Volume 46,Issue 7,2023 Table of Contents

1 A DDoS attack detection method based on conditional entropy and decision tree in SDN

FU You , ZOU Dongsheng

2023, 46(7):1-8. DOI: 10.11835/j.issn.1000.582X.2023.07.001

[Abstract](230) [HTML](49) [PDF 1.10 M](528)

Abstract:
Software defined network (SDN), as a novel network architecture, introduces significant flexibility through the ideas including separation between forwarding and controlling and centralized control. It also facilitates the global awareness of the network status. Distributed denial of service (DDoS) is a typical attack method. This paper focuses on the problem DDoS attack detection in SDN and proposes a DDoS attack detection method based on conditional entropy and decision tree. The proposed method used conditional entropy to evaluate the current network status. It analyzed the characteristics of DDoS attacks in SDN and extracted six key features for traffic detection. The C4.5 decision tree algorithm was utilized to classify network traffic and achieved DDoS attack detection in SDN. Experimental results show that the method presented in this paper exhibits superior detection precision and recall to other research methods. Additionally, it can significantly reduce the detection time.

2 Efficient and trusted query index model and method for blockchain data based on Merkle Patricia tree

YUAN Xu , HUANG Lihuang , CHEN Zhikui , YU Shuo

2023, 46(7):9-22. DOI: 10.11835/j.issn.1000-582X.2023.07.002

[Abstract](358) [HTML](60) [PDF 2.10 M](614)

Abstract:
Blockchain technology has attracted significantly attention in the field of distributed data management because of its decentralized and immutable nature. However, current blockchain systems face limitations in data query processing including single query function, low query efficiency and difficulties in ensuring query credibility. To address these challenges, in this paper, a global index structure called KMPT is proposed, inspired by the design concept of Ethereum Merkle Patricia tree on the premise of ensuring the immutability of index. The KMPT structure aims to realize the function of locating the target block at one time, avoiding the retrieval process of traversing blocks. Furthermore, by incorporating the intra-block index TMPT, the proposed approach enables high-efficiency content-based blockchain data retrieval. Experiments demonstrate that, compared with the method of only building intra block index, the proposed index model significantly improved the efficiency and stability of query retrieval within the acceptable index construction cost. In addition, it can provide the proof of existence or non-existence of data query at the same time, enhancing the credibility of query results.

3 A membrane evolutionary algorithm for solving graph coloring problem

GUO Ping , GUO Bin

2023, 46(7):23-35. DOI: 10.11835/j.issn.1000-582X.2022.208

[Abstract](296) [HTML](52) [PDF 1.47 M](587)

Abstract:
The graph coloring problem is one of the popular NP-hard problems in graph theory. Various heuristic algorithms have been proposed to solve this problems; however, they often suffer from poor quality and long computation time. In recent years, the membrane evolutionary algorithm has shown unique advantages in dealing with NP-hard problems. Based on the membrane evolutionary algorithm framework, this study proposed a membrane evolutionary algorithm to solve the graph coloring problem. Six membrane evolutionary operators, namely, copy, fusion, division, cytolysis, fusion-division, and tabucol were designed to facilitate the evolution of the membranes and membrane structures, leading to the discovery of more optimal solutions. Experiments were conducted on 40 challenging datasets from DIMACS, and the results were compared with three latest algorithms. The resalts show the proposed algorithm effectively reduces the computation time while maintaining the solution quality, outperforming the other algorithms in 58% of the instances.

4 Identification of Hammerstein systems using decomposition based finite-data-window recursive least squares method with a forgetting factor

ZHANG Yangming , SU Hao , LIU Jawei

2023, 46(7):36-43. DOI: 10.11835/j.issn.1000-582X.2023.07.004

[Abstract](218) [HTML](41) [PDF 864.58 K](418)

Abstract:
In this paper, a decomposition based recursive finite-data-window least squares identification method with a forgetting factor is proposed for Hammerstein systems. The proposed method aims to identify the parameters of Hammerstein systems by decomposing them into two subsystems, one involving linear subsystem parameters, and the other containing the nonlinear subsystem parameters. To achieve this, a two-step finite-data-window recursive least squares method with a forgetting factor is developed. To verify the effectiveness and merits of the proposed algorithm, a simulation example is provided, demonstrating that the proposed algorithm can quickly track parameters and accurately and effectively identify Hammerstein systems.

5 Research on LTE-R handover algorithm based on improved grey-Markov model

WANG Ruifeng , FAN Wenjing

2023, 46(7):44-52. DOI: 10.11835/j.issn.1000.582X.2023.07.005

[Abstract](206) [HTML](42) [PDF 1.46 M](622)

Abstract:
During the handover process of high-speed trains, the reference signal receiving power (RSRP) experiences fluctuations caused by path loss and terrain, leading to issues with the traditional A3 event-based handover decision method, such as ping-pong occurrences and a decrease in handover success rate. To address this problem, a handover algorithm based on an improved gray-Markov model is proposed. This algorithm processes and predicts the received power of the reference signal using an enhanced grey-Markov model. The handover process then utilizes the prediction results as the basis for the handover decision based on the preloading method. Simulation results demonstrate that the improved handover algorithm significantly reduces the fluctuation of RSRP values received by the train, lowers the probability of ping-pong handovers, and effectively improves the handover success rate.

6 A duplicate bug report detection model with enhanced text relevance semantics and multi-feature extraction

ZHOU Wenjie , XIE Qi , CUI Mengtian

2023, 46(7):53-62. DOI: 10.11835/j.issn.1000-582X.2021.213

[Abstract](275) [HTML](45) [PDF 979.18 K](476)

Abstract:
A duplicate bug report detection model with enhanced text relevance semantics and multi-feature extraction was proposed to address the issues of semantic long-distance dependence and the singleness of bug report features in the current research on duplicate bug report detection. The model introduced the self-attention mechanism to capture the semantic relevance within the bug report text sequence. This mechanism calculates the contextual semantic vector dynamically for semantic analysis and resolves the problem of long-distance dependence. Additionally, the model employed the latent Dirichlet allocation algorithm to capture the topic characteristics of the bug report text. Furthermore, a feature extraction network was constructed to calculate category difference features, providing category information for the bug report simultaneously. Finally, comprehensive detection was performed based on three types of feature vectors. The experimental results demonstrate that the model achieves improved detection performance.

7 A data-driven dynamic time series classification algorithm

ZHAO Shuxu , ZHANG Jiazhen , WANG Xiaolong , ZHANG Zhanping

2023, 46(7):63-74. DOI: 10.11835/j.issn.1000-582X.2023.07.007

[Abstract](233) [HTML](73) [PDF 3.35 M](564)

Abstract:
Aiming at the problems of data redundancy and difficulty in capturing dynamic information in IoT time series data, this paper proposes a data-driven dynamic time series classification algorithm. The dynamic information in the time series collected by sensing devices is extracted by DiPCA (dynamic internal principal component analysis) to realize the role of dimensionality reduction and refining dynamic information; the parameters of the classification algorithm are optimized by using the sparrow search algorithm to enhance the performance of the SVM algorithm and make it model the temporal features containing shapelet local features, which finally constitutes a two-way evolutionary algorithm framework to realize the temporal classification function. The performance of the algorithm is examined using UCR temporal data set and edge computing simulation data, and the results show that the comprehensive performance of the algorithm is significantly improved compared with the basic algorithm, and the effectiveness and superiority of the classification function of the algorithm in the simulation environment is verified.

8 An intelligent diagnosis method of switch machine based on deep belief network

SI Yongbo , ZHANG Guorui , CHEN Guangwu , WEI Zongshou

2023, 46(7):75-85. DOI: 10.11835/j.issn.1000-582X.2023.07.008

[Abstract](274) [HTML](59) [PDF 1.62 M](586)

Abstract:
The traditional fault diagnosis method often relies on the complex signal processing procedures and experts’ rich experience. It requires precise signal segmentation, which is a tedious process and is not conducive to the field use. In this paper, the deep belief network (DBN) method optimized by particle swarm optimization (PSO) is used to directly extract features from the original power data, and the restricted Boltzmann machine (RBM) is employed to fit the data features layer by layer, achieving the data dimension reduction at the same time. Then, extreme learning machine (ELM) is used to classify each state, thereby improving the diagnosis speed. The results show the accuracy reaches 96%, which is a 4% improvement, and the required time is significantly reduced, when compared to support vector machine (SVM) optimized by PSO.

9 Optimization and efficiency evaluation of new train control system of headway

ZHU Aihong , HE Mingming , YUAN Xiaomei , SHU Hao

2023, 46(7):86-96. DOI: 10.11835/j.issn.1000.582X.2023.07.009

[Abstract](261) [HTML](51) [PDF 1.49 M](867)

Abstract:
In order to solve the problem of subway train capacity shortage and reduce the train headway, a method combining a new train control system, relative mobile blocking and cooperative operation is proposed. A cooperative operation model for train communication is constructed, which focuses on refining the conflict area between the front and rear trains. Additionally, the model optimizes and models the minimum headway of the mainline and the turnaround after the station. A driving strategy is also proposed to further shorten the headway. Through simulation calculations on an actual line, it is found that the train passing capacity improves by 32.3% compared with the Communication Based Train Control System. Furthermore, the 4A marshaling can achieve a headway of 79.9 s. Considering the impact of shortening the headway on operational efficiency, the operational efficiency is quantified as transportation rate, full load rate, unit energy consumption, waiting time, and different driving schemes are evaluated. The results indicate that for lines with a one-way hourly passenger flow of less than 64 000, the 4A marshaling scheme consumes less energy compared to the 6A and 8A marshaling schemes, and reduces the waiting time when the full load rate is satisfied.

10 Road image recognition for road adhesion estimation

HUANG Kaiqi , HUANG Maoyun , LIU Xiaorong

2023, 46(7):97-106. DOI: 10.11835/j.issn.1000-582X.2021.215

[Abstract](290) [HTML](122) [PDF 3.06 M](582)

Abstract:
To enhance the accuracy and real-time performance of the intelligent assisted driving system in estimating the road adhesion coefficient, a deep learning algorithm based on visual information was developed for road recognition. The algorithm aims to achieve a pre-estimation of the road adhesion coefficient. A compression convolution mechanism was designed to reduce the network’s operation parameters. Additionally, the fully connection layer was replaced by the global average of the feature map to enhance the network’s fitting performance. Furthermore, a pavement recognition depth convolutional neural network called DW-VGG was constructed. The network was trained using a self-built pavement image dataset. The test results demonstrate that the DW-VGG network, utilizing the proposed multi-layer knowledge distillation algorithm, achieves a high recognition accuracy, with a classification performance evaluation index (F₁ score) of 96.57%. Moreover, it effectively reduces the network’s time and space costs, as it only takes 32.06 ms to identify a single image, and the prediction model size is merely 5.63 M.

11 Wavelength selection of visible light communication in atmospheric channel at sea

ZHANG Xu , LIU Hongbo , CHEN Kewei

2023, 46(7):107-112. DOI: 10.11835/j.issn.1000-582X.2023.07.011

[Abstract](201) [HTML](44) [PDF 1.10 M](506)

Abstract:
In order to address the issue of wavelength selection in offshore visible light communication, this study analyzed the background light model and atmospheric turbulence channel model that impacted marine visible light communication. The key factors that influenced the quality of visible light communication were identified. Simulations of the visible light communication system under three different conditions were also conducted. These simulations provided insights into the correlation between the light source wavelength and the bit error rate. Specifically, the correlation was examined under varying communication distances, refractive index structure parameters, and field angles. The obtained results serve as a foundation for selecting the appropriate light source wavelength in offshore visible light communication.

12 Multi-UAV identity recognition method based on signal coil

GONG Wenlan , CHEN Shaonan , XIAO Jing , WU Xiaorui , WU Ning

2023, 46(7):113-120. DOI: 10.11835/j.issn.1000-582X.2023.07.012

[Abstract](298) [HTML](70) [PDF 2.87 M](488)

Abstract:
Wireless power transfer technology has freed itself from the constraints of physical media and has advantages such as flexibility, reliability and security, making it increasingly widely used in the field of unmanned aerial vehicles (UAVs). However, the commonly used wide area communication methods in UAV wireless charging systems, such as Zigee, bluetooth, and WiFi, present challenges in terms of lengthy access time, non point-to-point transmission and limited identity recognition capabilities. These limitations make it difficult to cope with multiple UAVs and cabin environments effectively. In this paper, a multi-UAV identification method based on signal coils is proposed. This study involves simulating and examining the cross-coupling effect between two sets of coupling mechanisms. Additionally, a wireless power transfer system is designed to enable synchronous transmission of power and signal in multi-UAV and cabin environments. Finally, an experimental UAV wireless power transfer system is constructed for verification. The experimental results show that UAVs and cabin can be quickly and effectively identified based on signal coils. The point-to-point near-field communication method that can identify UAVs can be used to cope with multiple UAV wireless charging scenarios. The separated channel transmission mode of power and signal synchronous transmission adopts two independent physical structures, thereby avoiding interference from traditional communication methods. This approach ensures the safety and reliability of charging processes.

Home

Volume 46,Issue 7,2023 Table of Contents

Current Issue

Volume

Issue

Most Read

Most Cited

Most Downloaded