2023, 32(1):1-11. DOI: 10.15888/j.cnki.csa.008848
Abstract:In recent decades, computer hardware performance and software scale technology have greatly changed, and they have been involved in all aspects of human social life and production. The rapid development of computer technology has also brought about the concern of program security issues. Since there is a large amount of legacy software on the market, which is unmaintained and lacks source code support, people are worried about its security. As a result, binary analysis techniques are used to address security issues of this kind of software. Furthermore, the techniques can be classified as follows according to their detection ways: static binary code analysis techniques, dynamic binary code analysis techniques, and dynamic and static binary code analysis techniques. This study reviews the recent research on binary code security analysis, describes the main approaches in the above three techniques, and introduces the key techniques in detail.
2023, 32(1):12-28. DOI: 10.15888/j.cnki.csa.008914
Abstract:Object tracking, a basic problem in computer vision, has a wide range of application scenarios. Due to the advance in the computational capacity of hardware and deep learning methods, conventional deep learning methods for object tracking have higher precision, but they face the problems of massive model parameters and high demand for computational resources and power consumption. In recent years, with the booming development of unmanned aerial vehicle (UAV) and Internet of Things (IoT) applications, a great deal of research focuses on how to achieve real-time tracking in embedded hardware environment with limited storage space and computational capacity and low power consumption. Firstly, object tracking algorithms in the embedded environment, including the ones combining correlation filters with deep learning and those based on lightweight neural networks, are analyzed and discussed. Secondly, deployment procedures of deep learning models and classical embedded object tracking applications, such as those in UAVs, are summarized. Finally, future research directions are given.
2023, 32(1):29-40. DOI: 10.15888/j.cnki.csa.008909
Abstract:Nowadays, the global navigation satellite system (GNSS) has basically achieved real-time positioning with high precision in outdoor open environments. With the acceleration of urbanization, however, providing pedestrian navigation services for densely built-up sites disturbed by GNSS signals generates great demand, which has significantly promoted indoor positioning technology in recent years. Furthermore, as there is no single universal positioning method to realize the seamless transition between indoor and outdoor environments, seamless navigation technology introduces new hot spots and research topics to solve the “last-kilometer” problem in the navigation field. This study summarizes the multi-sensor fusion technology for indoor pedestrian navigation: (1) The advantages and limitations of a single sensor in indoor positioning are analyzed and compared from the perspective of radio frequency signals and non-electrical signals separately; (2) the positioning methods in the field of indoor multi-sensor fusion are introduced, including multimodal fingerprint fusion, geometric ranging fusion, and PDR-based fusion. Finally, the solution to the application of indoor positioning technology in seamless navigation is studied, and the challenges and prospects of seamless positioning in indoor and outdoor environments are presented. The research provides references and assistance to the follow-up research on high-precision seamless positioning.
2023, 32(1):41-49. DOI: 10.15888/j.cnki.csa.008805
Abstract:Action recognition aims to make computers understand human actions by the processing and analysis of video data. As different modality data have different strengths in the main features such as appearance, gesture, geometric shapes, illumination, and viewpoints, action recognition based on the multi-modality fusion of these features can achieve better performance than the recognition based on single modality data. In this study, a comprehensive survey of multi-modality fusion methods for action recognition is given, and their characteristics and performance improvements are compared. These methods are divided into the late fusion methods and the early fusion methods, where the former includes prediction score fusion, attention mechanisms, and knowledge distillation, and the latter includes feature map fusion, convolution, fusion architecture search, and attention mechanisms. Upon the above analysis and comparison, the future research directions are discussed.
2023, 32(1):50-60. DOI: 10.15888/j.cnki.csa.008922
Abstract:The prediction of impurity disruption during the discharge period of experimental advanced superconducting tokamak (EAST) is of great significance for the long-pulse steady-state discharge of future EAST. According to the physical characteristics of impurity disruption, the data of 334 impurity disruptive discharges in 2018 and 1 628 non-disruptive discharges in 2021 are selected as training discharges. Then, the training samples composed of eight diagnostic signals, including plasma equilibrium, density, current, and radiation signals, are used to train the impurity disruption prediction model by LightGBM. The test results reveal that the LightGBM model can accurately predict the impurity disruption, with a success rate of 96.29%, while for non-disruptive discharges, the false positive rate is 6.87%. The research results indicate that it is feasible to use LightGBM to predict plasma impurity disruption of EAST.
2023, 32(1):61-74. DOI: 10.15888/j.cnki.csa.008849
Abstract:Hash tables play an important role in network message processing, especially in the processing of messages with states. With the rapid growth of network traffic, the hash tables of traditional software can hardly meet the needs of network performance, and search is one of the key factors affecting the performance of hash tables. In addition, the improvement in the search rate of hash tables has always been a difficult problem. The research reveals that the existing network traffic presents the characteristics of Pareto distribution, namely that there is a small number of massive traffic data—elephant flow. On the basis of the computing mode of software-hardware co-design used in the current data center, a large-scale hash table architecture with software-hardware co-design is proposed on the basis of DPDK+FPGA. According to the characteristics of existing network traffic, this method divides the traffic into elephant flow and background flow, and meanwhile, the hash table is divided into a hardware table and a software table. A small-scale hardware table is constructed in FPGA to unload the hash calculation of all messages and the hash search of elephant flow. In the software, a large-scale software table is constructed on the basis of DPDK, and the hash calculation is unloaded by FPGA to speed up the search of background flow. As the software has all the flow information, the sampling method is used to identify the elephant flow and update the key-value pair of the elephant flow to the hardware table of FPGA, so as to accelerate the search rate of the large-scale software table in the software. The Xilinx U200 accelerator card and general server are employed as the hardware platform to realize the large-scale hash table with software-hardware co-design, and the traffic data in line with the current network characteristics is constructed by the tester. The accurate forwarding of DPDK is used as an example to verify the performance of the hash table with hardware-software co-design. The results reveal that when the hash search of elephant flow is completely unloaded, its performance is 64%–75% higher than the original accurate forwarding of DPDK; when the elephant flow is not unloaded, its performance is improved by 5%–48%.
2023, 32(1):75-86. DOI: 10.15888/j.cnki.csa.008901
Abstract:Assisting users in understanding the clauses of insurance products is one of the hot issues in insurance applications. It is feasible to assist the life insurance business with knowledge graph technology. The life insurance knowledge graph (LIKG) is extracted and constructed by multi-source data. Specifically, the BERT-IDCNN-BiLSTM-CRF model is applied to extract entities from unstructured data, and the entity is aligned by a variety of short text similarity algorithms and ranking ensemble algorithm. A two-stage extraction algorithm is designed to fill the attributes of insurance products by Bootstrapping and classification prediction. Then a prototype system is designed based on LIKG. The system uses the entity extraction and the attribute extraction to provide knowledge acquisition, designs an index called CF-IIF to provide attribute recommendation function, and realizes a visual interface to help users quickly master the information of life insurance, which demonstrates the application value of LIKG.
2023, 32(1):87-98. DOI: 10.15888/j.cnki.csa.008905
Abstract:Sleep problems are becoming increasingly prominent in contemporary society. Timely detection and evaluation of sleep quality can help diagnose sleep diseases. In view of the uneven development of sleep monitoring products on the market, this study builds an online real-time sleep staging system based on dual-channel EEG signals, which uses the third-party interface brain ring to obtain EEG data, and the study combines with a CNN-BiLSTM neural network model to realize online real-time sleep staging and music regulation on the personal computer (PC). The system uses the algorithm model based on both a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) neural network to automatically extract features of EEG signals. CNN can extract high-order features, and BiLSTM can capture the dependence and correlation of data before and after sleep, which makes the accuracy of sleep staging higher. The experimental results show that the proposed algorithm model achieves a staging accuracy of 92.33% and a Kappa coefficient of 0.84 in the four-classification task on the Sleep-EDF public data set. The real-time sleep staging function of the system achieves a staging accuracy of 79.17% in a self-collected sleep data staging experiment, with a Kappa coefficient of 0.70. Compared with other sleep monitoring products, this system has higher accuracy in sleep staging, diversified application scenarios, and strong real-time capability and reliability. Besides, it can regulate music for users according to the staging results to improve the sleep quality of users.
2023, 32(1):99-108. DOI: 10.15888/j.cnki.csa.008883
Abstract:Amid the further development of the marine meteorological business, marine meteorological services are gradually developing towards specialization, visualization, and intelligence. As a result, comprehensive marine meteorological services can no longer meet the actual business needs of meteorological services to ports. To ensure the safety of port production and improve the efficiency of meteorological services to ports, this study proposes a construction scheme for an intelligent meteorological service system for ports based on the service-oriented architecture (SOA). Multi-source heterogeneous business data, such as meteorological, port, and geographic information, are dynamically integrated, and extensive markup language (XML), Web service, data warehouse, middleware mode, WebGIS, message queue, and other computer-related technologies are employed. Various functions are thereby fulfilled, including real-time monitoring of meteorological business data of a port area, professional forecast and early warning for ports, preparation and release of emergency plans, and threshold management of professional users and meteorological elements. The business application results of the proposed system show that the system deserves application and promotion as it meets the demand of professional meteorological services to ports, effectively reduces the adverse impact of marine meteorological disasters on the production activities in the port area, and is highly scalable.
2023, 32(1):109-118. DOI: 10.15888/j.cnki.csa.008894
Abstract:When designing a fault-tolerant scheduling algorithm in a real-time heterogeneous system, it is necessary to consider the constraints of real-time and maximize the reliability of the system. Furthermore, parallel application scheduling problems in heterogeneous systems have been shown to be NP-complete. Most of the existing fault-tolerant scheduling algorithms use replication technology to improve the reliability of the system, but the multiple execution of tasks will lead to longer application execution time and reduced system real-time performance. Therefore, a fault-tolerant scheduling algorithm based on active replication technology is proposed. The algorithm continuously replicates the tasks that have the least impact on the real-time performance of the current system in the task set and then schedules all tasks in the task set to the earliest completed processor. While meeting the real-time constraints, the algorithm improves the reliability of the system. Experiments show that the reliability of the proposed algorithm has been improved under strict time constraints compared with that of the DB-FTSA algorithm which also focuses on real-time heterogeneous systems.
2023, 32(1):119-126. DOI: 10.15888/j.cnki.csa.008925
Abstract:As an innovative distributed ledger technology, a Blockchain has broad application prospects in many industries due to its features of decentralization, traceability, and tamper resistance. However, the existing single-chain structure of Blockchains faces problems such as low concurrency and high latency. The emergence of a new ledger technology based on the directed acyclic graph (DAG) structure is expected to break through the performance bottleneck of traditional Blockchains, but the current consensus mechanism based on the DAG-based Blockchain system is not mature. This study improves the security problems in the open representative voting (ORV), a consensus mechanism of the Nano network for the typical DAG-based Blockchain system, and proposes a consensus mechanism of open election representative voting (OERV) based on the representative election model. The rights and interests of the main representative nodes are dispersed; the degree of decentralization is enhanced, and the network security is improved. The experimental results reveal that the OERV algorithm has high performance and can enhance the stability and security of the system without sacrificing system efficiency. It is of practical significance for promoting the research on the consensus mechanism of DAG-based Blockchains.
2023, 32(1):127-134. DOI: 10.15888/j.cnki.csa.008885
Abstract:The object detection algorithms based on the feature pyramid network do not give due consideration to the scale differences among different objects and the high-frequency information loss during cross-layer feature fusion, denying the network sufficient fusion of global multi-scale information and consequently resulting in poor detection effects. To solve these problems, this study proposes a scale-enhanced feature pyramid network. This method improves the lateral connection and cross-layer feature fusion modes of the feature pyramid network. Specifically, a multi-scale convolution group with the dynamic receptive field is designed to serve as a lateral connection so that the feature information of each object can be extracted sufficiently, and a high-frequency information enhancement module based on the attention mechanism is introduced to promote the fusion of high-layer features with low-layer ones. The experimental results on the MS COCO dataset show that the proposed method can effectively improve the detection accuracy on objects at each scale and its overall performance is better than that of the existing methods.
2023, 32(1):135-145. DOI: 10.15888/j.cnki.csa.008864
Abstract:Neural process (NP) combines the advantages of neural networks and Gaussian processes to estimate uncertainty distribution functions from a small number of contexts and implement function regression. It has been applied to a variety of machine learning tasks such as data complementation and classification. However, for 2D data regression problems (e.g., image data completion), the prediction accuracy of NP and the fitting of the contexts are deficient. To this end, an image-faced neural process (IFNP) is constructed by integrating a convolutional neural network (CNN) into the neural process based on the lower bound of evidence and loss function derivation. Then, a local pooled attention (LPA) module and a global cross-attention (GCA) module are designed for the IFNP, and an image-faced attentive neural process (IFANP) model with significantly better performance than the NP and IFNP is constructed. Finally, these models are applied to MNIST and CelebA datasets, and the scalability of IFNP is demonstrated by combining qualitative and quantitative analysis. In addition, the better data completion and detail-fitting ability of IFNP are confirmed.
2023, 32(1):146-155. DOI: 10.15888/j.cnki.csa.008889
Abstract:Traditional image stitching algorithms are slow and fail to meet the requirements of obtaining large-resolution panoramic images in real time. To solve these problems, this study proposes an image registration algorithm based on CUDA’s speeded-up-robust features (SURF) and carries out CUDA parallel optimization on the detection and description of feature points of traditional SURF algorithms in terms of GPU thread execution model, programming model, and memory model. In addition, based on FLANN and RANSAC algorithms, the study adopts a bidirectional matching strategy to match features and improve registration accuracy. The experimental results show that compared with serial algorithms, the proposed parallel algorithm can achieve an acceleration ratio of more than 10 times for images with different resolutions, and the registration accuracy is 17% higher than that of traditional registration algorithms, with an optimal accuracy of as high as 96%. Therefore, the SURF algorithm based on CUDA acceleration can be widely used in the field of security monitoring to realize the real-time registration of panoramic images.
2023, 32(1):156-165. DOI: 10.15888/j.cnki.csa.008902
Abstract:Conformance checking refers to the alignment between a computational process model and its actual execution. Conformance checking at runtime has become a new problem in current conformance checking due to the real-time feedback and positive application prospects. For each newly generated event, how to calculate and obtain the optimal conformance checking at a low performance cost is a difficult point for conformance checking at runtime. Based on the refined process structure tree (RPST) of the process model, this study proposes a conformance monitoring tree (CMT) and a dynamic programming algorithm to obtain the optimal conformance result based on the CMT. Through three experimental datasets, it is shown that compared with the existing work, the proposed algorithm has obvious performance advantages.
2023, 32(1):166-178. DOI: 10.15888/j.cnki.csa.008911
Abstract:Original Harris hawks optimization (HHO) has low convergence accuracy and slow convergence speed and is easy to fall into local optimum. In view of these problems, an improved HHO based on a hybrid strategy (HSHHO) is proposed. Firstly, the Sobol sequence is introduced in the population initialization stage to generate a uniformly distributed population, which enriches the diversity of the population and helps to improve the convergence speed of the algorithm. Secondly, the limit threshold is introduced to make the algorithm perform global exploration when it does not obtain a better value within a certain number of iterations. This can improve the ability of the algorithm to jump out of a locally optimal solution and solve the problem that HHO is prone to fall into a locally optimal solution in late iterations because it only executes the development phase. Finally, a dynamic backward learning mechanism is proposed to improve the algorithm’s convergence accuracy and ability to jump out of the local optimum. The proposed algorithm is tested by nine benchmark functions and six CEC2017 functions and compared with various optimization algorithms and HHO variants. As a result, this study verifies the effectiveness of the proposed strategies and performs Wilcoxon signed rank test, Friedman test, and Quade test. The experimental results show that HSHHO has great performance in terms of convergence speed, optimization accuracy, and statistical tests. Furthermore, the proposed algorithm is applied to the design optimization of welded beams. The results show that HSHHO also has a positive effect on practical engineering optimization problems with constraints.
2023, 32(1):179-186. DOI: 10.15888/j.cnki.csa.008917
Abstract:With the increasing number of electric vehicles (EVs), the related supporting facilities are also facing great challenges. Unreasonable charging resource allocation will cause overcrowding at some charging stations during the peak charging period and affect the stable operation of power grids. A scheduling model considering multi-objective optimization is proposed. Upon the analysis of the queuing time of different charging options at the charging stations, a dynamic pricing model considering the queuing rate and time-of-use tariff is presented to affect the charging behavior of EV owners. The charging cost is calculated with the dynamic pricing model and the charging demand. Considering the travel time of the total charging path based on the starting and ending points, the optimization objective is to minimize the total cost, which is solved by the DEB-ABC algorithm. The simulations of 1 500 EVs in a certain area indicate that the proposed optimal scheduling model can reduce the waiting time for charging, charging costs, and total driving time and improve the utilization of charging stations in the area.
2023, 32(1):187-196. DOI: 10.15888/j.cnki.csa.008918
Abstract:As the current data encryption algorithms lack covertness, a visually secure image encryption algorithm is proposed, which combines the P-tensor product compressive sensing (PTP-CS) model and the new segmented chaotic map (SCM). First, the new SCM with fractional structure is designed according to the “stretching and squeezing” mechanism to construct the key-controlled measurement matrix. Secondly, under the joint control of the measurement matrix and cipher code streams, the intermediate secret image without visual semantics is generated after the two-dimensional (2D) Arnold scrambling, linear measurement, and bidirectional XOR diffusion of the plaintext wavelet-packet coefficient matrix. Then, the digital steganographic coding approach is employed to embed it stochastically into the non-secret-involved transmission medium to synchronously protect the content and appearance of the sensitive plaintext data. Simulation experiments and security analysis indicate that the proposed encryption algorithm is capable of defending against various common attacks, and it has good visual security and compression performance.
2023, 32(1):197-205. DOI: 10.15888/j.cnki.csa.008887
Abstract:As information technology develops, recommendation system serves as an important tool in the era of information overload and plays an increasingly important role. Traditional recommendation systems based on content and collaborative filtering tend to model the interaction between users and items in a static way to obtain users’ previous long-term preferences. Because users’ preferences are often dynamic, unsustainable, and behavior-dependent, sequential recommendation methods model the interaction histories between users and items as ordered sequences, which can effectively capture the dependencies between items and users’ short-term preferences. However, most sequential recommendation models overemphasize the behavior order of user-item interaction and ignore the temporal information in interaction sequences. In other words, they implicitly assume that adjacent items in the sequences have the same time interval, which leads to limitations in capturing users’ preferences that include temporal dynamics. In response to the above problems, this study proposes a self-attention-based network for time-aware sequential recommendation (SNTSR) model, which integrates temporal information into an improved self-attention network to explore the impact of dynamic time on the prediction of the next item. At the same time, SNTSR independently calculates position correlation to eliminate the noise correlations that may be introduced and enhance the ability to capture users’ sequential patterns. Extensive experimental studies are carried out on two real-world datasets, and results show that SNTSR consistently outperforms a set of state-of-the-art sequential recommendation models.
2023, 32(1):206-213. DOI: 10.15888/j.cnki.csa.008937
Abstract:Energy distribution is often related to the local environment. Regarding energy distribution prediction, data on local environmental factors can be availed to predict the value of energy to be distributed to the region, thereby maximizing the extent of proper energy distribution. The long short-term memory (LSTM) network, despite its favorable short-term prediction effect, is weakened by error accumulation, a slow speed, and poor accuracy when it is used for long-term data prediction. As a new algorithmic energy prediction model recently proposed, Informer is fast but not sufficiently capable of prediction in this task. This study proposes a Conv1d-LSTM model that achieves better prediction results than those of the above two models with a smaller mean absolute error (MAE) and root mean square error (RMSE).
2023, 32(1):214-223. DOI: 10.15888/j.cnki.csa.008879
Abstract:The detection of continuous outliers for sliding windows is an important problem in data stream management, which plays an important role in many fields such as credit card fraud detection, network intrusion prevention, and early warning for geological hazards. Most of the existing algorithms require the use of the range query to determine the positional relationship between objects, but the cost of the range query is usually high, which cannot meet real-time requirements. Therefore, this study proposes the grid-based excepted heap (GBEH), a query processing framework based on sliding windows. Specifically, GBEH proposes a grid queue based index (GQBI) on the basis of the grid to manage data streams, which maintains the positional relationship between data streams and the temporal relationship of data streams. Furthermore, GBEH proposes an outlier detection algorithm, namely, the priority based heap. This algorithm calculates the mathematical expectation of the number of objects in the cell that is included in the query range by use of the intersection area of the query range and the cell and on this basis, establishes an execution range query based on the min-heap. In this way, it effectively reduces the cost of range queries and achieves efficient detection. Theoretical analysis and experiments verify the efficiency and stability of GBEH.
2023, 32(1):224-232. DOI: 10.15888/j.cnki.csa.008858
Abstract:Considering the problems that the traditional Seq2Seq model cannot accurately extract key information from texts and process words outside the word list in text summarization tasks, this study proposes a pointer generator network (PGN) model based on Fastformer. The model combines the text summarization methods of extraction and generation. Specifically, the Fastformer model is used to efficiently obtain the word embedding vector with context information, and then PGN helps choose to copy words from the source text or use vocabulary to generate new summary information, so as to solve the out-of-vocabulary (OOV) problem that often occurs in text summarization tasks. At the same time, the model uses the coverage mechanism to track the attention distribution of the past time step and dynamically adjust the importance of words to solve the problem of repeated words. Finally, the Beam Search algorithm is introduced in the decoding stage to make the decoder obtain more accurate summary results. The experiments on the dataset of auto-diagnosis dialogues provided by Auto Master in AI Studio of Baidu show that the Fastformer-PGN model proposed in this study achieves better performance in text summarization tasks of Chinese dialogues than the benchmark model.
2023, 32(1):233-240. DOI: 10.15888/j.cnki.csa.008893
Abstract:Traditional low-power adaptive hierarchical cluster protocols in wireless sensor networks have high node energy consumption, short network lifetime, and unbalanced load. In order to solve these problems, this study proposes a Harris hawks routing optimization algorithm that reflects multi-objective cluster head election and is based on simulated annealing in heterogeneous sensor networks. On the basis of calculating the optimal threshold of nodes, the improved algorithm firstly constructs a new fitness function considering energy consumption and load to find the optimal cluster head node and ensure the uniform distribution of cluster head nodes. Then, a path selection strategy based on Harris hawks optimizer is established, and the simulated annealing algorithm is embedded to prevent from premature local optimum. Finally, the study uses an evaluation function to select cluster heads that can be added to the optimal path to shorten the communication distance between cluster head nodes and base stations. The simulation results show that compared with the CREEP, LEACH-C, and LEACH algorithms, the proposed algorithm prolong the network lifetime by 22.18%, 77.83%, and 180.52%, respectively, and thus they can prolong the network lifetime more effectively.
2023, 32(1):241-248. DOI: 10.15888/j.cnki.csa.008892
Abstract:Given the common problems of crowd counting with a complex background, occlusion, and uneven crowd distribution, a joint loss-based space-channel dual attention network (JL-SCDANet) is proposed. The front end of the network extracts coarse-grained features of an image, and the spatial attention mechanism and channel attention mechanism are added in the middle to highlight the key areas of the image, while the back end uses dilated convolution that can increase the receptive field without losing the image resolution to extract deep two-dimensional features. In addition, the model is trained with the joint loss function to enhance its robustness. Comparative experiments are carried out on three public data sets (i.e., ShanghaiTech Part B, mall, and UCF_CC_50) to verify the improvement effect of the model. In terms of the mean absolute error (MAE) and mean square error (MSE), the results on ShanghaiTech Part B, mall, and UCF_CC_50 reach 8.13 and 13.13, 1.78 and 2.28, and 182.12 and 210.24, respectively. The experimental results prove the effectiveness of the network in improving the accuracy of population statistics.
2023, 32(1):249-256. DOI: 10.15888/j.cnki.csa.008916
Abstract:Yak grade evaluation is an important part of high-efficiency yak breeding. To reduce the influence of imbalanced data set distribution on the prediction results of yak grading in the research, this study proposes a yak grade evaluation model based on an improved conditional generative adversarial network model, called VAE-CGAN. Firstly, to obtain high-quality generated samples, the model reduces the uncertainty from random variables by introducing a variational autoencoder to replace the random noise in the input of the conditional generative adversarial network. In addition, the model inputs the yak label as conditional information into the generative adversarial model to obtain the generated samples of the specified category, and the generated samples and training samples are utilized to train the deep neural network classifier. The experimental results show that the overall prediction accuracy of the model has reached 97.9%. The Precision, Recall, and F1 value on the grade prediction of premium yak have increased by 16.7%, 16.6%, and 19.4% respectively compared with those of the generative adversarial network. The results indicate the model can achieve yak classification with high accuracy and low misclassification rate.
2023, 32(1):257-265. DOI: 10.15888/j.cnki.csa.008915
Abstract:The purpose of influence maximization is to find a small group of nodes in a network that can trigger the maximum number of remaining nodes to participate in the process of information transmission. At present, the research on the influence maximization of heterogeneous information networks usually extracts homogeneous subgraphs from the network or evaluates the influence of nodes according to the meta-path of local node structure. However, it does not consider the global features of nodes and the influence loss of the final spread range of the seed set caused by the clustering phenomenon among highly influential nodes. This study proposes an influence maximization algorithm for heterogeneous information networks based on community and structure entropy, which can effectively measure the influence of nodes locally and globally. Firstly, the local structure information and heterogeneous information of nodes in the network are retained by the construction of meta-structure to measure the local influence of nodes. Secondly, the global influence of nodes is measured by the weight ratio of the community to which the nodes belong to the whole network. Finally, the final influence of nodes is calculated, and the seed set is selected. Many experiments on real data sets indicate that the proposed algorithm is effective and efficient.
2023, 32(1):266-274. DOI: 10.15888/j.cnki.csa.008912
Abstract:Present image encryption algorithms ignore the protection of the visual security of encrypted images. Therefore, it is valuable to combine a new cosine chaotic map (CCM) with Bayesian compressive sensing (BCS) and thus propose a visually meaningful image encryption (VMIE) algorithm. Firstly, a new one-dimensional chaotic map based on the cosine function is proposed to construct a controlled measurement matrix. In addition, the proposed new CCM can better disrupt the strong correlation of images. Secondly, the wavelet packet coefficient matrix of a plain image is scrambled by 2D Arnold scrambling algorithm. Then, the scrambled secret image is compressed and encrypted by a chaotic measurement matrix and bidirectional modulo-adding diffusion strategy. Finally, a visually meaningful ciphertext image is obtained by embedding the secret image into the carrier image after game-of-life (GOL) mixed scrambling through the least significant bit embedding algorithm. Simulation results and security analysis show that the proposed algorithm is feasible and efficient on the premise of ensuring visual security and decryption quality.
2023, 32(1):275-280. DOI: 10.15888/j.cnki.csa.008908
Abstract:The detection and segmentation of human blood cells can assist doctors to quickly make simple judgments on the current health of the human body, which is of great significance for disease diagnosis. In segmentation tasks of blood cells, the traditional image segmentation algorithm may wrongly segment the target and is unable to completely segment the target. To address these problems, this study proposes a blood cell segmentation algorithm XCA-Unet++ fusing Xception feature extraction and the coordinate attention mechanism. On the basis of the Unet++ network structure, the algorithm introduces the Xception feature extraction network in the encoder part to better extract low-level feature information. Moreover, a cell detection module based on the coordinate attention mechanism is designed to enhance the network’s feature extraction ability for blood cells with blurred edges and incomplete cells. DiceLoss is used as the loss function to optimize the imbalance of positive and negative samples in the dataset and speed up network convergence. The experimental comparison on the public blood cell dataset indicates that the XCA-Unet++ network achieves the results of 94.44%, 96.78%, and 97.12% for the evaluation indicators IoU, Acc, and F1, respectively, and the segmentation performance is better than that of other segmentation networks. Thus, it meets the high-precision requirements of blood cell segmentation tasks.
2023, 32(1):281-287. DOI: 10.15888/j.cnki.csa.008886
Abstract:In the cloud storage environment, data owners can store and share data through cloud servers, but the following security issues may exist. First, data owners need to guarantee the authentication of their data. Secondly, the data may contain the data owner’s sensitive information, such as name, age, and other information. Therefore, data owners may reveal their sensitive information when sharing data with other users. To solve the above problems, this study proposes a certificateless sanitizable signature scheme to ensure the authentication of shared data and the sensitive information hiding in cloud storage environments. Specifically, the proposed scheme is based on certificateless cryptography, which avoids the high certificate management overhead in traditional public key infrastructure and eliminates the key escrow defect in identity-based cryptography. In addition, the scheme adds access control, so that the data stored in the cloud server can only be accessed by authorized users. Finally, the security analysis shows the security of the scheme and the performance analysis reflects the efficiency of the scheme.
2023, 32(1):288-295. DOI: 10.15888/j.cnki.csa.008899
Abstract:Football match scenes are featured with dense crowds and many mobile targets, and YOLOv3 algorithm has low detection accuracy and requires massive model parameters, which makes it unable to be deployed on mobile devices with limited computing power. In view of these problems, this study proposes a pedestrian detection method based on improved YOLOv3. Specifically, the study replaces the Darknet-53 backbone feature extraction network with a more efficient and lightweight GhostNet network, selects detection branch layers with four scales, and adopts the K-means++ algorithm to improve the clustering effect of the anchor box. Furthermore, the study adds spatial pyramid pooling to achieve an output with the same size as the input image, puts forward the CIoU loss function to calculate the loss value of target positioning, adds heatmap visualization, and uses Mosaic data enhancement in training. The experimental results show that YOLOv3-GhostNet achieves a mAP of 90.97% on the VOC fusion dataset, with an improvement of 1.75% compared with the YOLOv3 algorithm. In addition, it reduces the number of parameters by about 81.4% and increases the real-time detection rate by about 1.5 times, which shows a positive detection effect on small mobile devices.
2023, 32(1):296-301. DOI: 10.15888/j.cnki.csa.008769
Abstract:Accurate recognition of speech emotion information can help to greatly improve the efficiency of human-computer interaction. At present, the speech emotion recognition system mainly consists of two steps: speech feature extraction and speech feature classification. In order to improve the accuracy of speech emotion recognition, the spectrogram is used as the model input instead of traditional acoustic features, and the CGRU network based on the attention mechanism is adopted to extract the frequency domain and time domain information in the spectrogram. The experimental results show that the introduction of the attention mechanism in the model is beneficial to reduce the interference of redundant information, and compared with the model based on the LSTM network, the model using the GRU network can fast converge during training and has higher prediction accuracy. In addition, the training time of the GRU-based model is only 60% of that of the LSTM-based baseline model.
2023, 32(1):302-309. DOI: 10.15888/j.cnki.csa.008898
Abstract:While ensemble learning has achieved remarkable success in generalization performance, the error analysis of ensemble learning needs further research. As cross-validation has an important application for model performance evaluation in statistical machine learning, block-3×2 cross-validation and k-fold cross-validation are applied to integrate the weighted prediction values for each sample point and analyze the error. Experiments on simulated data and real data show that the prediction error of ensemble learning based on block-3×2 cross-validation is smaller than that of a single learner, and the variance of ensemble learning is smaller than that of a single learner. The generalization error of the ensemble learning based on block-3×2 cross-validation is less than that of the one based on k-fold cross-validation, which indicates that the ensemble learning model based on block-3×2 cross-validation has good stability.
2023, 32(1):310-315. DOI: 10.15888/j.cnki.csa.008949
Abstract:In this study, a monocular vision measurement method based on AKAZE feature detection and the PnP algorithm is used to calculate the relative attitude of a camera and quickly and accurately determine the attitude relationship between two objects in the space. Specifically, the template image of the cooperative target is collected, and the pixel coordinates of the four feature points attached to the cooperative target are extracted. Then, the template image and the image to be measured are matched by key points of AKAZE, and the mapping matrix is calculated. After that, the pixel coordinates of the four feature points in the image to be measured are obtained through the mapping matrix. Finally, given the size information of the cooperative target, the PnP problem based on the four coplanar feature points is solved, and the relative positions of the camera and the cooperative target are calculated. The experimental analysis shows that the real-time image camera attitude calculated by this method is close to the real result, which verifies the effectiveness of this method.
2023, 32(1):316-326. DOI: 10.15888/j.cnki.csa.008927
Abstract:Accurate prediction of the water level can guide urban flood control and calamity reduction, as well as water conservancy construction to improve the speed of urban flood emergency response. Data-driven water level prediction models, especially the long short-term memory (LSTM) models, have shown advantages in simulating the strong nonlinear relationships of hydrological elements in nature and thus are widely used. However, the collection of hydrological data in nature is often accompanied by noise and human interference factors, which affect the prediction performance of the models. To address this problem, this study develops a new prediction model combining singular spectrum analysis (SSA) and LSTM, i.e., the SSA-LSTM model. Specifically, SSA first decomposes the observed time series into periodic, trend, and noise components, and then LSTM is used to train the model on the denoised time series to obtain the final prediction results. In this study, the water levels of Guoyang Sluice in the Guohe River Basin from May 1971 to December 2020 are selected as the data set for experiments: 1) The original time series data of water levels are decomposed into multiple trend and noise components (RC1–RC12) by SSA, and the components (RC1–RC10) are selected as the trend term and reconstructed into a new water-level time-series signal. 2) The reconstructed signal is trained and verified by the LSTM model, and the predicted results are compared with those of the LSTM model. 3) To obtain the optimal SSA-LSTM model, this study conducts single-step prediction performance evaluation experiments for different time steps (7, 14, 21, 28, and 35 d). The experimental results reveal that the coefficient of determination R2, root mean square error (RMSE), and mean absolute percentage error (MAPE) of the SSA-LSTM water-level prediction model are better than those of the LSTM model at different time steps. The pre-processing of the water level at the Guoyang Sluice by SSA can effectively improve the prediction effect of LSTM. Compared with the traditional LSTM models, the SSA-LSTM model has the characteristic of high reliability and low errors and is more adaptable in water-level prediction applications, which can provide a better decision basis for the rational scheduling of urban flood control, irrigation, water supply, and other water conservation measures.
2023, 32(1):327-336. DOI: 10.15888/j.cnki.csa.008878
Abstract:As the terrain generation algorithm has trouble balancing ease of use, controllability, realism, and speed, this study proposes a terrain generation method based on sketch maps. This method uses the generative adversarial network to model the terrain slope, slope aspect, and other information in the hidden space so that the generated terrain conforms to the constraints of the user’s hand-drawn sketch map. This study also proposes a sketch map extraction algorithm based on terrain height maps, and it can extract a sketch map to a hand-drawn effect from a real terrain height map and quickly build the data set. An algorithm for multi-scale terrain detail filling is proposed. Owing to the introduction of the multi-scale concept, the terrain texture details are dynamically supplemented, and the realism and aesthetic properties are greatly improved. A terrain satisfaction evaluation method based on user feedback is proposed and verified by experiments. The results show that the proposed terrain generation method can accurately and efficiently generate digital terrain that meets users’ expectations.
2023, 32(1):337-347. DOI: 10.15888/j.cnki.csa.008907
Abstract:In this study, a multimodal emotion recognition method is proposed, which combines the emotion recognition results of speech, electroencephalogram (EEG), and faces to comprehensively judge people’s emotions from multiple angles and effectively solve the problems of low accuracy and poor robustness of the model in the past research. For speech signals, a lightweight fully convolutional neural network is designed, which can learn the emotional characteristics of speech well and is overwhelming at the lightweight level. For EEG signals, a tree-structured LSTM model is proposed, which can comprehensively learn the emotional characteristics of each stage. For face signals, GhostNet is used for feature learning, and the structure of GhostNet is improved to greatly promote its performance. In addition, an optimal weight distribution algorithm is designed to search for the reliability of modal recognition results for decision-level fusion and thus more comprehensive and accurate results. The above methods can achieve the accuracy of 94.36% and 98.27% on EMO-DB and CK+ datasets, respectively, and the proposed fusion method can achieve the accuracy of 90.25% and 89.33% on the MAHNOB-HCI database regarding arousal and valence, respectively. The experimental results reveal that the multimodal emotion recognition method proposed in this study effectively improves the recognition accuracy compared with the single mode and the traditional fusion methods.
2023, 32(1):348-357. DOI: 10.15888/j.cnki.csa.008910
Abstract:Text-to-image algorithm requires high image quality and text matching. In order to improve the clarity of generated images, a generative adversarial network model is improved based on existing algorithms. Dynamic memory network, detail correction module (DCM), and text image affine combination module (ACM) are added to improve the quality of generated images. Specifically, the dynamic memory network can refine fuzzy images and select important text information storage to improve the quality of images generated in the next stage. DCM corrects details and repairs missing parts of composite images. ACM encodes original image features and reconstructs parts irrelevant to the text description. The improved model achieves two goals. On the one hand, high-quality images are generated according to given texts, with contents that are irrelevant to the texts preserved. Second, generated images do not greatly rely on the quality of initial images. Through experiments on the CUB-200-2011 bird data set, the results show that compared with previous algorithm models, the Frechet inception (FID) has been significantly improved, and the result has changed from 16.09 to 10.40, which proves that the algorithm is feasible and advanced.
2023, 32(1):358-367. DOI: 10.15888/j.cnki.csa.008930
Abstract:With the comprehensive application of encryption techniques, a growing number of malware also resort to encryption to hide their activities online, consequently preventing traditional methods based on patterns and features from meeting the requirements of accuracy and universality. To solve this problem, this study proposes a malicious encrypted traffic identification method based on hierarchical feature fusion and attention. The algorithm has a hierarchical structure and sequentially extracts the features of data packets and session flows. In the former phase, a global mixed pooling method is designed for feature fusion. In the latter phase, the attention mechanism is used to improve the ability of the bidirectional long short-term memory (BiLSTM) network to analyze sequential relationships. Finally, verification experiments are conducted on the CIC-AndMal 2017 dataset, and the results show that the proposed model is well-designed. Compared with the text convolutional neural network (TextCNN) model and the hierarchical spatiotemporal feature and multi-head self-attention (HST-MHSA) model, the proposed model reduces the false negative rate respectively by 5.8% and 2.6% and increases the weighted F1-score respectively by 4.7% and 3.5%. In other words, the proposed model achieves a satisfactory optimization effect in the identification and classification of malicious encrypted traffic.
2023, 32(1):368-375. DOI: 10.15888/j.cnki.csa.008888
Abstract:Glioma is one of the most lethal tumors in the world. It is a malignant disease with high mortality, easy recurrence, and great harm to the body. At present, magnetic resonance imaging (MRI) technology, due to its characteristics of clear imaging effect and sharp contrast between different soft tissues, has become a commonly used medical method to diagnose patients with glioma. Given the lack of original glioma data set, this study, in cooperation with Liaoning Tumor Hospital, analyzed MRI images of 300 glioma patients in the hospital. The original glioma data set is established by classifying and further grading the original data through lesion determination, lesion location, and lesion qualitative. Analysis and experiment are conducted to verify its subsequent application. It is proved that the original data set can be used for image classification and segmentation, providing image data for tumor growth and reconstruction and sufficient help for clinical research and application of glioma.
2023, 32(1):376-384. DOI: 10.15888/j.cnki.csa.008884
Abstract:Program dependency graph usually judges the data dependency according to definition-use relationships of variables in statements, and it cannot make an accurate judgment according to the semantics, which leads to the introduction of false dependency relationships and the repair failure caused by the use of error information in repairing defects. Therefore, this study will prune false dependencies related to null objects or null pointers by using abstract attributes and propose an abstract semantic-based program dependency graph to reduce the analysis of dependency relationships unrelated to the semantics of program defects and repair null pointer references. Based on the dependency relationships obtained from the analysis, a multi-strategies repair scheme is implemented under the guidance of different repair strategies for null pointer references, and the null pointer references are repaired with side effects minimized as much as possible. In addition, in this study, the null pointer references in Defects4J are adopted to evaluate the repair tool DTSFix through experiments. The results show that the repair effect of DTSFix is much better than that of other tools, which proves the effectiveness of the method.
2023, 32(1):385-391. DOI: 10.15888/j.cnki.csa.008926
Abstract:The varieties of tomato leaf diseases are of small differences and are hard to distinguish with the naked eye. Given that the classical convolutional neural network is exposed to various problems, such as a large number of parameters, heavy computation burden, a low identification rate of the model, and a large prediction error, this study proposes a disease identification method based on an improved MobileNetV2 network. A channel and a spatial attention mechanism are added to the right network layer to enhance the ability of the network to specify the features of diseased leaves and reduce the interference of irrelevant features. The Ghost module is used to replace some of the inverted residual blocks in the original model to ensure the accuracy of the model and reduce the number of parameters. The LeakyReLU activation function is employed to retain more positive and negative feature information in the feature map and thereby enhance the robustness of the model. Ten tomato leaf diseases, including early blight, late blight, spot blight, bacterial canker, erythema tetranycariasis, leaf mildew, and bacterial spot, are selected from the public dataset PlantVillage to serve as the experimental dataset. The experimental results show that the classification accuracy of the improved MobileNetV2 network reaches 98.57%, which is 2.29% higher than that of the original MobileNetV2, and the model size is reduced by 22.52%, representing a remarkable optimization effect.
2023, 32(1):392-398. DOI: 10.15888/j.cnki.csa.008896
Abstract:RISC-V is a free and open instruction set architecture built by the principle of reduced instruction sets, which features complete open source, simple architecture, easy portability, and modular design. With the rapid development of networks, security risks are ubiquitous. The extensibility feature of RISC-V can be utilized to effectively improve the security of RISC-V devices. Therefore, this study designs a simple and efficient RISC-V custom instruction considering the security capabilities of RISC-V custom instructions and by use of trusted computing and stream cipher technology to realize the function of data security storage based on the trusted computing base. Moreover, the compilation support for the custom instruction is achieved with the GNU compilation toolchain. The calling and execution of the custom instruction by an application are tested on a simulator. This instruction fully combines the security features of trusted computing and stream ciphers, and hence, it can achieve strong security.
2023, 32(1):399-405. DOI: 10.15888/j.cnki.csa.008897
Abstract:Individual electroencephalogram (EEG) signals are different and vulnerable to environmental factors. In view of these problems, this study adopts methods of removing baseline interference and EEG channel selection and proposes an emotion classification and recognition algorithm based on a continuous convolutional neural network (CNN). Firstly, the selection of differential entropy (DE) characteristics of baseline signals is studied. After the data is processed into multi-channel input, the continuous CNN is used for classification experiments, and then the optimal number of electrodes is determined. The experimental results show that after the difference between the DE of experimental EEG signals and that of baseline signals of the subject one second before the experimental EEG is mapped into a two-dimensional matrix, and the frequency dimension is turned into a multi-channel form to serve as the input of the continuous CNN, the average classification accuracy of arousal and valence on 22 channel is 95.63% and 95.13%, respectively, which are close to that on 32 channel.
2023, 32(1):406-412. DOI: 10.15888/j.cnki.csa.008891
Abstract:Insufficient training data is often faced in the task of text intent detection, and due to the discreteness of text data, it is difficult to perform data augmentation and improve the performance of the original model with the unchanged label. This study proposes a method combining stepwise data augmentation with a phased training strategy to solve the above problems in the few-shot intent detection. The method progressively augments the original data on whole statements and sample pairs in the same category from both global and local perspectives. During model training, the original data is learned according to different partition stages of the progressive level. Finally, experiments are performed on multiple intent detection datasets to evaluate the validity of the method. The experimental results show that the proposed method can effectively improve the accuracy and the stability of the few-shot intent detection model.
2023, 32(1):413-419. DOI: 10.15888/j.cnki.csa.008961
Abstract:A multi-class image segmentation method based on multi-task learning is proposed for diabetic retinopathy (DR) images. Specifically, the dominant pixels without lesion information are removed by the Otsu thresholding algorithm; subsequently, the image is segmented into several small-sized images by the method of sliding window segmentation to solve the problems that the resolution of medical images is too large and the proportion of lesions in the image is small; then, sub-images without lesions are eliminated to increase the proportion of those with lesions; finally, multi-output multi-lesion image segmentation is performed by leveraging the multi-task learning properties of UNet++ and replacing traditional upsampling with transposed convolution. When the proposed method is verified on the international public Indian diabetic retinopathy image dataset (IDRID) and dataset for diabetic retinopathy (DDR), it achieves a mean area under precision-recall curve (mAUPR) of 0.7131 on IDRID and an mAUPR of 0.5691 on DDR.