Office

Top Read Articles

    Published in last 1 year |  In last 2 years |  In last 3 years |  All
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Detection method for a dynamic small target using the improved YOLOv3
    CUI Yanpeng,WANG Yuanhao,HU Jianwei
    Journal of Xidian University    2020, 47 (3): 1-7.   DOI: 10.19665/j.issn1001-2400.2020.03.001
    Abstract490)   HTML60)    PDF(pc) (1988KB)(407)       Save

    The visual characteristics of low-altitude drones are less obvious and the scale changes during the detection process. Traditional detection methods are susceptible to interference during detection, and most of those methods cannot work quickly and robustly. To solve this problem, a real-time drone detection algorithm combined with the improved YOLOv3 model and the super resolution method is proposed in this paper. First, frame difference is used to propose the candidate area, and the super-resolution method is used to strengthen the details. Then the dimensional clustering algorithm is used to regenerate the anchors for the model, and the model is slightly adjusted. Finally, we use the improved YOLOv3 to scan both the whole frame and the processed candidate area so as to detect the drones. The frame relationship is also used to implement tracking of drones by real-time detection. With GPU (GTX 1070Ti) acceleration, the method works at a speed of about 20FPS and has an accuracy rate of 96.8% and a recall rate of 95.6%. The results prove that the method can detect drones in different complex backgrounds with a considerable effective detection distance. Compared with the traditional method or normal machine learning method, our method is of a certain theoretical and practical value.

    Table and Figures | Reference | Related Articles | Metrics
    Design and analysis of an improved OMU-NRDCSK communication system
    ZHANG Gang,LIU Jinhui,ZHANG Peng
    Journal of Xidian University    2020, 47 (4): 1-9.   DOI: 10.19665/j.issn1001-2400.2020.04.001
    Abstract458)   HTML195)    PDF(pc) (1356KB)(389)       Save

    Aiming at the shortcomings of a low transmission rate in traditional Differential Chaos Shift Keying (DCSK) and a high bite error rate when transmitting multi-user information, an improved orthogonal multi-user noise reduction differential chaotic keying (OMU-NRDCSK) is proposed. The chaotic sequence generated at the sending end of the system is used as an information bearing signal after being duplicated, the multi-users’ information modulated by the Walsh codes are transmitted respectively through different delays. At the receiver, after passing through the moving average filter, the received signals are correlated with themselves to demodulate the initial information signals. The bit error rate formula for the system under the Rayleigh fading channel is derived and Monte Carlo simulation is carried out. Analytical and simulation results show that the OMU-NRDCSK system reduces the noise term variance by averaging the received signals and improves the bit error performance, with its transmission rate improved compared to the DCSK system, which effectively improves the bit error performance of the multi-user DCSK system.

    Table and Figures | Reference | Related Articles | Metrics
    360-degree real-time stitching technology for multi-channel video
    HUANG Zhangqin,MU Zhao,CEN Chen,GAO Han
    Journal of Xidian University    2020, 47 (2): 1-8.   DOI: 10.19665/j.issn1001-2400.2020.02.001
    Abstract442)   HTML128)    PDF(pc) (2402KB)(361)       Save

    Aiming at the time-consuming problem of image registration in video mosaic, a combined algorithm based on the BRISK and GMS is designed and optimized. Based on the fast feature extraction feature of the BRISK, the grid image method is used to divide the overlap region image to make the feature point distribution more uniform, thus reducing the number of feature points that need to be operated. In the feature matching stage after feature extraction, the GMS is used to eliminate the mismatching pair, and improves the matching accuracy according to the two-way matching strategy. In order to make the image fusion more natural and smooth, this paper designs a regionalized feather blending weighted fusion algorithm. To reduce the error in solving the overlapping area, the fusion area is constructed and divided into regions. The best suture method is used to get the seam. The gradual in and out weighting algorithm is used in different regions to achieve image fusion, so as to obtain the panoramic image with higher fusion quality. Finally, a complete prototype of the panoramic video stitching system is designed. The feasibility and practicability of the system scheme are verified by experiments which show that, compared with the traditional video splicing technology, this algorithm ensures the real-time performance of video splicing while eliminating the ghosting and seaming problems that occur during splicing.

    Table and Figures | Reference | Related Articles | Metrics
    Method for comprehensive evaluation of effectiveness of radar emitter signals recognition
    LIU Mingqian,MENG Yan,ZHANG Weidong
    Journal of Xidian University    2019, 46 (6): 1-8.   DOI: 10.19665/j.issn1001-2400.2019.06.001
    Abstract288)   HTML332)    PDF(pc) (922KB)(212)       Save

    Aiming at the problems of the existing evaluation methods, such as unscientific index weight setting and unreasonable evaluation method, a method for comprehensive evaluation of the radar radiation source signal identification efficiency is proposed. The performance evaluation index system based on the effect of radar radiation source signal recognition is first established. And then, under the evaluation criteria, an intuitionistic fuzzy network analysis method is used to analyze the indexes with the characteristics of relevance to solve the index weight. Finally, on the basis of the interval-valued hesitant fuzzy idea, the ranking priority relation is established by combining the elimination and selection conversion method and approximate ideal ranking method to realize the comprehensive evaluation of the effectiveness of radar radiation source signal identification. Simulation results show that the method proposed can obtain a reasonable evaluation order of the effectiveness of the radar source signal identification method. Compared with the existing methods, the proposed method can reasonably and effectively solve the problem of index correlation, and avoid the error evaluation caused by the defects of the evaluation method.

    Table and Figures | Reference | Related Articles | Metrics
    Improved face image classification method based on the local embedding network
    LIU Daohua,WANG Shasha,YANG Zhipeng,CUI Yushuang
    Journal of Xidian University    2020, 47 (4): 18-23.   DOI: 10.19665/j.issn1001-2400.2020.04.003
    Abstract198)   HTML40)    PDF(pc) (1374KB)(119)       Save

    In order to improve the accuracy of facial expression recognition and face classification in a local linear embedding network, an improved face image classification method based on the local linear embedding network is proposed. Based on the local linear embedding algorithm, the intra-class to inter-class discrimination matrix is used as the input of the network. At the same time, the reconstruction of the face image set is used to improve the local linear embedding algorithm, and the improvement of the local linear embedding algorithm based on clustering is embedded into the construction process of the convolution kernel, thus increasing the discrimination degree of different types of faces. By the Extended Yale B data set and Olivetti Research Laboratory data set on the contrast experiment, the experiment is analyzed in the treatment of facial expressions and the effects of various methods in the face recognition task, the results show that, compared with the other methods, the recognition rate of the proposed improved locally linear embedding network face image classification method is raised by 11%~26%.

    Table and Figures | Reference | Related Articles | Metrics
    Algorithm for recursive Bayesian localization triggered by temporalseries measurement information
    QIN Ningning,WANG Chao
    Journal of Xidian University    2020, 47 (4): 10-17.   DOI: 10.19665/j.issn1001-2400.2020.04.002
    Abstract176)   HTML36)    PDF(pc) (1445KB)(99)       Save

    To improve the robustness of a position system and reduce the localization error, this paper proposes a fingerprint positioning method based on the recursive Bayesian. To solve the blindness and unreliability of the location fingerprint data in an offline phase, the fingerprint database based on the sample variance is developed to measure the confidence of sampling values and reduce the impact of environmental factors, improving the reliability for online localization. The proposed method provides the target position at the current moment by utilizing the Markov model that is established by the constraint relationship between moments in the source movement, which avoids the jump problem of the position estimation and poor robustness and improves the localization accuracy. Extensive experimental results demonstrate that the average localization error norm of the proposed algorithm is no more than 0.927m, indicating significantly lower errors than other traditional schemes (often by more than 30 percent).

    Table and Figures | Reference | Related Articles | Metrics
    Classifying health questions with local semantic and global structural information
    ZHANG Zhichang,ZHANG Zhiman,ZHANG Zhenwen
    Journal of Xidian University    2020, 47 (2): 9-15.   DOI: 10.19665/j.issn1001-2400.2020.02.002
    Abstract173)   HTML29)    PDF(pc) (1328KB)(97)       Save

    Considering the shortcomings of existing research methods in the Chinese medical health questions classification task, this paper proposes a new health questions classification method that incorporates the health questions’ local semantic information and global structural information. We first obtain the questions’ local semantic representation and global structural representation by the convolutional neural network (CNN) and independent recurrent neural network (IndRNN). Then, we extract the questions’ semantic representation, and especially we get the questions’ semantic representation by fusing the local semantic representation and global structural representation using a self-attention mechanism. Finally, we classify the semantic representation of the medical health question through the softmax layer and output classification result. Experimental results show that this method leads to a good performance in the Chinese medical health questions dataset, and that it effectively improves the semantic representation ability of the model and significantly resolves the gradient vanishing and gradient explosion problems.

    Table and Figures | Reference | Related Articles | Metrics
    Design and performance analysis of the PQMC-NRCDSK
    ZHANG Gang,HUANG Nanfei,ZHANG Tianqi
    Journal of Xidian University    2020, 47 (1): 1-9.   DOI: 10.19665/j.issn1001-2400.2020.01.001
    Abstract156)   HTML29)    PDF(pc) (3160KB)(112)       Save

    Aiming at the problems of a low information rate and the poor bit error performance of traditional chaotic keying schemes, a Phase Quadrature Multi-Carrier Noise Reduction Correlated Delay Shift Keying (PQMC-NRCDSK) scheme is proposed. In this scheme, the superposition of chaotic sequence and its time delay sequence is used as the reference signal, and the product of the chaotic sequence and its time delay sequence with data information is used as the information bearing signal. The reference signal and information bearing signal are transmitted by the carrier with different frequencies and quadrature phase, and multiple antennas are used to transmit and acquire signals at the sender and receiver, respectively. The error performance of this scheme in the multi-path fading channel is studied in detail and verified by theoretical analysis and experimental verification. Experimental results show that the theoretical analysis is consistent with the simulation results, and the correctness of the theoretical analysis is verified. The information rate of the PQMC-NRCDSK scheme is higher than that of the MC-CDSK and CDSK schemes under the same carrier number, and is twice as high as that of the MC-CDSK scheme. On the other hand, the error performance of the PQMC-NRCDSK scheme is obviously better than that of the above schemes.

    Table and Figures | Reference | Related Articles | Metrics
    Algorithm for extraction of features of robot speech control in the factory environment
    WANG Xiaohua,YAO Pengchao,MA Liping,WANG Wenjie,ZHANG Lei
    Journal of Xidian University    2020, 47 (2): 16-22.   DOI: 10.19665/j.issn1001-2400.2020.02.003
    Abstract147)   HTML27)    PDF(pc) (1670KB)(91)       Save

    In the real working environment,the mobile robots have a poor recognition performance to speech control commands due to the noise effect. Aiming at this issue,this paper proposes a new algorithm based on the gammatone frequency cepstral coefficient and the mixed feature extraction of the Teager energy operator. This algorithm replaces the common Mel filter with the Gammatone filter. In the process of extracting gammatone frequency cepstral coefficients,the Teager energy operator reflecting the energy of speech signal is added to form a new feature, with the dynamic characteristics of the speech signal considered. It is combined with the first-order difference parameters to form a mixed feature. And the principal component analysis is made to reduce the dimension,and the final mixed features are used to the speech recognition system for control command of the mobile robot. Experimental results show that,in the environment of the workshop noise and signal-to-noise ratio of 10dB,the recognition rate of mixed features is improved by 12.20% compared with the mel frequency cepstrum coefficient. The recognition rate of the mixed feature is increased by 1.02% when the dimension is reduced by principal component analysis.

    Table and Figures | Reference | Related Articles | Metrics
    Network security situation adaptive prediction model
    YANG Hongyu,ZHANG Xugao
    Journal of Xidian University    2020, 47 (3): 14-22.   DOI: 10.19665/j.issn1001-2400.2020.03.003
    Abstract142)   HTML24)    PDF(pc) (1380KB)(85)       Save

    Aiming at the low prediction accuracy of traditional network security situation prediction technology, a network security situation adaptive prediction model (NAP) is proposed. First, it extracts alarm elements and calculate network security situation time sequences based on the entropy correlation method. Then, the sequences are taken as the input of the sliding adaptive cubic exponential smoothing method with initial security situation predicted value sequences generated. Finally, the time-varying weighted Markov chain is used to predict the error value based on the error state and the initial predicted values are modified. Experimental results show that the NAP has a better prediction accuracy than other existing models.

    Table and Figures | Reference | Related Articles | Metrics
    Design and optimization of the piezoelectric micromechanical ultrasonic transducer with an AlN thin film
    LOU Lifei,ZHAO Jianxin,LIANG Ya’nan,ZHAO Mingyang,AN Zaifang
    Journal of Xidian University    2020, 47 (3): 8-13.   DOI: 10.19665/j.issn1001-2400.2020.03.002
    Abstract135)   HTML18)    PDF(pc) (1433KB)(73)       Save

    Because existing ultrasonic transducers mostly use PZT and ZnO materials as piezoelectric thin films, while the PZT contains lead and ZnO has the problem of contaminating CMOS manufacturing, a piezoelectric ultrasonic micromechanical transducer with circular bi-laminate bending vibration which uses the aluminium nitride as the piezoelectric layer is designed. The working principle of the transducer is analyzed, the finite element model is established, and the finite element simulation is carried out for the size parameters of the transducer. It is found that the resonant frequency of the transducer is proportional to the thickness of each layer and inversely proportional to the square of the radius of the transducer; when the radius of the upper electrode is about 65% of the radius of the transducer, the resonant amplitude of the transducer is the largest; when the thickness ratio of the silicon and the aluminum nitride of the piezoelectric layer is about 0.6, the resonant amplitude is also the largest. The optimized transducer is simulated and compared with the original model. The results show that the working frequency in air is 9.21MHz, the electromechanical coupling coefficient increases from 21.44% to 27.16% in air and from 3.55% to 11.93% in water. These conclusions provide basic data for the research on the medical imaging probe.

    Table and Figures | Reference | Related Articles | Metrics
    Pedestrian trajectory prediction model with social features and attention
    ZHANG Zhiyuan,DIAO Yinghua
    Journal of Xidian University    2020, 47 (1): 10-17.   DOI: 10.19665/j.issn1001-2400.2020.01.002
    Abstract116)   HTML22)    PDF(pc) (1776KB)(61)       Save

    To address the problems that the pedestrian interaction feature of the Social GAN is simple and that it cannot make full use of the most of pedestrian interaction information, this paper proposes a pedestrian trajectory prediction model with social features and attention mechanism. This model adapts the structure of generative adversarial networks. The generator adapts an encoder-decoder model and the attention model is put between encoder and decoder. Three social features are set to enrich pedestrian interaction information which assists the attention module to make full use of the most of pedestrian interaction information by allocating the influence of pedestrians in the scene, so that the accuracy of the model is improved. Experimental results on multiple datasets show that the accuracy of this model in the pedestrian trajectory prediction task is increased by 15% compared with the previous pedestrian trajectory prediction model based on the pooling module. The improvement effect is most obvious in scenes with dense pedestrians and lots of non-straight tracks, with the accuracy increased by 34%.

    Table and Figures | Reference | Related Articles | Metrics
    Urban sound event classification with the N-order dense convolutional network
    CAO Yi,HUANG Zilong,ZHANG Wei,LIU Chen,LI Wei
    Journal of Xidian University    2019, 46 (6): 9-16.   DOI: 10.19665/j.issn1001-2400.2019.06.002
    Abstract116)   HTML99)    PDF(pc) (1484KB)(60)       Save

    An urban sound event classification model based on the N-order Dense Convolutional Network (abbreviated to N-DenseNet) is proposed for the problems of insufficient classification accuracy and generalization ability of existing models. First, the network structure of the DenseNet is briefly introduced. Then, dense connection in the DenseNet is improved by N-order state-dependent connection based on the N-order Markov model. Furthermore, combining advantages of both the DenseNet and N-order Markov, a novel network architecture, i.e., the N-DenseNet, is proposed in this paper. Theoretically, the N-DenseNet satisfying the premise of alleviating vanishing-gradient, can not only produce efficient integration of feature information from the layers, but also accelerate the convergence speed. Finally, in order to validate advantages of the new model, 1-DenseNet and 2-DenseNet are respectively exploited in the urban sound event classification based on the UrbanSound8K and Dcase2016 dataset. Experimental results show that the accuracy of the two above-mentioned models is respectively 83.63% and 81.03%, which also demonstrates a higher classification accuracy and a better generalization performance of the N-DenseNet.

    Table and Figures | Reference | Related Articles | Metrics
    Hardware Trojan detection algorithm based on deep learning
    LIU Zhiqiang,ZHANG Mingjin,CHI Yuan,LI Yunsong
    Journal of Xidian University    2019, 46 (6): 37-45.   DOI: 10.19665/j.issn1001-2400.2019.06.006
    Abstract108)   HTML20)    PDF(pc) (2535KB)(50)       Save

    The traditional way of hardware trojan detection based on electrical signal detection has problems of low positive rate, low efficiency and high cost. To solve these problems, we propose a new way of hardware trojan detection based on deep learning which is not electrical signal detection. First, the algorithm changes chip microscopic images of low resolution into chip microscopic images of high resolution by using an enhanced residual network. Then these chip microscopic images of high resolution will generate another chip microscopic images which are similar to those of the golden model. The algorithm for image enhancement distinguishes between target area and background area by combining with the algorithm of image segmentation. Finally, we use the change detection algorithm to detect the hardware trojans existing in the chip after removing minor interference due to industrial noise. Through the experiments on the micrograph dataset of the chip, the positive detection rate of the hardware trojan detection method based on deep learning is as high as 92.4%. Compared with the traditional electrical signal detection method, our algorithm has the advantages of higher precision, faster speed, and easier operation.

    Table and Figures | Reference | Related Articles | Metrics
    Approach to FPGA placement using resource negotiation
    WANG Dekui
    Journal of Xidian University    2019, 46 (6): 17-22.   DOI: 10.19665/j.issn1001-2400.2019.06.003
    Abstract107)   HTML96)    PDF(pc) (805KB)(66)       Save

    Placement is one of the most time-consuming steps of the Field Programmable Gate Array (FPGA) computer aided design flow. In order to accelerate the placement step, a novel approach to FPGA placement is proposed. First, circuit logic blocks choose to use the lowest cost physical resources, and it is allowed that multiple logic blocks share the same resource. Second, the logic blocks using the overused physical resources are re-placed iteratively; the cost of the overused resources is gradually increased, thus eliminating the overuse of the physical resources progressively. Finally, the low-temperature simulated annealing algorithm is applied to optimize the placement result. Experimental results show that the proposed approach reduces the placement runtime by 52% compared with the state-of-the art placement tool, with a reduction of critical path delay and total wirelength by 4.8% and 1.9%, respectively. The proposed approach significantly accelerates the FPGA placement and hence shortens the compile-debug cycle of circuits, which is helpful to improving the efficiency of the developers.

    Table and Figures | Reference | Related Articles | Metrics
    Analysis of targeted sentiment by the attention gated convolutional network model
    CAO Weidong,LI Jiaqi,WANG Huaichao
    Journal of Xidian University    2019, 46 (6): 30-36.   DOI: 10.19665/j.issn1001-2400.2019.06.005
    Abstract96)   HTML10)    PDF(pc) (1108KB)(46)       Save

    The recurrent neural networks are used for traditional targeted sentiment analysis and usually lead to a long training time. And other alternative models are unable to make a good interaction between context and target words. An attention gated convolutional network model for targeted sentiment analysis is proposed. First, context and target words are processed by the multiple attention mechanism to enhance their interactions. Second, the gated convolution mechanism is used to selectively generate emotional features. Finally, the emotional features are classified by the Softmax classifier to output the emotional polarity. Experimental results show that compared with the Recurrent Attention Network model, which has the highest accuracy rate in the recurrent neural network models, the proposed model improves the accuracy rate by 1.29% and 0.12% respectively on the Restaurant and Laptop datasets of SemEval 2014 Task4. Compared with the Attention-based Long Short-Term Memory Network model, which has a faster convergence rate in the recurrent neural network model, the convergence time is reduced by 29.17 s.

    Table and Figures | Reference | Related Articles | Metrics
    Detection of the airborne MIMO radar moving target in the non-Gaussian clutter
    ZHANG Yanfei,SUN Wenjie,SUN Yumei,MENG Xiangwei,CHEN Xiangguang
    Journal of Xidian University    2020, 47 (3): 23-31.   DOI: 10.19665/j.issn1001-2400.2020.03.004
    Abstract95)   HTML14)    PDF(pc) (1308KB)(65)       Save

    Due to the moving platforms, the clutters in distributed airborne MIMO radar are non-Gaussian and non-homogeneous, which leads to having no independent and identically distributed training data to estimate the clutter covariance matrix. To solve the problem, we propose that the covariance of the clutter should be modeled as an inverse complex Wishart distribution whose average value is a Hadamard product of the covariance matrix taper (CMT) and the clutter Doppler spectrum component. Based on this clutter model, a novel detector combing the Bayesian approach and the generalized likelihood ratio test(GLRT) is proposed. Numerical simulation results show that the proposed detector has a better detection performance compared with two current commonly used non-Bayesian detectors.

    Table and Figures | Reference | Related Articles | Metrics
    Lightweight deep neural network for point cloud classification
    YAN Lin,LIU Kai,DUAN Meiyu
    Journal of Xidian University    2020, 47 (2): 46-53.   DOI: 10.19665/j.issn1001-2400.2020.02.007
    Abstract91)   HTML11)    PDF(pc) (1824KB)(52)       Save

    For point cloud classification, deep learning based methods use operations like voxelization to generate regular 3D grids or render the 3D mesh into a collection of images from multiple angles. However, the conversion will introduce additional computing and storage consumption. Some methods directly consume the raw point cloud. But their network scale and computational complexity make it difficult for them to deploy in embedded environments. On the basis of intensive studies of these algorithms, a novel lightweight dual path way network is proposed in this paper. Without additional conversion, our network attains a comparable performance but has 0.8 million floating parameters only. With point-wise and neighbor-wise representations, our approach incorporates global and local features of the point cloud. Experimental results on ModelNet40 and MNIST data-set demonstrate that our method achieves a good accuracy, and prove the effectiveness of our design.

    Table and Figures | Reference | Related Articles | Metrics
    Optimization algorithm for estimating the human pose by using the morphable model
    LI Jian,ZHANG Haoruo,HE Bin
    Journal of Xidian University    2020, 47 (2): 23-31.   DOI: 10.19665/j.issn1001-2400.2020.02.004
    Abstract87)   HTML9)    PDF(pc) (5771KB)(60)       Save

    An optimization algorithm is proposed utilizing the video data and point cloud data captured by the depth camera to solve the problems such as error-proneness and incoherence of motion sequence caused by the existing human pose estimation algorithms based on the morphable model. For video data, the neural network is first used in extracting the model parameters from each color image frame. Next, the human key-points and contour constraint are considered to optimize the above parameters. Then the coherence between every two consecutive frames is utilized to correct the error of pose estimation, thus making the resulting motion sequence smoother. In addition, the point cloud and the model obtained from the corresponding color image frame are used as the joint input to further improve the estimation accuracy. Finally, the distance between the point cloud and the corresponding point of the model is constrained to be as small as possible to obtain a more reasonable solution. The proposed algorithm and the state-of-the-art algorithms are compared qualitatively and quantitatively on the data set and real video set. Experimental results show that the algorithm can effectively correct the error and incoherence in the single-frame pose estimation results and greatly improve the accuracy when using point cloud data optimization.

    Table and Figures | Reference | Related Articles | Metrics
    Improved algorithm for detection of the malicious domain name based on the convolutional neural network
    YANG Luhui,LIU Guangjie,ZHAI Jiangtao,LIU Weiwei,BAI Huiwen,DAI Yuewei
    Journal of Xidian University    2020, 47 (1): 37-43.   DOI: 10.19665/j.issn1001-2400.2020.01.006
    Abstract87)   HTML11)    PDF(pc) (1358KB)(46)       Save

    Aiming at the problem that the existing detection methods are not efficient in detecting the malicious domain name generated by the algorithm, especially the detection rate of several types of malicious domain names that are difficult to detect is low, an improved algorithm for detection of the malicious domain name based on the convolutional neural network is proposed. Based on the existing convolutional neural network model, this algorithm adds convolutional branches to extract deeper character-level features, so that both shallow and deep character-level features of malicious domain names could be extracted and fused simultaneously. A focal loss function is introduced as a loss function to solve the problem of sample imbalance caused by difficulty and quantity, which is used to improve the detection accuracy of hard-to-detect samples. The average detection accuracy of the improved algorithm for 20 types of malicious domain names is 97.62%, that is, 0.94% higher than that of the original algorithm, and the detection accuracy of four hard-to-detect domain names is increased by 3.71%, 4.6%, 11.18% and 17.8%, respectively. Experimental results show that the improved algorithm can effectively improve the detection accuracy of malicious domain names, especially for some hard-to-detect domain names.

    Table and Figures | Reference | Related Articles | Metrics
    Datafusion method of multi-sensor target recognition in complex environment
    LU Liping,ZHANG Xiaoqian
    Journal of Xidian University    2020, 47 (4): 31-38.   DOI: 10.19665/j.issn1001-2400.2020.04.005
    Abstract84)   HTML16)    PDF(pc) (1182KB)(37)       Save

    In the complex battlefield environment, the uncertainty of target information causes the target recognition difficulty and misjudgment, which brings about the problem of a low accuracy of target recognition results. This paper proposes a data fusion method for multi-sensor target recognition based on the discrete factor, which can give rise to the output data of the multi-sensor at the multi-period and multi-regions detection, and bring about the discrete factor of obtaining target characteristic corresponding sensors. It can provide the current weight of multi-sensor target recognition according to the discrete factor, establish the relative consistency and the relative weighted consistency function of multi-sensor target recognition, combine the current weight of multi-sensor target recognition and the related consistency function, and construct the data fusion result support calculation model of multi-sensor target recognition. Experimental results show that when the environment is complex, the data fusion method for multi-sensor target recognition based on the discrete factor has more accurate target recognition results, which conforms to the reality in comparison with the data fusion method for target recognition with a given sensor weight in advance. It is shown that the method proposed in this paper is more reliable and has a certain anti-interference ability.

    Table and Figures | Reference | Related Articles | Metrics
    Improved Siamese network based object tracking combined with the deep contour feature
    YU Zhichao,ZHANG Ruihong
    Journal of Xidian University    2020, 47 (3): 40-49.   DOI: 10.19665/j.issn1001-2400.2020.03.006
    Abstract82)   HTML14)    PDF(pc) (3638KB)(42)       Save

    The existing Siamese object tracking algorithms easily lead to tracking drift under the influence of object deformation and occlusion, this paper proposes an improved object tracking algorithm based on deep contour extraction networks to achieve stable detection and tracking of any object under complex backgrounds. First, the contour detection network automatically obtains the closed contour information on the object and uses the flood-filling clustering algorithm to obtain the contour template. Then, the contour template and the search area are input into the improved Siamese network so as to obtain the optimal tracking score value and adaptively update the contour template. If the object is fully obscured or lost, the Yolov3 network is used to search the object in the entire field of view to achieve stable tracking throughout the process. A large number of qualitative and quantitative simulation results show that the improved model can not only improve the object tracking performance under complex backgrounds, but also improve the response time of airborne systems, which is suitable for engineering applications.

    Table and Figures | Reference | Related Articles | Metrics
    Sliding window decoding algorithm for spatially coupled LDPC codes with a variable window
    ZHANG Yamei,ZHOU Lin,CHEN Chen,GUO Rongxin,HE Yucheng
    Journal of Xidian University    2020, 47 (3): 128-134.   DOI: 10.19665/j.issn1001-2400.2020.03.018
    Abstract82)   HTML14)    PDF(pc) (1343KB)(33)       Save

    Spatially coupled low density parity check (SC-LDPC) codes can achieve a better decoding performance with a small message recovery latency due to the sliding window decoding. An improved decoding scheme based on window extension is proposed for further enhancing the performance of the sliding window decoding. In contrast to conventional sliding window decoding, the window size of this scheme can vary according to the average logarithmic likelihood ratio (LLR) value of the target symbol. Specifically, for every iteration in the decoding process, we compare the average LLR value of the target symbol with the preset threshold. If the average LLR value of the target symbol is less than the preset threshold and the current window size does not exceed the maximum size, the decoding window size adds one and then performs a new iteration with the new window size. By this means, the scheme can achieve trade-off between decoding performance, complexity and latency. Simulation results on the additive white Gaussian noise (AWGN) channel show that this scheme can significantly improve the sliding window decoding performance of SC-LDPC codes.

    Table and Figures | Reference | Related Articles | Metrics
    Algorithm for segmentation of smoke using the improved DeeplabV3 network
    WANG Ziyi,SU Yuting,LIU Yanyan,ZHANG Wei
    Journal of Xidian University    2019, 46 (6): 52-59.   DOI: 10.19665/j.issn1001-2400.2019.06.008
    Abstract80)   HTML39)    PDF(pc) (1730KB)(29)       Save

    Existing smoke detection methods depend mostly on features which are selected manually and the smoke areas in video images often cannot be segmented accurately. This paper proposes an improved DeeplabV3 smoke segmentation algorithm based on this. A feature refinement module is added after the basic encoder network to weaken the gridding effects caused by dilated convolutions. For the non-rigid objects such as smoke with variable scales and postures, the Atrous Spatial Pyramid Pooling module is combined with the deformable convolution to better adapt to the smoke deformation. And a channel attention decoder module is proposed to further restore the spatial details of smoke images. According to the test of the smoke image data set, the proposed model has a faster average prediction speed of 71.73ms per image. Besides, compared with the DeeplabV3 network, this algorithm can lead to a higher MPA (Mean Pixel Accuracy) of 97.78% and a higher MIoU (Mean Intersection over Union) of 91.21%, thus improving the performance by 0.56% and 2.17% respectively, and making it more suitable for smoke segmentation. Public smoke video test results show that this model outperforms other video-based smoke detection methods for the detection rate, and that it is of certain research significance and practical value.

    Table and Figures | Reference | Related Articles | Metrics
    Method for suppressing clutters with the joint low-rank and sparse model
    HUANG Chen,LIU Hongqing,LUO Zhen,ZHOU Yi
    Journal of Xidian University    2019, 46 (6): 60-66.   DOI: 10.19665/j.issn1001-2400.2019.06.009
    Abstract77)   HTML9)    PDF(pc) (1291KB)(29)       Save

    The existing method for suppression of clutters of the through-the-wall radar system requires full size data, which may increase the complexity of the system. To this end, a wall clutter suppression method with the joint low-rank and sparse model is developed in this paper. In the proposed method, the task of separating wall clutters and target returns is transformed into a low-rank and sparse constrained optimization model requiring less data. To solve this optimization, the alternating direction method for multipliers is adopted. After clutter suppression, the return signals are used for the image formation. Experimental results demonstrate that the proposed method is significantly effective on clutter suppression in different scenes. Compared with the existing methods such as singular value decomposition and iterative soft thresholding, the proposed method has a higher target-to-clutter ratio in the radar imaging results.

    Table and Figures | Reference | Related Articles | Metrics
    Algorithm for foggy-image pedestrian and vehicle detection
    WANG Yudong,GUO Jichang,WANG Tianbao
    Journal of Xidian University    2020, 47 (4): 70-77.   DOI: 10.19665/j.issn1001-2400.2020.04.010
    Abstract76)   HTML12)    PDF(pc) (2276KB)(45)       Save

    In order to improve the accuracy of the foggy-image pedestrian and vehicle detection, a novel and practical Foggy-image pedestrian and vehicle detection network (FPVDNet) based on the Faster R-CNN is proposed. First, a foggy-density discriminating module (FDM) is proposed to influence the density of the foggy images. In this way, the prediction from the FDM could determine the subsequent operations for different densities of the fog (No-fog, Light fog, and Dense fog). Then, the squeeze and excitation module (SE Module) is designed to use the attention mechanism to improve the feature extraction capability of the network. Meanwhile, the method of the deformable convolution network is applied to add offsets and learn the offsets from target tasks to enhance the transformation modeling capacity of CNNs. Finally, for lack of the annotated fog image dataset, it is necessary to generate a simulated fog image training dataset through the atmospheric scattering model. The simulated foggy image inherits the annotation of the clear image and increases the information on the fog density. Experiments by the proposed FPVDNet are carried out on the 1, 500 real-fog images and 500 real-clear images, with experimental results showing that, compared with the original Faster R-CNN, the mean average detection accuracies are improved 2%~4% by using the FPVDNet.

    Table and Figures | Reference | Related Articles | Metrics
    Contour reconstruction method for noisy image based on depth residual learning
    WANG Xiaoming,ZHANG Shuyan,ZHANG Jie,YUAN Sicong
    Journal of Xidian University    2020, 47 (3): 66-71.   DOI: 10.19665/j.issn1001-2400.2020.03.009
    Abstract75)   HTML10)    PDF(pc) (1381KB)(30)       Save

    In order to improve the recognition ability of noisy images, a method of contour reconstruction based on depth residuals learning is proposed. The sharpening template matching technique is used to enhance the noisy image information, the local gray level information on the image is used to construct the edge active contour model of the image, and the active contour lasso method is used to reconstruct the image with a high resolution. The feature quantities of local gray energy and local gradient energy of the noisy image are extracted, and a convolutional neural network classifier is constructed to classify the features. The learning depth of the learning convolutional neural network is judged by combining the similarity of the gray histogram of the image. The resolution ability of image detail information is improved, and the contour high resolution reconstruction of the noisy image is realized. Simulation results show that the proposed method has a high resolution and a high peak signal to noise ratio (PSNR), which improves the recognition ability of the image effectively.

    Table and Figures | Reference | Related Articles | Metrics
    Scheme for miniature time difference measurement with a high resolution and a large range
    QU Bayi,LIU Yehao,ZHANG Taojing,LIU Wei,YU Dongsong,ZHOU Wei
    Journal of Xidian University    2020, 47 (4): 24-30.   DOI: 10.19665/j.issn1001-2400.2020.04.004
    Abstract73)   HTML13)    PDF(pc) (1254KB)(38)       Save

    This paper presents some solutions to the problems in the precise time interval measuring instrument such as the contradiction between high resolution and wide measurement range, the high temperature sensitivity, the low reliability and the big volume and power consumption. The reference signal is used to generate calibration signals to automatically calibrate the analog circuits which are greatly affected by the temperature. The calibration data are used to amend the conversion coefficient between voltage and time interval and the temperature sensitivity of the instrument is greatly reduced. To avoid the gross error in the measurement result caused by the false trigger of the counter, the double counter synchronous measurement technique is adopted and the logic algorithm is used for analyzing and correcting the measured results. Electronic counting method and time-to-voltage converter method are combined together to meet the requirements of the measurement range and resolution of the instrument. The circuit board’s area of the prototype is only 10cm2. The prototype’s effective resolution is above 10ps and the standard deviation of multiple measurement results is below 15ps, the measurement range is wider than 20, 000 seconds, and its measurement results are highly reliable.

    Table and Figures | Reference | Related Articles | Metrics
    Health prediction algorithm for edge layer nodes
    SUN Qian,ZHANG Jiarui,GAO Ling,WANG Yuxiang,YANG Jianfeng
    Journal of Xidian University    2020, 47 (3): 32-39.   DOI: 10.19665/j.issn1001-2400.2020.03.005
    Abstract71)   HTML11)    PDF(pc) (1284KB)(31)       Save

    An improved state prediction algorithm for edge layer nodes is proposed to solve the problem of the existing state prediction algorithm for edge layer nodes based on Hidden Markov, such as the subjectivity of initial parameter selection, the dependence of feature weights setting on experience, and the bad adaptability of multidimension feature node analysis. At the data processing layer of the algorithm, the parameter of the model and observation sequence are optimized by the method of clustering; and then at the training layer of the algorithm, the single-feature Hidden Markov Model is used to model the multi-feature Hidden Markov Model; finally, an adaptive genetic algorithm based on the information gain is used to optimize and reduce the state sequence generated by the Hidden Markov Model. The problems of feature weight setting and parameter initial value selection are solved effectively. Experimental results show that the proposed algorithm effectively improves the accuracy of the high-dimensional health state of large-scale edge layer nodes compared with the existing algorithms.

    Table and Figures | Reference | Related Articles | Metrics
    Urine cell image classification algorithm based on the squeeze and excitation mechanism
    SONG Jianfeng,WEI Yue,MIAO Qiguang,QUAN Yining,CHEN Yusheng
    Journal of Xidian University    2020, 47 (2): 39-45.   DOI: 10.19665/j.issn1001-2400.2020.02.006
    Abstract70)   HTML8)    PDF(pc) (1438KB)(36)       Save

    In order to solve the classification problem on the urine-forming sub-cell images, a urine cell image classification algorithm based on the Squeeze-and-Excitation GoogLeNet is proposed. The algorithm uses the feature recalibration mechanism and brings about significant improvement in the useful feature for the current task through squeeze and excitation operations, which explicitly models interdependencies between cell feature channels learned by the Inception architecture during the training process. On the urine cell datasets, comparative experimental results show that the algorithm provides a better classification effect, which improves the accuracy of classification by 3% and the recall rate by 1% at the similar speed of the GoogLeNet network.

    Table and Figures | Reference | Related Articles | Metrics
    Simulation analysis of directivity and optimization of the array of the AlN thin film PMUT array
    LOU Lifei,AN Zaifang,LI Yining,ZHAO Mingyang,ZHAO Jianxin
    Journal of Xidian University    2020, 47 (2): 32-38.   DOI: 10.19665/j.issn1001-2400.2020.02.005
    Abstract69)   HTML11)    PDF(pc) (3196KB)(36)       Save

    The relatively low piezoelectric constant of the aluminum nitride piezoelectric film limits the development and application of the piezoelectric micro-machined ultrasonic transducer based on the aluminum nitride. Therefore, the directivity of the piezoelectric micro-machined ultrasonic transducer array is studied for this problem. First, the far-field sound pressure and normalized directivity function of the transducer array are calculated according to the Rayleigh principle. Furthermore, the effects of array element radius, array element spacing, array element number and operating frequency on the beam width, direction sharpness angle and sidelobe level of the array are analyzed, and the transducer array is optimized. Finally, based on the optimization results, area and filling efficiency, the final structure size of the transducer array is determined and the sound pressure distribution visually simulated. The results show that the optimized transducer array has an ideal sound pressure distribution, good directivity and sharp main lobe. The-3dB beamwidth of the main lobe is about 9 ° and the sidelobe level is about 0.228.

    Table and Figures | Reference | Related Articles | Metrics
    Low resolution face recognition method based on wavelet and recursive neural networks
    OUYANG Ning,WANG Xian’ao,CAI Xiaodong,LIN Leping
    Journal of Xidian University    2019, 46 (6): 95-101.   DOI: 10.19665/j.issn1001-2400.2019.06.014
    Abstract69)   HTML15)    PDF(pc) (1562KB)(33)       Save

    To improve the accuracy of low-resolution face recognition with limited information, a method based on the Haar wavelet and recurrent neural network is proposed. First, the wavelet coefficients are directly predicted through the deep neural network. High-resolution face images with high-frequency information can be reconstructed by the inverse wavelet transform. Second, a recursive module is added to the convolutional neural network to increase the depth of the network, which can reduce the redundancy of parameters effectively. Finally, a fusion loss method is utilized, in which the loss of wavelet coefficients reconstruction and the perceptual are weighted and fusioned to generate images for recognition. Based on open dataset, the image reconstruction quality and recognition performance are compared, respectively. Experimental results show that sharper face images can be reconstructed even with extremely low resolutions (8×8, 16×16), and that its recognition ability outperforms that of state-of-the-art face super resolution algorithms.

    Table and Figures | Reference | Related Articles | Metrics
    Method of cancer biomarker prediction in the gene regulatory network
    QIN Guimin,LIU Jiayan,YIN Yu,YANG Luqiong
    Journal of Xidian University    2019, 46 (6): 81-87.   DOI: 10.19665/j.issn1001-2400.2019.06.012
    Abstract69)   HTML11)    PDF(pc) (1413KB)(21)       Save

    Cancer biomarkers identification based on multi-omics data is of great significance for the study of molecular mechanisms of cancer, while most of the current work is based on protein-protein interaction data. Therefore, a new method based on the gene regulatory network and multi-omic data is proposed to analyze cancer molecular mechanisms and predict cancer biomarkers. Taking stomach adenocarcinoma (STAD) and esophageal carcinoma (ESCA) for example, first we integrate multi-omics data to construct cancer-specific networks for STAD and ESCA respectively. Then, analysis of weighted co-expression gene networks is carried out on the two networks, and hierarchical clustering modules are used to calculate the relationship between the first principal component of the module and all known cancer biomarkers. Furthermore, cancer-specific modules are screened out. Finally, disease-specific biological pathways are extracted, and potential cancer biomarkers are prioritized using similarity assessment methods. Experimental results show that the specific module predicted has functional characteristics, and that the Pearson correlation coefficient method is more accurate.

    Table and Figures | Reference | Related Articles | Metrics
    Video deblurring using the generative adversarial network
    SHEN Haijie,BIAN Qian,CHEN Xiaofan,WANG Zhenduo,TIAN Xinzhi
    Journal of Xidian University    2019, 46 (6): 112-117.   DOI: 10.19665/j.issn1001-2400.2019.06.016
    Abstract66)   HTML8)    PDF(pc) (1315KB)(21)       Save

    A video deblurring network based on the generative adversarial network and the Markovian discriminator is proposed to solve the video deblurring problem, which is caused by camera shaking or object movement. In this paper, we combine the pixel-space and feature-space loss, and design a discriminator based on the Markovian discriminator, which promotes the learning of image texture details and improves the quality of the generated image. The proposed method and the state-of-the-art methods are compared qualitatively and quantitatively on the test set and real video set, respectively. Experimental results indicate that the image deblurred by the proposed method has a higher peak signal-to-noise ratio and richer details.

    Table and Figures | Reference | Related Articles | Metrics
    Wideband high-gain ring circularly polarized microstrip antenna
    CHEN Qingqing,LI Jianying,DING Yuxin,ZHANG Lingkai,FENG Yao,XIE Jing
    Journal of Xidian University    2019, 46 (6): 46-51.   DOI: 10.19665/j.issn1001-2400.2019.06.007
    Abstract65)   HTML15)    PDF(pc) (2063KB)(45)       Save

    Two novel single-fed ring circularly polarized microstrip antenna with an enhancing bandwidth are designed to broaden the axial ratio bandwidth of the cut ring patch antenna. Since the lateral slot perturbs the surface current of the ring patch, two equal-amplitude radiation modes with a phase difference of 90° are excited to radiate circular polarization. The measured results show that good circularly polarized characteristics of the annular-ring and the square-ring antennas have been obtained respectively from 3.74 to 3.98 GHz and from 3.80 to 4.04 GHz. The axial ratios (ARs) are less than 3 dB and the voltage standing wave ratios (VSWR) are less than 2. In addition, the antenna peak gains are higher than 10.0 dB for annular-ring and square-ring microstrip antennas over the operating bandwidth.

    Table and Figures | Reference | Related Articles | Metrics
    Hardware obfuscation design of the RM logical camouflage gate
    WU Qiufeng,ZHANG Yuejun,WANG Pengjun,ZHANG Huihong
    Journal of Xidian University    2020, 47 (2): 135-141.   DOI: 10.19665/j.issn1001-2400.2020.02.018
    Abstract64)   HTML4)    PDF(pc) (3887KB)(38)       Save

    To improve the ability of the integrated circuit to resist reverse engineering, we study the logic obfuscation technology and propose a logic obfuscation scheme based on the Reed-Muller camouflage gate. First, different virtual hole configurations are adopted to realize XOR/AND logical functions on the same layout, and feature information of the logical obfuscating circuit is extracted to make the standard cell physical library. Then, the obfuscation physical library is applied in the circuit netlist by the random insertion algorithm. Finally, the ISCAS benchmark is used to verify the effectiveness of the proposed scheme. Simulation results reveal that the similarity of the Reed-Muller logic camouflage layout is improved by 14.36%, and that the power consumption overhead is about 2.36% under the larger scale benchmark. Experiment indicates that the designed obfuscation gate can effectively resist reverse engineering and improve the hardware security of the circuit.

    Table and Figures | Reference | Related Articles | Metrics
    Combined multi-features method for the detection of SAR man-made weak trace
    WANG Zhihao,ZHANG Jinsong,SUN Guangcai,LI Jun,XING Mengdao
    Journal of Xidian University    2019, 46 (6): 131-139.   DOI: 10.19665/j.issn1001-2400.2019.06.019
    Abstract63)   HTML6)    PDF(pc) (3415KB)(42)       Save

    When detecting the man-made weak trace like the footprints and wheel prints, a large number of false alarm areas caused by natural scenes appear in the detection results due to their low correlation, such as the vegetation and rivers. To solve this problem, this paper first gets the preliminary detection results with the Coherent Change Detection (CCD). Then by analyzing the Radar Cross Section (RCS) model of the natural scenes, it is found that the vegetation region varies much on image intensity while the river region gets a lower image intensity compared to the man-made weak trace. Based on this research, the differential and the sum of the image-pair intensity are taken as two test statistics to eliminate the vegetation and river regions from the preliminary detection results, and then a combined multi-feature method is proposed for man-made weak trace detection. The proposed method can reduce the false alarm rate and lead to fine detection results by multi-features. Finally, the processing results of the millimeter wave Synthetic Aperture Radar (SAR) real data verify the efficiency of the proposed method.

    Table and Figures | Reference | Related Articles | Metrics
    Novel dual circular polarization planar microstrip slot antenna
    LIU Fan,ZHAO Xiaoyan,ZHAO Hongzhi,JIANG Zhaoneng
    Journal of Xidian University    2020, 47 (3): 86-91.   DOI: 10.19665/j.issn1001-2400.2020.03.012
    Abstract61)   HTML9)    PDF(pc) (2445KB)(29)       Save

    With the rapid development of wireless communication technology, how to use an antenna to realize the function of multiple antennas has become a hot research topic. The double circularly polarized antenna studied in this paper can achieve right-handed circular polarization and left-handed circular polarization in the same frequency band by using a circular annular groove and two orthogonal L-shaped feed lines in the ground plane. At the same time, properly grooving at the center of the ground plane and adding parasitic elements to the front of the L-shaped feed line can change the current on the surface of the feed line and in the ground plane, thereby improving the circular polarization performance of the antenna. Measurement and simulation results show that the impedance bandwidth of the antenna is about 59% (3.13~5.75GHz), and the 3dB axial ratio bandwidth is about 40.5% (3.23~4.87GHz). Also, the isolation between the two ports is higher than 10dB. The results show that the designed antenna has a good performance in both impedance bandwidth and axial ratio bandwidth.

    Table and Figures | Reference | Related Articles | Metrics
    Scheme for antenna design used in in-band full-duplex communication
    LIU Weirong,XUN Jianhui,SHI Lingfeng
    Journal of Xidian University    2020, 47 (1): 60-65.   DOI: 10.19665/j.issn1001-2400.2020.01.009
    Abstract59)   HTML4)    PDF(pc) (1862KB)(20)       Save

    In order to effectively suppress the self-interference of the in-band full-duplex communication system, a solution for designing the transceiver antenna based on the simple ring structure and collinear dipole is proposed. In this design, two printed dipole antennas are placed in the zero radiation direction of each other to achieve low port isolation between the two transceiver antennas. Then a simple ring structure is added to improve the isolation between the two antennas. Experimental results show that the two transceiver antennas designed by this scheme have omnidirectional radiation characteristics and can obtain a high port isolation of better than 45.9 dB in 2.4~2.6 GHz band. The scheme for designing the transceiver antenna proposed in this paper can not only effectively reduce the interference between two transceiver antennas, but also provide omnidirectional signal coverage. It is an effective solution for designing transceiver antennas for the in-band full-duplex communication system.

    Table and Figures | Reference | Related Articles | Metrics
    Approximate computing method based on cross-layer dynamic precision scaling for the k-means
    LI Zhao,YUAN Wenhao,REN Chongguang,HUANG Chengcheng,DONG Xiaoxiao
    Journal of Xidian University    2020, 47 (3): 50-57.   DOI: 10.19665/j.issn1001-2400.2020.03.007
    Abstract59)   HTML6)    PDF(pc) (1293KB)(32)       Save

    With the application of artificial intelligence on the embedded platform, the k-means clustering algorithm, as the basis of the artificial intelligence method, is implemented on the embedded platform. Energy consumption is the key for the algorithm implementation on the embedded platform. In order to reduce the energy consumption of the k-means on the embedded platform, an approximate computing method based on cross-layer dynamic precision scaling for the k-means is proposed. First, the iteration process is constrained from the distance between data point to centroid and data point change trend. And a dynamic precision scaling method is proposed. Then the data reorganization and access method of external memory is designed from the structural level, which can realize the access of approximate memory. In addition, the approximate adder and multiplier are designed which can automatically adjust the calculation accuracy. Finally, the approximate computing of the k-means is realized. Experimental results show that the proposed method can reduce the energy consumption by 55%~58% compared with the accurate computing without affecting the quality of clustering. The proportion of the energy saving is the highest.

    Table and Figures | Reference | Related Articles | Metrics
    Low complexity probability-based piecewise linear approximation of the sigmoid function
    NGUYEN Van-Truong,CAI Jueping,WEI Linyu,CHU Jie
    Journal of Xidian University    2020, 47 (3): 58-65.   DOI: 10.19665/j.issn1001-2400.2020.03.008
    Abstract58)   HTML7)    PDF(pc) (1349KB)(14)       Save

    In order to improve the network recognition accuracy in the low complexity condition, a piecewise linear sigmoid function approximation based on the distribution probability of the neurons’ values is proposed only with one addition circuit. The sigmoid function is first divided into three fixed regions. Second, according to the neurons’ values distribution probability, the curve in each region is segmented into sub-regions to reduce the approximation error and improve the recognition accuracy. The slope of the piecewise linear function is set as 2-n, effectively reducing the hardware implementation complexity. Experiments performed on Xilinx’s FPGA-XC7A200T implement the MNIST handwritten digits recognition. The results show that the proposed method achieves a 97.45% recognition accuracy in a deep neural network and 98.42% in a convolutional neural network, up to 0.84% and 0.57% higher than other approximation methods only with one addition circuit.

    Table and Figures | Reference | Related Articles | Metrics
    High performance multiply-accumulator for the convolutional neural networks accelerator
    KONG Xin,CHEN Gang,GONG Guoliang,LU Huaxiang,Mao Wenyu
    Journal of Xidian University    2020, 47 (4): 55-63.   DOI: 10.19665/j.issn1001-2400.2020.04.008
    Abstract58)   HTML13)    PDF(pc) (2691KB)(44)       Save

    The multiply-accumulator (MAC) in existing convolutional neural network(CNN) accelerators generally have some problems, such as a large area, a high power consumption and a long critical path. Aiming at these problems, this paper presents a high-performance MAC based on transmission gates for CNN accelerators. This paper proposes a new data accumulation and compression structure suitable for the MAC, which reduces the hardware overhead. Moreover, we propose a new parallel adder architecture. Compared with the Brent Kung adder, the proposed adder reduces the number of gate delay stages and improves the calculation speed without causing an increase in hardware resources. In addition, we use the advantages of the transmission gate to optimize each unit circuit of the MAC. The 16-by-8 fixed-point high performance MAC based on the methods presented in this paper has a critical path delay of 1.173ns, a layout area of 9049.41μm2, and an average power consumption of 4.153mW at 800MHz under the SMIC 130nm tt corner. Compared with the traditional MAC, the speed is increased by 37.42%, the area is reduced by 47.84%, and the power consumption is reduced by56.77% under the same conditions.

    Table and Figures | Reference | Related Articles | Metrics
    Blindrecognition of the long constrained non-recursive systematic convolutional code
    WANG Jiafeng,HU Maohai,JIANG Hongyu,QI Gang
    Journal of Xidian University    2020, 47 (1): 18-23.   DOI: 10.19665/j.issn1001-2400.2020.01.003
    Abstract57)   HTML14)    PDF(pc) (1329KB)(29)       Save

    A coding parameters identification method is proposed, which is suitable for long constrained non-recursive systematic convolutional codes with a code rate of 1/2 and (n-1)/n obtained by puncturing the 1/2 code as the mother code. First, according to the coding principle, a linear block code with a code length of about 1/n of the original convolutional code constrained length is constructed by using the coding data; then, the check matrix of the linear block code is obtained, and the generator polynomial of the original convolutional code is reconstructed from the check matrix. Simulation experiments are carried out for two convolutional codes involved in IESS309. Compared with the existing method, when the code rate is 1/2, the recognition performance is improved by about 1dB; when the code rate is 2/3 and 3/4, the improvement is more than 2dB. Simulation results show that the proposed method is more effective than the existing method.

    Table and Figures | Reference | Related Articles | Metrics
    Analysis of sensitivity uncertainty of the MEMS microphone based on Latin hypercube Monte Carlo simulation
    LIU Lei,JIA Renxu
    Journal of Xidian University    2019, 46 (6): 23-29.   DOI: 10.19665/j.issn1001-2400.2019.06.004
    Abstract56)   HTML86)    PDF(pc) (1526KB)(27)       Save

    Due to the diaphragm uncertainties from manufacturing processes, the MEMS microphone may exhibit significant variations in their performance compared to the nominal design. In order to reduce calculation time and improve simulation efficiency, this paper presents the Latin hypercube Monte Carlo Simulation (LHMCS) based on artificial neural networks (ANNs), which is used to analyze the sensitivity uncertainty of the polysilicon circular clamped diaphragm microphone. Experimental results show that the simulated qualified rate of the MEMS microphone is 92.9% and the time-consuming is less than 10 seconds and that compared with the traditional Monte Carlo simulation based on random sampling, LHMCS needs only 11% of the sampling number at the same accuracy. This paper also analyzes the effects of nominal design values of the diaphragm on the probability distributions of microphone sensitivities. The mean values and standard deviations of the sensitivity distributions are obtained by fitting the simulation results with normal distribution. The results show that three main factors affecting the distribution in the order from strength to weakness are radius, thickness, and young modulus. Young modulus only affects the mean value, but does not affect the standard deviation. The presented LHMCS with high accuracy and efficiency is an alternative to the traditional methods.

    Table and Figures | Reference | Related Articles | Metrics
    W-band 3.4 W/mm GaN power amplifier MMIC
    GE Qin,XU Bo,TAO Hongqi,WANG Weibo,MA Xiaohua,GUO Fangjin,LIU Yu
    Journal of Xidian University    2020, 47 (1): 24-29.   DOI: 10.19665/j.issn1001-2400.2020.01.004
    Abstract56)   HTML10)    PDF(pc) (1463KB)(16)       Save

    A high power density monolithic microwave integrated circuit (MMIC) power amplifier is presented for W band application. The chip is fabricated using the 100 nm GaN high electron mobility transistor (HEMT) technology on a 50 μm SiC substrate. The amplifier is designed for a high gain and high output power with three stage topology and low-loss impedance matching networks designed with high and low characteristic impedance micro-strips and metal-insulator-metal (MIM) capacitors. And quarter-wave micro-strips are employed for the DC bias networks, while the power amplifier is also fully integrated with bias networks on the wafer.Measurement results show that, at the drain bias of 15 V, the amplifier MMIC achieves a typical small signal gain of 20 dB within the frequency range of 88~98 GHz. Moreover, the saturated output power is more than 250 mW at the continuous-wave mode. At 98 GHz, a peak output power of 405 mW has been achieved with an associated power gain of 13 dB and a power-added-efficiency of 14.4%. Thus, this GaN MMIC delivers a corresponding peak power density of 3.4 W/mm at the W band.

    Table and Figures | Reference | Related Articles | Metrics
    Method for multi-band image feature-level fusion based on the attention mechanism
    YANG Xiaoli,LIN Suzhen
    Journal of Xidian University    2020, 47 (1): 120-127.   DOI: 10.19665/j.issn1001-2400.2020.01.017
    Abstract55)   HTML4)    PDF(pc) (3259KB)(21)       Save

    Aiming at the low definition and poor details of synchronous multi-band image fusion, a novel method based on attention generative adversarial networks is proposed. First, the attention weight map is constructed using the difference between the multi-band feature map and its mean, then the feature enhancement map is obtained by the point multiplication and addition of the feature map and the attention weight map to construct the feature enhancement module. Second, the feature-level fusion module is designed, which connects the multi-band feature enhancement map and reconstructs the fused image through normalization, upsampling, convolution, etc. Finally, the feature enhancement module and the feature-level fusion module are cascaded to build the generator, and the VGG-16 is used as a discriminator to establish a Generative Adversarial Network, thereby implementing multi-band image end-to-end fusion. Experimental results show that the proposed fusion method can lead to the most prominent average gradient compared with classical fusion methods, and that the effectiveness of the proposed method is verified.

    Table and Figures | Reference | Related Articles | Metrics
    Improved gravitational search algorithm for shaped beam forming
    SUN Cuizhen,DING Jun,GUO Chenjiang
    Journal of Xidian University    2020, 47 (2): 83-90.   DOI: 10.19665/j.issn1001-2400.2020.02.012
    Abstract51)   HTML14)    PDF(pc) (1376KB)(27)       Save

    In view of the adverse effect of the random initial value on the performance and convergence speed of the gravitation search algorithm, a quasi-oppositional gravity search algorithm (QOGSA) is proposed. The quasi-oppositional based learning OBL is embedded into the GSA algorithm, the number of iteration is divided into multiple learning cycle, the oppositional probability is adjusted according to the success rate of the past learning cycle, and an adjustable oppositional probability is designed to optimize the timing of the mechanism in the evolution, which improves the speed of the algorithm to search for the optimal solution greatly. On this basis, in order to improve the population diversity, elite particles are retained to the next generation population. They replace the particles with a poor fitness value and acquire a higher optimization accuracy. Compared with the existing algorithms in the literature, the optimization accuracy of the QOGSA for the average optimal value of the single-peak and multi-peak test functions can be improved by 1016. For the shaping results of different types of beam, the optimization accuracy of the improved algorithm for the sidelobe can be improved from 1.26dB to 5.99dB. On the premise of the fastest convergence speed, the QOGSA can greatly avoid the problem that other optimization algorithms tend to fall into local optimization, with the overall performance being the best.

    Table and Figures | Reference | Related Articles | Metrics
    Satellite image RPC parameters estimation method using the heteroscedastic errors-in-variables model
    ZHOU Yu,HU Xin,CAO Kailang,ZHOU Yongjun,LI Yunsong
    Journal of Xidian University    2020, 47 (2): 108-117.   DOI: 10.19665/j.issn1001-2400.2020.02.015
    Abstract51)   HTML46)    PDF(pc) (1217KB)(15)       Save

    The positioning accuracy of a satellite image is mainly affected by the estimation accuracy of the rational polynomial coefficients (RPCs). Image point compensation or ground control point correction methods are usually used in the existing algorithms. Because the error characteristics of the design matrix elements are not considered, there are problems such as incomplete systematic error elimination and low parameter estimation accuracy. Considering the influence of the model systematic error, a heteroscedastic estimation method is proposed in this paper. First, the random model of matrix elements is established in the algorithm to describe the system characteristics more accurately. Taking into account the system deviations of the design matrix elements, the least square model is constructed using the Mahalanobis distance as the metric, and parameters are solved using the generalized eigenvalue method. The systematic error can be reduced theoretically. Experiment on different terrain images of TH-1 shows that the image correction accuracy of the proposed method is improved by more than 36 times compared with the traditional method, and the precision consistency is superior, which is of great significance to improving the accuracy of RPC parameters estimation and satellite imagery positioning.

    Table and Figures | Reference | Related Articles | Metrics
    Improved scheme for spectrum allocation in cognitive wireless sensor networks
    ZHOU Ji,XU Mengying,WANG Jiaojiao,LU Yi
    Journal of Xidian University    2020, 47 (3): 80-85.   DOI: 10.19665/j.issn1001-2400.2020.03.011
    Abstract51)   HTML4)    PDF(pc) (1175KB)(28)       Save

    In order to effectively allocate the idle spectrum and improve spectrum utilization of cognitive wireless sensor networks, it is necessary to design an efficient spectrum allocation algorithm. Aiming at the problem of spectrum allocation in cognitive wireless sensor networks, an improved method for spectrum allocation is suggested. A new chaotic dynamic clonal evolution algorithm is designed. Then the graph theory coloring model is established with the corresponding fitness function derived. Traditional evolutionary algorithms have the problem of premature convergence, so chaotic operators, adaptive operators and cloning operators are added to the traditional evolutionary algorithms to accelerate the convergence of the algorithm. The chaotic dynamic clonal evolutionary algorithm is compared with the simulated annealing algorithm and the ant colony algorithm by simulation. The simulation results show that compared with the ant colony algorithm and the simulated annealing algorithm, the chaotic dynamic clonal evolution algorithm can effectively improve the global search ability, and significantly improve the network benefit value of spectrum allocation. The results also show that the proposed chaotic dynamic clonal evolution algorithm can make full use of existing spectrum resources and improve the system throughput.

    Table and Figures | Reference | Related Articles | Metrics
    Model of abstractive text summarization for topic-aware communicating agents
    ZHANG Zheming,REN Shuxia,GUO Kaijie
    Journal of Xidian University    2020, 47 (3): 97-104.   DOI: 10.19665/j.issn1001-2400.2020.03.014
    Abstract51)   HTML11)    PDF(pc) (1231KB)(16)       Save

    To solve the problem that the traditional automatic text summary model cannot generate a high-quality long text summary due to the limitation of the length of the RNN (Recurrent Neural Network), a model of abstractive text summarization for topic-aware communicating agents has been proposed. First, the problem that the LSTM (Long Short-Term Memory) input sequence is too long to generate the abstract with prior information has been solved by dividing the encoder into multiple collaborating agents. Then for providing topic information and improving the correlation between the generated abstract and the source text, the joint attention mechanism has been added into our model. Finally, a hybrid training method with reinforcement learning has been employed in order to solve the problem of exposure bias, and optimize the evaluation index directly. The results show that our model not only generate long text summaries with prominent themes, but also has a higher score than the state-of-the-art models, which indicates that with the help of topic information, the model for communicating agents can be expected to generate long text summaries better.

    Table and Figures | Reference | Related Articles | Metrics