are implemented for solving the MOFJSP. Furthermore, the algorithm performance is tested by using different strategies, including OBL and recursive halving, and the OGHS is compared with existing algorithms in the latest studies. Experimental results on representative examples validate the performance of the proposed algorithm for solving the MOFJSP.

Resource allocation approach to associate business-IT alignment to enterprise architecture design
Mengmeng ZHANG, Honghui CHEN, Junxian LIU
2019, 30(2):  343-351.  doi:10.21629/JSEE.2019.02.13
Abstract ( )   HTML ( )   PDF (552KB) ( )  
Figures and Tables | References | Related Articles | Metrics

Enterprise architecture (EA) development is always a superior way to address business-IT alignment (BITA) issue. However, most EA design frameworks are inadequate to allocate IT resources, which is an important metric of BITA maturity. Under this situation, the idea of IT resource allocation is combined with the EA design process, in order to extend prior EA research on BITA and to demonstrate EAos capability of implementing IT governance. As an effective resource allocation method, portfolio decision analysis (PDA) is used to align business functions of business architecture and applications of system architecture. Furthermore, this paper exhibits an illustrative case with the proposed framework.

Antlion optimizer algorithm based on chaos search and its application
Zhenxing ZHANG, Rennong YANG, Huanyu LI, Yuhuan FANG, Zhenyu HUANG, Ying ZHANG
2019, 30(2):  352-365.  doi:10.21629/JSEE.2019.02.14
Abstract ( )   HTML ( )   PDF (2132KB) ( )  
Figures and Tables | References | Related Articles | Metrics

Aiming at the problems of premature convergence and easily falling into local optimums of the antlion optimization algorithm, a chaos antlion optimization algorithm based on the chaos search is proposed. Firstly, in the algorithm, the population is initialized by using the tent chaotic mapping, and the self-adaptive dynamic adjustment of chaotic search scopes is proposed in order to improve the overall fitness and the optimization efficiency of the population. Then, the tournament strategy is used to select antlions. Finally, the logistic chaos operator is used to optimize the random walk of ants, which forms a global and local parallel search mode with the antlionos foraging behavior. The performance algorithm is tested through 13 complex high-dimensional benchmark functions and three dimensional path planning problems. The experimental results of six complex high-dimensional benchmark functions show that the presented algorithm has a better convergence speed and precision than the standard antlion algorithm and other optimization algorithms, and is suitable for the optimization of complex high dimensional functions. The trajectory planning experimental results show that compared with the antlion optimizer (ALO) algorithm, grey wolf optimizer (GWO), particle swarm optimization (PSO) and artificial bee colony (ABC) algorithm, it has advantages in speed and accuracy to obtain a specific path, and it is of great value in actual problems.

Control Theory and Application
Smart homing guidance strategy with control saturation against a cooperative target-defender team
Hang GUO, Wenxing FU, Bin FU, Kang CHEN, NJie YA
2019, 30(2):  366-383.  doi:10.21629/JSEE.2019.02.15
Abstract ( )   HTML ( )   PDF (1082KB) ( )  
Figures and Tables | References | Related Articles | Metrics

A smart homing guidance strategy with control saturation against a target-defender team is derived. It is noteworthy that a cooperative strategy of the target-defender team is applied, which has been proved more challenging for the homing guidance. The defender missile is launched by the target and guided by a cooperative augmented proportional navigation (APN). At the same time, the target performs a one-switch maneuver to cooperate and minimize the defenderos acceleration requirement. The problem is analyzed for arbitrary-order linear dynamics of the agents in the linearized form but validated by the mathematical simulations by using nonlinear kinematics. The perfect information of three agentso states is assumed. Then, a method to deal with the target-defender team is proposed. It contains a combined performance index penalizing the miss distance relative to the target and energy consumption in the whole duration. Besides, the specific miss distance related to the defender is regarded as an inequality constraint. An analytical solution for the smart guidance strategy against the APN guided defender is derived. Meanwhile, the control saturations are introduced to get more realistic and reasonable insights to this practical target-missile-defender problem. A simple but effective iterative searching technique is proposed to determine the saturation time points. The solution provides an optimal homing strategy to evade the defender with a specific miss distance and intercept the target with the minimum miss distance in the minimum energy manner. Nonlinear two-dimensional simulation results are used to validate the theoretical analysis. By comparison with the optimal differential game guidance (ODGG) and the combined minimum effort guidance (CMEG), the superiority of this smart guidance strategy is concluded.

Fixed-wing UAV guidance law for ground target over-flight tracking
Min ZHANG, Chenming ZHENG, Kun HUANG
2019, 30(2):  384-392.  doi:10.21629/JSEE.2019.02.16
Abstract ( )   HTML ( )   PDF (647KB) ( )  
Figures and Tables | References | Related Articles | Metrics

This paper studies the problem of tracking a ground target for a fixed-wing unmanned aerial vehicle (UAV) based on the proposed guidance law. The algorithm ensures that a UAV continuously overflies the target whether it is fixed or moving. The requirements of the UAV flight constraints such as bounded airspeed and acceleration are considered. A Lyapunov function is constructed to prove the stability of the proposed guidance law, and parameter design criteria have been developed. Considering the fixed and moving ground targets, numerical simulations are performed to verify the feasibility and benefits of the proposed guidance algorithm.

Sensor management of LEO constellation based on covariance control
Zheng QIN, Yan'gang LIANG
2019, 30(2):  393-401.  doi:10.21629/JSEE.2019.02.17
Abstract ( )   HTML ( )   PDF (513KB) ( )  
Figures and Tables | References | Related Articles | Metrics

This paper studies the multi-sensor management problem for low earth orbit (LEO) infrared warning constellation used to track a midcourse missile. A covariance control approach, which selects sensor combinations or subset based on the difference between the desired covariance matrix and the actual covariance of each target, is used for sensor management, including some matrix metrics to measure the differentia between two covariance matrices. Besides, to meet the requirements of the space based warning system, the original covariance control approach is improved. Simulation results demonstrate that the covariance control approach is able to provide a better tracking performance by providing a well-designed desired covariance and balance tracking performance goals with system demands.

MAV/UAV task coalition phased-formation method
Zhiqiang JIAO, Peiyang YAO, Jieyong ZHANG, Yun ZHONG, Xun WANG
2019, 30(2):  402-414.  doi:10.21629/JSEE.2019.02.18
Abstract ( )   HTML ( )   PDF (622KB) ( )  
Figures and Tables | References | Related Articles | Metrics

The formation of the manned aerial vehicle/unmanned aerial vehicle (MAV/UAV) task coalition is considered. To reduce the scale of the problem, the formation progress is divided into three phases. For the task clustering phase, the geographical position of tasks is taken into consideration and a cluster method is proposed. For the UAV allocation phase, the UAV requirement for both constrained and unconstrained resources is introduced, and a multi-objective optimal algorithm is proposed to solve the allocation problem. For the MAV allocation phase, the optimal model is firstly constructed and it is decomposed according to the ideal of greed to reduce the time complexity of the algorithm. Based on the above phases, the MAV/UAV task coalition formation method is proposed and the effectiveness and practicability are demonstrated by simulation examples.

Consistency check of degradation mechanism between natural storage and enhancement test for missile servo system
Xu Wang, Quan Sun
2019, 30(2):  415-424.  doi:10.21629/JSEE.2019.02.19
Abstract ( )   HTML ( )   PDF (527KB) ( )  
Figures and Tables | References | Related Articles | Metrics

Reliability enhancement testing (RET) is an accelerated testing which hastens the performance degradation process to surface its inherent defects of design and manufacture. It is an important hypothesis that the degradation mechanism of the RET is the same as the one of the normal stress condition. In order to check the consistency of two mechanisms, we conduct two enhancement tests with a missile servo system as an object of the study, and preprocess two sets of test data to establish the accelerated degradation models regarding the temperature change rate that is assumed to be the main applied stress of the servo system during the natural storage. Based on the accelerated degradation models and natural storage profile of the servo system, we provide and demonstrate a procedure to check the consistency of two mechanisms by checking the correlation and difference of two sets of degradation data. The results indicate that the two degradation mechanisms are significantly consistent with each other.

Optimal selection of tests for fault detection and isolation in multi-operating mode system
Yuanhong LIU
2019, 30(2):  425-434.  doi:10.21629/JSEE.2019.02.20
Abstract ( )   HTML ( )   PDF (248KB) ( )  
Figures and Tables | References | Related Articles | Metrics

The complex systems are often in the structure of multi-operating modes, and the components implementing system functions are different under different operation modes, which results in the problems that components often fail in different operating modes, faults can be only detected in specified operating modes, tests can be available in specified operating modes, and the cost and efficiency of detecting and isolating faults are different under different operating modes and isolation levels. Aiming at these problems, an optimal test selection method for fault detection and isolation in the multi-operating mode system is proposed by using the fault pair coding and rollout algorithm. Firstly, the faults in fault-test correlation matrices under different operating modes are combined to fault-pairs, which is used to construct the fault pair-test correlation matrices under different operating modes. Secondly, the final fault pair-test correlation matrix of the multioperating mode system is obtained by operating the fault pair-test correlation matrices under different operating modes. Based on the final fault pair-test correlation matrix, the necessary tests are selected by the rollout algorithm orderly. Finally, the effectiveness of the proposed method is verified by examples of the optimal test selection in the multi-operating mode system with faults isolated to different levels. The result shows that the proposed method can effectively mine the fault detection and isolation ability of tests and it is suitable for the optimal test selection of the multi-operating mode system with faults isolated to the replacement unit and specific fault.