2022 Vol.40

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Journal of Applied Sciences    2022, 40 (1): 0-0.   Abstract （7）      PDF（pc） （86KB）（46）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2022, 40 (1): 0-0.   Abstract （1701）      PDF（pc） （47KB）（115）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Emotional Analysis of Brain Waves Based on CNN and Bi-LSTM ZHU Li, YANG Qing, WU Tao, LI Chen, LI Ming Journal of Applied Sciences    2022, 40 (1): 1-12.   DOI: 10.3969/j.issn.0255-8297.2022.01.001 Abstract （2357）      PDF（pc） （1792KB）（402）       Knowledge map    Save Aiming at the problem that most emotion recognition methods rely on manual feature extraction, a hybrid model based on convolutional neural network (CNN) and bidirectional long short-term memory (Bi-LSTM) network is proposed. Firstly, one-dimensional data is converted into two-dimensional data, and spatial features are extracted by CNN. Then the one-dimensional data is input into Bi-LSTM to obtain temporal features. Finally, the fused spatial and temporal features are input into Softmax classifier to obtain final classification results. Experimental results on DEAP dataset show that CNN and BiLSTM hybrid model has good classification performance, and the accuracy in potency and arousal reaches 88.55% and 89.07%, respectively, proving the proposed model is a feasible and affective EEG emotion classification model. Reference | Related Articles | Metrics | Comments（0）

Select

Behavior Imitation Robotic System with Cognition Capacity BAO Zhenshan, DING Yilong, ZHANG Wenbo Journal of Applied Sciences    2022, 40 (1): 13-24.   DOI: 10.3969/j.issn.0255-8297.2022.01.002 Abstract （1825）      PDF（pc） （4503KB）（135）       Knowledge map    Save Behavioral imitation is one of the important technologies for robots to show their intelligence. How to make the behaviors and actions imitated by robots similar to the demonstrating actions of human has become a hot research topic. In this paper, we design an improved robot behavior modeling framework based on simple method. The framework collects teaching action using normal monocular camera, and introduces behavior semantic recognition module and key action extraction module into the simple method. The framework enables robots to understand instructor's behavior semantics and then imitate instructor's behaviors. Finally, this framework is deployed on the HBE-ROBONOVA-AI II humanoid robot platform, and experiments are conducted using independently collected single-person action video data as input. Compared with the experimental results of other mainstream frameworks, this framework works with more excellent comprehensive performance in three aspects of accuracy, balance and similarity, and demonstrates a unique cognitive ability to instructor's behaviors. Reference | Related Articles | Metrics | Comments（0）

Select

Static Multimodal Sentiment Analysis of Online Reviews WANG Kaixin, XU Xiujuan, LIU Yu, ZHAO Zhehuan, ZHAO Xiaowei Journal of Applied Sciences    2022, 40 (1): 25-35.   DOI: 10.3969/j.issn.0255-8297.2022.01.003 Abstract （1875）      PDF（pc） （1977KB）（165）       Knowledge map    Save This paper proposes a static multi-modal sentiment classification model based on Pre-LN Transformer. This model firstly extracts semantic features from reviews using the encoder in Pre-LN Transformer structure, in which the multi-head self-attention mechanism allows the model to learn relevant emotional information in different subspaces. Then our model extracts the image features according to ResNet in the reviews. On the basis of feature level fusion, the visual attention mechanism guides the sentiment classification of text and realizes the static multimodal sentiment analysis of online reviews. Experimental results show that our model improves the performance by 1.34% and 1.10% in evaluation accuracy than BiGRU-mVGG and Trans-mVGG on Yelp datasets, which verifies the effectiveness and feasibility of the proposed model. Reference | Related Articles | Metrics | Comments（0）

Select

Fine-Grained Image Classification Based on Inference Graph of Attention Network ZHENG Zhiwen, GAN Jianhou, ZHOU Juxiang, OUYANG Zhaoxiang, LU Zeguang Journal of Applied Sciences    2022, 40 (1): 36-46.   DOI: 10.3969/j.issn.0255-8297.2022.01.004 Abstract （1840）      PDF（pc） （4758KB）（152）       Knowledge map    Save Aiming at the task of fine-grained classification of scene images, this paper proposes a fine-grained image classification method based on the attention network inference graph by integrating the multimodal information of image visual and textual features. First, we extract the global visual feature, local visual features and text features of the scene image, and form a new splicing feature by embedding the position information into the local visual features and textual features respectively. The feature is accordingly used as a node of the graph structure to generate a heterogeneous graph. Then, we design two meta-paths to decompose the heterogeneous graph into two isomorphic graphs, and put them into a two-level attention network inference graph with node-level attention and semantic-level attention. Finally, richer fine-grained feature expression can be obtained by multimodal fusion operations with the output node features and global visual feature. The proposed model enables effective combination of multimodal fusion and graph attention network, and performs strong competitiveness comparing with the current advanced mainstream methods on the two scene text fine-grained image datasets of Con-Text and Drink Bottle. Reference | Related Articles | Metrics | Comments（0）

Select

Modeling of Multi-agent City Safety and Livability Based on Street Perspective PAN Lihu, YANG Fenyu, LU Feiping, QIN Shipeng Journal of Applied Sciences    2022, 40 (1): 47-60.   DOI: 10.3969/j.issn.0255-8297.2022.01.005 Abstract （1803）      PDF（pc） （4740KB）（102）       Knowledge map    Save In order to solve the problem of urban safety livability under the influence of environmental and human activities, this paper builds a multi-agent model of city safety livability based on the data of ten streets in Futian District, Shenzhen. The model is realized by integrating geographic information system (GIS) with Repast simulation platform. With the model, we have simulated the evolution of urban safety development in Futian District in the next 20 years from the perspective of streets, and analyzed the dynamic interactive feedback mechanism of safety livability, resident satisfaction, and family relocation behavior of each street in Futian District. The simulation experiment proves that the multi-agent model is effective for predicting urban development under the influence of multiple factors. Reference | Related Articles | Metrics | Comments（0）

Select

Deep-Level Kernel Hook Mining Algorithm and Its Application in Software Security LU Dengkai, YU Yongbin, YU Wenjian, TANG Qian, LIANG Shouyi Journal of Applied Sciences    2022, 40 (1): 61-68.   DOI: 10.3969/j.issn.0255-8297.2022.01.006 Abstract （1720）      PDF（pc） （967KB）（71）       Knowledge map    Save This paper studies the protection principle of kernel hooks in the Windows operating system and proposes a deep-level kernel hook mining algorithm to solve the shortcomings of the interactive disassembler professional (IDA) cross-reference function. Firstly, the algorithm is used to dig out the internal calls of specified kernel functions and all the called positions of the kernel functions containing hooks. Then, we use Python to write mining algorithms based on the principle of function calls. Finally, we use C++ to write a driver program for passing-protection experiment. The performance of overprotection experiment is successful, which proves the effectiveness of the mining algorithm and the comprehensiveness of mining results. Reference | Related Articles | Metrics | Comments（0）

Select

Ensemble Classification Algorithm Based on Cost Sensitive Convolutional Neural Networks ZHOU Chuanhua, XU Wenqian, ZHU Junjie Journal of Applied Sciences    2022, 40 (1): 69-79.   DOI: 10.3969/j.issn.0255-8297.2022.01.007 Abstract （2082）      PDF（pc） （623KB）（246）       Knowledge map    Save Aiming at the problem of low recognition rate of a few types of samples in unbalanced data sets, a classification algorithm based on cost sensitive convolutional neural network and AdaBoost (AdaBoost-CSCNN) was proposed. The cost sensitive convolutional neural network (CSCNN) is constructed by coordinating the cross entropy loss function of convolutional neural network (CNN) with a specific cost sensitive index. In training process, cost weighting mechanism is used to reduce the loss degree of key feature attributes of a few samples and realize the classification effect of a single CSCNN as a base classifier in AdaBoost. To verify the effectiveness of the algorithm, we carried out experiments on 9 data sets with different imbalance rates. Experimental performances, including Accuracy, Recall, F1-score and AUC, show that the AdaBoost-CSCNN algorithm has a good display for unbalanced data set classification. Reference | Related Articles | Metrics | Comments（0）

Select

Infrared Image Fusion Based on NSCT and Compressed Sensing JIN An'an, LI Xiang, ZHANG Li, XIONG Qingzhi Journal of Applied Sciences    2022, 40 (1): 80-92.   DOI: 10.3969/j.issn.0255-8297.2022.01.008 Abstract （1801）      PDF（pc） （11751KB）（91）       Knowledge map    Save Aiming at the problems of low quality, lack of information and non-prominent edge details in the fusion process of infrared and visible images, this paper proposes a compressed sensing image fusion and reconstruction algorithm based on non-subsampled contourlet transform (NSCT) and sparse representation. Firstly, a source image is decomposed by using NSCT to obtain corresponding high-frequency sub-band and low-frequency sub-band images. Then, the high-frequency sub-band images are fused by using the highfrequency fusion rules based on compressed sensing to obtain high-frequency fusion coefficients. For the low-frequency sub-band images, low-frequency fusion coefficients are obtained by using the low-frequency fusion rules based on dictionary learning. Finally, a fusion image is obtained by using the inverse NSCT transformation to achieve superresolution recovery of infrared and visible images. Experimental results show that the images fused by this algorithm have good performance in metrics, such as average gradient, edge intensity, information entropy, edge information retention and spatial frequency, and prove that this fusion algorithm has significant advantages in image fusion quality. Reference | Related Articles | Metrics | Comments（0）

Select

Mask Wearing Detection in Complex Scenes Based on Mask-YOLO WEI Mingjun, ZHOU Taiyu, JI Zhanlin, ZHANG Xinnan Journal of Applied Sciences    2022, 40 (1): 93-104.   DOI: 10.3969/j.issn.0255-8297.2022.01.009 Abstract （2194）      PDF（pc） （22008KB）（451）       Knowledge map    Save Aiming at the problem of low detection accuracy caused by occlusion, density and small scale in mask wearing detection in public places, a Mask-YOLO algorithm is proposed based on real-time target detection algorithm YOLOv3. First, the algorithm introduces channel attention mechanism in the process of feature fusion, effectively highlights the important features, reduces the influence of redundant features after fusion, and effectively improves the feature utilization. Then, complete intersection over union (CIoU) loss is used instead of mean square error (MSE) as the loss function of frame regression to improve the positioning accuracy. Finally, in addition to the cases of detecting wearing and not wearing masks, incorrect wearing of masks is also detected. Experimental results show that Mask-YOLO algorithm improves mean average precision (mAP) by 4.78% when frame per second (FPS) decreases by only 1% compared with YOLOv3 algorithm. As compared with other mainstream target detection algorithms, Mask-YOLO algorithm also has better detection effect and robustness for mask wearing detection in complex scenes. Reference | Related Articles | Metrics | Comments（0）

Select

Segmentation Model of COVID-19 Lesions Based on Triple Attention Mechanism LEI Qianhui, PAN Lili, SHAO Weizhi, HU Haipeng, HUANG Yao Journal of Applied Sciences    2022, 40 (1): 105-115.   DOI: 10.3969/j.issn.0255-8297.2022.01.010 Abstract （1934）      PDF（pc） （3285KB）（159）       Knowledge map    Save In order to solve the problem of low intensity contrast between infected areas and normal tissues, A corona virus disease 2019 (COVID-19) segmentation model TMNet is proposed based on triple attention mechanism (TAM), and applied to conditional generative adversarial network in this paper. The MultiConv module in TM-Net can automatically extract rich features of infected areas in lung slices. These features contain different types of lesion information. The designed TAM, which integrates spatial, channel and positional attention modules, can accurately locate lesions in the infected area. By composing of three types of loss functions, the loss function of TM-Net can minimize the differences between prediction graphs and real labels, thus optimizing the TM-Net. Experiment and evaluations conducted on COVID-19 data sets show that the average dice similarity coefficient (DSC) of ground glass opacities (GGO) and consolidation of TM-Net are 1.4% and 0.5% higher than the results of attention U-Net and R2U-Net, respectively, proving the accuracy improvement of TM-Net in COVID-19 lesions segmentation. Reference | Related Articles | Metrics | Comments（0）

Select

Sparrow Search Algorithm Based on Levy Flight Disturbance Strategy MA Wei, ZHU Xian Journal of Applied Sciences    2022, 40 (1): 116-130.   DOI: 10.3969/j.issn.0255-8297.2022.01.011 Abstract （2147）      PDF（pc） （817KB）（192）       Knowledge map    Save In order to solve the problems of insufficient search diversity in late iteration and easy falling of local optimization in traditional sparrow search algorithm, an improved sparrow search algorithm (ISSA) based on Levy flight disturbance strategy is proposed. Firstly, the algorithm uses Sin chaos search mechanism to improve population initialization strategy. Secondly, in the process of sparrow population foraging search, Levy flight disturbance mechanism is introduced to drag the appropriate step of population movement, and the diversity of spatial search is then increased. Finally, experiment on 14 typical highdimensional test functions has been carried out, and the results show that compared with the traditional sparrow search algorithm and two other recently proposed chaos sparrow search algorithm (CSSA) and ISSA, the proposed algorithm in this paper can effectively avoid the search process falling into local optimization, and achieve high optimization rate and strong convergence ability, and shows feasibility in solving problems of multi-peak and high-dimensional space optimization. Reference | Related Articles | Metrics | Comments（0）

Select

Remote Sensing Image Object Detection Based on MFANet and Contextual Features Fusion WANG Peng, ZHENG Wenfeng, SHI Jin, JIN Shuo, LIU Zihao Journal of Applied Sciences    2022, 40 (1): 131-144.   DOI: 10.3969/j.issn.0255-8297.2022.01.012 Abstract （1774）      PDF（pc） （12424KB）（158）       Knowledge map    Save Remote sensing images have the characteristics of complex background, large variations of object sizes and inter-class similarity, which lead to poor object detection results. An effective and robust remote sensing image object detection method based on Faster R-CNN is proposed. First, we introduce deformable convolution, feature modulation mechanisms and dilated convolution to construct a modulated feature adaptation network named MFANet, which can extract more accurate and complete object information. Second, a contextual feature pyramid network named CFPN is introduced to exploit richer and more discriminative feature representations. CFPN can solve the problems of insufficient high-level semantic information in the process of feature transfer and lack of effective communication between multi-size receptive fields. Finally, complete IoU (CIoU) loss is introduced into bounding box regression to further improve the accuracy of object detection. To verify the validity of the proposed method, we conduct experiments on public datasets DIOR, RSOD, and NWPU VHR-10. Experimental results show that compared with the Faster R-CNN with FPN method, IF-RCNN obtains an absolute gain of 8.43%, 7.5% and 8.0% in the average detection accuracy on the three datasets, respectively, which suggests that our proposed method is more effective and robust. Reference | Related Articles | Metrics | Comments（0）

Select

KNN-GWD Recommendation Model and Its Application JI Deqiang, WANG Hairong, CHE Miao, WANG Jiaxin Journal of Applied Sciences    2022, 40 (1): 145-154.   DOI: 10.3969/j.issn.0255-8297.2022.01.013 Abstract （1668）      PDF（pc） （652KB）（100）       Knowledge map    Save In order to solve the problem of poor accuracy in traditional recommendation, a multi-layer K-nearest neighbor (KNN) network recommend model KNN-GWD, in combination of graph neural network (GNN) and wide & deep network was constructed. In the model, the KNN classification method is for data noise filtering to improve data quality. GNN is used to extract the node embedding representation of user's conversation graphs, and capture user's short-term interest by weighting user's global characteristics based on attention mechanism. Wide&Deep is used to solve the problem of model overgeneralization in the case of sparse data. In order to verify the effectiveness of the model, comparative experiments were carried out on MovieLens-1M, Bing-News and Book-Crossing data sets with this model and six other traditional recommendation methods. Experimental results show that the evaluation indicators of this model are better. In order to further verify the feasibility of the proposed model in the actual application field, an agricultural integrated management App fertilizer recommendation system was built with the accuracy of recommended results of 0.721 and the area under curve of 0.784, which met the expected application requirements. Reference | Related Articles | Metrics | Comments（0）

Select

Track Slab Crack Detection Method Based on TSCD Model LI Wenju, ZHANG Yaoxing, CHEN Huiling, LI Peigang, SHA Liye Journal of Applied Sciences    2022, 40 (1): 155-166.   DOI: 10.3969/j.issn.0255-8297.2022.01.014 Abstract （1797）      PDF（pc） （2650KB）（91）       Knowledge map    Save In order to solve the problem of track slab crack detection, a track slab crack detection model based on branch cascaded convolutional neural network, TSCD, is proposed. First, the model highlights the position information of track slab cracks through attention mechanism and structure of search branches to suppress interference information. Second, it realizes the pixel-level detection of cracks by structure of detecting branches. Finally, in order to solve the problem of image detail degradation in detection results, parameter mapping is used to achieve up-sampling of the feature maps. Experimental results show that the proposed model in this paper can not only detect the cracks in track plate surface images accurately with pixel accuracy rate of 97.56% and F1-score of 86.28%, but also performs strong generalization in cross-dataset tests. Reference | Related Articles | Metrics | Comments（0）

Select

Research on UAV Detection and Counter Technologies for Security in Key Areas JIANG Dongting, FAN Changjun, YONG Qirun, QU Chongxiao, LIU Shuo, ZHANG Yongjin Journal of Applied Sciences    2022, 40 (1): 167-178.   DOI: 10.3969/j.issn.0255-8297.2022.01.015 Abstract （1812）      PDF（pc） （630KB）（219）       Knowledge map    Save This study analyzes the characteristics of unmanned aircraft vehicle (UAV), security risks of UAV and difficulties in counter unmanned aircraft vehicle (C-UAV). UAV detection techniques including radar, radio electro-optical, and acoustic sensors as well as UAV interdiction techniques including RF/GNSS jamming, spoofing, laser, nets and so on have been thoroughly studied in this paper. The market application of these technologies is analyzed, and the advantages and disadvantages of these technologies are compared and analyzed. Finally, some suggestions on UAV defense and control systems in various key areas are provided. Reference | Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2022, 40 (2): 1-.   Abstract （1321）      PDF（pc） （97KB）（161）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2022, 40 (2): 2-.   Abstract （1306）      PDF（pc） （58KB）（41）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Refractive Index Measurement of Photopolymer Based on Digital Holographic Microscopy LI Weixia, HUANG Sujuan, YAN Cheng, XIA Shengli, YIN Weihao Journal of Applied Sciences    2022, 40 (2): 179-189.   DOI: 10.3969/j.issn.0255-8297.2022.02.001 Abstract （1540）      PDF（pc） （10065KB）（128）       Knowledge map    Save A method based on the digital holographic microscopy (DHM) for measuring the refractive index of photopolymer is proposed. The digital hologram is recorded by the Mach-Zehnder off-axis interference system. The high-precision phase distribution is extracted by the hybrid reconstruction algorithm. Combining the profile distribution measured by optical profilometer, the refractive index of photopolymer is obtained by image registration. The evolution of refractive index of photopolymer during the UV curing process is quantitatively analyzed. The dynamic phase distribution of photopolymer is measured by DHM, and then the dynamic refractive index distribution is obtained. The relationship between the average refractive index and exposure time is plotted. The proposed method can be used to reveal the optical performance of microscopic optical devices and design high-quality optical systems. Reference | Related Articles | Metrics | Comments（0）

Select

Fracturing Monitoring of Oil-Wells Using Microstructured Optical Fiber Based Distributed Sensing LIU Shuai, WANG Zhi, WANG Aiqing, LI Shijian, TU Dongsheng, ZHENG Yu, NUERMAIMAITI·Wumaierjiang Journal of Applied Sciences    2022, 40 (2): 190-203.   DOI: 10.3969/j.issn.0255-8297.2022.02.002 Abstract （1609）      PDF（pc） （11312KB）（221）       Knowledge map    Save This paper presents several high-temperature resistance polyimide coated microstructured optical fibers, with enhanced scatterings benefited from the specially designed fiber structures. Beyond that, these fibers also possess high resistance to humidity and a long lifetime in hydrogen-rich environments. Using one of these fibers, we study the scattering enhancement in a distributed sensor system. When the fiber loss is 3 dB/km, the measurement accuracy can be effectively improved by 2~5 times. Further testing this system for fracturing monitoring in oil wells, the collected data from the sensing system prove that the underneath fracturing can be monitored and be further used for supervising fracturing and temporary plugging operations. Reference | Related Articles | Metrics | Comments（0）

Select

Influence of Irradiation on Magneto-Optical Properties of Bi/Er/La Co-doped Active Silica Fiber YE Le, WEN Jianxiang, ZENG Jiawei, DONG Yanhua, WANG Tingyun Journal of Applied Sciences    2022, 40 (2): 204-211.   DOI: 10.3969/j.issn.0255-8297.2022.02.003 Abstract （1508）      PDF（pc） （1263KB）（165）       Knowledge map    Save To improve the weak magneto-optical properties of standard single-mode fibers, in this paper, we fabricated a Bi/Er/La co-doped active silica fiber by using modified chemical vapor deposition (MCVD) method in combination with atomic layer deposition (ALD) technology. Furthermore, we processed the fiber with gamma-ray irradiation. A Verdet constant measurement system for fibers was built to study the magneto-optical properties of Bi/Er/La co-doped active silica fiber before and after irradiation. Experimental results show that the Verdet constant of Bi/Er/La co-doped active silica fiber is 1.02 rad/(T · m)at 1 310 nm, which is 36.2% higher than that of standard single-mode fiber. It is also shown that the processing of gamma-ray irradiation can improve the magneto-optical property of the fiber, and the Verdet constant of Bi/Er/La co-doped active silica fiber increases with the increase of irradiation dose. Especially under the irradiation dose of 3.0 kGy, the Verdet constant increases by 54.90%, whereas that of standard single-mode fibers increases only by 26.3% and gets saturation at the irradiation dose of 1.0 kGy. Reference | Related Articles | Metrics | Comments（0）

Select

Circle Center Detection and Correction Method of Circular Markers in Helicopter Blade Image ZHANG Yubin, CHEN Yaofeng, LE Juan, CHENG Qiyou Journal of Applied Sciences    2022, 40 (2): 212-223.   DOI: 10.3969/j.issn.0255-8297.2022.02.004 Abstract （1609）      PDF（pc） （879KB）（95）       Knowledge map    Save The deformation measurement of rotating helicopter high-speed rotor blades is usually based on circular markers. However, circular markers are usually with problems, such as low exposure, small target region, and asymmetric projection, which easily lead to detection missing of markers and location error of circle centers. In order to avoid these problems, a detection method based on circular markers in helicopter rotor blade images is proposed in this paper. Firstly, pixel coordinates of local gray extreme value centers in the image are extracted, and interferences are removed according to array arrangement structure, then pixel coordinates of all circular marker extreme values are obtained. Secondly, the circular region of interest (ROI) is established with each extremum coordinate as the center and the minimum distance from the adjacent extremum as the diameter. Within the ROI, the circle center is obtained by parallel watershed transformation and least square circle fitting. Thirdly, based on perspective transformation, the projection mapping relationship between the image and another helicopter rotor blade image, which with the same phase and perpendicular to the camera optical axis is established. And the projection mapping matrix is optimized by levenberg-marquardt (LM). Finally, the images is converted to a positive image for circle center fitting, and exact circle center coordinates are obtained by inverse transformation of circle center coordinates. Experimental results show that the accuracy and the precision of the proposed method are 98.89% and 0.191 mm, and it has been applied in the high-precision visual measurement of the motion trajectory and deformation of the helicopter high-speed rotor baled. Reference | Related Articles | Metrics | Comments（0）

Select

An OTSU Image Segmentation Method Based on Attribute Weighted Naive Bayesian Algorithm MA Feihu, ZENG Cong, JIN Yichen, SUN Cuiyu, CHEN Huapeng Journal of Applied Sciences    2022, 40 (2): 224-232.   DOI: 10.3969/j.issn.0255-8297.2022.02.005 Abstract （1654）      PDF（pc） （961KB）（71）       Knowledge map    Save In order to enhance the accuracy of image segmentation and optimize the detail segmentation effect of image segmentation, an improved OTSU image segmentation method based on attribute weighted naive Bayesian algorithm is proposed. The foreground and background of an image are selected according to the grayscale characteristics of the image as using OTSU algorithm, and then classified by using the attribute Weighted Naive Bayesian algorithm. Thus, the probability of the foreground and background of the image is calculated. By training this model to obtain the optimal threshold for the image segmentation process, the optimized effect of image segmentation can be obtained. Experiment with image data collected by drone aerial photography is conducted, and results show that the image segmentation of OTSU based on the attribute weighted naive Bayesian algorithm optimizes the image segmentation effect and shows much finer details of the image after segmentation, promising a prospective application value. Reference | Related Articles | Metrics | Comments（0）

Select

Tensor Model Based on Total Variation Regularized and L2,1 Norm for Video Rain Streaks Removal LU Xinghan, ZHENG Yuhui, ZHANG Jianwei Journal of Applied Sciences    2022, 40 (2): 233-245.   DOI: 10.3969/j.issn.0255-8297.2022.02.006 Abstract （1522）      PDF（pc） （8321KB）（142）       Knowledge map    Save This paper proposes a tensor model for video rain streaks removal based on total variational regularization and L2,1 norm to solve rain streaks shielding. Firstly, the prior information of rain streaks component and the video background are preprocessed to obtain the corresponding regularization condition, so as to enhance the sparsity of each part and facilitate the separation of rain streaks. Then, considering the existence of irregular dynamic objects in the video, a total variational regularization term is introduced to suppress the variation of background intensity and alleviate the misjudgment of rain streaks. The alternating direction method of multipliers (ADMM) can be used to effectively solve the proposed tensor model, and carried out a large number of experiments on the synthetic and real datasets. Experimental results show that the proposed method under dynamic background can effectively remove the video rain streaks and retain more background details simultaneously. Compared with other relevant methods, the proposed method has great advantages in three comprehensive quantitative performance measures of peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and residual error (RES). Reference | Related Articles | Metrics | Comments（0）

Select

Infrared Image ROI Encryption Method Based on Lorenz Chaos System WANG Congli, PING Xijian, ZHANG Tao Journal of Applied Sciences    2022, 40 (2): 246-252.   DOI: 10.3969/j.issn.0255-8297.2022.02.007 Abstract （1626）      PDF（pc） （1397KB）（143）       Knowledge map    Save In order to improve the security of monitoring system and the speed of full image encrypting, based on the fast image-block encryption method, the concept of Region of interest encryption for infrared image is advanced in this paper. The OSTU algorithm are used to extract the ROI for encryption, then a Lorenz sequence is processed in order to ensure the randomness. Based on the random Lorenz data sequence, the ROI encryption is processed. Compared to the other encryption methods, the Lorenz ROI encryption has better performance on operation speed, security and encryption effect. Reference | Related Articles | Metrics | Comments（0）

Select

Reversible Data Hiding Based on Multi-Pair Asymmetric Histogram Modification HE Yufen, TANG Jin, YIN Zhaoxia Journal of Applied Sciences    2022, 40 (2): 253-265.   DOI: 10.3969/j.issn.0255-8297.2022.02.008 Abstract （1574）      PDF（pc） （1065KB）（73）       Knowledge map    Save There are many invalid modifications of pixels in traditional reversible image information hiding algorithms based on asymmetric histogram modification. To solve this problem, a reversible information hiding scheme based on multi-pair asymmetric prediction error histogram modification is proposed in this paper. This scheme combines the advantages of asymmetric histogram modification algorithm and the characteristics of multihistogram modification algorithm, and selects the smooth region of the image to modify the asymmetric histogram for embedding information. At the same time of achieving the compensation reduction effect of asymmetric histogram, it can further reduce the invalid pixel modification and improve the rate distortion performance. Reference | Related Articles | Metrics | Comments（0）

Select

An Improved ORB Algorithm Based on Quad-Tree Partition NI Cui, WANG Peng, SUN Hao, LI Qian Journal of Applied Sciences    2022, 40 (2): 266-278.   DOI: 10.3969/j.issn.0255-8297.2022.02.009 Abstract （1768）      PDF（pc） （7068KB）（127）       Knowledge map    Save The image feature points extracted by the original ORB algorithm often appear the phenomenon of "clustering and overlapping", and their distribution is relatively dense and lack of scale invariance, which easily leads to the problem of mismatching of image feature points. In order to solve this problem, this paper proposes an image feature point extraction algorithm based on quad-tree structure. First, the scale pyramid of the image is built, and then the quad-tree is used to divide the image, and the depth of the partition is limited. The FAST algorithm is employed to detect the feature points of the scaled image by multiple detection thresholds. Second, the ORB feature points will be extracted based on the division of the total sub-block and the total number of the feature points. And then the best feature points are obtained by taking the maximum inhibition method, and the feature points' descriptors are calculated with the help of the improved BRIEF algorithm. Finally the work of feature points matching will be realized. Experimental results show that compared with the original ORB algorithm, the uniformity of feature points extracted by the proposed algorithm in this paper is significantly improved. The number of redundant and overlapping feature points is reduced, and the extraction speed of feature points is improved by more than 30%. Reference | Related Articles | Metrics | Comments（0）

Select

Image High Resolution Reconstruction Algorithm Using Directional Cycle Spinning Operations in Wavelet Domain ABUDURUSULI Aosiman, AILIMINUER Abulijiang, ZULIHAYETI Aihemaiti Journal of Applied Sciences    2022, 40 (2): 279-287.   DOI: 10.3969/j.issn.0255-8297.2022.02.010 Abstract （1517）      PDF（pc） （1088KB）（142）       Knowledge map    Save Traditional image interpolation algorithm is good at global handling of images, but weak in dealing with edge details of images, thus leading to sawtooth lines in detail areas. For this problem, this paper proposes an image resolution and contrast enhancement algorithm. First, a high-resolution image is obtained from an original one by using wavelet zero padding algorithm, and the lost edge and texture features of the image are compensated by using residual error correction process. Then, directional cycle spinning operations are performed on the image. Considering that the high frequency components in horizontal, vertical and diagonal directions of the image after wavelet decomposition can reflect the edge changes in the image, we use high frequency components in different directions of the image to describe mutation degrees in corresponding directions of image pixels. According to the mutation degrees, an adaptive fusion process of cycle spinning operations is realized, which can avoid excessive suppression of edge details. Finally, a nonlinear enhancement function is used to improve image contrast and highlight edge and contour information, Experimental results show that this algorithm not only enhances the spatial resolution and contrast of images, but also retains the edge and contour information contained in original ones. Compared with other image interpolation algorithms, this algorithm shows improved performs both in visual effect and anti-noise ability. Reference | Related Articles | Metrics | Comments（0）

Select

Photovoltaic Power Forecast Improved Stacking Algorithm LI Pengqin, ZHANG Changsheng, LI Yingna, LI Chuan Journal of Applied Sciences    2022, 40 (2): 288-301.   DOI: 10.3969/j.issn.0255-8297.2022.02.011 Abstract （1553）      PDF（pc） （839KB）（112）       Knowledge map    Save Stacking algorithm is good at alleviating over fitting problem in the prediction of photovoltaic power generation, but with drawbacks of long computation time and less sample data. To solve the problem, this paper proposes an improved 3-layer stacking algorithm based on new vector representation and cross validation accuracy weighting. The first and second layers are the primary layer, which use random forest, SVR and XGboost3. The third layer is the secondary layer, and uses LightGBM to learn the output of the second layer again to reduce noise. A new vector representation method is used to increase the sample size and sample distribution density of input and output data between levels to ensure that the data dimension will not increase with the increase of the number of primary level learners. At the same time, the results are weighted according to the difference in the prediction accuracy of different prediction models in the primary layer under cross-validation. Practical analysis is demonstrated by using the power generation data of a photovoltaic power station. Compared with random forest model and Stacking model, the prediction performance of the proposed model has been greatly improved in MAE, MSE and R-Squared. Reference | Related Articles | Metrics | Comments（0）

Select

Air Quality Prediction Based on MLP&ST Model ZHENG Hong, CHENG Yunhui, HU Yangsheng, HUANG Jianhua Journal of Applied Sciences    2022, 40 (2): 302-315.   DOI: 10.3969/j.issn.0255-8297.2022.02.012 Abstract （1536）      PDF（pc） （1266KB）（177）       Knowledge map    Save Air quality prediction system is necessary in guarding human and environment health, and the historical air pollution data collected by monitoring stations in a city and advanced computer equipment makes it possible to forecast air quality in a data-driven way. However, most of the existing methods are suitable for forecasting the air quality in monitored areas, and only few are for unmonitored areas. In this paper, a joint training model MLP&ST (MLP&Spatial-Temporal) is proposed which takes the consideration of the comprehensive impact of meteorological factors, spatial correlation and time dependence on air quality, to predict the future air quality index (AQI) of unmonitored areas in Beijing. Compared with several other air quality forecast models, the optimized historical time step P value of 29 is experimentally obtained. Experimental results show that the hybrid model is superior to other models in performance indices (RMSE, MAE and MAPE) and has good ability of predictability. Reference | Related Articles | Metrics | Comments（0）

Select

Control of Uncertain Bilateral Teleoperation System under DOS Attack ZHENG Kaizhong, FAN Chunxia Journal of Applied Sciences    2022, 40 (2): 316-327.   DOI: 10.3969/j.issn.0255-8297.2022.02.013 Abstract （1450）      PDF（pc） （645KB）（43）       Knowledge map    Save The stability of bilateral teleoperating system with time-delay and uncertain model parameters under denial of service (DoS) attack is studied. First, based on position error structures, event-triggered controllers can be designed, and then the unknown model parameters of manipulators are estimated by using the adaptive law. The stability of bilateral teleoperating system is proved by Lyapunov function theory, and the event-triggered controller does not have Zeno behavior. Numerical simulations are carried out to demonstrate the effectiveness of the proposed adaptive event-triggered controller on a bilateral teleoperation system under DOS attacks. Reference | Related Articles | Metrics | Comments（0）

Select

3D Point Cloud Classification and Segmentation Network Based on Local Feature Enhancement CHEN Lifang, WEI Mengru Journal of Applied Sciences    2022, 40 (2): 328-337.   DOI: 10.3969/j.issn.0255-8297.2022.02.014 Abstract （1536）      PDF（pc） （1205KB）（171）       Knowledge map    Save In the process of point cloud processing, many deep learning networks fail to fully consider the complicated relationships between local points, resulting in the loss of a large number of spatial geometric information. To solve this problem, an enriching local features network for point cloud classification and segmentation is proposed. The network designs an encoding unit to encode the multi-directional information of points, applies the attention mechanism to learn features of the local points formed after sampling and grouping, and proposes a new multi-dimensional loss function, which combines cross entropy loss function and the center loss function to act on the classification task. Extensive experiments are carried out on Modelnet40 and ScanNet datasets. The experimental results show that the network performs well in object classification and semantic segmentation tasks of 3D point cloud. Reference | Related Articles | Metrics | Comments（0）

Select

Impact of Epidemic on Consumer Economy via Transaction Data PAN Jing, CHAI Hongfeng, QIN Zheng, SUN Quan, GAO Pengfei, ZHENG Jianbin Journal of Applied Sciences    2022, 40 (2): 338-348.   DOI: 10.3969/j.issn.0255-8297.2022.02.015 Abstract （1427）      PDF（pc） （627KB）（82）       Knowledge map    Save The sudden COVID-19 pandemic has led to unprecedented impact on China's economic and social development, especially on consumer economy. Payment is the most closely related economic activity regarding consumers, the data of which can accurately capture the characteristic of the consumer economy. Given the point of view, this paper makes an in-depth exploration in the research direction of payment data. Based on the transaction data from China UnionPay, this paper quantifies the impact of the epidemic on consumer economy and makes a comparative analysis of different provinces and industries. The paper quantitatively reveals that the epidemic progress significantly affects the consumer confidence and the development of consumer economy. According to our analysis, it is unwise to restart work resumption when the epidemic is still not under effective control. From the perspective of payment, this paper profoundly tells about the story of how China fights against the epidemic and puts forward relevant suggestions for the follow-up epidemic prevention and control as well as the comprehensive economic recovery policies. Reference | Related Articles | Metrics | Comments（0）

Select

Energy-Saving Scheduling Algorithm for Multi-Variable Neighborhood Based on Pruning Optimization QIU Bin, SUN Manman, CUI Suli Journal of Applied Sciences    2022, 40 (2): 349-360.   DOI: 10.3969/j.issn.0255-8297.2022.02.016 Abstract （1319）      PDF（pc） （725KB）（119）       Knowledge map    Save In order to improve the energy-saving level of task scheduling in heterogeneous computer systems, a multi-variable neighborhood energy-saving scheduling algorithm fused with pruning optimization is proposed. Processor constraint and time constraint neighborhood structures are constructed in the algorithm. The number of redundant processors is reduced by constraining the neighborhood of processors, thus lowering the overall energy consumption. Pruning optimization is introduced into the time and energy consumption neighborhood to improve the efficiency of local optimization. Simulation results show that the proposed algorithm achieves good energy-saving effect under different problem scales, processor capacity and communication ratio. Reference | Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2022, 40 (3): 1-0.   Abstract （1680）      PDF（pc） （82KB）（97）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

Journal of Applied Sciences    2022, 40 (3): 2-0.   Abstract （1662）      PDF（pc） （47KB）（42）       Knowledge map    Save Related Articles | Metrics | Comments（0）

Select

EDFA-Relaying Long-Haul Chaos Synchronization of Semiconductor Lasers Driven by a Common Signal DONG Hongxia, GAO Hua, WANG Longsheng, YANG Yibiao, WANG Anbang Journal of Applied Sciences    2022, 40 (3): 361-371.   DOI: 10.3969/j.issn.0255-8297.2022.03.001 Abstract （1979）      PDF（pc） （2226KB）（155）       Knowledge map    Save This paper numerically studies the long-haul chaotic synchronization scheme of semiconductor lasers driven by a common signal based on erbium-doped fiber amplifier (EDFA) relay and periodic dispersion compensation. By optimizing the injection conditions of the driving light and the mismatch of the relaxation oscillation frequency between driving and response lasers, the response laser achieves synchronization with a synchronization coefficient of 0.98 in back-to-back situations. At the same time, the correlation between the driving and response lasers is reduced to 0.32, ensuring the security of the co-drive synchronization system. Furthermore, considering the damage factors such as fiber dispersion, nonlinear effects, and EDFA noise, the optimal conditions for fiber input power and single-span fiber length are numerically studied. It is expected that under the condition of dispersion compensation deviation of 5 ps/nm per 100 km fiber, a high-quality chaotic synchronization with a synchronization coefficient of 0.90 can be achieved after 700 km of fiber transmission. This research result has reference significance for long-distance chaotic laser carrier communication and key distribution. Reference | Related Articles | Metrics | Comments（0）

Select

Semi-automatic Extraction and Regularization of Buildings of Different Shapes from High-Resolution Remote Sensing Images CUI Weihong, LI Jia, LIU Yu Journal of Applied Sciences    2022, 40 (3): 372-388.   DOI: 10.3969/j.issn.0255-8297.2022.03.002 Abstract （1965）      PDF（pc） （8968KB）（332）       Knowledge map    Save The current methods of interactive extraction of buildings from high-resolution remote sensing images mostly require complex user interaction and most of them only support extraction of buildings with right angles. In order to reduce interaction and achieve high-precision extraction of buildings in different shapes, this paper uses region grow, Gaussian mixture models (GMM), CannyLines edge detection and the max-flow/min-cut segmentation method based on multiple star constraints sequentially to obtain building patch, followed by regularization methods to get the building contours which are consistent with the actual building shapes. The average of F1 is up to 0.9 in extraction experiments, and the experimental results also show the facility and strong robustness of the proposed method. Reference | Related Articles | Metrics | Comments（0）

Select

Tilt Rate Measurement of Power Tower Based on UAV LiDAR Point Cloud LU Zhumao, GONG Hao, JIN Qiuheng, HU Qingwu, LI Jiayuan Journal of Applied Sciences    2022, 40 (3): 389-399.   DOI: 10.3969/j.issn.0255-8297.2022.03.003 Abstract （2098）      PDF（pc） （1603KB）（219）       Knowledge map    Save Power towers are the most basic equipment of the transmission line. Various weather or terrain conditions can cause damage to transmission lines such as wear, corrosion, strand breakage, resulting in deformation or tilting of the tower, which may cause serious accidents such as regional power outages if not repaired and inspected in time. Considering the difficulty, low efficiency and low accuracy of traditional measurement methods, an accurate measurement method of power tower tilt rate based on UAV LiDAR point cloud is proposed. This method uses the scattered 3D laser point cloud of power tower to calculate the tower centerline by fitting the tower body structure, so as to calculate the tilt rate. The measurement error sources and application conditions of this method are discussed. The application in transmission line detection proves the effectiveness and correctness of this method. To verify the effectiveness of the method, the paper selects 6 types of towers, 3 of each, 18 in total, to analyze the influence of point cloud density to the tilt rate measurement method, and calculate the accuracy of the method. The relative error of the calculation of the tilt rate is better than 0.7°, proves the validity and correctness of this method. Reference | Related Articles | Metrics | Comments（0）

• page
• Page 1 of 3
• Total 98 records
• First page
• Prev page
• Next page
• Last page