2024 Vol.42

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Journal of Applied Sciences    2024, 42 (1): 0-0.   Abstract （66）      PDF（pc） （47KB）（58）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Object Detection Based on Nonlinear Gaussian Squared Distance Loss LI Rui, LI Yi Journal of Applied Sciences    2024, 42 (1): 1-14.   DOI: 10.3969/j.issn.0255-8297.2024.01.001 Abstract （85）      PDF（pc） （7094KB）（64）       Knowledge map    Save Existing series of loss functions based on intersection over union (IoU) have certain limitations, impacting the accuracy and stability of bounding box regression in object detection. To address this problem, a bounding box regression loss based on nonlinear Gaussian squared distance is proposed. Firstly, the three factors including overlapping, center point distance and aspect ratio in the bounding box are comprehensively considered, and the bounding box is modeled as a Gaussian distribution. Then a Gaussian squared distance is proposed to measure the distance between two distributions. Finally, a nonlinear function is designed to transform the Gaussian square distance into a loss function that facilitates neural network learning. Experimental results show that compared with IoU loss, the mean average precision of the proposed method on mask region-based convolutional neural network, fully convolutional one-stage object detector and adaptive training sample selection object detector is improved by 0.3%, 1.1% and 2.3%, respectively. These results demonstrate the efficiency of the proposed method in enhancing target detection performance and supporting the regression of high-precision bounding boxes. Reference | Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2024, 42 (1): 2-0.   Abstract （30）      PDF（pc） （89KB）（23）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

An Automatic Atrial Fibrillation Detection Model Based on GAN and MS-ResNet QIN Jing, HAN Yue, WANG Liyong, JI Changqing, LIU Lu, WANG Zumin Journal of Applied Sciences    2024, 42 (1): 15-26.   DOI: 10.3969/j.issn.0255-8297.2024.01.002 Abstract （91）      PDF（pc） （3052KB）（80）       Knowledge map    Save Atrial fibrillation (AF) is a common cardiac arrhythmia. However, existing research often relies on single-scale signal segments and overlooks potential complementary information at different scales as well as data imbalance issues, leading to decreased diagnostic performance. This paper proposes a novel AF automatic detection model based on generative adversarial network (GAN) and residual multi-scale network. The model utilizes GAN to synthesize single-lead ECG data with high morphological similarity, hence addressing data privacy and imbalance issues. A multi-scale residual network (MS-ResNet) feature extraction strategy was designed to extract the features of signal segments of different sizes from various scales, so as to effectively capture the features of P wave disappearance and RR interval irregularity. The model combines these two strategies not only to generate high-quality ECG (electrocardiogram) data for the automatic AF detection but also to extract temporal features between different waves using multi-scale grids. The performance of MS-ResNet is evaluated on the PhysioNet Challenge 2017 public ECG dataset and a balanced dataset, comparing it with other existing atrial fibrillation classification models. Experimental results show that the average F1 value and accuracy rate of MS-ResNet on the balanced dataset are 0.914 1 and 91.56%, respectively. Compared with the unbalanced dataset, F1 increases by 4.5%, and the accuracy rate increases by 3.5%. Reference | Related Articles | Metrics | Comments（0）

Select

Semi-supervised Rock Slice Image Classification Based on Hierarchy Consistency Mean Teacher Model YAN Zijie, WANG Yang, CHEN Yan, ZHANG Chong Journal of Applied Sciences    2024, 42 (1): 27-38.   DOI: 10.3969/j.issn.0255-8297.2024.01.003 Abstract （82）      PDF（pc） （10754KB）（47）       Knowledge map    Save Traditional rock slice image classification relies on a large number of manually labeled image samples, which is subject to the experience and ability of the labelers. This practice limits the scalability of classification enhancement as increasing unlabeled rock slice image samples does not contribute effectively. In order to achieve effective utilization of unlabeled data information, the hierarchy consistency mean teacher (HCMT) model adds a hierarchy consistency regularization term to the unsupervised loss of the mean teacher (MT) model to constrain the hierarchical structure of the teacher-student model. Ablation experiments and comparative analyses reveal that the introduction of hierarchy consistency regularization method improves the classification performance of the MT model by using the effective information of unlabeled data. As a result, the HCMT model achieves comparable classification capability in both half-labeled and fully labeled dataset. The experiments show the potential of the semi-supervised learning model to improve the classification ability of the model by using a large number of unlabeled rock slice image data. Reference | Related Articles | Metrics | Comments（0）

Select

Quantum Attacks on Symmetric Cryptosystems FENG Xiaoning, WU Hongyu Journal of Applied Sciences    2024, 42 (1): 39-52.   DOI: 10.3969/j.issn.0255-8297.2024.01.004 Abstract （100）      PDF（pc） （682KB）（50）       Knowledge map    Save This paper undertakes an investigation of recent research trends in quantum attacks on symmetric encryption schemes, offering an analysis of the connections between mainstream attack methods and various literature sources. Mainstream attack methods are systematically categorized into three types: quantum period attacks, Grover algorithmrelated attacks, and quantum differential attacks. For each category, representative attack methods are introduced, accompanied by an elucidation of the core concepts underlying each approach. Furthermore, we contemplate future research directions within this domain, considering potential advancements in light of existing attack schemes. Reference | Related Articles | Metrics | Comments（0）

Select

Server Energy Consumption Model Based on ConvLSTM in Mobile Edge Computing LI Xiaolong, LI Xi, YANG Lingfeng, HUANG Hua Journal of Applied Sciences    2024, 42 (1): 53-66.   DOI: 10.3969/j.issn.0255-8297.2024.01.005 Abstract （75）      PDF（pc） （974KB）（50）       Knowledge map    Save To address the issue of low sensitivity and accuracy of existing energy consumption models in accommodating dynamic workload fluctuations, this paper proposes an intelligence server energy consumption model (IECM) based on the convolutional long short-term memory (ConvLSTM) neural network in mobile edge computing, which is used to predict and optimize energy consumption in servers. By collecting server runtime parameters and using the entropy method to filter and retain parameters significantly affecting server energy consumption, a deep network for training the server energy consumption model is constructed based on the selected parameters using the ConvLSTM neural network. Compared with existing energy consumption models, IECM exhibits superior adaptability to dynamic changes in server workload in CPU-intensive, I/O-intensive, memoryintensive, and mixed tasks, offering enhanced accuracy in energy consumption prediction. Reference | Related Articles | Metrics | Comments（0）

Select

Target Counting Method Based on UAV View in Large Area Scenes XIE Ting, ZHANG Shoulong, DING Laihui, XU Zhiwei, YANG Xiaogang, WANG Shengke Journal of Applied Sciences    2024, 42 (1): 67-82.   DOI: 10.3969/j.issn.0255-8297.2024.01.006 Abstract （97）      PDF（pc） （9343KB）（89）       Knowledge map    Save In recent years, unmanned aerial vehicles (UAVs) have been widely used in the field of crowd counting due to their high flexibility and maneuverability. However, most of the existing crowd counting methods are based on single viewpoints, with limited studies focusing on multi-viewpoint counting in large-scale, multi-camera scenes. To solve this problem, this paper proposes a UAV-based target counting method which can accurately count the number of targets in a given scene. Specifically, this study selects a sea-front area for data acquisition, utilizes deep learning technology for target detection and image stitching fusion on the acquired images. The detection information is then mapped onto the spliced image, and a counting algorithm is employed to fulfill the counting task for the regional scene. The effectiveness of the counting algorithm based on target detection is validated through experiments conducted on both public dataset and the dataset produced in this paper. Reference | Related Articles | Metrics | Comments（0）

Select

Research on Enhanced Routing for Reinforcement Learning in Wireless Sensor Networks ZHANG Huanan, LI Shijun, JIN Hong Journal of Applied Sciences    2024, 42 (1): 83-93.   DOI: 10.3969/j.issn.0255-8297.2024.01.007 Abstract （65）      PDF（pc） （648KB）（50）       Knowledge map    Save The classical problem of finding the optimal parent node in wireless network tree routing is discussed in this study. Various indexes affecting the decision rules of tree routing are analyzed, such as weighted average received signal strength, buffer occupation rate and power consumption ratio. A system model of enhanced tree routing protocol and reinforcement learning algorithm based on reinforcement learning is proposed in wireless sensor networks. The basic operation of the proposed tree-based routing protocol is described in detail, and the algorithm is updated for cyclic detection of parent node. In order to make adaptive decisions in complex scenarios, a state space, an action set and an excitation function are defined. The optimal parent node with the highest excitation is identified through trial and error. Through simulation and comparative study, it is verified that the parent node selection scheme achieves reasonable tradeoff among the performance indicators such as end-to-end delay, reliability and energy consumption. Through simulation and comparative analysis, the efficacy of the parent node selection scheme is validated, demonstrating a judicious tradeoff among performance indicators such as end-to-end delay, reliability, and energy consumption. Reference | Related Articles | Metrics | Comments（0）

Select

Research on Different Desensitization Data Based on Federated Ensemble Algorithm LUO Changyin, CHEN Xuebin, ZHANG Shufen, YIN Zhiqiang, SHI Yi, LI Fengjun Journal of Applied Sciences    2024, 42 (1): 94-102.   DOI: 10.3969/j.issn.0255-8297.2024.01.008 Abstract （71）      PDF（pc） （542KB）（54）       Knowledge map    Save To solve the problem that gradient updating leads to the possible leakage of local data in federated learning, federated ensemble algorithms based on local desensitization data are proposed. The algorithm desensitizes the raw data with different values of variability and fitness thresholds, employing diverse models for local training on data with different desensitization levels to ascertain parameters suitable for a federated ensemble approach. Experimental results show that the stacking federated ensemble algorithm and voting federated integration algorithm outperform the baseline accuracy achieved by the federated average algorithm with traditional centralized training. In practical applications, different desensitization parameters can be set according to different needs to protect data and improve its security. Reference | Related Articles | Metrics | Comments（0）

Select

Object Tracking Algorithm Based on Vehicle Appearance Features and Inter-frame Optical Flow LI Shaoqian, CHENG Xin, ZHOU Jingmei, ZHAO Xiangmo Journal of Applied Sciences    2024, 42 (1): 103-118.   DOI: 10.3969/j.issn.0255-8297.2024.01.009 Abstract （63）      PDF（pc） （70923KB）（36）       Knowledge map    Save In complex road scenes, frequent occlusions and similar appearances between vehicle targets, coupled with the use of static preset parameters used throughout the entire movement of the targets collectively contribute to a decline in tracking accuracy. This paper proposes an object tracking algorithm based on vehicle appearance features and inter-frame optical flow. Firstly, the position information of the vehicle target frame is obtained through the YOLOv5x network model. Secondly, the optical flow between the current frame and the previous frame is calculated using the RAFT (recurrent all-pairs field transforms for optical flow) algorithm, and the optical flow map is clipped according to the obtained position information. Finally, in the process of Kalman filtering, inter-frame optical flow is used to compensate for more accurate motion state information, while vehicle appearance features and intersection over union (IOU) features are used to complete trajectory matching. Experimental results show that the tracking algorithm correlating inter-frame optical flow performs well on the MOT16 data set. Compared with simple online and realtime tracking with a deep association metric (DeepSORT), mostly tracked trajectories (MT) has increased by 1.6%, multiple object tracking accuracy (MOTA) has increased by 1.3%, and multiple object tracking precision (MOTP) has increased by 0.6%. The accuracy of the improved vehicle appearance feature extraction model has been improved by 1.7% and 6.3% on the training and verification sets, respectively. Consequently, leveraging the high-precision vehicle appearance feature model and motion state information from the associated inter-frame optical flow enables effective vehicle target tracking in traffic scenes. Reference | Related Articles | Metrics | Comments（0）

Select

Knowledge Graph Completion Method Based on Semantic Hierarchy in Spherical Coordinates GUO Ziyi, ZHU Tong, LIN Guangyan, TAN Huobin Journal of Applied Sciences    2024, 42 (1): 119-133.   DOI: 10.3969/j.issn.0255-8297.2024.01.010 Abstract （60）      PDF（pc） （1249KB）（83）       Knowledge map    Save Most of existing knowledge graph completion methods often neglect the semantic hierarchical differences that objectively exist between entities. To address these limitations, we propose a knowledge graph completion method named spherical hierarchical knowledge completion (SpHKC), which models semantic hierarchical phenomena using spherical coordinates. In this method, entities are mapped to points on a spherical surface, and entities located on different spheres correspond to different semantic hierarchy levels. The radius of the sphere determines the level of the semantic hierarchy for entities on that sphere, with larger spheres representing lower levels. Relationships are modeled as movements from one entity on the spherical surface to another entity (on the same or different spheres), involving rotation and positioning operations to handle both similar and different semantic hierarchy levels between entities. The polar angle and azimuth angle in spherical coordinates provide entities with richer expressions. Experimental results demonstrate that SpHKC achieves comparable performance to state-of-the-art methods on the FB15k-237 and WN18RR datasets. Moreover, it consistently improves important metrics such as MRR (mean reciprocal ranking) and Hits@10 by approximately 1% compared to recent algorithms on the YAGO3-10 dataset, showcasing the effectiveness of incorporating semantic hierarchical information. Reference | Related Articles | Metrics | Comments（0）

Select

Browser Power Optimization Based on CPU-GPU Co-regulation and Web Page Feature Perception ZHANG Jin, HUANG Jiangjie, PENG Long, LIU Xiaodong, YU Jie, HUANG Haowei, WANG Wenzhu Journal of Applied Sciences    2024, 42 (1): 134-144.   DOI: 10.3969/j.issn.0255-8297.2024.01.011 Abstract （80）      PDF（pc） （755KB）（46）       Knowledge map    Save Android's inability to sense web page content during resources allocation to the browser often results in over-allocation of resources and unnecessary loss of power. At the same time, due to the growth of CPU adjustable frequency density, optimizing energy consumption through dynamic voltage and frequency scaling (DVFS) technology becomes increasingly challenging. Furthermore, the role of the graphics processing unit (GPU) in browser operation is ignored under the system's default regulation policy. Aiming at the above problems, we propose a method to optimize power consumption by co-regulating CPU and GPU. First, web pages are classified by logistic regression based on the processor operating characteristics when loading web pages. We assign weights to webpage characteristics to quantify the complexity, and then use DVFS to limit the CPU frequency while adjusting the GPU frequency based on webpage category and complexity. The proposed method is applied to the Chromium browser on Google Pixel2 XL, and tested on the top 500 Chinese websites, resulting in a 12% reduction in power consumption and an average 5% decrease in webpage loading time. Reference | Related Articles | Metrics | Comments（0）

Select

Track Area Detection for Railway Switches CHEN Yijun, CHEN Yu, TENG Fei Journal of Applied Sciences    2024, 42 (1): 145-160.   DOI: 10.3969/j.issn.0255-8297.2024.01.012 Abstract （61）      PDF（pc） （12570KB）（61）       Knowledge map    Save The detection of the railway track area in front of the train is a key link in active train collision avoidance technology. The existing railway area segmentation methods are mostly used for track detection in simple scenarios, posing challenges when confronted with complex scenarios such as railway switches in actual operation. We propose a method for detecting railway track areas for railway switches, which solves the problem that existing technology encounters difficulty in detecting the actual running area of trains under railway switches. First, a railway track area segmentation model based on information fusion is proposed. Aiming at the problem of difficulty in matching the left and right rails of the railway, the railway area and the rails are segmented and the segmentation results are used for rail matching. Second, a railway area reconstruction method based on inverse perspective transformation is designed to reconstruct the railway area by preserving the key points of the rails. Meanwhile, a railway switch classification model based on grouped convolution is used to identify the switch direction. Experimental results show that the proposed method achieves high accuracy in complex environments, with pixel accuracy (PA) index of 98.67% and Mean Intersection over Union (MioU) index of 98.12%, showcasing its potential applicability to trains. Reference | Related Articles | Metrics | Comments（0）

Select

A Multi-label Semantic Calibration Method for Few Shot Extractive Question LIU Qing, CHEN Yanping, ZOU Anqi, QIN Yongbin, HUANG Ruizhang Journal of Applied Sciences    2024, 42 (1): 161-173.   DOI: 10.3969/j.issn.0255-8297.2024.01.013 Abstract （62）      PDF（pc） （1295KB）（26）       Knowledge map    Save biases, especially in instances involving multiple sets of distinct repeated spans. Therefore, this paper proposes a multi-label semantic calibration method for few-shot extractive QA to mitigate the above issues. Specifically, this method uses the head label, which contains global semantic information, and the special character in the baseline model to form a multi-label for semantic fusion. The semantic fusion gate is then used to control the introduction of global information flow to integrate global semantic information into the semantic information of the special character. Next, the semantic selection gate is used to retain or replace the newly integrated global semantic information and the original semantic information of the special character, achieving semantic adjustment of label bias. The results of 56 experiments on 8 few-shot extractive QA datasets consistently outperformed the baseline model in terms of the evaluation metric F1 score. This demonstrates the effectiveness and advancement of the method. Reference | Related Articles | Metrics | Comments（0）

Select

Projected Reward for Multi-robot Formation and Obstacle Avoidance GE Xing, QIN Li, SHA Ying Journal of Applied Sciences    2024, 42 (1): 174-188.   DOI: 10.3969/j.issn.0255-8297.2024.01.014 Abstract （83）      PDF（pc） （1502KB）（91）       Knowledge map    Save To address issues of excessive centralization, low system robustness, and formation instability in multi-robot formation tasks, this paper introduces the projected reward for multi-robot formation and obstacle avoidance (PRMFO) approach. PRMFO achieves decentralized decision-making for multi-robot using a unified state representation method, ensuring consistency in processing information regarding interactions between robots and the external environment. The projected reward mechanism, based on this unified state representation, enhances the decision-making foundation by vectorizing rewards in both distance and direction dimensions. To mitigate excessive centralization, an autonomous decision layer is established by integrating the soft actor-critic (SAC) algorithm with uniform state representation and the projected reward mechanism. Simulation results in the robot operating system (ROS) environment demonstrate that PRMFO enhances average return, success rate, and time metrics by 42%, 8%, and 9%, respectively. Moreover, PRMFO keeps the multi-robot formation error within the range of 0 to 0.06, achieving a high level of accuracy. Reference | Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2024, 42 (2): 0-0.   Abstract （21）      PDF（pc） （93KB）（10）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2024, 42 (2): 1-0.   Abstract （22）      PDF（pc） （47KB）（9）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Sign Language Recognition Based on Two-Stream Adaptive Enhanced Spatial Temporal Graph Convolutional Network JIN Yanliang, WU Xiaowei Journal of Applied Sciences    2024, 42 (2): 189-199.   DOI: 10.3969/j.issn.0255-8297.2024.02.001 Abstract （51）      PDF（pc） （1979KB）（73）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

UAV Path Planning and Radio Mapping Based on Deep Reinforcement Learning WANG Xin, ZHONG Weizhi, WANG Junzhi, XIAO Lijun, ZHU Qiuming Journal of Applied Sciences    2024, 42 (2): 200-210.   DOI: 10.3969/j.issn.0255-8297.2024.02.002 Abstract （71）      PDF（pc） （3338KB）（39）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

Interference and Scalability Analysis of LoRa Spread Spectrum Channel LEI Fang, CHEN Bo, LYU Jingzhao Journal of Applied Sciences    2024, 42 (2): 211-221.   DOI: 10.3969/j.issn.0255-8297.2024.02.003 Abstract （25）      PDF（pc） （2049KB）（24）       Knowledge map    Save 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%. Reference | Related Articles | Metrics | Comments（0）

Select

High Time Transmission Efficiency CP-UFMC Receiving Method Based on CP Reconstruction ZHENG Xiaokang, WEN Jiangang, ZOU Yuanping, WANG Anding, HUA Jingyu Journal of Applied Sciences    2024, 42 (2): 222-236.   DOI: 10.3969/j.issn.0255-8297.2024.02.004 Abstract （24）      PDF（pc） （819KB）（33）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

Multi-point Tapered Fiber Flexible Curvaturer Sensor Based on Fiber Grating WU Kai, GONG Huaping, NI Kai, MAO Bangning, ZHAO Chunliu Journal of Applied Sciences    2024, 42 (2): 237-247.   DOI: 10.3969/j.issn.0255-8297.2024.02.005 Abstract （31）      PDF（pc） （4062KB）（29）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

Optimal Design and Sensitivity Analysis of Double-Diaphragm Structure FBG Soil Pressure Sensors XING Guangzhi, CHEN Bozhi, WU Wenjing Journal of Applied Sciences    2024, 42 (2): 248-261.   DOI: 10.3969/j.issn.0255-8297.2024.02.006 Abstract （25）      PDF（pc） （3541KB）（24）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

High-Precision Liquid Level Sensor Based on Microwave Principle CUI Zhigang, LIU Jincheng, LU Enlong, ZHAO Xuxin, ZHANG Qi Journal of Applied Sciences    2024, 42 (2): 262-268.   DOI: 10.3969/j.issn.0255-8297.2024.02.007 Abstract （28）      PDF（pc） （1082KB）（25）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

A Large FOV Convergence Binocular Stereo Vision Calibration Method CUI Shuaihua, YU Lei, HE Xi, XIONG Bangshu, OU Qiaofeng Journal of Applied Sciences    2024, 42 (2): 269-279.   DOI: 10.3969/j.issn.0255-8297.2024.02.008 Abstract （36）      PDF（pc） （1750KB）（25）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

CT Based Non-human Tissue 3D Reconstruction DONG Jingxian, MA Jingwen, CAI Hongsen, LI Xin, DENG Xianbo, HOU Wenguang Journal of Applied Sciences    2024, 42 (2): 280-289.   DOI: 10.3969/j.issn.0255-8297.2024.02.009 Abstract （29）      PDF（pc） （7333KB）（24）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

Gamma Correction Parameter Estimation Via Histogram Gap Feature WANG Wenjuan, YAO Heng Journal of Applied Sciences    2024, 42 (2): 290-301.   DOI: 10.3969/j.issn.0255-8297.2024.02.010 Abstract （27）      PDF（pc） （1515KB）（19）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

Three-Dimensional Measurement of Fringe-Gray Linear Projection Based on Hilbert Transform ZHAI Yayu, WANG Meihui, YANG Cheng, LU Jing, LI You Journal of Applied Sciences    2024, 42 (2): 302-313.   DOI: 10.3969/j.issn.0255-8297.2024.02.011 Abstract （34）      PDF（pc） （9284KB）（27）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

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 Journal of Applied Sciences    2024, 42 (2): 314-322.   DOI: 10.3969/j.issn.0255-8297.2024.02.012 Abstract （38）      PDF（pc） （12640KB）（12）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

Automatic Event Semantic Division Based on Instance Distribution Constraints GAO Jianqi, LUO Xiangfeng, PEI Xinmiao Journal of Applied Sciences    2024, 42 (2): 323-333.   DOI: 10.3969/j.issn.0255-8297.2024.02.013 Abstract （31）      PDF（pc） （656KB）（9）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

Network Security Situation Assessment Based on Improved SKNet-SVM ZHAO Dongmei, SUN Mingwei, SU Mengyue, WU Yaxing Journal of Applied Sciences    2024, 42 (2): 334-349.   DOI: 10.3969/j.issn.0255-8297.2024.02.014 Abstract （39）      PDF（pc） （1949KB）（27）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

Intuition Fuzzy and Structural Least Squares Twin Support Vector Machine ZHANG Faying, LYU Li, HAN Longzhe, LIU Dongxiao, FAN Tanghuai Journal of Applied Sciences    2024, 42 (2): 350-363.   DOI: 10.3969/j.issn.0255-8297.2024.02.015 Abstract （26）      PDF（pc） （1179KB）（14）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）

Select

Smart Contract Vulnerability Detection of Symbol Execution with Critical Path Pre-searching WANG Zexu, WEN Bin Journal of Applied Sciences    2024, 42 (2): 364-374.   DOI: 10.3969/j.issn.0255-8297.2024.02.016 Abstract （30）      PDF（pc） （2151KB）（16）       Knowledge map    Save 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. Reference | Related Articles | Metrics | Comments（0）