Table of Content

30 March 2024, Volume 42 Issue 2

Previous Issue   

Communication Engineering

Sign Language Recognition Based on Two-Stream Adaptive Enhanced Spatial Temporal Graph Convolutional Network

JIN Yanliang, WU Xiaowei

2024, 42(2):  189-199.  doi:10.3969/j.issn.0255-8297.2024.02.001

Asbtract ( 39 )   PDF (1979KB) ( 50 )  

References | Related Articles | Metrics

Aiming at the issues of poor information representation ability and incomplete information during the extraction of sign language features, this paper designs a two-stream adaptive enhanced spatial temporal graph convolutional network (TAEST-GCN) for sign language recognition based on isolated words. The network uses human body, hands and face nodes as inputs to construct a two-stream structure based on human joints and bones. The connection between different parts is generated by the adaptive spatial temporal graph convolutional module, ensuring the full utilization of the position and direction information. Meanwhile, an adaptive multi-scale spatial temporal attention module is built through residual connection to further enhance the convolution ability of the network in both spatial and temporal domain. The effective features extracted from the dual stream network are weighted and fused to classify and output sign language vocabulary. Finally, experiments are carried out on the public Chinese sign language isolated word dataset, achieving accuracy rates of 95.57% and 89.62% in 100 and 500 categories of words, respectively.

UAV Path Planning and Radio Mapping Based on Deep Reinforcement Learning

WANG Xin, ZHONG Weizhi, WANG Junzhi, XIAO Lijun, ZHU Qiuming

2024, 42(2):  200-210.  doi:10.3969/j.issn.0255-8297.2024.02.002

Asbtract ( 43 )   PDF (3338KB) ( 26 )  

References | Related Articles | Metrics

To address the limitations of traditional UAV trajectory optimization design methods in building communication models, this paper presents a deep reinforcement learning-based UAV path planning and radio mapping in cellular-connected UAV communication systems. The proposed method utilizes an extended double-deep Q-network (DDQN) model combined with a radio prediction network to generate UAV trajectories and predict the reward values accumulated due to action selection. Furthermore, the method trains the DDQN model by combining actual and simulated flights based on Dyna framework, which greatly improves the learning efficiency. Simulation results show that the proposed method utilizes the learned coverage area probability map more effectively compared to the Direct-RL algorithm, enabling the UAV to avoid weak coverage areas and reducing the weighted sum of flight time and expected interruption time.

Interference and Scalability Analysis of LoRa Spread Spectrum Channel

LEI Fang, CHEN Bo, LYU Jingzhao

2024, 42(2):  211-221.  doi:10.3969/j.issn.0255-8297.2024.02.003

Asbtract ( 15 )   PDF (2049KB) ( 17 )  

References | Related Articles | Metrics

In order to improve the access capacity of LoRa communication system nodes, the interference and scalability of LoRa communication system are analyzed in detail. Firstly, this paper analyzes the interference between the same spread spectrum channel and the interference between different spread spectrum channels in LoRa, and obtains the reasons for the serious interference of the same spread spectrum channel and the certain interference of different spread spectrum channels. It is found that the closer the chip spacing between spread spectrum channels, the more serious the interference is. Secondly, an interference cancellation algorithm between different LoRa spread spectrum channels is proposed. Simulation results show that the algorithm can effectively eliminate the interference of low spread spectrum channels and is feasible. Finally, the expansibility of LoRa's original modulation and demodulation algorithm is analyzed through theory. Combined with the characteristics of LoRa technology and interference simulation results, it is concluded that the difference between the number of chips of LoRa's new spread spectrum channel and adjacent spread spectrum channel is greater than or equal to 128. The antinoise performance and feasibility of four typical new spread spectrum channels are verified by simulation, and the accessible capacity of system nodes can be increased by 36.94%.

High Time Transmission Efficiency CP-UFMC Receiving Method Based on CP Reconstruction

ZHENG Xiaokang, WEN Jiangang, ZOU Yuanping, WANG Anding, HUA Jingyu

2024, 42(2):  222-236.  doi:10.3969/j.issn.0255-8297.2024.02.004

Asbtract ( 18 )   PDF (819KB) ( 25 )  

References | Related Articles | Metrics

In this paper, to address the impact of CP deficiency, a cyclic prefix-universal filtered multi-carrier (CP-UFMC) receiving method based on CP reconstruction is proposed to enhance the transmission efficiency and improve the system performance. The performance of selective reconstruction method is further investigated. Then the symbol error rate (SER) performance of the system is simulated with varying CP lengths, carrier frequency offsets and quadrature amplitude modulation orders. Simulation results show that the proposed CP-UFMC receiving method can mitigate the SER deterioration caused by CP deficiency. It effectively brings the system SER closer to the levels achieved when CP is sufficient, outperforming other universal filtered multi-carrier receiving methods.

Multi-point Tapered Fiber Flexible Curvaturer Sensor Based on Fiber Grating

WU Kai, GONG Huaping, NI Kai, MAO Bangning, ZHAO Chunliu

2024, 42(2):  237-247.  doi:10.3969/j.issn.0255-8297.2024.02.005

Asbtract ( 22 )   PDF (4062KB) ( 22 )  

References | Related Articles | Metrics

Aiming at the shortcomings of the complicated manufacturing process and the high cost of the existing curvature sensors, a flexible curvature sensor based on fiber grating is proposed. Using the wavelength division multiplexing characteristics of fiber Bragg grating (FBG), it is cascaded with multiple taper fiber curvature sensors to realize the flexible curvature of multi-point taper fiber. This enables simultaneous sensing of the curvature information at multiple points. Experimental results show that the film-like PDMS has good flexibility, allowing synchronous bending of the tapered fiber and the PDMS film. The bending sensitivity is about 0.593 48~0.606 96 dB/m^-1. The flexible curvature sensing of multi-point taper fiber based on FBG exhibits strong anti-crosstalk ability and can sense the curvature information of multiple points at the same time. Further, the flexible sensor is used to monitor human activity at the throat and wrist. Experimental results show that the sensor can not only detect small muscle changes in the human body but also capture larger movements, which suggests promising prospects for development.

Optimal Design and Sensitivity Analysis of Double-Diaphragm Structure FBG Soil Pressure Sensors

XING Guangzhi, CHEN Bozhi, WU Wenjing

2024, 42(2):  248-261.  doi:10.3969/j.issn.0255-8297.2024.02.006

Asbtract ( 18 )   PDF (3541KB) ( 20 )  

References | Related Articles | Metrics

In order to realize the health monitoring and effective evaluation of the pile foundation structure safety and its service state, a double-diaphragm structure soil pressure sensor is proposed in this paper. Fiber Bragg gratings (FBGs) are used as the sensing element. By adding a temperature compensation film in the protective structure, complete separation of temperature effects and external load impacts is achieved. Based on the working principle of a double-diaphragm structure soil pressure sensor, the pressure sensitivity coefficient characteristics of the sensor are discussed. A systematic analysis is conducted on the influencing parameters of sensitivity coefficient by combining finite element analysis and experimental research. Numerical analysis results show that the thickness of the membrane has the greatest impact on the pressure sensitivity coefficient. The structural radius and membrane thickness can be set as 20 mm and 1.8 mm, respectively. Experimental results show that within the range of 0~2 MPa, the pressure sensitivity coefficient reaches 3.32 pm/kPa.

High-Precision Liquid Level Sensor Based on Microwave Principle

CUI Zhigang, LIU Jincheng, LU Enlong, ZHAO Xuxin, ZHANG Qi

2024, 42(2):  262-268.  doi:10.3969/j.issn.0255-8297.2024.02.007

Asbtract ( 20 )   PDF (1082KB) ( 19 )  

References | Related Articles | Metrics

In this paper, a high-precision liquid level microwave sensor assisted with energy dissipation control is proposed and demonstrated. The sensor achieves a micrometer-level resolution within a measurement range of 0~50 mm. Built on microwave resonators, the sensor comprises an inner conductor, an outer conductor, a resonant cavity, and a resistor. The resonant cavity is constructed of two reflection surfaces, where the first is a fixed point located inside the sensor, and the second is the measured liquid level. When the liquid level changes, the second reflection point changes accordingly, introducing cavity length shift. The liquid level change can be determined by measuring the variation of the resonant cavity shift. Meanwhile, the added resistance not only extends the liquid level measurement range, but also improves the spectral quality and measurement accuracy. Experimental results show that the liquid level sensor reaches micron resolution and a sensitivity of -1.927 2 mm/mm (resonant wavelength change/liquid level) in the range of 0~50 mm. Due to its mechanical robustness, easy fabrication process, low cost and high measuring resolution, the proposed sensor can be applied in fields such as water conservancy and hydropower weir monitoring.

Signal and Information Processing

A Large FOV Convergence Binocular Stereo Vision Calibration Method

CUI Shuaihua, YU Lei, HE Xi, XIONG Bangshu, OU Qiaofeng

2024, 42(2):  269-279.  doi:10.3969/j.issn.0255-8297.2024.02.008

Asbtract ( 26 )   PDF (1750KB) ( 16 )  

References | Related Articles | Metrics

The convergent placement of binocular cameras can lead to defocus blur and perspective deformation of the marked points, introducing positioning deviations and calibration errors, especially problematic in large field of view (FOV) environments and consequently affecting measurement accuracy. To address this problem, a large FOV convergence binocular stereo vision calibration method based on the weighting of mark points positioning deviation degree is proposed. Firstly, the defocus blur and perspective deformation of the mark points are calculated by using the position of the target in the camera coordinate system. Secondly, the corresponding weight is set according to the positioning deviation degree of mark points. Finally, the mark points weight coefficients are added to the objective function to guide the optimization of calibration parameters. Experimental results show that the root-mean-square error and standard deviation of distance measurement can reach 0.809 and 0.290, respectively, when the observation value is 505 mm. This method not only effectively improves the calibration accuracy of large field convergence binocular stereo vision, but also exhibits good stability.

CT Based Non-human Tissue 3D Reconstruction

DONG Jingxian, MA Jingwen, CAI Hongsen, LI Xin, DENG Xianbo, HOU Wenguang

2024, 42(2):  280-289.  doi:10.3969/j.issn.0255-8297.2024.02.009

Asbtract ( 18 )   PDF (7333KB) ( 17 )  

References | Related Articles | Metrics

In scenarios involving hollowed-out structures, occlusions and narrow spaces, the scanning process tend to be lengthy. Moreover, substantial manual interaction is often required for mesh generation, and the effect of 3D surface rendering is not always ideal. This paper attempts to perform 3D scanning for various handicrafts made of porcelain, pottery, wood and bronze based on medical CT. Contour points on each image are extracted to obtain 3D point cloud, subsequently facilitating surface rendering through meshing. Meanwhile, 3D display is directly conducted based on a volume rendering algorithm. The results indicate the superiority of volume rendering over surface rendering, as it reveals more detailed information and involves fewer manual operations. Quantitative accuracy evaluation demonstrates the feasibility and efficiency of CT-based non-human tissue 3D reconstruction.

Gamma Correction Parameter Estimation Via Histogram Gap Feature

WANG Wenjuan, YAO Heng

2024, 42(2):  290-301.  doi:10.3969/j.issn.0255-8297.2024.02.010

Asbtract ( 19 )   PDF (1515KB) ( 15 )  

References | Related Articles | Metrics

This paper first analyzes the empty-bin distribution characteristics of the histogram of the gamma-corrected image and the gap feature of the histogram after the inverse gamma transformation on the gramma-corrected image. Subsequently, this gap feature from the inverse transform histogram is applied to estimate the tampered image parameters. Specifically, we first determine whether the image has undergone gamma correction by comparing the number of zero values at both ends of the histogram. Then we estimate the parameters accurately by the inverse-transformed histogram gap feature. Experimental results show that the proposed method outperforms the existing methods in terms of parameter estimation accuracy and demonstrating robustness on JPEG images with different quality factors before the transformation.

Three-Dimensional Measurement of Fringe-Gray Linear Projection Based on Hilbert Transform

ZHAI Yayu, WANG Meihui, YANG Cheng, LU Jing, LI You

2024, 42(2):  302-313.  doi:10.3969/j.issn.0255-8297.2024.02.011

Asbtract ( 22 )   PDF (9284KB) ( 21 )  

References | Related Articles | Metrics

To address the problems of large number of projected images and high complexity in the traditional fringe projection measurement, this paper proposes a fringe-gray linear projection strategy and phase solution method based on Hilbert transform. The proposed method simplifies the measurement process by using only three projection images:one high-frequency fringe image and two grayscale linear change maps. The wrapping phase is obtained by the Hilbert transform, and the basic phase is obtained by using the grayscale linear change image. By combining the wrapping phase and the basic phase, the absolute phase, which represents the fringe progression, can be obtained. The 3D reconstruction results obtained by the constructed active binocular system shows that the proposed method can effectively restore the 3D shape of the measured object, with a measurement accuracy of 0.1 mm.

Real-Time Measurement for Tip Clearance of Twin-Rotor Helicopter under Complex Background and Illumination

ZENG Leping, XIONG Bangshu, YI Hui, OU Qiaofeng, YU Lei

2024, 42(2):  314-322.  doi:10.3969/j.issn.0255-8297.2024.02.012

Asbtract ( 24 )   PDF (12640KB) ( 7 )  

References | Related Articles | Metrics

In order to address the limitations of existing tip clearance measurement methods in complex outdoor environments, this paper proposes a real-time measurement method based on deep learning networks. The method utilizes the YOLOv3-tiny network to locate the rotor tip area in collected rotor tip images. The OTSU algorithm is then applied to segment the rotor tip from the background, and the rotor tip contour is extracted to locate the pneumatic center points of the upper and lower rotor tips. The rotor tip clearance is calculated based on the located center points. Experimental results conducted in both simulated and real environments demonstrate the high accuracy of the proposed method. The maximum error in tip clearance measurement is 1.99 mm when the camera is positioned 20 meters away from the tip. The proposed method has been successfully applied in real experiments involving tip clearance measurements under various complex background and illumination conditions, where the method exhibits strong adaptability and fast processing speed with a frame rate of 50 fps.

Computer Science and Applications

Automatic Event Semantic Division Based on Instance Distribution Constraints

GAO Jianqi, LUO Xiangfeng, PEI Xinmiao

2024, 42(2):  323-333.  doi:10.3969/j.issn.0255-8297.2024.02.013

Asbtract ( 19 )   PDF (656KB) ( 8 )  

References | Related Articles | Metrics

This paper proposes an automatic event semantic division algorithm based on instance distribution constraints to address the difficulty in aggregating event semantics that are discretely distributed in news text collections. First, the distant supervision method is used to construct training dataset for event semantic division. Second, a semantic classifier based on instance constraints is designed to determine whether the addition of new event trigger affects the aggregation of event semantics. Finally, an event semantic set generation algorithm is designed based on the classifier, which can automatically divide the discrete event triggers into different event semantic sets without the need for pre-setting event types. Experimental results show that the proposed method can effectively classify event semantics, and offer a new approach for achieving high-quality aggregation of event semantics.

Network Security Situation Assessment Based on Improved SKNet-SVM

ZHAO Dongmei, SUN Mingwei, SU Mengyue, WU Yaxing

2024, 42(2):  334-349.  doi:10.3969/j.issn.0255-8297.2024.02.014

Asbtract ( 25 )   PDF (1949KB) ( 17 )  

References | Related Articles | Metrics

In order to improve the accuracy, stability, and robustness of network security situation assessment, a network security situation assessment model based on improved selective kernel convolutional neural network and support vector machine is proposed. Firstly,the traditional kernel for feature extraction is replaced with the improved selective kernel to enhance the adaptability of the convolutional neural network to changes in receptive field,thereby strengthening the correlation between features. Then, the extracted features are fed into the support vector machine for classification, and the grid optimization algorithm is used to optimize the parameters in the support vector machine globally. Finally, the network security situation value is calculated according to the network attack impact index.Experimental results show that the situation assessment model based on improved selective kernel convolutional neural network and support vector machine achieves higher accuracy,stronger stability and robustness compared to traditional convolutional neural networks.

Intuition Fuzzy and Structural Least Squares Twin Support Vector Machine

ZHANG Faying, LYU Li, HAN Longzhe, LIU Dongxiao, FAN Tanghuai

2024, 42(2):  350-363.  doi:10.3969/j.issn.0255-8297.2024.02.015

Asbtract ( 21 )   PDF (1179KB) ( 9 )  

References | Related Articles | Metrics

Addressing the sensitivity of the least squares twin support vector machine(LS-SVM) to noise or abnormal data, and its tendency to overlook intrinsic structural information in the data, this paper introduces an intuition fuzzy and structural least squares twin support vector machine(IF-SLSTSVM). Firstly, the input sample points undergo preprocessing using isolated forest. Subsequently, leveraging the concept of intuitionistic fuzzy, varying weights are assigned to the input sample points to mitigate the impact of noise or abnormal data on the classification hyperplane. Finally, the K-Means algorithm is employed to extract structural information, represented in the form of covariance, among the input sample points. Built upon LS-SVM, IF-SLSTSVM takes into account the distribution information of input sample points in the feature space and their interrelationships,thereby enhancing the model's robustness. Experimental validation is performed using the UCI dataset in noise environments with different proportions of 0%, 5%, 10%, and 20%. The results demonstrate that the IF-SLSTSVM algorithm exhibits superior robustness compared to six other evaluated algorithms.

Smart Contract Vulnerability Detection of Symbol Execution with Critical Path Pre-searching

WANG Zexu, WEN Bin

2024, 42(2):  364-374.  doi:10.3969/j.issn.0255-8297.2024.02.016

Asbtract ( 21 )   PDF (2151KB) ( 9 )  

References | Related Articles | Metrics

This paper proposes a pre-searching paths for symbolic execution method to guide the critical path symbol execution of scanning smart contract vulnerabilities through static detection. This approach aims to avoid unnecessary resource consumption of path search, thereby achieving accurate and fast smart contract vulnerability detection. This method is compared with existing mainstream detection tools. The results show that the Gas exhaustion denial of service vulnerability coverage reaches 98%, with a detection accuracy of 84.3%, which is far higher than the average value of 37.2%. Furthermore, the full coverage of storage coverage vulnerability contracts is realized with a detection accuracy of 86.1%, which validates the efficiency and stability of this method.