Table of Content

10 June 2022, Volume 42 Issue 6

Previous Issue   

National Open Distributed and Parallel Computing Conference 2021 (DPCS 2021）

Performance interference analysis and prediction for distributed machine learning jobs

Hongliang LI, Nong ZHANG, Ting SUN, Xiang LI

2022, 42(6):  1649-1655.  DOI: 10.11772/j.issn.1001-9081.2021061404

Asbtract ( )   HTML ( )   PDF (1121KB) ( )  

Figures and Tables | References | Related Articles | Metrics

By analyzing the problem of job performance interference in distributed machine learning， it is found that performance interference is caused by the uneven allocation of GPU resources such as memory overload and bandwidth competition， and to this end， a mechanism for quickly predicting performance interference between jobs was designed and implemented， which can adaptively predict the degree of job interference according to the given GPU parameters and job types. First， the GPU parameters and interference rates during the operation of distributed machine learning jobs were obtained through experiments， and the influences of various parameters on performance interference were analyzed. Second， some GPU parameter-interference rate models were established by using multiple prediction technologies to analyze the job interference rate errors. Finally， an adaptive job interference rate prediction algorithm was proposed to automatically select the prediction model with the smallest error for a given equipment environment and job set to predict the job interference rates quickly and accurately. By selecting five commonly used neural network tasks， experiments were designed on two GPU devices and the results were analyzed. The results show that the proposed Adaptive Interference Prediction （AIP） mechanism can quickly complete the selection of prediction model and the performance interference prediction without providing any pre-assumed information， it has comsumption time less than 300 s and achieves prediction error rate in the range of 2% to 13%， which can be applied to scenarios such as job scheduling and load balancing.

New computing power network architecture and application case analysis

Zheng DI, Yifan CAO, Chao QIU, Tao LUO, Xiaofei WANG

2022, 42(6):  1656-1661.  DOI: 10.11772/j.issn.1001-9081.2021061497

Asbtract ( )   HTML ( )   PDF (1584KB) ( )  

Figures and Tables | References | Related Articles | Metrics

With the proliferation of Artificial Intelligence （AI） computing power to the edge of the network and even to terminal devices， the computing power network of end-edge-supercloud collaboration has become the best computing solution. The emerging new opportunities have spawned the deep integration between end-edge-supercloud computing and the network. However， the complete development of the integrated system is unsolved， including adaptability， flexibility， and valuability. Therefore， a computing power network for ubiquitous AI named ACPN was proposed with the assistance of blockchain. In ACPN， the end-edge-supercloud collaboration provides infrastructure for the framework， and the computing power resource pool formed by the infrastructure provides safe and reliable computing power for the users， the network satisfies users’ demands by scheduling resources， and the neural network and execution platform in the framework provide interfaces for AI task execution. At the same time， the blockchain guarantees the reliability of resource transaction and encourage more computing power contributors to join the platform. This framework provides adaptability for users of computing power network， flexibility for resource scheduling of networking computing power， and valuability for computing power providers. A clear description of this new computing power network architecture was given through a case.

Dynamic service deployment strategy in resource constrained mobile edge computing

Jingling YUAN, Huihua MAO, Nana WANG, Yao XIANG

2022, 42(6):  1662-1667.  DOI: 10.11772/j.issn.1001-9081.2021061615

Asbtract ( )   HTML ( )   PDF (1940KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The emergence of Mobile Edge Computing （MEC） enables mobile users to easily access services deployed on edge servers with low latency. However， there are various challenges in MEC， especially service deployment issues. The number and resources of edge servers are usually limited and only a limited number of services can be deployed on the edge servers； in addition， the mobility of users changes the popularities of different services in different regions. In this context， deploying suitable services for dynamic service requests becomes a critical problem. To address this problem， by deploying appropriate services by awareness of the dynamic user requirements to minimize interaction delay， the service deployment problem was formulated as a global optimization problem， and a cluster-based resource aggregation algorithm was proposed， which initially deployed suitable services under the resource constraints such as computing and bandwidth. Moreover， considering the influence of dynamic user requests on service popularity and edge server load， a dynamic adjustment algorithm was developed to update the existing services to ensure that the Quality of Service （QoS） always met user expectations. The performance of this deployment strategy was verified through a series of simulation experiments. Simulation results show that compared with the existing benchmark algorithms， the proposed strategy can reduce service interaction delay and achieve a more stable load balance.

Multi-objective task offloading algorithm based on deep Q-network

Shiquan DENG, Xuguo YE

2022, 42(6):  1668-1674.  DOI: 10.11772/j.issn.1001-9081.2021061367

Asbtract ( )   HTML ( )   PDF (1781KB) ( )  

Figures and Tables | References | Related Articles | Metrics

For the Mobile Device （MD） with limited computing resources and battery capacity in Mobile Edge Computing （MEC）， its computing capacity can be enhanced and its energy consumption can be reduced through offloading its own computing-intensive applications to the edge server. However， unreasonable task offloading strategy will bring a bad experience for users since it will increase the application completion time and energy consumption. To overcome above challenge， firstly， a multi-objective task offloading problem model with minimizing the application completion time and energy consumption as optimization targets was built in the dynamic MEC network via analyzing the mobility of the mobile device and the sequential dependencies between tasks. Then， a Markov Decision Process （MDP） model， including state space， action space， and reward function， was designed to solve this problem， and a Multi-Objective Task Offloading Algorithm based on Deep Q-Network （MTOA-DQN） was proposed， which uses a trajectory as the smallest unit of the experience buffer to improve the original DQN. The proposed MTOA-DQN outperforms three comparison algorithms including MultiObjective Evolutionary Algorithm based on Decomposition （MOEA/D）， Adaptive DAG （Directed Acyclic Graph） Tasks Scheduling （ADTS） and original DQN in terms of cumulative reward and cost in a number of test scenarios， verifying the effectiveness and reliability of the algorithm.

Efficient wireless federated learning algorithm based on 1‑bit compressive sensing

Zhenyu ZHANG, Guoping TAN, Siyuan ZHOU

2022, 42(6):  1675-1682.  DOI: 10.11772/j.issn.1001-9081.2021061374

Asbtract ( )   HTML ( )   PDF (2504KB) ( )  

Figures and Tables | References | Related Articles | Metrics

In the wireless Federated Learning （FL） architecture， the model parameter data need to be continuously exchanged between the client and the server to update the model， thus causing a large communication overhead and power consumption on the client. At present， there are many methods to reduce communication overhead by data quantization and data sparseness. In order to further reduce the communication overhead， a wireless FL algorithm based on 1?bit compressive sensing was proposed. In the uplink of wireless FL architecture， the data update parameters of its local model， including update amplitude and trend， were firstly recorded on the client. Then， sparsification was performed to the amplitude and trend information， and the threshold required for updating was determined. Finally， 1?bit compressive sensing was performed on the update trend information， thereby compressing the uplink data. On this basis， the data size was further compressed by setting dynamic threshold. Experimental results on MNIST datasets show that the 1?bit compressive sensing process with the introduction of dynamic threshold can achieve the same results as the lossless transmission process， and reduce the amount of model parameter data to be transmitted by the client during the uplink communication of FL applications to 1/25 of the normal FL process without this method； and can reduce the total user upload data size to 2/11 of the original size and reduce the transmission energy consumption to 1/10 of the original size when the global model is trained to the same level.

Multimodal sequential recommendation algorithm based on contrastive learning

Tengyue HAN, Shaozhang NIU, Wen ZHANG

2022, 42(6):  1683-1688.  DOI: 10.11772/j.issn.1001-9081.2021081417

Asbtract ( )   HTML ( )   PDF (1339KB) ( )  

Figures and Tables | References | Related Articles | Metrics

A multimodal sequential recommendation algorithm based on contrastive learning technology was proposed to improve the accuracy of sequential recommendation algorithm by using multimodal information of commodities. Firstly， to obtain the visual representations such as the color and shape of the product， the visual modal information of the product was extracted by utilizing the contrastive learning framework， where the data enhancement was performed by changing the color and intercepting the center area of the product. Secondly， the textual information of each commodity was embedded into a low-dimensional space， so that the complete multimodal representation of each commodity could be obtained. Finally， a Recurrent Neural Network （RNN） was used for modeling the sequential interactions of multimodal information according to the time sequence of the product， then the preference representation of user was obtained and used for commodity recommendation. The proposed algorithm was tested on two public datasets and compared with the existing sequential recommendation algorithm LESSR. Experimental results prove that the ranking performance of the proposed algorithm is improved， and the recommendation performance remains basically unchanged after the feature dimension value reaches 50.

Recommendation model of penetration path based on reinforcement learning

Haini ZHAO, Jian JIAO

2022, 42(6):  1689-1694.  DOI: 10.11772/j.issn.1001-9081.2021061424

Asbtract ( )   HTML ( )   PDF (1756KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The core problem of penetration test is the planning of penetration test paths. Manual planning relies on the experience of testers， while automated generation of penetration paths is mainly based on the priori knowledge of network security and specific vulnerabilities or network scenarios， which requires high cost and lacks flexibility. To address these problems， a reinforcement learning-based penetration path recommendation model named Q Learning Penetration Test （QLPT） was proposed to finally give the optimal penetration path for the penetration object through multiple rounds of vulnerability selection and reward feedback. It is found that the recommended path of QLPT has a high consistency with the path of manual penetration test by implementing penetration experiments at open source cyber range， verifying the feasibility and accuracy of this model； compared with the automated penetration test framework Metasploit， QLPT is more flexible in adapting to all penetration scenarios.

Traceable and revocable multi-authority attribute-based encryption scheme for vehicular ad hoc networks

Jingwen WU, Xinchun YIN, Jianting NING

2022, 42(6):  1695-1701.  DOI: 10.11772/j.issn.1001-9081.2021061449

Asbtract ( )   HTML ( )   PDF (965KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Ensuring the confidentiality of message transmission is a fundamental security requirement for communications in Vehicular Ad hoc NETworks （VANETs）. While utilizing symmetric group keys to encrypt messages， it is hard for system manager to trace inner attackers. Therefore， an attribute-based encryption scheme for VANETs was proposed. The scheme enables tracking and revocation of malicious vehicles and fine-grained division of vehicle access rights； meanwhile， the scheme allows multiple authority centers to distribute attributes and their corresponding keys independently， preventing compromised authority centers from forging attribute keys that are managed by other authorities， thus guaranteeing a high security for communication and collaboration among multiple institutions. This scheme was proven indistinguishable under q-DPBDHE2 （q-Decisional Parallel Bilinear Diffie-Hellman Exponent） assumption； and experimental results of encryption and decryption overhead comparison of this scheme and similar schemes show that while the number of attributes is 10， the decryption overhead of the proposed scheme is 459.541 ms， indicating that the scheme is suitable for communication encryption in VANETs.

Coupling related code smell detection method based on deep learning

Shan SU, Yang ZHANG, Dongwen ZHANG

2022, 42(6):  1702-1707.  DOI: 10.11772/j.issn.1001-9081.2021061403

Asbtract ( )   HTML ( )   PDF (1071KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Heuristic and machine learning based code smell detection methods have been proved to have limitations， and most of these methods focus on the common code smells. In order to solve these problems， a deep learning based method was proposed to detect three relatively rare code smells which are related to coupling， those are Intensive Coupling， Dispersed Coupling and Shotgun Surgery. First， the metrics of three code smells were extracted， and the obtained data were processed. Second， a deep learning model combining Convolutional Neural Network （CNN） and attention mechanism was constructed， and the introduced attention mechanism was able to assign weights to the metric features. The datasets were extracted from 21 open source projects， and the detection methods were validated in 10 open source projects and compared with CNN model. Experimental results show that the proposed model achieves the better performance with the code smell precisions of 93.61% and 99.76% for Intensive Coupling and Dispersed Coupling respectively， and the CNN model achieves the better results with the code smell precision of 98.59% for Shotgun Surgery.

Malicious code detection method based on attention mechanism and residual network

Yang ZHANG, Jiangbo HAO

2022, 42(6):  1708-1715.  DOI: 10.11772/j.issn.1001-9081.2021061410

Asbtract ( )   HTML ( )   PDF (1407KB) ( )  

Figures and Tables | References | Related Articles | Metrics

As the existing malicious code detection methods based on deep learning have problems of insufficiency and low accuracy of feature extraction， a malicious code detection method based on attention mechanism and Residual Network （ResNet） called ARMD was proposed. To support the training of this method， the hash values of 47 580 malicious and benign codes were obtained from Kaggle website， and the APIs called by each code were extracted by analysis tool VirusTotal. After that， the called APIs were integrated into 1 000 non-repeated APIs as the detection features， and the training sample data was constructed through these features. Then， the sample data was labeled by determining the benignity and maliciousness based on the VirusTotal analysis results， and the SMOTE （Synthetic Minority Over-sampling Technique） enhancement algorithm was used to equalize the data samples. Finally， the ResNet injecting with the attention mechanism was built and trained to complete the malicious code detection. Experimental results show that the accuracy of malicious code detection of ARMD is 97.76%， and compared with the existing detection methods based on Convolutional Neural Network （CNN） and ResNet models， ARMD has the average precision improved by at least 2%， verifying the effectiveness of ARMD.

Reversible data hiding in encrypted image based on multi-objective optimization

Xiangyu ZHANG, Yang YANG, Guohui FENG, Chuan QIN

2022, 42(6):  1716-1723.  DOI: 10.11772/j.issn.1001-9081.2021061495

Asbtract ( )   HTML ( )   PDF (1250KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Focusing on the issues that the Reserving Room Before Encryption （RRBE） embedding algorithm requires a series of pre-processing work and Vacating Room After Encryption （VRAE） embedding algorithm has less embedding space， an algorithm of reversible data hiding in encrypted image based on multi-objective optimization was proposed to improve the embedding rate as well as reducing the algorithm process and workload. In this algorithm， two representative algorithms in RRBE and VRAE were combined and used in the same carrier， and performance evaluation indicators such as the amount of information embedded， distortion of direct decryption of image， extraction error rate， and computational complexity were formulated as the optimization sub-objectives. Then， the efficiency coefficient method was used to establish a model to solve the relative optimal solution of the application ratio of the two algorithms. Experimental results show that the proposed algorithm reduces the computational complexity of using RRBE algorithm alone， enables image processing users to flexibly allocate optimization objectives according to different needs in actual application scenarios， and at the same time obtains better image quality and a satisfactory amount of information embedding.

Detection algorithm of audio scene sound replacement falsification based on ResNet

Mingyu DONG, Diqun YAN

2022, 42(6):  1724-1728.  DOI: 10.11772/j.issn.1001-9081.2021061432

Asbtract ( )   HTML ( )   PDF (2217KB) ( )  

Figures and Tables | References | Related Articles | Metrics

A ResNet-based faked sample detection algorithm was proposed for the detection of faked samples in audio scenes with low faking cost and undetectable sound replacement. The Constant Q Cepstral Coefficient （CQCC） features of the audio were extracted firstly， then the input features were learnt by the Residual Network （ResNet） structure， by combining the multi-layer residual blocks of the network and feature normalization， the classification results were output finally. On TIMIT and Voicebank databases， the highest detection accuracy of the proposed algorithm can reach 100%， and the lowest false acceptance rate of the algorithm can reach 1.37%. In realistic scenes， the highest detection accuracy of this algorithm is up to 99.27% when detecting the audios recorded by three different recording devices with the background noise of the device and the audio of the original scene. Experimental results show that it is effective to use the CQCC features of audio to detect the scene replacement trace of audio.

Research on Bloom filter： a survey

Wendi HUA, Yuan GAO, Meng LYU, Ping XIE

2022, 42(6):  1729-1747.  DOI: 10.11772/j.issn.1001-9081.2021061392

Asbtract ( )   HTML ( )   PDF (3209KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Bloom Filter （BF） is a binary vector data structure based on hashing strategy. With the idea of sharing hash collisions， the characteristic of one-way misjudgment and the very small time complexity of constant query， BF is often used to represent membership and as an “accelerator” for membership query operations. As the best mathematical tool to solve the membership query problem in computer engineering， BF has been widely used and developed in network engineering， storage system， database， file system， distributed system and some other fields. In the past few years， in order to adapt to various hardware environments and application scenarios， a large number of variant optimization schemes of BF based on the ideas of changing structure and optimizing algorithm appeared. With the development of big data era， it has become an important direction of membership query to improve the characteristics and operation logic of BF.

Refined short-term traffic flow prediction model and migration deployment scheme

Jiachen GUO, Yushen YANG, Yan WANG, Shilong MAO, Lijun SUN

2022, 42(6):  1748-1755.  DOI: 10.11772/j.issn.1001-9081.2021061411

Asbtract ( )   HTML ( )   PDF (3372KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Refined short-term traffic flow prediction is the premise to ensure the rational decision making in Intelligent Transportation System （ITS）. In order to establish the lane-changing model of self-driving car， predict vehicle trajectories， and guide vehicle routes， the timely traffic flow prediction for each lane has become an urgent problem to solve. However， refined short-term traffic flow prediction faces the following challenges： first， with the increasing diversity of traffic flow data， the traditional prediction methods cannot meet the requirements of ITS for high precision and short time delay； second， training prediction model for each lane make a huge waste of resources. To solve the above problems， a refined short-term traffic flow prediction model combined Convolutional-Gated Recurrent Unit （Conv-GRU） with Grey Relational Analysis （GRA） was proposed to predict lane flow. Considering the characteristics of long training time and relatively short reasoning time of deep learning， a cloud-fog deployment scheme was designed. Meanwhile， to avoid training prediction models for each lane， a model migration deployment scheme was proposed， which only needs to train the prediction model of some lanes， and then the trained prediction models were migrated to the associated lane for prediction through GRA. Experimental results of extensive comparisons on a real-world dataset show that， compared with traditional deep learning prediction methods， the proposed model has more accurate prediction performance； compared with Convolutional-Long Short-Term Memory （Conv-LSTM） network， the model has shorter running time. Furthermore， the model migration is realized by the proposed model under the condition of ensuring high-precision prediction， which saves about 49% of training time compared to training prediction model for each lane.

Hydrological model based on temporal convolutional network

Qingqing NIE, Dingsheng WAN, Yuelong ZHU, Zhijia LI, Cheng YAO

2022, 42(6):  1756-1761.  DOI: 10.11772/j.issn.1001-9081.2021061366

Asbtract ( )   HTML ( )   PDF (2132KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Water level prediction is an auxiliary decision support for flood warning work. For accurate water level prediction and providing scientific basis for natural disaster prevention， a prediction model combining Modified Gray Wolf Optimization （MGWO） algorithm and Temporal Convolutional Network （TCN） was proposed， namely MGWO-TCN. In view of the shortage of premature and stagnation in the original Gray Wolf Optimization （MGWO） algorithm， the idea of Differential Evolution （DE） algorithm was introduced to extend the diversity of the grey wolf population. The convergence factor during update and the mutation operator during mutation of the grey wolf population were improved to adjust the parameters in the adaptive manner， thereby improving the convergence speed and balancing the global and local search capabilities of the algorithm. The proposed MGWO algorithm was used to optimize the important parameters of TCN to improve the prediction performance of TCN. The proposed prediction model MGWO-TCN was used for river water level prediction， and the Root Mean Square Error （RMSE） of the model’s prediction results was 0.039. Experimental results show that compared with the comparison model， the proposed MGWO-TCN has better optimization ability and higher prediction accuracy.

Lip language recognition algorithm based on single-tag radio frequency identification

Yingqi ZHANG, Dawei PENG, Sen LI, Ying SUN, Qiang NIU

2022, 42(6):  1762-1769.  DOI: 10.11772/j.issn.1001-9081.2021061390

Asbtract ( )   HTML ( )   PDF (4019KB) ( )  

Figures and Tables | References | Related Articles | Metrics

In recent years， a wireless platform for speech recognition using multiple customized and stretchable Radio Frequency Identification （RFID） tags has been proposed， however， it is difficult for the tags to accurately capture large frequency shifts caused by stretching， and multiple tags need to be detected and recalibrated when the tags fall off or wear out naturally. In response to the above problems， a lip language recognition algorithm based on single-tag RFID was proposed， in which a flexible， easily concealable and non-invasive single universal RFID tag was attached to the face， allowing lip language recognition even if the user does not make a sound and relies only on facial micro-actions. Firstly， a model was established to process the Received Signal Strength （RSS） and phase changes of individual tags received by an RFID reader responding over time and frequency. Then the Gaussian function was used to preprocess the noise of the original data by smoothing and denoising， and the Dynamic Time Warping （DTW） algorithm was used to evaluate and analyze the collected signal characteristics to solve the problem of pronunciation length mismatch. Finally， a wireless speech recognition system was created to recognize and distinguish the facial expressions corresponding to the voice， thus achieving the purpose of lip language recognition. Experimental results show that the accuracy of RSS can reach more than 86.5% by the proposed algorithm for identifying 200 groups of digital signal characteristics of different users.

The 18th CCF Conference on Web Information Systems and Applications

Election-based supply chain： a supply chain autonomy framework based on blockchain

Yuntao XU, Junwu ZHU, Binwen SUN, Maosheng SUN, Sihai CHEN

2022, 42(6):  1770-1775.  DOI: 10.11772/j.issn.1001-9081.2021091761

Asbtract ( )   HTML ( )   PDF (1819KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The combination of blockchain and supply chain is a popular research topic in recent years. The advantages of blockchain such as data traceability， tamper proof and distributed storage can guarantee good data security for supply chain， while the autonomy property of blockchain also provides possibility of supply chain autonomy. The autonomy of blockchain mainly depends on consensus mechanism， but the existing consensus mechanism is difficult to realize good support for supply chain autonomy. To solve the above problems， an election-based consensus mechanism based on Delegated Proof of Stake （DPoS） was proposed， and on this basis， a self-made framework of supply chain based on blockchain was constructed， namely Election-based Supply Chain （ESC）. In ESC， the credit score of a node was first calculated according to the smart contract activities participated in by this node. Then， from the perspective of game theory， the influences of node active degree and credit score on stake under ESC were analyzed. Finally， theorem proving and simulation experiments verify that the proposed mechanism has a good incentive effect on nodes and can effectively inhibit the maximum transaction cost paid by rational nodes，and the inhibition increasing with the increase of the number of delegates.

Cross-regional order allocation strategy for ride-hailing under tight transport capacity

Yu XIA, Junwu ZHU, Yi JIANG, Xin GAO, Maosheng SUN

2022, 42(6):  1776-1781.  DOI: 10.11772/j.issn.1001-9081.2021091627

Asbtract ( )   HTML ( )   PDF (1163KB) ( )  

Figures and Tables | References | Related Articles | Metrics

In the ride-hailing platform， matching is a core function，and the platform needs to increase the number of matched orders as much as possible. However， the demand distribution of ride-hailing is usually extremely uneven， and the starting points or end points of orders show the characteristic of high concentration in some time periods. Therefore， an incentive mechanism with early warning was proposed to encourage drivers to take orders across regions， thus achieving the purpose of rebalancing the platform cross-regional transport capacity. The order information was analyzed and processed in this strategy， and an early warning mechanism of transport capacity in adjacent regions was established. To reduce the number of unmatched orders in the region during the period of tight transport capacity and improve the platform utility and passenger satisfaction， drivers in adjacent regions were encouraged to accept cross-regional orders when regional transport capacity was tight. Experimental results on instances show that the proposed rebalancing mechanism improves the average utility by 15% and 38% compared with Greedy and Surge mechanisms， indicating that the cross-regional transport capacity rebalancing mechanism can improve the platform revenue and driver utility， rebalance the supply-demand relationship between regions to a certain extent， and provide a reference for the ride-hailing platform to balance the supply-demand relationship macroscopically.

Community structure representation learning for "15-minute living circle"

Huanliang SUN, Cheng PENG, Junling LIU, Jingke XU

2022, 42(6):  1782-1788.  DOI: 10.11772/j.issn.1001-9081.2021091750

Asbtract ( )   HTML ( )   PDF (1566KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The discovery of community structures using urban big data is an important research direction in urban computing. Effective representation of the structural characteristics of the communities in the "15-minute living circle" can be used to evaluate the facilities around the living circle communities in a fine-grained manner， which is conducive to urban planning as well as the construction and creation of a livable living environment. Firstly， the urban community structure oriented to "15-minute living circle" was defined， and the structural characteristics of the living circle communities were obtained by representation learning method. Then， the embedding representation framework of the living circle community structure was proposed， in which the relationship between the Points Of Interest （POI） and the residential area was determined by using the travel trajectory data of the residents， and a dynamic activity map reflecting the travel rules of the residents at different times was constructed. Finally， the representation learning to the constructed dynamic activity map was performed by an auto-encoder to obtain the vector representations of the potential characteristics of the communities in the living circle， thus effectively summarizing the community structure formed by the residents’ daily activities. Experimental evaluations were conducted using real datasets for applications such as community convenience evaluation and similarity metrics in living circles. The results show that the daily latent feature expression method based on POI categories is better than the weekly latent feature expression method. Compared to the latter， the minimum increase of Normalized Discounted Cumulative Gain （NDCG） of the former is 24.28% and the maximum increase of NDCG is 60.71%， which verifies the effectiveness of the proposed method.

Integrating posterior probability calibration training into text classification algorithm

Jing JIANG, Yu CHEN, Jieping SUN, Shenggen JU

2022, 42(6):  1789-1795.  DOI: 10.11772/j.issn.1001-9081.2021091638

Asbtract ( )   HTML ( )   PDF (738KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The pre-training language models used for text representation have achieved high accuracy on various text classification tasks， but the following problems still remain： on the one hand， the category with the largest posterior probability is selected as the final classification result of the model after calculating the posterior probabilities on all categories in the pre-training language model. However， in many scenarios， the quality of the posterior probability itself can provide more reliable information than the final classification result. On the other hand， the classifier of the pre-training language model has performance degradation when assigning different labels to texts with similar semantics. In response to the above two problems， a model combining posterior probability calibration and negative example supervision named PosCal-negative was proposed. In PosCal-negative model， the difference between the predicted probability and the empirical posterior probability was dynamically penalized in an end-to-and way during the training process， and the texts with different labels were used to realize the negative supervision of the encoder， so that different feature vector representations were generated for different categories. Experimental results show that the classification accuracies of the proposed model on two Chinese maternal and child care text classification datasets MATINF-C-AGE and MATINF-C-TOPIC reach 91.55% and 69.19% respectively， which are 1.13 percentage points and 2.53 percentage points higher than those of Enhanced Representation through kNowledge IntEgration （ERNIE） model respectively.

Relation extraction method based on entity boundary combination

Hao LI, Yanping CHEN, Ruixue TANG, Ruizhang HUANG, Yongbin QIN, Guorong WANG, Xi TAN

2022, 42(6):  1796-1801.  DOI: 10.11772/j.issn.1001-9081.2021091747

Asbtract ( )   HTML ( )   PDF (1005KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Relation extraction aims to extract the semantic relationships between entities from the text. As the upper-level task of relation extraction， entity recognition will generate errors and spread them to relation extraction， resulting in cascading errors. Compared with entities， entity boundaries have small granularity and ambiguity， making them easier to recognize. Therefore， a relationship extraction method based on entity boundary combination was proposed to realize relation extraction by skipping the entity and combining the entity boundaries in pairs. Since the boundary performance is higher than the entity performance， the problem of error propagation was alleviated； in addition， the performance was further improved by adding the type features and location features of entities through the feature combination method， which reduced the impact caused by error propagation. Experimental results on ACE 2005 English dataset show that the proposed method outperforms the table-sequence encoders method by 8.61 percentage points on Macro average F1-score.

Recognition of sentencing circumstances in adjudication documents based on abductive learning

Jinye LI, Ruizhang HUANG, Yongbin QIN, Yanping CHEN, Xiaoyu TIAN

2022, 42(6):  1802-1807.  DOI: 10.11772/j.issn.1001-9081.2021091748

Asbtract ( )   HTML ( )   PDF (1407KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Aiming at the problem of poor recognition of sentencing circumstances in adjudication documents caused by the lack of labeled data， low quality of labeling and existence of strong logicality in judicial field， a sentencing circumstance recognition model based on abductive learning named ABL-CON （ABductive Learning in CONfidence） was proposed. Firstly， combining with neural network and domain logic inference， through the semi-supervised method， a confidence learning method was used to characterize the confidence of circumstance recognition. Then， the illogical error circumstances generated by neural network of the unlabeled data were corrected， and the recognition model was retrained to improve the recognition accuracy. Experimental results on the self-constructed judicial dataset show that the ABL-CON model using 50% labeled data and 50% unlabeled data achieves 90.35% and 90.58% in Macro_F1 and Micro_F1， respectively， which is better than BERT （Bidirectional Encoder Representations from Transformers） and SS-ABL （Semi-Supervised ABductive Learning） under the same conditions， and also surpasses the BERT model using 100% labeled data. The ABL-CON model can effectively improve the logical rationality of labels as well as the recognition ability of labels by correcting illogical labels through logical abductive correctness.

MOOC video recommendation method based on meta-path attention mechanism

Jiafan ZHOU, Yuefeng DU, Baoyan SONG, Xiaoguang LI, Azhu ZHAO, Xujie XIAO

2022, 42(6):  1808-1813.  DOI: 10.11772/j.issn.1001-9081.2021091800

Asbtract ( )   HTML ( )   PDF (1544KB) ( )  

Figures and Tables | References | Related Articles | Metrics

On the MOOC platform， there may be multiple versions of videos for one course，in order to recommend a MOOC video that satisfies the learning interest of the student，it is necessary to analyze the relationship between student interests and video contents. For this purpose， a video recommendation model named Mrec was proposed based on meta-path attention mechanism. For one thing， the Heterogeneous Information Network （HIN） was used to describe the relationships between learners and MOOC resources， and then meta-path was used to express the interaction between students and videos. For another， the attention mechanism was used to capture the influences of the characteristics of students， videos and meta-paths on learning interest. Specifically， the Mrec model was composed of two layers of attention mechanism： the first layer was the node attention layer， the node own characteristics were weightely combined with neighbor characteristics， and the feature representations of entities under different meta-paths were obtained by multi-head attention； the second layer was the path attention layer， in which the feature representations of entities learned under the guidance of different meta-paths were integrated to capture the feature representations of entities under different interests， and the learned users and video entities were put into Multi-Layer Perceptron （MLP） to obtain the prediction scores for top-K recommendation. Experimental results on MOOCCube and MOOCdata datasets show that Mrec outperforms the comparison methods in terms of Hit Ratio （HR）， Normalized Discounted Cumulative Gain （NDCG）， Mean Reciprocal Ranking （MRR） and Area Under receiver operating characteristic Curve （AUC）.

Source code vulnerability detection based on relational graph convolution network

Min WEN, Rongcun WANG, Shujuan JIANG

2022, 42(6):  1814-1821.  DOI: 10.11772/j.issn.1001-9081.2021091691

Asbtract ( )   HTML ( )   PDF (1719KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The root cause of software security lies in the source code developed by software developers， but with the continues increasing size and complexity of software， it is costly and difficult to perform vulnerability detection only manually， while the existing code analysis tools have high false positive rate and false negative rate. Therefore， an automatic vulnerability detection method based on Relational Graph Convolution Network （RGCN） was proposed to further improve the accuracy of vulnerability detection. Firstly， the program source code was transformed into CPG containing syntax and semantic information. Then， representation learning was performed to the graph structure by RGCN. Finally， a neural network model was trained to predict the vulnerabilities in the program source code. To verify the effectiveness of the proposed method， an experimental validation was conducted on the real-world software vulnerability samples， and the results show that the recall and F1-measure of vulnerability detection results of the proposed method reach 80.27% and 63.78% respectively. Compared with Flawfinder， VulDeepecker and similar method based on Graph Convolution Network （GCN）， the proposed method has the F1-measure increased by 182%， 12% and 55% respectively. It can be seen that the proposed method can effectively improve the vulnerability detection capability.

Artificial intelligence

Intrinsic curiosity method based on reward prediction error

Qing TAN, Hui LI, Haolin WU, Zhuang WANG, Shuchao DENG

2022, 42(6):  1822-1828.  DOI: 10.11772/j.issn.1001-9081.2021040552

Asbtract ( )   HTML ( )   PDF (2455KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Concerning the problem that when the state prediction error is directly used as the intrinsic curiosity reward， the reinforcement learning agent cannot effectively explore the environment in the task with low correlation between state novelty and reward， an Intrinsic Curiosity Module with Reward Prediction Error （RPE-ICM） was proposed. In RPE-ICM， the Reward Prediction Error Network （RPE-Network） model was used to learn and correct the state prediction error reward， and the output of the Reward Prediction Error （RPE） model was used as an intrinsic reward signal to balance over-exploration and under-exploration， so that the agent was able to explore the environment more effectively and use the reward to learn skills to achieve better learning effect. In different MuJoCo （Multi-Joint dynamics with Contact） environments， comparative experiments were conducted on RPE-ICM， Intrinsic Curiosity Module （ICM）， Random Network Distillation （RND） and traditional Deep Deterministic Strategy Gradient （DDPG） algorithm. The results show that compared with traditional DDPG， ICM-DDPG and RND-DDPG， the DDPG algorithm based on RPE-ICM has the average performance improved by 13.85%， 13.34% and 20.80% respectively in Hopper environment.

Integrated prediction model of Cauchy adaptive backtracking search and least square support vector machine

Zhonghua ZHANG, Fuyuan ZHAO, Junfeng GUO, Gaochang ZHAO

2022, 42(6):  1829-1836.  DOI: 10.11772/j.issn.1001-9081.2021040577

Asbtract ( )   HTML ( )   PDF (2163KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Aiming at the problem that Backtracking Search optimization Algorithm （BSA） is easy to premature and has weak local development ability in the optimization of kernel function parameters and regularization parameters of Least Square Support Vector Machine （LSSVM）， an integrated prediction model named CABSA-LSSVM was proposed. Firstly， the Cauchy population generation strategy was used to improve the diversity of historical populations， so that the algorithm was not easy to fall into the local optimal solution. Then， the adaptive mutation factor strategy was used to balance the global exploration and local development abilities of the algorithm by adjusting the mutation scale coefficient. Finally， the improved Cauchy Adaptive Backtracking Search Algorithm （CABSA） was used to optimize the LSSVM to form a new integrated prediction model. Ten UCI datasets were selected for numerical experiments. The results show that the proposed model CABSA-LSSVM has the best regression prediction performance when the population size is 80. Compared with the LSSVMs optimized by the standard BSA， Particle Swarm Optimization （PSO） algorithm， Artificial Bee Colony （ABC） algorithm and Grey Wolf Optimization （GWO） algorithm， the proposed model has the coefficient of determination increased by 1.21%-15.28%， the prediction error reduced by 6.36%-29.00%， and the running time reduced by 5.88%-94.16%. In conclusion， the proposed model has high prediction accuracy and fast computation speed.

Artificial cooperative search algorithm for solving traveling salesman problems

Xiaoping XU, Yangli TANG, Feng WANG

2022, 42(6):  1837-1843.  DOI: 10.11772/j.issn.1001-9081.2021040567

Asbtract ( )   HTML ( )   PDF (1295KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Concerning low solution accuracy and slow convergence of traditional Artificial Cooperative Search （ACS） algorithm， a Quasi opposition Artificial Cooperative Search algorithm based on Sigmoid function （SQACS） algorithm was proposed to solve Traveling Salesman Problem （TSP）. Firstly， the Sigmoid function was used to construct the scale factor to enhance the global search ability of the algorithm. Then， in the mutation stage， the mutation strategy DE/rand/1 of Differential Evolution （DE） algorithm was introduced into the current population for secondary mutation， thereby improving the calculation accuracy of the algorithm and the diversity of the population. Finally， in the later development stage， the quasi opposition learning strategy was introduced to further improve the quality of the solution. Four instances in TSP test library TSPLIB were used to perform simulation experiments， and the results show that SQACS algorithm is superior to seven comparison algorithms such as Sparrow Search Algorithm （SSA）， DE and Archimedes Optimization Algorithm （AOA） in the shortest path and time consumption， and has good robustness； and compared with other improved algorithms for solving TSP comprehensively， SQACS algorithm also shows good performance. Experimental results prove that the SQACS algorithm is effective in solving small-scale TSPs.

Equilibrium optimizer considering distance factor and elite evolutionary strategy

Weikang ZHANG, Sheng LIU, Qian HUANG, Yuxin GUO

2022, 42(6):  1844-1851.  DOI: 10.11772/j.issn.1001-9081.2021040574

Asbtract ( )   HTML ( )   PDF (1083KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Aiming at the shortcomings of Equilibrium Optimizer （EO） such as low optimization accuracy， slow convergence and being easy to fall into local optimum， a new EO in consideration with distance factor and Elite Evolutionary Strategy （EES） named E-SFDBEO was proposed. Firstly， the distance factor was introduced to select the candidate solutions of the equilibrium pool， and the adaptive weight was used to balance the fitness value and distance， thereby adjusting the exploration and development capabilities of the algorithm in different iterations. Secondly， the EES was introduced to improve the convergence speed and accuracy of the algorithm by both elite natural evolution and elite random mutation. Finally， the adaptive t-distribution mutation strategy was used to perturb some individuals， and the individuals were retained with greedy strategy， so that the algorithm was able to jump out of the local optimum effectively. In the simulation experiment， the proposed algorithm was compared with 4 basic algorithms and 2 improved algorithms based on 10 benchmark test functions and Wilcoxon rank sum test was performed to the algorithms. The results show that the proposed algorithm has better convergence and higher solution accuracy.

Improved sine cosine algorithm for optimizing feature selection and data classification

Liang CHEN, Xianfeng TANG

2022, 42(6):  1852-1861.  DOI: 10.11772/j.issn.1001-9081.2021040555

Asbtract ( )   HTML ( )   PDF (3684KB) ( )  

Figures and Tables | References | Related Articles | Metrics

To address the shortcomings of the traditional Sine Cosine Algorithm （SCA） in dealing with complex optimization problems with local optimum and slow convergence，an improved SCA based on Inertia Weights and Cauchy Chaotic mutation （IWCCSCA） was proposed. Firstly， a curve adaptive amplitude adjustment factor update method based on exponential function was designed to balance global search and local development capacities； then， an adaptive decreasing inertia weight update mechanism was designed to improve the way of individual position update and accelerate algorithm convergence； and an individual disturbance mechanism based on elite Cauchy chaotic mutation was proposed to enhance the population diversity and avoid falling into the local optimum. IWCCSCA was verified to be effective in improving convergence speed and optimizing accuracy by solving the best solutions of eight benchmark functions. Furthermore， IWCCSCA was used for feature subset selection problem in original data feature set， and a feature selection algorithm based on IWCCSCA was put forward， namely IWCCSCA-FS. The mapping relationship between individual position and feature subset was realized through converting the continuous optimization of sine cosine function to binary optimization of feature selection， and the quality of candidate solutions was evaluated by a fitness function considering feature selection number and classification accuracy simultaneously. Test results on UCI benchmark datasets validate that IWCCSCA-FS can effectively select the optimal feature subset， reduce feature dimension and improve data classification accuracy.

Material entity recognition based on subword embedding and relative attention

Yumin HAN, Xiaoyan HAO

2022, 42(6):  1862-1868.  DOI: 10.11772/j.issn.1001-9081.2021040582

Asbtract ( )   HTML ( )   PDF (1612KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Accurately identifying named entities is helpful to construct professional knowledge graphs and question answering systems. Named Entity Recognition （NER） technology based on deep learning has been widely used in a variety of professional fields. However， there are relatively few researches on NER in the field of materials. Concerning the problem of small scale of datasets and high complexity of entity words for supervised learning in NER of materials field， the large-scale unstructured materials field literature data were used to train the subword embedding word segmentation model based on Unigram Language Model （ULM）， and the information contained in the word structure was fully utilized to enhance the robustness of the model. At the same time， the entity recognition model with BiLSTM-CRF （Bi-directional Long-Short Term Memory-Conditional Random Field） model as the basis and combined with the Relative Multi-Head Attention（RMHA）capable of perceiving direction and distance of words was proposed to improve the sensitivity of the model to keywords. Compared with BiLSTM-CNNs-CRF， SciBERT （Scientific BERT） and other models， the obtained BiLSTM-RMHA-CRF model combining with the ULM subword embedding method increased the value of Macro F1 by 2-4 percentage points on Solid Oxide Fuel Cell （SOFC） NER dataset， and 3-8 percentage points on SOFC fine-grained entity recognition dataset. Experimental results show that the recognition model based on subword embedding and relative attention can effectively improve the recognition accuracy of entities in the materials field.

End-to-end speech emotion recognition based on multi-head attention

Lei YANG, Hongdong ZHAO, Kuaikuai YU

2022, 42(6):  1869-1875.  DOI: 10.11772/j.issn.1001-9081.2021040578

Asbtract ( )   HTML ( )   PDF (2133KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Aiming at the characteristics of small size and high data dimensionality of speech emotion datasets， to solve the problem of long-range dependence disappearance in traditional Recurrent Neural Network （RNN） and insufficient excavation of potential relationship between frames within the input sequence because of focus on local information of Convolutional Neural Network （CNN）， a new neural network MAH-SVM based on Multi-Head Attention （MHA） and Support Vector Machine （SVM） was proposed for Speech Emotion Recognition （SER）. First， the original audio data were input into the MHA network to train the parameters of MHA and obtain the classification results of MHA. Then， the same original audio data were input into the pre-trained MHA again for feature extraction. Finally， these obtained features were fed into SVM after the fully connected layer to obtain classification results of MHA-SVM. After fully evaluating the effect of the heads and layers in the MHA module on the experimental results， it was found that MHA-SVM achieved the highest recognition accuracy of 69.6% on IEMOCAP dataset. Experimental results indicate that the end-to-end model based on MHA mechanism is more suitable for SER tasks compared with models based on RNN and CNN.

Convolutional network-based vehicle re-identification combining wavelet features and attention mechanism

Guangkai LIAO, Zheng ZHANG, Zhiguo SONG

2022, 42(6):  1876-1883.  DOI: 10.11772/j.issn.1001-9081.2021040545

Asbtract ( )   HTML ( )   PDF (2250KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Aiming at the problem of insufficient representation ability of features extracted by the existing vehicle re-identification methods based on convolution Neural Network （CNN）， a vehicle re-identification method based on the combination of wavelet features and attention mechanism was proposed. Firstly， the single-layer wavelet module was embedded in the convolution module to replace the pooling layer for subsampling， thereby reducing the loss of fine-grained features. Secondly， a new local attention module named Feature Extraction Module （FEM） was put forward by combining Channel Attention （CA） mechanism and Pixel Attention （PA） mechanism， which was embedded into CNN to weight and strengthen the key information. Comparison experiments with the benchmark residual convolutional network ResNet-50 and ResNet-101 were conducted on VeRi dataset. Experimental results show that increasing the number of wavelet decomposition layers in ResNet-50 can improve mean Average Precision （mAP）. In the ablation experiment， although ResNet-50+Discrete Wavelet Transform （DWT） has the mAP reduced by 0.25 percentage points compared with ResNet-101， it has the number of parameters and computational complexity lower than those of ResNet-101， and has the mAP， Rank-1 and Rank-5 higher than those of ResNet-50 without DWT， verifying that the proposed model can effectively improve the accuracy of vehicle retrieval in vehicle re-identification.

Re-identification of vehicles based on joint stripe relations

Tingping ZHANG, Cong SHUAI, Jianxi YANG, Junzhi ZOU, Chaoshun YU, Lifang DU

2022, 42(6):  1884-1891.  DOI: 10.11772/j.issn.1001-9081.2021040544

Asbtract ( )   HTML ( )   PDF (5038KB) ( )  

Figures and Tables | References | Related Articles | Metrics

In order to solve the problem of spatial information loss caused by the splitting of vehicle feature maps in the process of vehicle re-identification， a module combining the relationship between stripe features was proposed to compensate for the lost spatial information. First， a two-branch neural network model was constructed for the special physical structure of the vehicle， and the output feature maps were divided horizontally and vertically equally and trained on different branches of the neural network. Then， a multi-activation value module was designed to reduce noise and enrich the feature map information. After that， triplet and cross-entropy loss functions were used to supervise the training of different features to restrict the intra-class distance and enlarge the inter-class distance. Finally， the Batch Normalization （BN） module was designed to eliminate the differences of different loss functions in the optimization direction， thereby accelerating the convergence of the model. Experimental results on two public datasets VeRi-776 and VehicleID show that the Rank1 value of the proposed method is better than that of the existing best method VehicleNet， which verifies the effectiveness of the proposed method.

ECG diagnostic classification based on improved RAKEL algorithm

Jing ZHAO, Jingyu HAN, Long QIAN, Yi MAO

2022, 42(6):  1892-1897.  DOI: 10.11772/j.issn.1001-9081.2021061068

Asbtract ( )   HTML ( )   PDF (1176KB) ( )  

Figures and Tables | References | Related Articles | Metrics

ElectroCardioGram （ECG） data usually contain many diseases， and ECG diagnosis is a typical multi-label classification problem. In RAndom k-labELsets （RAKEL） algorithm， one of multi-label classification methods， all labels are randomly decomposed into several labelsets of size k， and a Label Powerset （LP） classifier is established for training； however， the lack of sufficient consideration of correlation between labels makes the LP classifier obtain quite few samples corresponding to certain label combinations， which affects the prediction performance. To fully consider the correlation between labels， a Bayesian Network-based RAKEL （BN-RAKEL） algorithm was proposed. Firstly， the correlation between labels was found by Bayesian network to determine the candidate labelsets. Then， a feature selection method based on information gain was applied to construct the optimal feature space for each label， and the optimal feature space similarity was used for each candidate label subset to detect its correlation degree， determing the final labelsets with strong correlation. Finally， the LP classifiers were trained in the optimal feature space of the corresponding labelsets. A comparison with K-Nearest Neighbors for Multi-label Learning （ML-KNN）， RAKEL， Classifier Chains （CC） and FP-Growth based RAKEL algorithm named FI-RAKEL on the real ECG dataset showed that the proposed algorithm achieved a minimum improvement of 3.6 percentage points and 2.3percentage points in recall and F-score， respectively. Experimental results show that BN-RAKEL algorithm has good prediction performance， and can effectively improve the ECG diagnosis accuracy.

Data science and technology

Review of recommendation system

Meng YU, Wentao HE, Xuchuan ZHOU, Mengtian CUI, Keqi WU, Wenjie ZHOU

2022, 42(6):  1898-1913.  DOI: 10.11772/j.issn.1001-9081.2021040607

Asbtract ( )   HTML ( )   PDF (3152KB) ( )  

Figures and Tables | References | Related Articles | Metrics

With the continuous development of network applications， network resources are growing exponentially and information overload is becoming increasingly serious， so how to efficiently obtain the resources that meet the user needs has become one of the problems that bothering people. Recommendation system can effectively filter mass information and recommend the resources that meet the users needs. The research status of the recommendation system was introduced in detail， including three traditional recommendation methods of content-based recommendation， collaborative filtering recommendation and hybrid recommendation， and the research progress of four common deep learning recommendation models based on Convolutional Neural Network （CNN）， Deep Neural Network （DNN）， Recurrent Neural Network （RNN） and Graph Neural Network （GNN） were analyzed in focus. The commonly used datasets in recommendation field were summarized， and the differences between the traditional recommendation algorithms and the deep learning-based recommendation algorithms were analyzed and compared. Finally， the representative recommendation models in practical applications were summarized， and the challenges and the future research directions of recommendation system were discussed.

Density peak clustering algorithm based on adaptive reachable distance

Man ZHANG, Zhengjun ZHANG, Junqi FENG, Tao YAN

2022, 42(6):  1914-1921.  DOI: 10.11772/j.issn.1001-9081.2021040551

Asbtract ( )   HTML ( )   PDF (3484KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Concerning the problem that the cutoff distance needs to be selected manually in Clustering by Fast Search and Find of Density Peaks （CFSFDP） algorithm， as well as the poor clustering effect on complex datasets with different density clusters due to the error caused by nearest neighbor assignment， a Density Peak Clustering algorithm based on Adaptive Reachable Distance （ARD-DPC） was proposed. In this algorithm， a non-parametric kernel density estimation method was used to calculate the local density of points， and the clustering centers were selected by the decision graph. Then， an adaptive reachable distance was used to assign the data points and obtain the final clustering result. Simulation experiments were conducted on 4 synthetic datasets and 6 UCI datasets， and the proposed algorithm was compared with CFSFDP （Clustering by Fast Search and Find of Density Peaks）， DBSCAN （Density-Based Spatial Clustering of Applications with Noise） and DADPC （Density Peaks Clustering based on Density Adaptive distance）. Experimental results show that compared to the three other algorithms， the proposed ARD-DPC algorithm achieves the all highest Normalized Mutual Information （NMI）， Rand Index （RI） and F1-measure on 4 synthetic datasets and 3 UCI datasets， the only highest NMI on UCI Breast dataset， the only highest F1-measure on UCI Heart dataset， but does not cluster UCI Pima dataset well， which has high fuzzyness and unclear clustering feature. At the same time， ARD-DPC algorithm can accurately identify the number of clusters and clusters with complex density on the synthetic datasets.

Cyber security

Smart contract-based access control architecture and verification for internet of things

Yang LI, Long XU, Yanqiang LI, Shaopeng LI

2022, 42(6):  1922-1931.  DOI: 10.11772/j.issn.1001-9081.2021040553

Asbtract ( )   HTML ( )   PDF (3580KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Concerning the problem that the traditional access control methods face single point of failure and fail to provide trusted， secure and dynamic access management， a new access control model based on blockchain and smart contract for Wireless Sensor Network （WSN） was proposed to solve the problems of access dynamics and low level of intelligence of existing blockchain-based access control methods. Firstly， a new access control architecture based on blockchain was proposed to reduce the network computing overhead. Secondly， a multi-level smart contract system including Agent Contract （AC）， Authority Management Contract （AMC） and Access Control Contract （ACC） was built， thereby realizing the trusted and dynamic access management of WSN. Finally， the dynamic access generation algorithm based on Radial Basis Function （RBF） neural network was adopted， and access policy was combined to generate the credit score threshold of access node to realize the intelligent， dynamic access control management for the large number of sensors in WSN. Experimental results verify the availability， security and effectiveness of the proposed model in WSN secure access control applications.

Design and implementation method of mimic cloud agent based on active-standby monitoring

Qiaoyu GUO, Fucai CHEN, Guozhen CHENG, Wei ZENG, Yuqiang XIAO

2022, 42(6):  1932-1940.  DOI: 10.11772/j.issn.1001-9081.2021040595

Asbtract ( )   HTML ( )   PDF (3122KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Aiming at the security threats and single point of failure of the agent in mimic cloud systems， a high-available mimic cloud agent with active-standby monitoring was proposed. Firstly， an active-standby monitoring mechanism based on distributed agents in the cloud environment was proposed to construct heterogeneous active-standby agents. The traffic to the active agent was analyzed by the standby agent through mirroring the traffic， and the output results of the active agent were cross-validated by the standby agent. Secondly， based on the Data Plane Development Kit （DPDK） platform， a synchronous adjudication mechanism for standby agents and a seamless active-standby switching mechanism were designed to achieve security reinforcement and performance optimization of cloud agents. Finally， an active-standby switching decision algorithm was proposed to avoid the waste of resources caused by frequent active/standby switching. Experimental results showed that compared with the traffic processing delay of Nginx based cloud agents， the loss of this mimic cloud agent was milliseconds under high concurrency. It can be seen that the designed method can greatly improve the security and stability of the cloud proxy， and reduce the impact of the single point of failure on the stability of the proxy.

Multimedia computing and computer simulation

Depth image super-resolution based on shape-adaptive non-local regression and non-local gradient regularization

Yingying ZHANG, Chao REN, Ce ZHU

2022, 42(6):  1941-1949.  DOI: 10.11772/j.issn.1001-9081.2021040594

Asbtract ( )   HTML ( )   PDF (3318KB) ( )  

Figures and Tables | References | Related Articles | Metrics

To deal with the low resolution of depth images and blurring depth discontinuities， a depth image super-resolution method based on shape-adaptive non-local regression and non-local gradient regularization was proposed. To explore the correlation between non-local similar patches of depth image， a shape-adaptive non-local regression method was proposed. The shape-adaptive self-similarity patch was extracted for each pixel， and a similar pixel group for the target pixel was constructed according to its shape-adaptive patch. Then for each pixel in the similar pixel group， a non-local weight was obtained with the assistant of the high-resolution color image of the same scene， thereby constructing the non-local regression prior. To maintain the edge information of the depth image， the non-locality of the gradient of the depth image was explored. Different from the Total Variation （TV） regularization which assumed that all pixels obeyed Laplacian distribution with zero mean value， through non-local similarity of the depth image， the gradient mean value of specific pixel was estimated by non-local patches， and the gradient distribution of each pixel was fit by using the learned mean value. Experimental results show that compared with Edge Inconsistency Evaluation Model （EIEM） on Middlebury datasets， the proposed method decreases Mean Absolute Difference （MAD） of 41.1% and 40.8% respectively.

Speckle removal algorithm for ultrasonic image based on multi-scale fast non-local means filtering

Lulu LEI, Yingyue ZHOU, Chi LI, Xinyu WANG, Jiaqi ZHAO

2022, 42(6):  1950-1956.  DOI: 10.11772/j.issn.1001-9081.2021040620

Asbtract ( )   HTML ( )   PDF (2513KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Ultrasound imaging is widely used in clinical diagnosis because of its advantages of convenience， low cost and non-radiation， however， speckle noise in the image may adversely affect clinical diagnosis or subsequent image analysis.As a typical denoising technology， when using Non-Local Means Filter（NLMF）for speckle removal of ultrasonic image，there will be shortcomings such as high time consumption and difficulty in setting filtering parameters. Therefore， a Multi-scale Fast Non-Local Means Filter （MF-NLMF） algorithm was proposed to remove speckle noise of ultrasonic image. A Fast NLMF （F-NLMF） algorithm was first give out to reduce the computing time by using the mutual correlation filtering technique. Then multiple window parameters were set to obtain multiple speckle removal results， and the model parameters were able to be adjusted adaptively according to the window size. The final speckle removal image was obtained by fusing the multiple speckle removal results. Experimental results show that under the same experimental conditions， the F-NLMF algorithm reduces the computing time by at least 96.04% compared with the traditional NLMF algorithm. Compared with other six algorithms such as Iterative Bayesian Non-Local Mean Filtering （IBNLMF）， the proposed MF-NLMF has the speckle removal image with the Peak Signal-to-Noise Ratio （PSNR） value improved by more than 0.73 dB， the Feature SIMilarity index （FSIM） value increased by more than 0.011， the Contrast-to-Noise Ratio （CNR） and Signal-to-Noise Ratio （SNR） values raised by more than 0.000 5 and 0.001 6 respectively.

No-reference image quality assessment algorithm based on saliency deep features

Jia LI, Yuanlin ZHENG, Kaiyang LIAO, Haojie LOU, Shiyu LI, Zehao CHEN

2022, 42(6):  1957-1964.  DOI: 10.11772/j.issn.1001-9081.2021040597

Asbtract ( )   HTML ( )   PDF (1551KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Aiming at the universal No-Reference Image Quality Assessment （NR-IQA） algorithms， a new NR-IQA algorithm based on the saliency deep features of the pseudo reference image was proposed. Firstly， based on the distorted image， the corresponding pseudo reference image of the distorted image generated by ConSinGAN model was used as compensation information of the distorted image， thereby making up for the weakness of NR-IQA methods： lacking real reference information. Secondly， the saliency information of the pseudo reference image was extracted， and the pseudo saliency map and the distorted image were input into VGG16 netwok to extract deep features. Finally， the obtained deep features were merged and mapped into the regression network composed of fully connected layers to obtain a quality prediction consistent with human vision.Experiments were conducted on four large public image datasets TID2013， TID2008， CSIQ and LIVE to prove the effectiveness of the proposed algorithm. The results show that the Spearman Rank-Order Correlation Coefficient （SROCC） of the proposed algorithm on the TID2013 dataset is 5 percentage points higher than that of H-IQA （Hallucinated-IQA） algorithm and 14 percentage points higher than that of RankIQA （learning from Rankings for no-reference IQA） algorithm. The proposed algorithm also has stable performance for the single distortion types. Experimental results indicate that the proposed algorithm is superior to the existing mainstream Full-Reference Image Quality Assessment （FR-IQA） and NR-IQA algorithms， and is consistent with human subjective perception performance.

Anchor-free remote sensing image detection method for dense objects with rotation

Zhipei YANG, Sheng DING, Li ZHANG, Xinyu ZHANG

2022, 42(6):  1965-1971.  DOI: 10.11772/j.issn.1001-9081.2021060890

Asbtract ( )   HTML ( )   PDF (4079KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Aiming at the problems of high missed rate and inaccurate classification of dense objects in remote sensing image detection methods based on deep learning， an anchor-free deep learning-based detection method for dense objects with rotation was established. Firstly， CenterNet was used as the baseline network， features were extracted through the backbone network， and the original detector structure was improved， which means an angle regression branch was added to perform object angle regression. Then， a feature enhancement module based on asymmetric convolution was proposed， and the feature map extracted by the backbone network was put into the feature enhancement module to enhance the rotation invariant feature of the object， reduce the influence caused by the rotation and turnover of the object， and improve the regression precision of the center point and size information of the object. When using HourGlass-101 as the backbone network， compared with Rotation Region Proposal Network （RRPN）， the proposed method achieved a 7.80 percentage point improvement in Mean Average Precision （mAP） and 7.50 improvement in Frames Per Second （FPS） on DOTA dataset. On the self-built dataset Ship3， the proposed method achieved a 8.68 percentage point improvement in mAP and 6.5 improvement vin FPS. The results show that the proposed method can obtain a balance between detection precision and speed.

Joint 1-2-order pooling network learning for remote sensing scene classification

Xiaoyong BIAN, Xiongjun FEI, Chunfang CHEN, Dongdong KAN, Sheng DING

2022, 42(6):  1972-1978.  DOI: 10.11772/j.issn.1001-9081.2021040647

Asbtract ( )   HTML ( )   PDF (1958KB) ( )  

Figures and Tables | References | Related Articles | Metrics

At present， most pooling methods mainly extract aggregated feature information from the 1-order pooling layer or the 2-order pooling layer， ignoring the comprehensive representation capability of multiple pooling strategies for scenes， which affects the scene recognition performance. To address the above problems， a joint model with first- and second-order pooling networks learning for remote sensing scene classification was proposed. Firstly， the convolutional layers of residual network ResNet-50 were utilized to extract the initial features of the input images. Then， a second-order pooling approach based on the similarity of feature vectors was proposed， where the information distribution of feature values was modulated by deriving their weight coefficients from the similarity between feature vectors， and the efficient second-order feature information was calculated. Meanwhile， an approximate solving method for calculating square root of covariance matrix was introduced to obtain the second-order feature representation with higher semantic information. Finally， the entire network was trained with the combination loss function composed of cross-entropy and class-distance weighting. As a result， a discriminative classification model was achieved. The proposed method was tested on AID （50% training proportion）， NWPU-RESISC45 （20% training proportion）， CIFAR-10 and CIFAR-100 datasets and achieved classification accuracies of 96.32%， 93.38%， 96.51% and 83.30% respectively， which were increased by 1.09 percentage points， 0.55 percentage points， 1.05 percentage points and 1.57 percentage points respectively， compared with iterative matrix SQuare RooT normalization of COVariance pooling （iSQRT-COV）. Experimental results show that the proposed method effectively improves the performance of remote sensing scene classification.