Online FirstList of IssuesDocument Types

    Volume51,Issue12,2023
    Issue Cover

      PAPERS

    • Prototype Design and Implementation for Large-Scale Antenna Based Wireless Powered Communication System

      CHE Yue-ling, LI Liang-zhu, ZENG Zhi-hao, LUO Sheng, WU Kai-shun
      Vol. 51, Issue 12, Pages: 3397-3409(2023) DOI: 10.12263/DZXB.20230054
      Abstract:The wireless powered communication is a key technology to support energy sustainable wireless communications in the future 6G era. For the first time, this paper proposes a complete prototype design for the large-scale antenna based wireless powered communication system, and realizes this prototype system, which consists of a base station with a 32-transmit-antenna array, a user equipment and a feedback link, on the software defined radio platforms. At the base station, by designing flexible frame structures, this paper originally proposes a dynamic wireless energy transmission scheme to properly balance the required channel estimation accuracy and the wireless energy transmission efficiency. At the user equipment, by applying the practical non-linear energy harvesting and energy consumption models, this paper proposes a novel information-energy double threshold based battery management scheme to meet the requirements of different information and energy transmission. Based on the prompt status feedback from the user equipment, this paper completes a close-loop controlled system framework for adaptive wireless information and energy transmissions. Extensive experiments for both indoor and outdoor scenarios are implemented to verify the good environment adaptation and transmission performance of the wireless powered communication prototype system.  
      Keywords:wireless powered communication;prototype design and implementation;large-scale antenna;dynamic wireless energy transmission;adaptive wireless energy and information transmissions  
      649
      |
      401
      |
      0
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Edge Caching Scheme Based on Value of Information Age in the Internet of Vehicles

      LIN Zhi-jian, HOU Ying, CAO Xiao-xiao, WU Wen-hao, CHEN Xiao-pei, CHEN Ping-ping
      Vol. 51, Issue 12, Pages: 3410-3421(2023) DOI: 10.12263/DZXB.20221409
      Abstract:With the rapid development of the fifth generation (5G) mobile communications technology, Internet of vehicles (IoV) has become one of the important scenarios for 5G applications. Due to the urgent requirements of these applications for timely content caching, a dynamic content caching-enabled edge caching scheme is investigated to ensure timeliness, which allows vehicles to obtain cache content with freshness constraints from an edge caching-enabled access point (CAP). Furthermore, based on the idea of collaborative cache, a random model of CAP cache refreshing and delivery is established by probability theory. Meanwhile, considering the metric of hit rate with age of information (AoI) as the quality of service (QoS) index of IoV cache, a system model of caching performance value is developed. To ensure the effectiveness of content caching, two types of vehicular content requests with different AoI requirements are considered in a hierarchical slicing framework. Finally, the optimization problem to maximize the content caching value of cooperative content placement is formulated, which is a multi-objective, multi-dimensional and multi-choice knapsack problem and is proved to be NP-hard. Therefore, the problem is divided into several independent optimization problems, and a maximum incremental algorithm based on the age value of the content is designed to solve it. Simulation results show that the CAP cooperative content placement strategy outperforms other traditional methods.  
      Keywords:cache placement;soft slice;age of information;dynamic content delivery;mobile edge cache;internet of vehicles  
      516
      |
      388
      |
      4
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Construction of Fault Injection Attacks Resistant S-Boxes

      CHAI Jin-jin, WU Xuan
      Vol. 51, Issue 12, Pages: 3422-3430(2023) DOI: 10.12263/DZXB.20221111
      Abstract:Block cipher is an important part of modern cryptography, and S-box is an essential nonlinear component in block cipher, which provides a good confusion for cryptographic algorithms. Both S-boxes in traditional block ciphers and S-boxes in lightweight block ciphers are vulnerable to fault injection attacks. In this paper, we design some S-boxes that can detect two-byte errors and correct one-byte error based on cellular automata with linear or nonlinear neighborhood functions to resist fault injection attacks. Compared with the S-boxes in Advanced Encryption Standard (AES), although the cryptographic performance has decreased, they can resist fault injection attacks. In addition, this paper considers the security index of boomerang uniformity, which is used to measure the ability of S-box to resist boomerang attacks.  
      Keywords:S-box;cellular automata;fault injection attacks;block cipher  
      63
      |
      114
      |
      2
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Leakage-Resilient Key Encapsulation Mechanism with Anonymity and Multi-Receiver

      ZHOU Yan-wei, HAN Yu, XU Ran, WANG Jia
      Vol. 51, Issue 12, Pages: 3431-3436(2023) DOI: 10.12263/DZXB.20221124
      Abstract:Certificate-based cryptography combines the best aspects of identity-based encryption (implicit certification management) and public key encryption (no key escrow). To provide the ability of broadcast communication and leakage resilience for the certificate-based key encapsulation mechanism, a new cryptographic primitive, called leakage-resilient key encapsulation mechanism with anonymity and multi-receiver, is proposed in this paper; the formal definition and the leakage-resilient security model of our proposal are also described. The concrete construction of the above cryptographic primitive is created, and the corresponding leakage-resilient chosen-plaintext attacks security is proved based on the hardness of the decisional Diffie-Hellman assumption. The corresponding analysis shows that our scheme has better performance in anonymity, leakage resilience, and multi-receiver and so on; also, better computational efficiency can be achieved when generating encapsulation keys for multiple users.  
      Keywords:certificate-based cryptography;key encapsulation mechanism;multi-receiver;leakage resilience  
      122
      |
      113
      |
      1
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Research on Efficient Implementation of SM2 for Mobile Devices

      ZHANG Ji-peng, HUANG Jun-hao, YU Xuan, LIU Zhe
      Vol. 51, Issue 12, Pages: 3437-3443(2023) DOI: 10.12263/DZXB.20221419
      Abstract:SM2 has been fully studied on x86-64 architecture, but its optimization on ARMv8-A architecture is inadequate. In this work, we propose the following optimizations to fill this gap: for the modular multiplication/squaring of p and n in SM2, we optimize Montgomery modular multiplication/squaring by leveraging the numerical characteristics of p and n; for the modular inversion of p and n in SM2, we derive and implement a faster modular inversion algorithm based on Fermat's little theorem; for fixed-point and unknown-point scalar multiplication, we implement window algorithms with a window width of 7 and 5, respectively; for the calculation of s during the signature generation process, we replace a modular multiplication of n with a cheaper modular addition/subtraction of n. After integrating the optimizations mentioned above into OpenSSL (3.0.0-beta1), the benchmark on the HUAWEI Cloud Kunpeng 920 computing platform shows that the performance of SM2 signature generation is accelerated by 8.7 times; the performance of SM2 signature verification is accelerated by 3.5 times. Meanwhile, on the mobile device Raspberry Pi 4 platform, the performance of SM2 signature generation is accelerated by 9.7 times; the performance of SM2 signature verification is accelerated by 3.4 times.  
      Keywords:elliptic curve cryptography;ARMv8-A platform;optimized implementation of SM2;finite field operation;modular inversion operation  
      58
      |
      93
      |
      0
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Single-State Multiparty Semiquantum Secret Sharing with d-Dimensional Bell States

      CHEN Ying, GAN Zhi-gang, YE Tian-yu
      Vol. 51, Issue 12, Pages: 3444-3449(2023) DOI: 10.12263/DZXB.20230126
      Abstract:A single-state multiparty semiquantum secret sharing(MSQSS) scheme with d-dimensional Bell states is proposed, which can accomplish the goal that only when all receivers work together can they restore the sender's secret key. This protocol is validated to be secure against both the outside attack and the participant attack. This protocol is adaptive for the d-dimensional system, which only employs one kind of d-dimensional Bell states as initial quantum resource and needs neither quantum entanglement swapping nor unitary operations.  
      Keywords:semiquantum cryptography;multiparty semiquantum secret sharing;d -dimensional Bell states  
      17
      |
      67
      |
      0
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Patch Verification Method Integrating Sentence Embedding Model and Code Features

      JIANG Ting-ting, JIANG Shu-juan, HAN Wei
      Vol. 51, Issue 12, Pages: 3450-3456(2023) DOI: 10.12263/DZXB.20230048
      Abstract:Patch verification often runs a test suite to verify the correctness of patches, however, the number of patches generated by automatic repair techniques is often huge, and passing each patch through the test suite in turn incurs an unbearable overhead. To address this problem, this paper proposes a static patch verification method consisting of a sentence embedding model InferSent and an support vector machine (SVM) classifier. InferSent is used to extract static features of the code and the SVM classifier is used to predict the patch correctness. The method focuses more on the static feature information of the code, and by extracting and analyzing the features, it can effectively predict the correctness of the patches generated by automatic repair tools without running a test suite. In this paper, it is validated on a collection of patches generated by several automatic repair tools. The experimental results show that the static patch validation method proposed in this paper achieves an F1 value of 71.89% for patch prediction on the patch sets generated by the repair tool, which is 11.64% and 6.43% higher than the other two state-of-the-art static patch validation methods, respectively, and outperforms the comparison models in terms of all five evaluation metrics. It is shown that the method can correctly predict patches without running the test suite and has good generalization capability.  
      Keywords:program automatic repair;patch verification;code static characteristics;sentence embedding technology;support vector machine;code similarity  
      48
      |
      114
      |
      0
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Analysis of Litz Wire AC Resistance Based on Semi-Analytical Finite Element Method

      JIN Feng-yi, MA Yu-fang
      Vol. 51, Issue 12, Pages: 3457-3462(2023) DOI: 10.12263/DZXB.20230001
      Abstract:Litz wire is widely used in wireless power transfer, eddy current testing and other fields. Due to the large number of strands and complex geometric structure, the difficulty in calculating AC resistance is the main reason for limiting the design of Litz wire structure and electromagnetic parameters. The traditional finite element method and analytical method cannot meet the requirements in terms of computational efficiency and universality. In this paper, the AC resistance of Litz wire considering skin effect, proximity effect and circulating current is analyzed by semi-analytical finite element method and circuit system based on Python language. In the frequency range of 100 Hz to 1 MHz, the accuracy and efficiency of the semi-analytical finite element method for AC resistance calculation are verified based on the parallel Litz wire model, and the influence of pitch on the spatial magnetic field distribution of Litz wire is analyzed. The work in this paper can provide a reference for the structure and electromagnetic parameters selection of Litz wire model in different application scenarios.  
      Keywords:Litz wire;AC resistance;finite element;homogenization;circuit;pitch  
      155
      |
      130
      |
      0
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • ZHOU Liu-fei, SHAO Xian-jie, WANG Hai-hong, WANG Bao-ping
      Vol. 51, Issue 12, Pages: 3463-3472(2023) DOI: 10.12263/DZXB.20230367
      Abstract:This paper presents a novel bidirectional gate driver on array (GOA) circuit based on IGZO (Indium Gallium Zinc Oxide) thin film transistor (TFT), especially for use in in-cell touch displays. The proposed GOA circuit exploits the time-division driving method (TDDM) to implement the in-cell touch panels with a high report rate and prevent the distortion of touch signals. This GOA circuit can operate in a scanning-pausing-restarting mode, i.e., after outputting dozens of continuous scanning pulses of display addressing, the gate driver outputs pause for touch sensing periods. During the time interval for touch operation, touch control unit of proposed GOA is started to work, so that all gate lines will output low potential in order to eliminate interferences from display driving signals. Moreover, the proposed GOA utilizes dual low-level maintaining (LLM) units to suppress threshold voltage shift of LLM TFTs. The operation principle of the GOA is described in detail. The simulated results illustrate that the proposed GOA circuit generates uniform output waveforms regardless of whether the circuit operates in forward or backward scanning, and output waveform in touch holding stage is almost identical to that in normal stage. We fabricated 10.4 inches in-cell touch display panel using IGZO TFT to assess the proposed GOA, and 90 Hz display with 180 Hz touch reporting rate can be perfectly supported. Moreover, the lifetime of GOA circuit under harsh environment is further improved with process and design optimization, the reliability test such as operation at high temperature and humidity (85 ℃/85%) 500 hours has been successfully passed.  
      Keywords:IGZO thin film transistor;gate driver on array;time division driving method;reliability;threshold voltage shift;in-cell touch  
      116
      |
      107
      |
      0
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Research on High-Efficiency Integrated Circuit DFT Technology Based on Machine Learning

      CAI Zhi-kuang, ZHAO Ze-yu, YANG Han, WANG Zi-xuan, GUO Yu-feng
      Vol. 51, Issue 12, Pages: 3473-3482(2023) DOI: 10.12263/DZXB.20220858
      Abstract:This paper proposes a high-efficiency design for test (DFT)technique for integrated circuits based on machine learning. The technology uses the automatically collected data as the training set and determination coefficient as the evaluation index, selects the best prediction model for each type of target parameters, and predicts the target parameters corresponding to the design for test structure based on different configuration parameters, and finally uses the optimal configuration. The inference technology uses the weighted sum of difference value of target parameters as a measure to output the optimal design for test configuration parameters. The experimental data shows that for the most important test coverage parameter in design for test technology, the average prediction error is only 0.075 6%; according to the minimum value of weighted sum of difference value of target parameters, the optimal configuration parameters of the design for test can be efficiently inferred. The prediction effect of this technology has high reliability, and can effectively reduce the test cost and area overhead on the premise of ensuring high test coverage.  
      Keywords:design for test;test compression;test coverage;test time;machine learning  
      136
      |
      119
      |
      1
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • CHAI Rong, CHEN Mi-ling, LI Jin-hong
      Vol. 51, Issue 12, Pages: 3483-3495(2023) DOI: 10.12263/DZXB.20220403
      Abstract:By organically integrating the satellite network with the terrestrial network, the integrated satellite-terrestrial networks can provide flexible network access services for users and meet the requirements of various application scenarios. However, the dynamic changes of satellite network topology, the complex characteristics of satellite-ground links, the significant difference of resource scheduling granularity between multi-network and multi-user and the diversity of resource sharing modes all pose great challenges to the data transmission in the integrated terrestrial-satellite network. The user association and resource scheduling problem is studied for the downlink data transmission scenario of the integrated terrestrial-satellite network which consists of enhanced mobile broadband user (EU) and ultra-reliable and low latency communications user (RU). The joint user association and resource allocation problem is modeled as the system utility function maximization problem under the constraints of user transmission requirements, network available resources and transmission limitations. The formulated optimization problem is a strong coupling problem, which is not easy to solve directly. Then, the original problem is transformed into two sub-problems, i.e., power allocation sub-problem, user association and resource scheduling sub-problem. To tackle the power allocation sub-problem, Lagrange partial relaxation method is used to relax discrete variables into continuous ones, then new variables are introduced to decouple the previously defined variables, and simplified power distribution sub-problem is formulated, which is solved by Lagrange dual algorithm. Based on the obtained power allocation strategies, a heuristic algorithm is proposed to determine user association and resource block allocation strategy. Based on evaluating the available state of time-frequency resources in cellular network, user association and resource block scheduling strategies are designed respectively for the situation of sufficient time-frequency resource and insufficient time-frequency resource. Under the condition of sufficient time-frequency resource, the time-space resource scheduling granularity of RU and EU is defined according to the user resource scheduling mode, and then the time-frequency resource block scheduling strategy is optimized and determined based on Kuhn-Munkres matching algorithm when users apply orthogonal frequency division multiple access (OFDMA) mode. Furthermore, for RU and EU that utilize puncturing mode, a resource block rescheduling strategy is proposed based on greedy algorithm to meet the minimum transmission rate of users. The OFDMA mode and non-orthogonal multiple access (NOMA) mode are determined for the EU occupying adjacent sub-channels to improve the utility function. In view of the insufficient time-frequency resources in cellular network, satellite association mode is assigned to users who cannot access the cellular network, and a resource block scheduling strategy is designed based on Kuhn-Munkres matching algorithm. Finally, the effectiveness of the proposed algorithm is verified by MATLAB simulation software.  
      Keywords:integrated terrestrial-satellite network;user association;resource scheduling;utility optimization;service requirement;dual algorithm  
      41
      |
      107
      |
      3
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Visual Relationship Detection Model Based on Label Hierarchy

      WANG Yuan-long, LEI Ming, WANG Zhi-qiang, ZHANG Hu, LI Ru, LIANG Ji-ye
      Vol. 51, Issue 12, Pages: 3496-3506(2023) DOI: 10.12263/DZXB.20221050
      Abstract:Visual relationship detection is based on target recognition, and further detects the relationship between targets, which is a key technology of visual understanding and reasoning. However, the recall of few-shot tail relation detection is low due to the visual similarity of relation labels and the problem of data imbalance. In order to improve the detection effect of the tail relationship, this paper divides the relationship tags into coarse and fine-grained to construct a hierarchical representation of tags, and proposes a visual relationship detection model based on the tag hierarchy. The model uses the similarity between visual relationships and the bias of the data to build a hierarchical representation of relationship labels, so as to distinguish between coarse-grained relationships and fine-grained relationships, so that the tail relationships can be structured from coarse-grained to fine-grained and get more attention. At the same time, the loss function is designed according to the nature of the label hierarchy. The loss function learns the differences between different category relationships layer by layer through structured information, so that the model can better detect the fine-grained relationship in the tail. The effect of the proposed model in detecting tail relationships is verified in the public datasets Visual Relationship Detection (VRD) and Visual Genome (VG), respectively. Compared with the existing models, the average recall rates mR@20, mR@50 and mR@100 are improved by 0.62%, 1.57% and 2.47% in the VRD dataset, and 0.67%, 0.83% and 1.15% in the VG dataset, respectively.  
      Keywords:visual relationship detection;tag hierarchical representation;long-tailed distributions;coarse-grained relationship;fine-grained relationship  
      123
      |
      109
      |
      0
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Research on Variational Graph Auto-Encoder Based on Multidimensional Cloud Concept Embedding

      DAI Jin, ZHANG Qi-rui, WANG Guo-ying, PENG Yan-hui, TU Sheng-xia
      Vol. 51, Issue 12, Pages: 3507-3519(2023) DOI: 10.12263/DZXB.20220354
      Abstract:Variational graph autoencoder (VGAE) is a significant deep learning model in graph embedding, but there are problems such as the normal prior distribution defect and the posterior collapse during training. Focusing on establishing the mapping relationship between cloud concept space and hidden space, the uncertain concepts of nodes in VGAE network are represented by the digital features of cloud model, and an optimized VGAE model based on multidimensional cloud model (MCM-VGAE) is reconstructed. The model implements a multidimensional cloud concept embedding in the latent space and the corresponding drift loss measure, extends the prior distribution to a generic normal distribution, and uses a multidimensional forward cloud generator and a cloud envelope with modified sampling algorithm to realize the reparameterization process and effectively mitigate the posterior collapse phenomenon. In terms of application, the model outperforms the benchmark model for link prediction, node clustering, and graph embedding visualization experiments on multi-type datasets, further illustrating the universal effectiveness of the method.  
      Keywords:variational graph autoencoder;graph embedding;multidimensional cloud model;concept embedding;link prediction  
      22
      |
      113
      |
      1
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Multi-Stage Feature Fusion Object Detection Method for Remote Sensing Image

      CHEN Li, ZHANG Fan, GUO Wei, HUANG Yun
      Vol. 51, Issue 12, Pages: 3520-3528(2023) DOI: 10.12263/DZXB.20211421
      Abstract:The remote sensing image objects has the characteristics of multi-scale, large aspect ratio, multi-angle and so on, which brings new challenges to traditional object detection methods. To solve the problem of loss of accuracy when existing methods are applied to remote sensing images with small object scales and unbalanced aspect ratios, an object detection method based on dual-stage feature fusion—MF2M (Multi-stage Feature Fusion Method) is proposed. This method combines and splits the feature map channels in first stage, and then adopts the fusion method of convolution splicing to aggregate the characteristics of the channel dimensions, thereby enhancing the output object spatial contour information; in the second stage, we design a multi-scale asymmetric convolution blocks, enhancing the high-dimensional global features of large aspect ratio targets, improving the problem of rough matching between the target and the detection frame, and using a combination of serial and parallel processing to reduce redundant convolution parameters. Finally, we achieve the effect of accelerating network convergence. The experimental results on the DOTA (Dataset for Object deTection in Aerial images) dataset show that after the benchmark method is introduced into MF2M, the accuracy index mAP is increased to 76.44% under the premise of ensuring the detection speed. The results verify the effectiveness and reliability of the algorithm.  
      Keywords:remote sensing image;object detection;double-stage feature fusion;channel splicing;asymmetric convolution  
      113
      |
      171
      |
      2
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Fault Diagnosis of Rotating Equipment Based on Double-Level Aligned Partial Transfer Network

      YU Kun, CHENG Yu-hu, XING Bin, WANG Xue-song
      Vol. 51, Issue 12, Pages: 3529-3539(2023) DOI: 10.12263/DZXB.20221132
      Abstract:With the rapid development of intelligent manufacturing and industrial big data, transfer learning has been widely applied in the field of fault diagnosis of rotating equipment. In the industrial field, there are a large number of scenarios where the label space of the target domain is a subset of the label space of the source domain. The existing transfer learning is unavailable to eliminate the effect of negative transfer of the outlier categories of the source domain on the classification performance of the target domain. In contract, partial transfer learning can realize the feature alignment between the shared categories of the source domain and target domain data by limiting the contribution of source data of different categories in the feature alignment process. However, the existing partial transfer learning only considers the marginal distribution alignment between the shared categories of the source domain and target domain data, while neglecting the conditional distribution alignment between the shared categories of the source domain and target domain data, which leads to a poor accuracy of the diagnostic task. To address this issue, a partial transfer fault diagnosis method based on double-level aligned partial transfer network is proposed. In the proposed method, vision transformer is adopted as the basic network to extract the global feature information from both source domain and target domain data. Meanwhile, a weighting balance mechanism is constructed to promote the marginal distribution alignment between the shared categories of the source domain and target domain data, and a series of metric learning measures are used to realize the conditional distribution alignment between the shared categories of the source domain and target domain data. The identification accuracies of the proposed method in all bearing cases are more than 95%, which verifies the superiority of the proposed method in comparison with other diagnostic methods.  
      Keywords:double-level aligned;weighting balance mechanism;metric learning;partial transfer learning;rotating equipment  
      56
      |
      83
      |
      2
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Automatic Test Pattern Solving with Fault Property Prediction

      HE Li-yuan, HUANG Jun-hua, TAO Ji-ping
      Vol. 51, Issue 12, Pages: 3540-3548(2023) DOI: 10.12263/DZXB.20221121
      Abstract:Automatic test pattern generation (ATPG) based on the Boolean satisfaction model plays a key part in chip fault detection flow, in which solving the corresponding Boolean satisfiability problem (SAT) becomes the efficacy bottleneck of the whole process. In this paper, the influence of different operators on the solution efficiency in the mainstream automatic test pattern solution framework is studied. While ensuring the integrity of the test pattern solution process, a fault analysis mechanism based on deep learning is introduced, and the output vectors are used for the automatic selection of operators and the determination of initial solution states so as to accelerate the overall solution process. To alleviate poor performance mainly caused by insufficient real-world circuit fault data, a generative adversarial network (GAN), followed by a multi-layer graph convolutional neural network (GCN) which is designed to boost representation learning, is leveraged for data augmentation. Experimental results on several real circuits show that the proposed new framework, compared with the original version, has an average solution improvement of nearly 20%.  
      Keywords:automation test pattern generation;graph neural network;generative adversarial network;data augmentation;operator selection  
      114
      |
      107
      |
      0
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Student-Problem Association Based Heterogeneous Graph Knowledge Tracing Model

      YAN Qiu-yan, SI Yu-qing, YUAN Guan, WANG Zhi-xiao
      Vol. 51, Issue 12, Pages: 3549-3556(2023) DOI: 10.12263/DZXB.20221427
      Abstract:Knowledge tracing aims to assess learners' learning status and predict their future performance based on previous answers. However, most of the existing knowledge tracing models only focus on the relationship between problems or skills, and ignore the structural relationship between students and problems. Therefore, we propose a student‑problem association based heterogeneous graph knowledge tracing model (SPKT) . The model integrates the learning ability of students and the importance of problems in knowledge tracing, and uses graph attention network to learn the interaction between students' problems, so as to obtain the embedded representation of students and problems, meanwhile predicting the learners' status. It is proved that SPKT is superior to the existing knowledge tracking model in terms of prediction performance through a large number of experiments and data visualization.  
      Keywords:knowledge tracing;heterogeneous graph network;attention mechanism;learning ability;importance of problems  
      56
      |
      138
      |
      6
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • A Teacher-Student Spatiotemporal Semi-Supervised Method for Urban Event Forecasting

      ZHOU Zheng-yang, LIU Hao, WANG Kun, WANG Peng-kun, WANG Xu, WANG Yang
      Vol. 51, Issue 12, Pages: 3557-3571(2023) DOI: 10.12263/DZXB.20211579
      Abstract:Discrete spatiotemporal event forecasting is one of critical scientific problems in the field of urban computing. Existing works mostly focus on leveraging various spatiotemporal neural networks to model spatiotemporal correlations among dynamic urban features and events, and have achieved promising results. However, it still remains the following problems. First, urban events are naturally induced by multiple causes and distributed spatiotemporal sparsely, while such spatiotemporal sparsity can be induced by the inherent infrequent occurrence and its collection incompleteness. Given that, existing works cannot well address such sparsity challenge and zero-inflated issue in short-term forecasting. Second, the occurred events have the potential to raise future risks on neighboring regions. Unfortunately, off-the-shelf literatures tend to homogenize the correlations of feature-event and event-event, and fail to capture the wane-and-wax influences of historical event sequences on future events. Therefore, to cooperatively exploit the event labels and spatiotemporal features, this paper proposes a teacher-student spatiotemporal semi-supervised learning framework, addressing the challenge of short-term spatiotemporal event forecasting. In the teacher network, to tackle the sparsity challenge of event labels, this paper introduces the semi-supervised scheme into spatiotemporal learning where it designs an AutoEncoder-based feature reconstruction learning and spatiotemporal variance-based anomaly descriptor to facilitate feature representations. In the student network, this work designs a feature-event disentangled dual pipeline and proposes the spatiotemporal attenuation graph convolution network (GCN) and long-short term memory network (LSTM) to imitate the natural risk propagation along spatiotemporal domains. In addition, this paper also develops the spatiotemporal multi-granularity risk prediction task, which emphasizes the easy-to-learn coarse-grained prediction to guide the high-quality fine-grained forecasting, and finally realizes the high-risk discrete region nomination with coarse-to-fine learning mechanism. Experiments on NYC and SIP datasets illustrate that the proposed event forecasting framework outperforms the best baselines by respectively 5.46% and 10.65%, verifying the effectiveness of our work.  
      Keywords:Event forecasting;spatiotemporal multi-granularity forecasting;graph neural network;spatiotemporal semi-supervised learning;teacher-student network  
      35
      |
      107
      |
      0
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Behavior Monitoring Based on Android Accessibility Service

      MA Wen-cong, TAN Yu-an, FENG Shuo, LIU Lu, LI Yuan-zhang
      Vol. 51, Issue 12, Pages: 3572-3581(2023) DOI: 10.12263/DZXB.20220319
      Abstract:The abnormal behavior of users on mobile phones brings certain losses and risks to the country, society, enterprises and individuals. Such as, users record sensitive information of enterprises with the help of mobile phones, or use mobile phones to spread false statements on social networks. However, there is no technology to directly run on the terminal to monitor the user's local application operation. Since most mobile phones are Android platforms, this paper takes Android smart phones as the research object, and proposes a user behavior monitoring technology based on accessibility service. When the phone's interface changes, there will be a large number of accessibility events written based on the view hierarchy. Our method selects the key accessibility events, traverses them, obtains the information on interface component elements, types of accessibility events, interface focus objects and so on, and then judges the user's behavior. Our method does not depend on a specific Android version; improves processing performance by filtering accessibility events; protects users' privacy by adjusting the application monitoring scope and monitoring granularity. In order to prove the feasibility of our method, we experiment on the devices in the physical world and correctly monitor the behavior of users in four different applications. Performance testing shows that our method has low CPU consumption and low average memory occupancy.  
      Keywords:Android;accessibility service;user behavior;monitor;privacy;UI interface  
      73
      |
      105
      |
      0
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • Raw Waveform-Based End-to-End Alzheimer's Disease Detection Method

      CHEN Xu-chu, ZHANG Wei-qiang, MA Yong
      Vol. 51, Issue 12, Pages: 3582-3590(2023) DOI: 10.12263/DZXB.20220162
      Abstract:Alzheimer's disease (AD) is a degenerative disease, as the disease worsens, the patient's language ability gradually decreases. Some researchers have already used acoustic features such as Mel spectrogram and Mel frequency cepstral coefficient (MFCC) to classify AD patients and healthy individuals, but there is a lack of further exploration on using neural networks to extract features from raw waveforms for AD detection. In this paper, we propose an end-to-end AD detection method based on raw waveforms. The method uses one-dimensional convolution to extract time-dimensional features from the original waveform and uses a residual block containing an inflated convolution to extract more complex features. To further improve performance, the squeeze-and-excitation block is introduced into the residual block. On the national conference on man-machine speech communication (NCMMSC) 2021 AD dataset, the model proposed in this paper achieves 86.55% and 81.35% accuracy on the long audio test set and short audio test set, respectively, which is 6.75% and 7.35% better than the baseline system, respectively. On the INTERSPEECH2020 ADReSS dataset, the accuracy of the model is 66.67%, an improvement of 4.17% over the baseline system.  
      Keywords:Alzheimer's disease;speech detection;residual blocks;squeeze-and-excitation block;end-to-end  
      166
      |
      110
      |
      2
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • 基于学生-问题关联的异构图知识追踪模型

      闫秋艳, 司雨晴, 袁冠, 王志晓
      Issue 12, Pages: 3549-3556(2023)
      Abstract:知识追踪旨在评估学习者的学习状态,并根据先前的答题情况预测他们未来的答题表现.然而现有的知识追踪模型大多仅关注问题或技能间的关联,忽略了学生与问题间的结构关系.为此我们提出了基于学生-问题关联的异构图知识追踪模型(Student-Problem association based heterogeneous graph Knowledge Tracing model,SPKT).该模型在知识追踪中融合了学生的学习能力和问题的重要性,并使用图注意力网络学习学生问题间的关联,获得学生、问题的嵌入表示并进行知识状态的预测.通过在真实公开数据集上的性能对比和模型消融实验,并可视化SPKT模型的知识追踪效果,证明了SPKT在预测性能上优于现有的知识追踪模型.  
      Keywords:知识追踪;异构图网络;注意力机制;学习能力;问题重要性  
      21
      |
      47
      |
      6
      <HTML>
      <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • 中英文目录

      Vol. 51, Issue 12, Pages: 3663(2023)
      11
      |
      47
      |
      0
      <HTML>
      <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11

      SURVEYS AND REVIEWS

    • Research on Processor Value Prediction

      HUANG Li-bo, YANG Ling, YANG Qian-ming, MA Sheng, WANG Yong-wen, SUI Bing-cai, SHEN Li, XU Wei-xia
      Vol. 51, Issue 12, Pages: 3591-3618(2023) DOI: 10.12263/DZXB.20230206
      Abstract:The extreme imbalance between processor performance and memory bandwidth/latency limits the overall performance of computing systems. In the post-Moore era, it is challenging to obtain processor performance benefits through the iteration of the integrated circuit manufacturing process, and memory performance is not sensitive to the process. Therefore, people tend to obtain higher-performance computing systems through architectural innovation. Processor value prediction technology is a solution that can effectively alleviate the memory wall problem without changing the storage system. By speculatively breaking the true dependency of data, more instructions can be executed in parallel in an out-of-order processor. There is no need to wait for the execution of long-cycle instructions caused by memory access, etc. In recent years, value prediction has made significant progress in various aspects. However, no commercial processors are using this technology, mainly because the development of value prediction technology still faces many challenges: the pipeline architecture of existing processors cannot directly use value prediction techniques; the register file read and write ports required for value prediction are physically challenging to implement; the huge storage overhead of the value predictor makes it difficult to implement on-chip; due to the significant performance loss when the value prediction is wrong, the value predictors with low prediction accuracy will reduce processor performance. In response to these problems, this paper focuses on value prediction technology. It discusses in detail the research at home and abroad and its solutions to problems and challenges around the value prediction pipeline architecture, value predictor structure, and misprediction recovery mechanism related to value prediction technology. Finally, this paper summarizes processor value prediction techniques and provides an outlook on future research directions.  
      Keywords:value prediction;data dependency;processor;pipeline;memory wall;superscalar  
      90
      |
      118
      |
      1
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • A Comprehension Survey on the Characterization and Development of Neuromorphic Devices

      CAO Zhen, ZHANG Yu-xuan, LI Ling-lei, GUO Zhang, SUN Qi, CAO Rong-rong, HOU Biao, JIAO Li-cheng
      Vol. 51, Issue 12, Pages: 3619-3642(2023) DOI: 10.12263/DZXB.20230458
      Abstract:With the advent of the big data era and the increasingly in-depth study of the human brain system, the field of neuromorphic computing has made breakthrough progress, offering hope to break through the performance issue of traditional computers at the root level. Neural synapses are important basic units for memory training and data processing in the human brain, therefore, it is of great significance for research on neural morphological devices and the implementation of neuromorphic hardware design to develop new materials and structures to study the plasticity of neural synapses based on novel artificial materials and optoelectronic devices. This paper firstly points out the main performance issue of Von Neumann architecture, draws forth the concept of brain-like computing, puts forward the main performance advantages of neuromorphic devices, and sorts out the development history of neuromorphic devices. Then in the field of memristors, the types of memristors, memristor structures and memristor mechanisms are described and analyzed, the advantages and disadvantages of several types of memristors are compared, and the examples of applications of memristors in different fields are presented. Next, based on neural morphological devices, the structures, working principles and applications of magnetic tunnel junctions, new floating gate transistors, and ferroelectric transistors are selected to introduce. Finally, this paper summarizes the achievements and directions of the current development of neural morphological devices and predicts the development prospects of the industry.  
      Keywords:brain-like computing;neuromorphic device;memristor;magnetic tunnel junction;artificial synapse  
      209
      |
      247
      |
      2
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • A Review of the Robust Technology of mMIMO Millimeter-Wave High-Speed Communication System

      LI Song-ting, CHEN Li-hu
      Vol. 51, Issue 12, Pages: 3643-3655(2023) DOI: 10.12263/DZXB.20230789
      Abstract:mMIMO millimeter-wave high-speed communication system is the key foundation for the better communication experience in future human society. Limited by the large random deviation and mismatch in the manufacturing process of integrated circuits, weak robustness has become the main bottleneck restricting the large-scale promotion and application of high-speed communication systems. This paper deeply explores the key factors affecting the performance of mMIMO millimeter-wave high-speed communication system, and summarizes the algorithms such as I/Q mismatch calibration of transceiver link, multi-channel amplitude and phase mismatch calibration of digital/analog hybrid beamforming transceiver link, and nonlinear distortion compensation of transmit array, so as to provide technical support for the construction of immersive, intelligent and global high-speed communication scenarios in the future.  
      Keywords:mMIMO millimeter-wave high-speed communication;robustness;I/Q mismatch calibration;multichannel amplitude phase mismatch calibration;transmission array power amplifier nonlinear distortion calibrationkey  
      91
      |
      119
      |
      2
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11
    • WEN Jun, HONG Hong, SUN Ling, HE Jie, LIU Ke
      Vol. 51, Issue 12, Pages: 3656-3662(2023) DOI: 10.12263/DZXB.20231126
      Abstract:This report provides a comprehensive summary and analysis of the application and funding statistics in various programs within the field of information acquisition and processing under the grant application code of the Information Science Department of the National Natural Science Foundation of China in 2023. These programs include the general program, young scientists fund, fund for less developed regions, key program, excellent young scientists fund, and national science fund for distinguished young scholars. Additionally, the report outlines a detailed work plan for the upcoming year's fund, offering strategic recommendations and insights for further development in the field.  
      Keywords:national natural science foundation of China;information acquisition and processing;application and funding  
      35
      |
      92
      |
      1
      <HTML>
      <L-PDF> <Meta-XML>
      <Citation><Bulk Citation>
      Updated:2025-12-11