2021 Vol.39

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Journal of Applied Sciences    2021, 39 (1): 0-0.   Abstract （8）      PDF（pc） （63KB）（140）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2021, 39 (1): 0-0.   Abstract （259）      PDF（pc） （23KB）（55）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Verification of Smart Contracts with Time Constraints ZHAO Yingqi, ZHU Xueyang, LI Guangyuan, GAO Ya, BAO Yulong Journal of Applied Sciences    2021, 39 (1): 1-16.   DOI: 10.3969/j.issn.0255-8297.2021.01.001 Abstract （608）      PDF（pc） （1292KB）（232）       Knowledge map    Save In real life, a type of smart contract is closely related to time constraint, and whether the contract meets its time property will directly affect the correctness of its applications. In order to avoid serious problems after its deployment, this paper focuses on smart contracts of Ethereum, gives a timed automata semantics for smart contracts, after the smart contract is converted into a time automata model, and uses model checking tool UPPAAL to check whether the smart contract meets timed properties expressed by temporal logic formulas. Finally, we study two cases, an auction contract and a flight insurance contract. Experimental results indicate whether the real-time property is satisfied. If not, counter examples can be used to locate the problem points in the smart contract, showing the effectiveness of the work. Reference | Related Articles | Metrics | Comments（0）

Select

SGX-Based Approach for Blockchain Transactions Security and Privacy Protection FAN Junsong, CHEN Jianhai, SHEN Rui, LIU Zhenguang, HE Qinming, HUANG Butian Journal of Applied Sciences    2021, 39 (1): 17-28.   DOI: 10.3969/j.issn.0255-8297.2021.01.002 Abstract （916）      PDF（pc） （404KB）（336）       Knowledge map    Save Compared to traditional payment, blockchain has the advantages of decentralization and privacy protection, while there are still issues with the privacy and security of transactions involving lightweight clients and with the user-friendliness of blockchain systems. This paper proposes SGXTrans, a system that can provide privacy protection for blockchain transaction. On the framework of lightweight clients, as SGXTrans creates a service, it uses Intel software guard extensions (SGX) to protect sensitive privacy information by putting them into the SGX enclave, including cryptographic data and operations such as the user key, the generation of user addresses, and the process of blockchain transactions. To hide the access patterns of local data storage processes, SGXTrans also introduces oblivious random access machine (ORAM) algorithm to prevent privacy information from being indirectly inferred by malicious attackers. Experiments based on the existing blockchain networks show that SGXTrans can provide better user-friendliness and higher security with a performance overhead less than 10%. Reference | Related Articles | Metrics | Comments（0）

Select

Auditable and Traceable Blockchain Anonymous Transaction Scheme ZHAO Xiaoqi, LI Yong Journal of Applied Sciences    2021, 39 (1): 29-41.   DOI: 10.3969/j.issn.0255-8297.2021.01.003 Abstract （583）      PDF（pc） （906KB）（172）       Knowledge map    Save In recent years, with the strengthening of privacy protection for blockchain transactions, it has become more difficult to audit blockchain transactions and track the identity of illegal traders. For this reason, an auditable and traceable blockchain anonymous transaction scheme is proposed in this paper. Elgamal encryption, digital signature and improved hidden address technologies are used to realize the privacy protection of the transaction content and the identities of transaction senders and transaction receivers, and realize the distribution of power by introducing two roles of auditor and regulator. When an illegal transaction is audited, auditor sends a tracking identity request with signature to the regulator. After the signature is verified, the regulator can use the received tracking key and the personal key to trace the identities of both parties to the transaction. This scheme satisfies the anonymity, auditability and identity traceability of transactions. Simulation experiment results show the high audit efficiency of the scheme. Reference | Related Articles | Metrics | Comments（0）

Select

Trusted Query Method for Data Provenance Based on Blockchain ZHANG Xuewang, FENG Jiaqi, YIN Zijie, LIN Jinzhao Journal of Applied Sciences    2021, 39 (1): 42-54.   DOI: 10.3969/j.issn.0255-8297.2021.01.004 Abstract （856）      PDF（pc） （296KB）（323）       Knowledge map    Save In order to reduce the storages needed in verifying provenance information of light clients in blockchain data provenance system, this paper firstly introduces a data structure titled by Merkle mountain range (MMR), which optimizes the dynamic append performance of Merkle trees and stores all block headers on blockchain in the MMR. Then we propose an efficient and reliable verification method for data provenance to reduce the size of the proof information required for the proof of the block contain. On this basis, a scheme of data provenance system based on block chain is designed, which encapsulates the common modules required for data provenance and opens them to the provenance application through interfaces. This scheme enables light clients to effectively verify whether the provenance information is contained in the block chain as long as they keep the information of the latest block in storage. Reference | Related Articles | Metrics | Comments（0）

Select

Blockchain and Capability Based Access Control Mechanism in Multi-domain IoT WANG Siyuan, ZOU Shihong Journal of Applied Sciences    2021, 39 (1): 55-69.   DOI: 10.3969/j.issn.0255-8297.2021.01.005 Abstract （607）      PDF（pc） （1041KB）（386）       Knowledge map    Save Data in Internet of things (IoT) usually contains a large amount of personal privacy information, In order to prevent privacy data leakage due to unauthorized access during device collaboration, this article proposes a set of access control mechanisms for multi-domain IoT device collaboration scenarios. By combining distributed capabilitybased access control (CapAC) with blockchain technology, this article designs a capability token stored in the blockchain and a token management contract based on smart contracts. According to CapACs access decision-making method, a blockchain-based token verification method is designed. The blockchain lightweight node is optimized for the characteristics of IoT. Finally, a blockchain system is built to implement the mechanism proposed in the article. Experimental test results show that compared to centralized access control mechanisms, this solution can safely and accurately execute access decisions in large-scale IoT scenarios and has more stable processing performance. Lightweight design can greatly reduce node storage burden. Reference | Related Articles | Metrics | Comments（0）

Select

Authentication Method of Integrated Energy Management System Based on Blockchain ZHOU Qi, SHEN Tao, ZHU Yan, LIU Yingli Journal of Applied Sciences    2021, 39 (1): 70-78.   DOI: 10.3969/j.issn.0255-8297.2021.01.006 Abstract （557）      PDF（pc） （305KB）（125）       Knowledge map    Save In order to improve the utilization of integrated energy management system, and simultaneously protect the identity information of accessing users in the process of energy trading account, this paper puts forward a integrated energy management system framework based on blockchain technology, and designed a special kind of zero-knowledge proof authentication method. First, this paper introduces applicability of blockchain technology in integrated energy management system, then analyzes privacy issues in data interaction between users and load aggregator's, and discusses the unique advantages of blockchain technology in integrated energy management system, such as traceability, openness, anonymity in solving trusting problems, and records all interactive information by using blocks. Finally, based on the proposed zero-knowledge proof method, the connection between user's biological information and user's stored information is established to realize an automatic, secured and trusted authentication mode. Reference | Related Articles | Metrics | Comments（0）

Select

Improved PBFT Scheme Based on Reputation Voting TU Yuanchao, CHEN Yuling, LI Tao, REN Xiaojun, QING Xinyi Journal of Applied Sciences    2021, 39 (1): 79-89.   DOI: 10.3969/j.issn.0255-8297.2021.01.007 Abstract （649）      PDF（pc） （364KB）（236）       Knowledge map    Save As a decentralized, tamper-proof distributed ledger, the performance of blockchain is fundamentally affected by the efficiency of consensus mechanisms. Practical Byzantine fault tolerance (PBFT) algorithm randomly selects master nodes through view-switching, leading to problems of security vulnerabilities and low consensus efficiency in the case of large number of nodes. In response to the two problems, a PBFT improvement scheme based on reputation voting is proposed. The reliability of nodes is evaluated according to node division mechanism, where high reputation nodes are dynamically selected to participate in the consensus, and a malicious node is assigned with lower probability of becoming a consensus node, accordingly increasing the security of the system. By switching the role of nodes according to node state transfer mechanism, the scheme can maintain the correct operation of the system and improve the stability of the system. Experiments on the proposed and the traditional PBFT schemes show that the proposed one can reduce Byzantine nodes and communication overhead in long-term consensus processes, and improve the fault tolerance rate and the data throughput of transaction. Reference | Related Articles | Metrics | Comments（0）

Select

Roadside Parking Management System Based on Blockchain Technology YANG Di, XU Han, LONG Chengnian, PENG Shaoliang Journal of Applied Sciences    2021, 39 (1): 90-98.   DOI: 10.3969/j.issn.0255-8297.2021.01.008 Abstract （592）      PDF（pc） （1624KB）（311）       Knowledge map    Save Aiming at the shortcomings of low efficiency and opaque transaction in current roadside parking management, a roadside parking management system based on blockchain technology is proposed. Parking information is collected by license plate recognition algorithm of edge device terminal, and key parking transaction data is sent and stored in MySQL database cache of Web server, and then stored in Hyperledger Fabric blockchain platform through Fabric SDK middleware. Relying on the decentralization of the blockchain and the non-tamperable nature of the on-chain data, the system not only meets business needs but also improves the privacy of users and the reliability of transactions. Reference | Related Articles | Metrics | Comments（0）

Select

An Architecture Based on Lightweight Blockchain Suitable for Vehicular Cloud FAN Jun, LI Ru, ZHANG Yihang Journal of Applied Sciences    2021, 39 (1): 99-108.   DOI: 10.3969/j.issn.0255-8297.2021.01.009 Abstract （423）      PDF（pc） （816KB）（218）       Knowledge map    Save The mobility of nodes in vehicular cloud, the dynamics of networks, the openness of communication methods, and the non-trustworthiness of vehicles bring more challenges to the security of task scheduling in vehicular cloud. Based on the full consideration of characteristics of vehicular cloud, this article introduces blockchain and proposes a lightweight blockchain architecture suitable for task scheduling in vehicular cloud. Road side units (RSU) are used to construct a blockchain network, and an improved practical Byzantine fault tolerance (PBFT) algorithm is used to complete the consensus. Based on the scheduling delay model of the architecture, the scheduling performance of the architecture is tested and analyzed through experiments. The comparison with Ethereum shows that the proposed architecture not only realizes the non-repudiation of the task scheduling process, avoids the single point failure of the task scheduling server, improves the availability, but also achieves lightweight, that is, no additional computing power or storage space is required, and can reach millisecond-level scheduling delay. Reference | Related Articles | Metrics | Comments（0）

Select

Research and Design of Legal Smart Contract Platform Model XIANG Weijing, TSAI Weitek Journal of Applied Sciences    2021, 39 (1): 109-122.   DOI: 10.3969/j.issn.0255-8297.2021.01.010 Abstract （522）      PDF（pc） （294KB）（210）       Knowledge map    Save Blockchain is essentially a distributed database or a network database. A real smart contract should be legally effective chain code, namely, the digitization of legal contracts, and can realize the automatic execution of contract terms. This article firstly introduces important technologies relevant to this type of smart contract, including legal considerations, oracles, event models and others, then proposes five standard development steps for legal smart contracts and a method for designing smart contract templates. Moreover, we also design a secure multi-channel event model for data preprocessing. Consequently, contracts processed on the above smart contract platform are expected to have legal effect. Reference | Related Articles | Metrics | Comments（0）

Select

Medical Data Security Sharing Scheme Based on Consortium Blockchain ZHOU Zhengqiang, CHEN Yuling, LI Tao, REN Xiaojun, QING Xinyi Journal of Applied Sciences    2021, 39 (1): 123-134.   DOI: 10.3969/j.issn.0255-8297.2021.01.011 Abstract （752）      PDF（pc） （593KB）（539）       Knowledge map    Save The existing blockchain-based medical data sharing schemes perform access control without the consideration of time dimension. To solve this problem, this paper proposes a medical data security sharing scheme, based on consortium blockchain in consideration of time dimension to perform access control. Firstly, medical data ciphertext is stored in cloud storage, and the metadata is stored in the consortium blockchain, such that the medical data can be stored and shared safely. Secondly, by combining smart contract with ciphertext-policy attribute-based encryption (CP-ABE), a data security sharing protocol is designed to realize fine-grained access control with time dimension. The security analysis and experimental results show that this scheme could realize fine-grained access control with time dimension, besides ensuring the security of the stored medical data. Reference | Related Articles | Metrics | Comments（0）

Select

Data Protection Scheme for Targeted Poverty Alleviation Based on Blockchain ZHANG Lihua, HUANG Yang, WANG Xinyi, BAI Jiayi, CAO Yu, ZHANG Ganzhe Journal of Applied Sciences    2021, 39 (1): 135-150.   DOI: 10.3969/j.issn.0255-8297.2021.01.012 Abstract （483）      PDF（pc） （541KB）（344）       Knowledge map    Save Aiming at the problems of centralized storage, weak tamper proofing, poor traceability and lack of safe and effective sharing channels, etc., a data protection scheme for targeted poverty alleviation based on blockchain is studied. By taking the advantages of blockchain technology, such as decentralization and unforgeability, poverty reduction data are recorded in the form of personal files. Through smart contract and inter-planetary file system (IPFS) technology, the data can be added, updated, verified and shared in the form of digital files. The combination of public chain and consortium ensures data security by anchoring data snapshot information. In the construction of smart contract, combined with secure multi-party computing (SMPC) technology, the security of contract execution is enhanced, and sensitive issues such as fund transfer are solved. With an improved Raft consensus algorithm, the performance, reliability and regional influence of each node are taken as comprehensive performance, based on which, a Raft consensus algorithm is designed to solve the problems of data storage and data processing efficiency. We use postman and JMeter tools to test the storage certificate and the throughput of the system, and obtain satisfying experimental results. Reference | Related Articles | Metrics | Comments（0）

Select

Analysis of Security Strategies for Smart Contracts Based on Ethereum ZHANG Dengji, ZHAO Xiangfu, CHEN Zhongyu, TONG Xiangrong Journal of Applied Sciences    2021, 39 (1): 151-163.   DOI: 10.3969/j.issn.0255-8297.2021.01.013 Abstract （411）      PDF（pc） （273KB）（193）       Knowledge map    Save A smart contract is a collection of code and data. Once a smart contract is deployed, it cannot be changed. Smart contracts have financial properties, thus, it would cause huge losses if there were vulnerabilities in smart contracts. Therefore, it is essential to write safe and reliable smart contracts. Based on the Ethereum platform, related security of smart contracts is analyzed, and several common vulnerabilities are summarized, including reentrancy vulnerabilities, integer overflow vulnerabilities, deny of service (DoS) vulnerabilities, timestamp dependence vulnerabilities, and transaction-ordering dependence vulnerabilities. We made theoretical analysis in detail and scenario recurrence on these vulnerabilities, proposed corresponding preventive security strategies, and verified the effectiveness of these strategies. Finally, we analyzed and compared several popular tools for detecting smart contract vulnerabilities. Reference | Related Articles | Metrics | Comments（0）

Select

Cloud Storage Data Integrity Verification Scheme Based on Blockchain LIU Feng, ZHAO Junfeng Journal of Applied Sciences    2021, 39 (1): 164-173.   DOI: 10.3969/j.issn.0255-8297.2021.01.014 Abstract （577）      PDF（pc） （343KB）（294）       Knowledge map    Save Aiming at the problems existing in data integrity of cloud storage services, a blockchain-based cloud storage data integrity verification scheme is proposed by referring to the current remote data integrity verification scheme. Firstly, an integrity certificate is stored in a tamper-proof blockchain, thus an accountable data integrity certificate is constructed. At the same time, the third-party auditor is replaced by the smart contract in the blockchain to verify the integrity of the data. In the verification stage, the integrity verification of data copies is added, and the cloud storage service is forced to store at least one data copy. In addition, a third-party arbitration organization is introduced for the first time, which uses the accountable data integrity certificate to arbitrate the integrity of illegal requests from malicious cloud storage providers and users. Finally, the proposed scheme is proved to be safe and feasible by analysis and experiment. Reference | Related Articles | Metrics | Comments（0）

Select

Convergence of Blockchain and IoT: Research Status and Prospect YAO Zhongyuan, PAN Heng, ZHU Weihua, SI Xueming Journal of Applied Sciences    2021, 39 (1): 174-184.   DOI: 10.3969/j.issn.0255-8297.2021.01.015 Abstract （912）      PDF（pc） （248KB）（421）       Knowledge map    Save With the rapid development of blockchain and Internet of things (IoT) technology, the research of integrating two technologies and the development of collaborating applications have become prominent. In order to help researchers in the field of blockchainIoT convergence to analyze and grasp the research hot-spots and trends conveniently, this paper extensively investigates current relevant research literature and summarizes a large number of relevant achievements according to the specific research content. This paper also makes a detailed comparison between the research works in our country and those of foreign counterparts, with an objective clarification of the advantages and disadvantages of these research works. Finally, based on the literature research results, this paper forecasts the development trend of the research on the convergence of blockchain and IoT. Reference | Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2021, 39 (2): 0-0.   Abstract （1541）      PDF（pc） （78KB）（61）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2021, 39 (2): 1-0.   Abstract （1671）      PDF（pc） （26KB）（41）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Short-Term Traffic Flow Prediction Method of Different Periods Based on Improved CNN-LSTM LI Lei, ZHANG Qingmiao, ZHAO Junhui, NIE Yiwen Journal of Applied Sciences    2021, 39 (2): 185-198.   DOI: 10.3969/j.issn.0255-8297.2021.02.001 Abstract （2618）      PDF（pc） （1339KB）（755）       Knowledge map    Save Aiming at solving the problem that existing prediction models could not fully extract the spatio-temporal features in traffic flow, we proposed an improved convolutional neural network (CNN) with long short-term memory neural network (LSTM) for shortterm traffic flow prediction. First of all, a layered extraction method was used to design the network structure and one-dimensional convolution kernel which enabled automatic extraction of spatial features of traffic flow sequences. Second, the LSTM network modules were optimized to reduce the long-term dependence of network on the data. Finally, the optimization algorithm for rectified adaptive moment estimation (RAdam) was introduced to the end-to-end model training process, which accelerated fitting effects of the weight and improved the accuracy and robustness of network output. Experimental results showed that compared with the prediction model of stacked auto-encoders (SAEs) network, performance of the proposed model was enhanced by 3.55% and 8.82% on weekdays and weekends with model running times reduced by 6.2% and 6.9%, respectively. Compared with the prediction model of long-short term memory-support vector regression (LSTM-SVR), its performance was enhanced by 0.29% and 1.79% with model running times reduced by 9.0% and 9.7%, respectively. Therefore, the proposed model was more applicable to the short-term traffic flow prediction of different time periods. Reference | Related Articles | Metrics | Comments（0）

Select

A Charging Vehicle Scheduling Scheme with Traffic Road Restrictions ZHONG Ping, CHEN Yuanming, DU Zhicheng, LI Lin, GUI Lin Journal of Applied Sciences    2021, 39 (2): 199-209.   DOI: 10.3969/j.issn.0255-8297.2021.02.002 Abstract （1835）      PDF（pc） （632KB）（96）       Knowledge map    Save Charging scheduling is a very important item for wireless rechargeable sensor networks. Existing researches mainly focus on scheduling charging vehicles to obtain the optimal mobile path. However, these algorithms cannot provide good performance when traffic is restricted. Considering the mobile charging vehicle scheduling problem with traffic road constraints, this paper proposes a mobility constrained charging scheduling scheme (MCCS). To better fit the actual scene, we formalize the problem as an edge coverage problem, and enhance the classical MAENS algorithm by adding a path decomposition operator and a mutation operator. The performance of MCCS is evaluated by extensive simulations. Compared with MAENS, experimental results show that MCCS achieves superior performance in terms of low average energy consumption and high charging stability. Reference | Related Articles | Metrics | Comments（0）

Select

New Location Algorithm Based on Sparse Grid Optimization in C-V2X XIA Xiaohan, CAI Chao, QIU Jiahui, YANG Jingyuan, ZHANG Xiangyun, XIAO Ran Journal of Applied Sciences    2021, 39 (2): 210-221.   DOI: 10.3969/j.issn.0255-8297.2021.02.003 Abstract （1806）      PDF（pc） （3427KB）（199）       Knowledge map    Save The location algorithm in cellular-V2X (C-V2X) has always been one of the important technical approaches for the development of vehicle-road collaboration and autonomous driving. Currently, in the vehicle-road collaboration scenarios of autonomous driving services, many positioning solutions including base stations and GNSS meet challenges in many aspects such as positioning accuracy, positioning processing delay and deployment cost. In response to these problems, a fingerprint location algorithm is proposed for C-V2X based on statistical information grid (STING) algorithm for grid optimization and extreme gradient boosting decision tree (XGBoost). Compared with traditional fingerprint positioning methods, the positioning accuracy and calculation rate are optimized after grid optimization. The new method is more suitable for vehicle-road collaboration scenarios, and provides an effective positioning method for C-V2X scenarios. Reference | Related Articles | Metrics | Comments（0）

Select

Research on Insulator Self Exploding Detection in UAV Inspection Based on Deep Learning WANG Wanguo, MU Shiyou, LIU Yue, LIU Guangxiu, LANG Fenling Journal of Applied Sciences    2021, 39 (2): 222-231.   DOI: 10.3969/j.issn.0255-8297.2021.02.004 Abstract （2032）      PDF（pc） （10566KB）（322）       Knowledge map    Save Insulator self-exploding detection is an important part of UAV inspection. Accurate, rapid and automatic searching for insulator self-exploding areas can greatly save the workload of UAV inspection data processing and improve inspection accuracy and efficiency. Aiming at the problem of low sample size, small target and low precision in the current insulator self-exploding detection, this paper proposes a deep learning self-exploding detection method for UAV inspection insulators. The method uses a large number of collected insulator samples to train the deep learning detection model, and then uses the computer vision method to detect the self-exploding region in the detected insulator. The method of this paper synthesizes the advantages of deep learning in detecting complex targets and the fact that computer vision does not require a large number of samples and can detect small targets. Experiments show that the detection accuracy of this algorithm can reach 84.8%. It has positive significance and application value for insulator self-exploding detection. Reference | Related Articles | Metrics | Comments（0）

Select

Design of the RT IP Core for Satellite Payload Data Bus LIU Wenting, WAN Xiaolei, XU Nan, YANG Tong, CHEN Liangliang Journal of Applied Sciences    2021, 39 (2): 232-240.   DOI: 10.3969/j.issn.0255-8297.2021.02.005 Abstract （1999）      PDF（pc） （2242KB）（90）       Knowledge map    Save Based on serial bus protocol, a remote terminal IP (intellectual property) core for satellite payload data bus is proposed. The IP core is composed of bus interface module, frequency divider module, protocol processing module and data collecting module. The IP core design is tested and verified by functional simulation and FPGA (field programmable gate array) test, and has been taped out successfully. Test results indicate that the designed IP core has good performance in capability, reliability and less resource occupancy. It can be used for testing the payload data bus in satellite systems or in verification equipment of satellite systems. Reference | Related Articles | Metrics | Comments（0）

Select

Development of NB-IoT Based Intelligent LED Light Pole Monitoring System JIN Yan, MAO Minmin, XU Qiuyu, OUYANG Yuling, JU Jiaqi Journal of Applied Sciences    2021, 39 (2): 241-249.   DOI: 10.3969/j.issn.0255-8297.2021.02.006 Abstract （2017）      PDF（pc） （1590KB）（276）       Knowledge map    Save In order to solve the problems of traditional LED light pole in remote controlling, automatic inspection, real-time single light regulation and control, and fault location recognition, an intelligent LED light pole monitoring system based on narrow band internet of things (NB-IoT) is proposed in this paper. In the system, STM32L151 micro controller unit (MCU) is adopted as the processor, together with multiple sensors to realize signal acquisition of street lamp. Through the connection between NB-IoT modules and core network, signals are collected and uploaded to OneNET cloud platform. And with a developed mobile application (APP) and a personal computer (PC) monitoring interface, fault location information of street lamps can be obtained in real time. Experimental results show that the developed system can not only achieve real time monitoring and control of street lights, accurate positioning of faulty street lights, but also realize the individual control of street lights. Reference | Related Articles | Metrics | Comments（0）

Select

Q-learning Based Relay Selection Strategy for Hybrid Satellite-Terrestrial Cooperative Transmission WANG Xiaoxiao, KONG Huaicong, ZHU Weiping, LIN Min Journal of Applied Sciences    2021, 39 (2): 250-260.   DOI: 10.3969/j.issn.0255-8297.2021.02.007 Abstract （1891）      PDF（pc） （310KB）（108）       Knowledge map    Save Cooperative relay networks can achieve spatial diversity, but their system performances heavily depends on relay selection schemes. To solve this problem, a hybrid satellite-terrestrial cooperative network relay selection strategy based on Q-learning is proposed. First, under the consideration that all the relay nodes employ amplify-and-forward protocol, the end-to-end output signal-to-noise ratio after combining the maximal ratio is derived. Next, the state, action and reward function of Q-learning are set to select the relay node with the greatest cumulative return. Then, in order to traverse all states, Boltzmann selection policy is induced to select action by probability approach, so that the source node can explore all states and find the optimal one. Finally, the optimal transmission power is obtained by using power allocation scheme between the selected relay node and the source node. Simulation results show that, compared with the random relay selection algorithm, the proposed strategy greatly improves the system performance. Reference | Related Articles | Metrics | Comments（0）

Select

Research on Adaptive Speech Enhancement Method for Microphone Array Based on Convex Combination ZHAO Yibo, LU Haozhi, LI Shuhui, YAN Tao Journal of Applied Sciences    2021, 39 (2): 261-271.   DOI: 10.3969/j.issn.0255-8297.2021.02.008 Abstract （1841）      PDF（pc） （750KB）（125）       Knowledge map    Save Generalized sidelobe canceller is a widely used microphone array speech enhancement method, which has obvious noise reduction effect on speech signals with Gaussian noise. However, when impulse noise is mixed in the speech signal, the recognizability of the enhanced speech signal becomes significantly worse as using this method. In order to improve the noise reduction effect on speech signals with impulse noise, in this paper, an adaptive speech enhancement method for microphone array based on convex combination is presented. In this method, a single linear adaptive filter is replaced by a convex combined filter composed of linear filter and nonlinear spline filter, and the maximum correntropy criterion is used to update the weight of the convex combination filter and the control point factor in the nonlinear spline filter. Results show that the presented speech enhancement method can effectively filter the Gaussian noise and impulse noise in the speech signal, and the speech enhancement effect is extremely obvious. Reference | Related Articles | Metrics | Comments（0）

Select

Attention Guided 3D ConvNet for Aerial Scene Change Detection ZHANG Han, QIN Kun, BI Qi, ZHANG Ye, XU Kai Journal of Applied Sciences    2021, 39 (2): 272-280.   DOI: 10.3969/j.issn.0255-8297.2021.02.009 Abstract （1922）      PDF（pc） （4717KB）（224）       Knowledge map    Save With high tolerance to the great amount of noise and precise depiction of image changes in high resolution remote sensing images (HRRSI), scene-level change detection strategy makes it possible to detect changes in HRRSI. In this paper, we propose an attention guided 3D ConvNet for HRRSI change detection. Firstly, we develop a simplified 3D AlexNet to extract convolutional features. Then we add a semantic attention module (SAM) to further extract the discriminative regions which strongly relate to land-cover changes. Finally, the refined features are fed into a classification layer to organize the whole framework in an end-to-end trainable manner. Scenes in different phases are put into the convolutional neural network (CNN) with the result of change detection. In order to evaluate the performance of scene level change detection methods, we create a public semantic level high resolution remote sensing images change detection benchmark. Experimental results on this dataset are obviously better than other related methods, demonstrate the effectiveness of our method, and show the prospect of scene level remote sensing change detection based on deep learning. Reference | Related Articles | Metrics | Comments（0）

Select

Orientation Method for Rail Weld Region Based on Level Set LIU Xingwu, XIONG Bangshu, LIAO Feng, CHEN Xinyun Journal of Applied Sciences    2021, 39 (2): 281-292.   DOI: 10.3969/j.issn.0255-8297.2021.02.010 Abstract （1955）      PDF（pc） （11140KB）（320）       Knowledge map    Save An orientation method for rail weld region based on level set is proposed to improve the adaptability, stability and accuracy of weld positioning under different illumination conditions. Firstly, in order to separate welds from rail waists, rail heads and background, level set is used to segment the contours in preprocessed weld image. Secondly, area sorting and domain connecting are used in combination to eliminate contour interference and achieve coarse positioning of weld contour. The weld contour is then accurately positioned by using double sorting method. Finally, the rail weld region is automatically positioned by sorting the abscissa of weld contour. Positioning experiments for the weld region of 60kg/m rail are conducted under different illumination conditions. Experiments demonstrate the advantages of strong adaptability, high accuracy and good stability, and prove that the proposed method can be used for automatically detecting the weld misalignment in welded rail site. Reference | Related Articles | Metrics | Comments（0）

Select

Improved Steganography Algorithm Based on J-UNIWARD WU Qian, WU Jianbin, LIU Zixuan, SONG Mengli Journal of Applied Sciences    2021, 39 (2): 293-301.   DOI: 10.3969/j.issn.0255-8297.2021.02.011 Abstract （1908）      PDF（pc） （251KB）（208）       Knowledge map    Save In order to further improve the security of adaptive steganography algorithms, this article introduces the idea of image blocking, rewrites the distortion function of the original J-UNIWARD algorithm, and changes additive distortion functions to non-additive distortion functions. The implementation process of the algorithm is as follows: The carrier image to be processed is divided into four sub-blocks, and the texture complexity of each sub-block is calculated separately, under the constraint of keeping total embedding amount unchanged. The more complex blocks are preferentially chosen to be embedded. By recalculating the distortion function after each block-embedding, the embedding amount is dynamically adjusted according to the complexity. Then the secret information is adaptively embed into the texture area by STC (syndrome trelliscodes) encoding. Finally, detection performance is analyzed by using DCTR and ccJRM steganalysis techniques. Experimental results show that under the same capacity, the proposed algorithm can significantly improve the anti-stealth analysis ability of the algorithm. Reference | Related Articles | Metrics | Comments（0）

Select

Data Augmentation Method Based on Image Gradient LIU Zhiyu, ZHANG Shufen, LIU Yang, LUO Changyin, LI Min Journal of Applied Sciences    2021, 39 (2): 302-311.   DOI: 10.3969/j.issn.0255-8297.2021.02.012 Abstract （1828）      PDF（pc） （2913KB）（78）       Knowledge map    Save As used in classification of image recognition, convolutional neural network requires large-scale image data set for training. Due to the limitation of the number of target images to be collected and the conditions of image acquisition equipment, it is difficult to obtain enough image samples by conventional methods because of time-consuming, laborconsuming and money-consuming. In order to solve the insufficiency of image samples, a variety of sample enlargement methods have been proposed. This paper introduces the research background and significance of data augmentation. For the purpose of improving the accuracy of image recognition of convolutional neural network, a data augmentation method based on image gradient is proposed. The image gradient is selected to increase image sample and enlarge image data set by precise clipping method, and the convolutional neural network is trained with the expanded data set. By using Tensorflow deep learning framework and VGG16 network model, and selecting some data sets of PlantVillage, the training set data can be expanded to 6 times of the original. The training set before and after the expansion is trained and compared. Experimental results show that the accuracy rate of the model trained by the training set after data augmentation is increased by 4.18%. Reference | Related Articles | Metrics | Comments（0）

Select

Land-Use Information of Object-Oriented Classification by UAV Image MA Feihu, XU Fadong, SUN Cuiyu Journal of Applied Sciences    2021, 39 (2): 312-320.   DOI: 10.3969/j.issn.0255-8297.2021.02.013 Abstract （1940）      PDF（pc） （10409KB）（268）       Knowledge map    Save In order to effectively classify the rural land, an object-oriented classification method is selected to extract the land classification information of drone aerial photography images. First, original drone-taking images are preprocessed, then by repeatedly performing segmentation tests on the study area, the optimal segmentation scale of each feature is selected, with which the images are segmented at different levels. And based on feature differences in feature vector, spectrum, shape, etc., the most suitable classification rules are established for the features on the optimal segmentation scale layer. Accordingly, the land use information of each layer can be extracted. Experimental results with 734 samples for accuracy verification show that the overall classification accuracy of multi-scale and multi-level segmentation classification reaches 84.20%, and the kappa coefficient is 0.8062, whereas the overall accuracy of single-scale segmentation classification is only 77.11%, and the kappa coefficient is 0.7214. It shows that the data used in this study and the classification accuracy of the categories inside the region are higher. Reference | Related Articles | Metrics | Comments（0）

Select

A Single Image Super-Resolution Method Based on the Dual Network Model NI Cui, WANG Peng, ZHANG Guangyuan, LI Kefeng Journal of Applied Sciences    2021, 39 (2): 321-329.   DOI: 10.3969/j.issn.0255-8297.2021.02.014 Abstract （1812）      PDF（pc） （11394KB）（259）       Knowledge map    Save This article mainly improves the efficient sub-pixel convolutional neural network (ESPCN) algorithm in the field of deep learning. By adding residual network knowledge and adjusting original ESPCN structure, a dual network model is proposed for single frame image super-resolution reconstruction method. Experimental results show that this algorithm can effectively improve the accuracy of single-image super-resolution reconstruction and enrich the detailed information after reconstruction. Reference | Related Articles | Metrics | Comments（0）

Select

Fingerprint Recognition System Based on Editable Blockchain ZHU Yanyan, LI Sheng, FENG Guorui, ZHANG Xinpeng Journal of Applied Sciences    2021, 39 (2): 330-337.   DOI: 10.3969/j.issn.0255-8297.2021.02.015 Abstract （1907）      PDF（pc） （2634KB）（164）       Knowledge map    Save Fingerprint identity authentication system has been widely used in access control, payment, public security and other fields. Existing systems typically store original fingerprint images or features in a database to identify or authenticate users’ identity. Fingerprint data in the database is at risk of being attacked or tampered with. In order to solve this problem, this paper proposes a fingerprint identification system based on editable blockchain. Firstly, we build a private chain environment, achieve multi-node cluster interconnection, and then calculate the fingerprint hash and store it in the blockchain. In order to facilitate the administrator to update the users in the fingerprint identification system, this paper uses the chameleon hash algorithm to calculate the hash of the constructed private chain block. The administrator who owns the chameleon hash private key can edit the information in the block body to implement deletion or modification of the user fingerprint data without changing the blockchain structure. Experiments show that the proposed system has good real-time performance and high accuracy of fingerprint recognition. Reference | Related Articles | Metrics | Comments（0）

Select

D2D Network Resource Allocation Based on Joint Interference Control and PSO LIU Yuheng, PENG Yi, FU Xiaoxia, AN Haojie Journal of Applied Sciences    2021, 39 (2): 338-346.   DOI: 10.3969/j.issn.0255-8297.2021.02.016 Abstract （1775）      PDF（pc） （257KB）（99）       Knowledge map    Save Address to interference problems faced by D2D (device-to-device) communication users in the process of multiplexing traditional cellular communication channel resources, a resource allocation algorithm based on particle swarm optimization (PSO) algorithm for D2D communication power matching joint interference control is proposed in this paper, which maximizes the throughput of the whole system while controlling interference. Firstly, security communication are divided into different ranges according to threshold values of user-powers, and only the users in the security communication range have opportunity to join in subsequent power distribution, thus effectively reducing system interference. Secondly, a power matching method based on PSO is adopted to take D2D senders as particle swarm. It maximizes the throughput of the whole system by searching for the optimal power through iteration. Simulation results show that the proposed algorithm can significantly improve the overall throughput of the system and minimize the interference, so as to achieve the optimal communication quality of the whole system. Reference | Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2021, 39 (3): 0-0.   Abstract （1500）      PDF（pc） （80KB）（203）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2021, 39 (3): 1-0.   Abstract （1498）      PDF（pc） （26KB）（56）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Emotion Classification Based on EEG Deep Learning HAO Yan, SHI Huiyu, HUO Shoujun, HAN Dan, CAO Rui Journal of Applied Sciences    2021, 39 (3): 347-346.   DOI: 10.3969/j.issn.0255-8297.2021.03.001 Abstract （2072）      PDF（pc） （2087KB）（365）       Knowledge map    Save Electroencephalograph (EEG) research of emotion, as an important task in the advanced stage of artificial intelligence, has received more and more attention in recent years. Emotional EEG classification is widely used in human-computer interaction, medical research and other fields. This study presents the design of an EEG classification system on a lightweight convolutional neural network (CNN). DEAP (dataset for emotion analysis using physiological signals) provides EEG data of two kinds of emotion: arousal and valence. In order to obtain frequency domain information, the power spectral density features of theta, alpha, beta and gamma bands are extracted for evaluation, and each power spectral density matrix is expressed as a two-dimensional gray-scale image. The images were input into the convolutional neural network to train the classification model and complete the task of two classification. Experimental results show that compared with traditional machine learning, CNN has better classification effect. The accuracy of the two classification is 82.33% (Arousal) and 75.46% (Valence) respectively. Reference | Related Articles | Metrics | Comments（0）

Select

Fully Expression Frame Localization and Recognition Based on Dynamic Face Image Sequences SIMA Yi, YI Jizheng, CHEN Aibin, ZHOU Mengna Journal of Applied Sciences    2021, 39 (3): 357-356.   DOI: 10.3969/j.issn.0255-8297.2021.03.002 Abstract （1796）      PDF（pc） （1528KB）（89）       Knowledge map    Save Considering that the evolution of facial expressions is a continuous process, compared to static images, dynamic image sequences are more suitable as the research objects for facial expression recognition. This paper proposes a sequence frame positioning model based on embedding network. The pre-trained Inception ResNet v1 network extracts the feature vectors of each frame, and then calculates the Euclidean distance between the feature vectors to position the complete frame with the maximum expression intensity, so a standardized facial expression sequences are obtained. In order to further verify the accuracy of the positioning model, we adopt VGG16 network and ResNet50 network to perform facial expression recognition on the positioned complete frame, respectively. Experiments were conducted on the CK+ and MMI facial expression databases. The average accuracy of the sequential frame positioning model proposed in this paper reached 98.31% and 98.08%, respectively. As using the VGG16 network and ResNet50 network to perform expression recognition on the positioned complete frame, the recognition accuracies on the two databases reached 96.32% and 96.5%, 87.23% and 87.88%, respectively. These experimental results show that the proposed model can pick up the complete frame from the facial expression sequence accurately and achieve better performance on facial expression recognition as well. Reference | Related Articles | Metrics | Comments（0）

Select

Seismic Fault Identification Method Based on ResUNet and Dense CRF Model DU Chengze, DUAN Youxiang, SUN Qifeng Journal of Applied Sciences    2021, 39 (3): 367-366.   DOI: 10.3969/j.issn.0255-8297.2021.03.003 Abstract （1758）      PDF（pc） （11549KB）（116）       Knowledge map    Save Aiming at the problems of time-consuming, low efficiency, and high subjective influence in artificial interpretation of seismic data, a crack identification method based on ResUNet and dense conditional random field (Dense CRF) model is proposed. First, the method uses the ResUNet model to extract the features of different resolution levels from the cracks in the seismic amplitude data volume to achieve seismic crack identification, then it uses the Dense CRF model to further optimize the recognition results, so as to achieve accurate recognition of seismic cracks. The proposed method is compared with the traditional UNet and ResUNet methods based on the synthetic seismic amplitude data volume and the seismic amplitude volume data of the F3 work area. Experimental results show that the proposed method performs higher accuracy, finer size and better continuity in crack identification. Reference | Related Articles | Metrics | Comments（0）

• page
• Page 1 of 3
• Total 93 records
• First page
• Prev page
• Next page
• Last page