Table of Content

30 May 2023, Volume 41 Issue 3

Previous Issue   

Business Process Management

Energy-Aware Resource Scheduling Method for Edge-Cloud Collaborative Computing

YANG Jun, ZHU Yingwen

2023, 41(3):  369-377.  doi:10.3969/j.issn.0255-8297.2023.03.001

Asbtract ( 734 )   PDF (1627KB) ( 186 )  

References | Related Articles | Metrics

An energy-aware resource scheduling method for edge-cloud collaborative computing is proposed to address the issues of degraded real-time execution performance and high energy consumption when processing computationally complex tasks in edge computing. First, tasks are assigned to cloud computing and edge computing according to the real-time guaranteed rate. Then, an energy-aware resource scheduling strategy is proposed based on elastic resource characteristics to generate virtual resource configuration schemes for real-time tasks. Finally, simulation results verify the effectiveness of the proposed algorithm, which reduces energy consumption while ensuring real-time performance.

Fault Analysis and Retrieval of Message Based on Knowledge Graph

JI Wenlu, DENG Xing, ZHU Hongqin, ZHAO Yang, JIANG Jielin

2023, 41(3):  378-390.  doi:10.3969/j.issn.0255-8297.2023.03.002

Asbtract ( 777 )   PDF (1490KB) ( 198 )  

References | Related Articles | Metrics

Aiming at the problems of complex fault analysis mode and increasing difficulty of fault removal caused by the expansion of the power grid, a fault analysis and retrieval of message based on knowledge graph is proposed. Firstly, the construction of power dispatching fault knowledge graph is completed by combining natural language processing technology with expert documents. Then the expert knowledge is stored in the graph in the form of atomic rules (indivisible rules) to achieve intelligent fault analysis and retrieval and assist maintenance personnel in decision-making, thereby improving the efficiency of business process. Finally, combined with the knowledge graph and log information, artificial intelligence is used to analyze the cause of failure, and the optimal solution is obtained from multiple potential solutions. Experimental results on both real and synthetic data sets show that the proposed method can achieve good results on fault analysis and retrieval in power dispatching.

Computing Offloading of Multi-dependent Tasks in Smart Cities

PENG Kai, LIU Peichen, XU Xiaolong, ZHOU Xingyu

2023, 41(3):  391-404.  doi:10.3969/j.issn.0255-8297.2023.03.003

Asbtract ( 720 )   PDF (7892KB) ( 85 )  

References | Related Articles | Metrics

Aiming at the delay-sensitive multi-dependent task scheduling problem of smart cities, this paper proposes a smart city architecture empowered by edge computing and designs a computation offloading method to meet the scheduling requirements of tasks. Firstly, this paper first establishes a multi-dependent task model, as well as a latency constraint for the task and a load balancing constraint model for the smart city server. Secondly, agents that perceive dependencies between tasks are trained using deep reinforcement learning algorithms to make computational transfer decisions in real-time. Finally, a series of experiments are conducted to verify the effectiveness of this method in latency and energy consumption optimization.

Game Theory and Particle Swarm Optimization Based Task Offloading Method in Mobile-Edge Computing

LI Han, MENG Shunmei, CAI Zhicheng

2023, 41(3):  405-418.  doi:10.3969/j.issn.0255-8297.2023.03.004

Asbtract ( 774 )   PDF (1603KB) ( 116 )  

References | Related Articles | Metrics

Mobile-edge computing (MEC) is an innovative computing paradigm. Mobile devices can reduce local computation energy consumption and delay by offloading computation intensive tasks to the edge servers. In this paper, we first study the computation offloading problem for multiple mobile devices with independent task sets in the dense area of microcell base stations, where each microcell base station is equipped with a computationally limited MEC server. To reduce the task sets computation energy consumption and delay of the mobile devices as much as possible, adopting a game theoretic approach, the problem is formulated as a non-cooperative multi-mobile-device computation offloading strategy game. Through analysis, the Nash equilibrium existence and the finite improvement property of the game are proved. Then, we design a game theory based distributed computation offloading algorithm, namely GDCOA, and introduce a particle swarm optimization (PSO) based improving computation offloading policy algorithm named PSOIPA in it. GDCOA can reach an equilibrium state after a finite number of iterations. Finally, the simulation and comparison experiments corroborate that the proposed algorithm GDCOA in this paper can achieve better computation offloading performance.

Multi-swarm Particle Swarm Optimization for Task Scheduling in Supply Chain Datacenter

ZENG Lei, BAI Jinming, LIU Qi

2023, 41(3):  419-430.  doi:10.3969/j.issn.0255-8297.2023.03.005

Asbtract ( 729 )   PDF (1585KB) ( 104 )  

References | Related Articles | Metrics

In order to deal with the problems of low service efficiency brought by the increasing scale of datacenters and task demands, a load balancing multi-swarm PSO task scheduling approach is proposed. Through the improved fitness function, the maximum completion time of the task and the variance of the completion time among machines are optimized to improve the cluster’s load balance. A novel adaptive inertia weights method is designed to enhance particle search efficiency and algorithm convergence speed. Meanwhile, a new particle initialization method is adopted to improve the quality and diversity of the initial solution. Multi-swarm particle collaborative search is further used to bring the final result closer to the optimal solution. The performance of the proposed algorithm is verified and compared with others based on the public dataset of Alibaba datacenter. The experimental results show that the method can improve task scheduling efficiency of datacenters in diversified supply chain environments.

Improved Hashed Timelock Contract Based on Miners

ZUO Yuxuan, QIANG Zhenping, DAI Fei, SU Shiqi, LIANG Zhihong

2023, 41(3):  431-447.  doi:10.3969/j.issn.0255-8297.2023.03.006

Asbtract ( 704 )   PDF (900KB) ( 63 )  

References | Related Articles | Metrics

To overcome the challenging problem of the inability of hashed timelock contract to realize cross-chain asset transfers, an improved cross-chain protocol based on miners is proposed. The protocol incorporates elliptic curve cryptography during the atomic swap process, enabling miners to generate and lock transactions on the target chain, thereby completing cross-chain asset transfers. Additionally, a competitive selection algorithm and a reward-punishment algorithm for miner nodes are integrated into the protocol to implement a new proof-of-coin-trust consensus mechanism. Finally, the protocol’s smart contracts and their functional capabilities are described in detail. Simulation results based on Ethereum show that cross-chain asset transfer is safely completed, and honest miners are motivated to actively participate in cross-chain transactions.

Signal and Information Processing

Building Change Detection in Remote Sensing Images Based on Semantic Segmentation

YIN Meijie, NI Cui, WANG Peng, ZHANG Guangyuan

2023, 41(3):  448-460.  doi:10.3969/j.issn.0255-8297.2023.03.007

Asbtract ( 880 )   PDF (6613KB) ( 261 )  

References | Related Articles | Metrics

Remote sensing image change detection is to use multi-temporal images to determine the changes of objects or phenomena within a certain period of time, and to provide qualitative and quantitative information on spatial changes of objects. Traditional remote sensing image change detection methods are mainly based on ground texture and spatial features, which is difficult to accurately identify new buildings in remote sensing images. Therefore, this paper adopts a building change detection method based on UNet network. Firstly, the lightweight efficient channel attention network (ECANet) is injected into the original UNet network model to adjust and optimize the network structure and improve the accuracy of image segmentation. The parameters of SENet are then tuned to enhance the accuracy of building change detection in remote sensing images. Experiments on a high-resolution dataset LIVER-CD show that the accuracy of the proposed method reaches a semantic segmentation accuracy of 99.03% and a building change detection accuracy of 98.62%. Compared with other methods, the proposed method can effectively enhance the effective features of images and improve the detection accuracy of ground buildings in remote sensing images.

Human Action Sequence Prediction of 3D Point Cloud Representation

WANG Hui, DING Boxu

2023, 41(3):  461-475.  doi:10.3969/j.issn.0255-8297.2023.03.008

Asbtract ( 708 )   PDF (9984KB) ( 106 )  

References | Related Articles | Metrics

Few works on action prediction of 3D human have been reported, and most of them represent human model with triangular mesh, which is not as simple and obtainable as 3D point clouds. Therefore, this paper proposes a point cloud action sequence prediction method based on MeteorNet by using 3D point clouds to represent human model. In an action sequence, the 3D point clouds at different times are fused together for finding spatiotemporal neighborhoods of the point clouds and grouping them; Three-layer Meteor modules are superimposed in the spatiotemporal neighborhoods for aggregating information and obtaining spatiotemporal features of the point cloud sequence; thus, the point cloud coordinates of action are predicted by a three-layer fully connected network. Experimental results show that the human actions predicted by the proposed method have lower errors with real actions.

Low-Light Image Enhancement Based on DBAFFNet

LUO Fan, XIONG Bangshu, YU Lei, WANG Wanling

2023, 41(3):  476-487.  doi:10.3969/j.issn.0255-8297.2023.03.009

Asbtract ( 678 )   PDF (38794KB) ( 40 )  

References | Related Articles | Metrics

To solve the problems of color cast, detail loss and noise amplification after lowlight image enhancement, an improved low-light image enhancement method is proposed based on dual-branch adaptive feature fusion network (DBAFFNet). Firstly, the adaptive feature fusion (AFF) module is designed to fuse more details and color information into deep features. Secondly, the channel and spatial attention (CASA) module is established to focus on the restoration of image details and color. Finally, a Poisson-Retinex loss function based on Retinex theory is designed to suppress noise of the image, thereby improving the enhancement effect of images. The results of subjective and objective comparisons on multiple datasets demonstrate that the proposed method not only restores the color and details of the enhanced image, but also suppress the noise better, and achievea good enhancement effect.

Computer Science and Applications

Federated Logistic Regression Scorecard System under Trusted Execution Environment

SHI Wenze, LU Lin, QIN Wenjie, YU Tao

2023, 41(3):  488-499.  doi:10.3969/j.issn.0255-8297.2023.03.010

Asbtract ( 685 )   PDF (940KB) ( 87 )  

References | Related Articles | Metrics

A federated logistic regression system under trusted execution environment is proposed to build a scorecard model while ensuring data privacy. This system uses the strong security of trusted execution environment to resist inference attacks in the process of parameter exchanging. Then, a joint normalization method and an improved federated average method are utilized to solve the problem of inconsistency of local data scale and improve the effectiveness of scorecard model under class imbalance condition, respectively. Test results on a public credit-overdue data set show that the improved federated average is more effective than typical federated average method in handling the problem of imbalanced class distribution. Compared with homomorphic encryption-based federated learning systems, the proposed federated logistic regression system performs a greatly improved execution efficiency.

Multi-dimensional Forecasting Method for Development Trend of Beidou Satellite Navigation Industry

LIU Zhanjie, SUN Yixin, YUAN Jiaqi, LIU Zhe, TANG Xuehua, ZHANG Yongsheng, GAO Mingzhe

2023, 41(3):  500-514.  doi:10.3969/j.issn.0255-8297.2023.03.011

Asbtract ( 665 )   PDF (704KB) ( 152 )  

References | Related Articles | Metrics

Aiming at the forecasting demands for different dimensions of market output value during the development of Beidou market, an output value forecasting model for Beidou market is constructed from three different dimensions, including overall output value, industry chain, and market value of listed companies. This paper studies and compares the output value prediction methods and accuracy of different forecasting models from the perspective of the overall market output forecasting demand, and obtains model selection references under different conditions. Then, based on the output value data of the industrial chain, different economic forecasting models are used to make statistical prediction of a single industrial chain or the overall output value. Finally, we track and forecast the market output value of specific listed companies and the overall Beidou market in different dimensions and levels. Finally, the accuracy and feasibility of different models and methods are analyzed through experimental verification, and the applicable methods are investigated under different data bases and forecast demands. Data and decision support are provided for Beidou market output value forecast in different dimensions.

Book Resource Sharing System of Inter-university Alliance Based on Blockchain

WANG Feng, LIU Linlin, LIU Yang, BAI Hao, ZHANG Qiang

2023, 41(3):  515-526.  doi:10.3969/j.issn.0255-8297.2023.03.012

Asbtract ( 687 )   PDF (1017KB) ( 75 )  

References | Related Articles | Metrics

Aiming at the problems of isolated information island, overlapping construction and low resource utilization in the resource sharing construction of university library, this paper proposes to build an inter-university alliance book resource sharing system based on blockchain. Flexible book leasing strategies of multiple parties are customized through smart contract, and seamlessly connect with the campus library management system through API interface, which enables the automation and traceability of the leasing process on the chain, and periodically completes the lease liquidation. The proposed system uses the trust building advantage of blockchain to improve the sharing mode between university libraries, enhance the marginal effect of book resource utilization, and effectively stimulate the endogenous power of university book sharing.

Text Detection Model Based on Mask Region Convolution Neural Network

ZHAO Xiaowei, JI Minghui, XU Xiujuan, SHEN Jiale

2023, 41(3):  527-540.  doi:10.3969/j.issn.0255-8297.2023.03.013

Asbtract ( 681 )   PDF (8568KB) ( 87 )  

References | Related Articles | Metrics

This paper proposes a text detection model based on mask region convolution neural network (Mask R-CNN). Firstly, the model optimizes the bottleneck structure of residual networks from the perspective of expanding the receptive field of the model and maintaining the efficiency of the model as much as possible, and proposes a residual network based on structural optimization (ResNetSO). Then for removing redundant features and improving the quality of fused features, the model generates a feature pyramid network based on lower feature guidance (FPNetLFG) by applying spatial attention mechanism to feature pyramid network. Finally, experimental results on two data sets show that as applying the proposed model, which consists of ResNetSO and FPNetLFG modules, in cascade region convolution neural network (Cascade R-CNN) and detecting objects with recursive feature pyramid and switchable atrous convolution (DetectoRS), F1 value can be improved by 0.8% and 0.3%, respectively, which verifies the effectiveness and universal applicability of this method.