Search

According to the problem of the current RGB-D feature extraction network used for pose estimation was too large, this paper proposed a lightweight improved XYZNet RGB-D feature extraction network. First, this paper designed a lightweight sub-network BaseNet to replace ResNet18 in XYZNet, which made the network scale significantly reduced and obtained more powerful performance. Then, this paper proposed a re-parameterized multiscale convolutional attention (Rep-MSCA) sub-module based on depth separable convolution, which enhanced the ability of BaseNet to extract contextual information of different scales, and constrained the amount of parameters in the model. Finally, in order to improve the geometric feature extraction ability of PointNet in XYZNet with a small parameter cost, this paper designed a re-parameterized residual multi-layer perceptron (Rep-ResP) module. The floating point operations (FLOPs) and parameters of the improved network are 60.8% and 64.8% lower, the inference speed is 21.2% higher, and the accuracy of the mainstream datasets LineMOD and YCB-Video is 0.5% and 0.6% higher. The proposed model is more suitable for deployment in scenarios where hardware resources are tight. [ABSTRACT FROM AUTHOR]

Effectively representing features of modalities is a hot issue in cross-modal recipe retrieval. The current methods generally adopt two independent neural networks to extract the features of images and recipes respectively, achieving retrieval through cross-modal alignment. However, these methods mainly focus on the intra-modal information and ignore the intermodal interactions, resulting in the loss of some effective modality information. To address the problem, this paper proposed a cross-modal recipe retrieval method to enhance modality semantics through multimodal encoders. Firstly, it used a pre-trained model to extract initial semantic features of images and recipes and utilizing modality alignment to reduce the inter-model differences. Secondly, it employed the pairwise cross-modal attention to repeatedly reinforce the features of one modality by using features from another modality, extracted valid information. Thirdly, it used the self-attention mechanism to modal the internal features of modalities to capture rich modality-specific semantic information and potential associations. Finally, it introduced the triplet loss to minimize the distance between similar samples, achieved cross-modal retrieval learning. Experimental results on Recipe 1M dataset show that the proposed approach outperforms the current mainstream methods in terms of median ranking(MedR) and recall rate at top K(R@K), providing a powerful solution for cross-modal retrieval tasks. [ABSTRACT FROM AUTHOR]

Autonomous vehicle can calculate the movement track of surrounding vehicles according to the track prediction algorithm, and make response to reduce driving risk, while the traditional track prediction model will produce large errors in the case of long-term series prediction. To address this issue, this paper proposed a trajectory prediction model based on the Informer algorithm, and used the publicly available dataset NGSIM to conduct experimental analysison. Firstly, it filtered the original data by using symmetric exponential moving average method(sEMA), and added a joint normalization layer to the original Informer encoder to extract features from different vehicles, reducing the motion error between different vehicles, and improving the prediction accuracy by considering the speed information of the vehicle itself and the vehicle movement information of the surrounding environment. Finally, it got the vehicle trajectory distribution at the future time through the decoder. The results show that the trajectory prediction error of the model is less than 0.5 m. Through the analysis of MAE and MSE results of trajectory prediction, when the prediction time exceeds 0.3 s, the trajectory prediction effect of Informer model is obviously better than other algorithms, which verifies the effectiveness of the model and algorithm. [ABSTRACT FROM AUTHOR]

Most of the existing user profile methods lack different granularity text information representation, and there is a noise problem in the feature extraction stage, resulting in the inaccurate construction of the profile. To address these issues, this paper proposed a user profile method based on multi-granularity information fusion, called UP-MGIF. Firstly, it integrated the character-level granularity and the word-level granularity representation vectors in the embedding layer to expand feature content. Secondly, based on the improved bi-directional gated recurrent unit network(Bi-GRU), it designed a hybrid feature extraction model called Bi-GRU-DAE-Attention by combining denoising autoencoder (DAE) and attention mechanism to achieve feature denoising and semantic enhancement. Finally, it input the robust feature vectors into the classifier to achieve user profile generation. Experiments show that the user profile generation method achieves higher classification accuracy than other baseline methods on two profile datasets in the medical and Internet domains, and validate the effectiveness of each module through ablation experiments. [ABSTRACT FROM AUTHOR]

[Objectives]Aiming at the difficulty of identifying pests and diseases in the real environment of bergamot in the field, this paper proposed a method for detecting pests and diseases of bergamot based on improved SSD(single shot MultiBox detector)algorithm—SSD-Res50-3C algorithm. [Methods]The backbone network partially replaced the original VGG16 network with the ResNet50 network, and enhanced the model's ability to extract the characteristics of pests and diseases of bergamot in the real background of the field. A lightweight and efficient feature fusion module was added before predicting the feature layer to improve the multi-scale feature fusion capability of the SSD algorithm, and further improved the anti-interference ability of the SSD algorithm in the real background of the field. [Results]The mean average precision of SSD-Res50-3C algorithm was 92.86%, which was 6.61% higher than that of the original SSD algorithm, and the FPS(frames per second)reached 64.1. Compared with YOLO v3, YOLO v4, YOLO v5x6, Faster R-CNN, and EfficientDet-D3 models, the mean average precision of SSD-Res50-3C algorithm was 6.41%, 2.01%, 0.79%, 0.58%, and 5.10%, respectively, and FPS was 16.20, 40.28, 24.40, 36.20, and 54.84, respectively. [Conclusions]The pests and diseases detection method of bergamot based on the improved SSD algorithm proposed in this paper could weaken the interference information of the real environment in the field, accurately identify the target of pests and diseases of bergamot in the real environment of the field, and provide a new idea for the detection of pests and diseases of bergamot in the real environment of the field. [ABSTRACT FROM AUTHOR]

Aiming at the issue of insufficient utilization of temporal information, speaker information, and multi-modal information in existing conversational emotion recognition methods, this paper proposed a multi-modal temporal-aware DAG model(MTDAG). The designed temporal-aware unit optimized the discourse weight setting in chronological order and collected historical emotional cues to achieve more effective utilization of temporal and historical information based on recency effect. The context and speaker information fusion module achieved the full utilization of discourse information by extracting the deep joint information of contextual context and speaker self-context. By setting the DAG subgraphs to capture multi-modal information and constrain the interaction direction, the model achieved full utilization of multi-modal information while reducing the introduction of noise. Extensive experiments conducted on two benchmark datasets, IEMOCAP and MELD, demonstrate that the model exhibits excellent performance in emotion recognition. [ABSTRACT FROM AUTHOR]

In the intelligent transformation of the mechanical manufacturing, a large amount of spare parts models is inevitably generated, which brings huge challenges to the efficient retrieval of data. Considering the user-friendly and lightweight characteristics of design sketches, this paper conducted model retrieval of mechanical parts based on design sketches by constructing a deep cross-domain representation model. Aiming at the problem of cross-modal information association between sketches and 3D models, this paper proposed a feature joint learning method, which controlled the differences within and between classes of retrieved models. By this method, feature descriptors could acquire single-domain features as well as fuse the cross-domain information, and thus, the method established a consistent association representation of cross-modal data in a co-embedding space. Finally, it constructed the index table by using hash coding to realize fast retrieval of massive data. The experimental results on the parts data show that the proposed retrieval method based on the design sketch can not only achieve the most accurate retrieval results, but also have higher retrieval efficiency among the comparison methods. The method not only improves the accuracy of cross-modal spare parts information retrieval, but also improves the efficiency of data management, thereby indirectly improving the efficiency and convenience of product design. The related systems have been applied in some enterprises and have received good feedback. [ABSTRACT FROM AUTHOR]

In the context of the rapid development of network information, the demand of different music lovers for music information retrieval is also increasing, and music classification has become an important research subject. This paper proposes a fast classification method of DUPSO-DSVM folk songs, which combines dissipative uniform particle swarm optimization (DUPSO) with distance sorted SVM (DSVM). This method uses DUPSO algorithm to optimize the penalty coefficient C and kernel function parameter g of SVM, and uses DSVM algorithm to optimize the parameter optimization time of DUPSO algorithm. The experimental results show that, DUPSO-SVM algorithm has a classification accuracy of 84%. After using DUPSO-DSVM algorithm, the training time of the algorithm only accounts for 26.26% of the unused DUPSO-DSVM algorithm, but it still maintains a high classification accuracy. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the siamese neural network is sensitive to position, complex background and intra-class differences due to the use of image-level feature metrics, this paper proposed a Dual Metric Siamese Neural Network (DM-SiameseNet) . DM-SiameseNet used image-level features and local features (local descriptors) to jointly represent each image, then learned feature maps based on two different levels of similarity measures, and finally used an adaptive fusion strategy to adaptively integrate two different measurement result represented by the level feature. Experimental results showed that the accuracy of the improved model was increased by 5.04% and 9.66%respectively, and was higher than the measurement methods that only use image-level feature representation or local descriptor representation on miniImageNet, TieredImageNet, Stanford Dogs, Stanford Cars and CUB-200 datasets. The experimental results prove that the proposed model not only considers the global features of the image, but also captures more effective local feature information in the image, which improves the generalization ability of the model. [ABSTRACT FROM AUTHOR]

There are many fields choose to fuse LiDAR point cloud and camera images for applying. The accurate extrinsic calibration is a prerequisite for fusing their information. The point cloud feature extraction is a key step in extrinsic calibration. However, the low resolution and low quality of point clouds can affect the accuracy of calibration results. To address these problems, this paper proposed a LiDAR and camera extrinsic calibration method based on edge correlation point cloud. Firstly, it extracted the edge correlation point cloud of the calibration plate by using dual echoes. Then, it obtained the corner points from the edge correlation point cloud by the optimization method, where the corner points were compatible with the actual calibrated plate size. Finally, it matched the corner points in the point cloud with corner points in the image, and solved the extrinsic parameter between the LiDAR and the camera by the multi-point perspective method. The experimental results show that the reprojection error of the method is 1. 602 px, which is lower than that of comparison methods, verifying the effectiveness and accuracy of the method. [ABSTRACT FROM AUTHOR]

Miao nationality is one of the oldest nationalities in the history of China. Miao costumes are a distinctive and colorful ethnic culture formed in the long historical process. The colorful Miao costume patterns highly summarize the pursuit of the national spirit, and the styles, colors and textures are the unique style characteristics of the costume patterns. Therefore, it is of great academic significance and application value for the digital protection and inheritance of Miao costume culture to efficiently and accurately segment minority costume patterns. At present, some scholars have carried out researches on minority costume images, but most of them are based on fuzzy C-means clustering algorithm and active contour model, and few of them are based on the deep learning algorithm for minority costume image segmentation. The traditional image segmentation algorithm used to segment the Miao costume patterns leads to the loss of some characteristics of spatial information and low efficiency and accuracy of image segmentation. In order to promote the digital protection of minority costume images and the inheritance of ethnic culture, aiming at the problems of large color differences, diversified styles and textures of Miao costume patterns, this paper proposes a Miao costume pattern segmentation model based on the attention mechanism. FCN is used as the main structure, and the feature weight of the input image is adjusted by the attention mechanism to improve the segmentation performance, so that the model can better associate the features of interest from the local level to the global level. Firstly, data enhancement is used to preprocess the image data to improve the generalization ability and robustness of the model and avoid over-fitting. Then, the feature extraction of Miao costume patterns is carried out by using the full convolutional network model fused with attention module (CBAM) to reduce the loss of spatial information, so as to effectively improve the segmentation accuracy of the model and reduce the loss rate. The model has a total of nine network layers and uses convolution, Batch Normalization (BN), CBAM, add, pooling, and concat operations. The convolution operation is used to extract image features and double the number of channels. BN operation is mainly used to normalize the training image to prevent the model from over-fitting. CBAM layers make the model pay more attention to foreground pixels while learning network weights. The add layer increases the amount of information under image features. The pooling operation performs down-sampling operation on the image to reduce the image size by two times, retain the main features while reducing the number of parameters, and improve the model generalization ability. Concat operation is used for skip connection between corresponding feature layers, so that the model can extract more rich feature information. Except Sigmoid activation function for the last convolutional layer, ReLU function is used for other layers. Analyzing the visual characteristics of ethnic costume from the perspective of deep learning and computer vision is not only convenient for researchers to store and retrieve ethnic costume images, but also conducive to the digital protection of ethnic costume images and the inheritance of ethnic culture. Finally, the experimental results on the Miao costume pattern data set show that compared with the traditional U-Net and FCN models, the IoU increases by 14.79% and 18.21%, respectively, and the Dice coefficient increases by 11.03% and 13.95%, respectively using less than half of the training parameters. Therefore, this paper provides an effective and feasible method for the research of Miao costume pattern segmentation algorithm. In the future, in-depth research regarding the mapping relationship between costume style feature points and image feature points after image segmentation will be conducted. On a certain basis, the research results play a role in the development and protection of minority costume culture, and also provide certain reference for minority costume image segmentation algorithm research. [ABSTRACT FROM AUTHOR]

The production and sales of high-quality fruits are inseparable from fruit quality testing, while traditional fruit quality testing methods have low precision, high cost, poor timeliness, and strong destructiveness. With the continuous advancement of science and technology in recent years, low-cost and high-efficiency non-destructive testing technology for fruit quality has been developed rapidly. Among them, hyperspectral imaging technology has gradually become a research hotspot. This paper summarizes the technical principle, application and development status of this technology in the field of fruit quality, and discusses its performance potential, existing problems, development trend and application prospects in the field of non-destructive testing of fruit quality. On the whole, hyperspectral imaging technology can non-destructively and efficiently realize the effective detection of various fruits and various quality indicators, such as maturity, sugar content, acidity, red index, etc.; Limited by hardware technology, its development focuses on data mining, that is, in the case of limited hardware development, accurate analysis results can be obtained through continuously updated and optimized targeted algorithms; on the other hand, expensive equipment, complex data processing, and poor model universality are the main problems that this technology needs to be further optimized and improved; Its future development will be based on efficient data processing of cloud computing and artificial intelligence, research and development of hyperspectral detection equipment for fruit quality with a wider range of applications, and multi-source comprehensive non-destructive testing. With the continuous development of technology, hyperspectral imaging technology has broad application prospects in non-destructive testing of fruit quality, and will become one of the important means of fruit quality testing in the future. [ABSTRACT FROM AUTHOR]

Federated learning is designed to solve the problem of data fragmentation and data isolation based on privacy protection in distributed machine learning. In the federated learning system, participants collaboratively train a model. Each participant uses local data to train the local model, and uploads the trained local model to the server for aggregation. In the real application environment, the data distribution between nodes is often very different, resulting in the accuracy of federated learning model is low. In order to solve the influence of non-independent identically distributed data on the accuracy of the model, this paper proposed a clustering federated learning framework by using the similarity of data distribution between different nodes. Extensive experiments were conducted on Synthetic, CIFAR-10 and FEMNIST standard datasets. Compared with other federated learning methods, clustering federated learning based on data distribution greatly improves the accuracy of the model and requires less computation. [ABSTRACT FROM AUTHOR]

In image retrieval based on deep hashing, to solve the problems of low feature extraction efficiency in convolutional neural networks (CNN ) and underutilization of feature correlation, this paper proposed a novel method combining sparse difference network and multi-supervised hashing( SDNMSH ), and used it for efficient image retrieval. SDNMSH took pairs of images as training inputs, and guided hash codes learning through an elaborately designed sparse difference convolutional neural network and a supervised hash function. The sparse difference convolutional layer and the vanilla convolutional layer composed the sparse difference convolutional neural network. The sparse difference convolutional layer could quickly extract rich feature information, to achieve efficient feature extraction of the entire network. At the same time, in order to make full use of the pairwise correlation of semantic information and features, so as to promote the feature information extracted by the network to be more effectively transformed into discriminative hash codes, and then to achieve efficient image retrieval by using SDNMSH, this paper adopted a multi-supervised hash( MSH) function and designed an objective function for this purpose. Extensive experimental results on three widely used datasets MNIST,CIFAR-10 and NUS-WIDE show that SDNMSH achieves better retrieval performance, compared with the state-of-the-arts. [ABSTRACT FROM AUTHOR]

Mild cognitive decline is the early stage of Alzheimer's disease, and the feature extraction and classification of mild cognitive decline using EEG signals is an important method for diagnosing mild cognitive decline. In the automatic detection technology of mild cognitive decline based on electroencephalogram artificial intelligence, the existing research only extracted a certain feature in the electroencephalogram signal or simply concatenates multiple features, which caused these methods to fail to well consider the correlation between different features and it would cause the problem of dimensional disaster. This paper proposed a convolutional neural network based automatic detection algorithm for resting state electroencephalogram data of mild cognitive decline. By extracting the power spectrum and brain network features of the electroencephalogram, it fused the two features by matrix operation, and designed a convolutional neural network to classify the fused features. This method achieves a high accuracy rate on the data set collected by a hospital in Shanghai. In addition, by inputting different subsets of the feature set, this method found the few groups of features that contribute the most to mild cognitive decline, thereby it also had a certain interpretability. Experiments on the dataset of this paper, it p roves the advantages of the power brain network for the automatic diagnosis of mild cognitive decline. [ABSTRACT FROM AUTHOR]

【Objective】The advantages of several classifiers were combined to improve the accuracy of crop information extraction from remote sensing images.【Method】The paper took Weiku Oasis as the research area, used the domestic GF-2 data and field survey data, and formulated different classification schemes based on the extracted remote sensing identification features.Five traditional machine learning methods as Mahalanobis distance (MsDC), minimum distance (MDC), maximum likelihood (MLC), neural network (NNC), and support vector machine (SVM) were used to classify the images of the six feature combination schemes.Then the base classifier was selected, and two multi-classifier integration algorithms, the majority voting method and the conservative voting method were applied to finely classify and extract the crops in the study area.【Result】 (i) The additional auxiliary features significantly improved the accuracy of sub-classifiers.Among the five classifiers, except MLC, the other four classifiers achieved the highest accuracy after adding NDVI and texture features. (ii) The most accurate base classifier was NNC-4 (the fourth feature combination scheme of artificial neural network), with OA reaching 83.54% and Kappa coefficient of 0.77. (iii) Compared with the base classifiers, the multi-classifier ensemble method could improve the extraction accuracy of crops in both producer’s accuracy and user’s accuracy.And the conservative voting method was better than the majority voting method, with OA being 85.89% and Kappa coefficient being 0.80. (iv) In the integrated classification results, except that the recognition accuracy of cotton was equal to the optimal base classifier NNC-4, reaching 94.94%, the recognition accuracy of other crops such as interplanted cotton, corn, interplanted corn and walnut orchards was higher than that of NNC-4.Among them, the extraction accuracy of interplanted corn and walnut orchard was better, with the accuracy reaching 86.05% and 79.09% respectively; The extraction of interplanted cotton was poor, only 63.86%; The extraction of corn was the worst, only 12.17%.【Conclusion】In the study, the GF-2 data was applied, and the multi-classifier ensemble method was used to conduct fine extraction research on various crops and planting structures under complex backgrounds, which expanded the direction of crop information extraction and the application field of GF-2 data. [ABSTRACT FROM AUTHOR]

In the process of registering point clouds with low feature recognition, traditional methods based on local feature extraction and matching are usually not accurate, while the accuracy and efficiency of methods based on global feature matching are also hard to guarantee. In response to this problem, this paper proposed an improved local feature matching method. In initial registration, it designed a key point extraction method based on normal vector projection covariance analysis. Then it used fast point feature histogram( FPFH) descriptor to characterize these key points,and defined multiple matching conditions to screen the feature points. Finally, it took the sum of the nearest distance of the corresponding points as the optimization goal for rough matching. In fine registration, this paper used the improved iteration closest point(ICP) algorithm, which took the minimum distance from point to plane as the object of iterative optimization, for accurate registration. Experimental results show that, compared with the other three registration methods, the proposed method can maintain high registration accuracy while reducing registration time. [ABSTRACT FROM AUTHOR]

The sentence level extraction method is insufficient to solve the problem of Chinese event element dispersion. To solve this problem, this paper proposed a document level event extraction method based on context fusion. Firstly, the paper divided the document into paragraphs, and used bidirectional long and short memory network to extract sequence features of paragraphs. Secondly, the method used self-attention mechanism to capture the interaction information of paragraph context. Then the method combined the document sequence features with the interaction information to update the semantic representation. Finally, the method used sequence annotation to extract event elements and match event types. Compared with other event extraction methods on the same Chinese data set, the experimental results show that this method can effectively extract scattered event elements from documents, and improve the extraction performance of the model. [ABSTRACT FROM AUTHOR]

The fuel metering unit (FMU) is one of the core components of an aero-engine, and its performance directly affects the overall safety and reliability of the aero engine. Therefore, the research on simulation modeling and fault diagnosis of FMU is an important part of aero engine health management technology and has great research value. Taking a certain type of fuel metering component as the research object, its simulation model based on AMESim was established in this paper. Considering the uncertainties in the working process of the system, the probability-based method was used to measure the system uncertainty and carry out the uncertainty propagation. The displacement of the metering valve spool and the control current of servo valve were extracted, and the velocity gain curve was established to characterize the overall operating performance of the assembly. Aiming at the uncertainty of the fault feature values, a fault feature evaluation method was proposed based on the receiver operating characteristic curve to quantitatively evaluate the potential of the fault features for fault diagnosis. [ABSTRACT FROM AUTHOR]

In view of the increasing concern on model efficiency in computer vision, this paper proposed several optimization schemes to improve the flame detection models in model efficiency as well as the detection performance.A backbone network (FIRE-Net) was constructed from a multi-convolution combined structure, which can efficiently extract rich flame features from multiple scales.Then an improved weighted bidirectional feature pyramid network (BiFPN-mini) was used to quickly achieve multi-scale feature fusion.In addition, a new attention mechanism (FIRE-Attention) was proposed to make the detector more sensitive to flame characteristics.The above optimizations were combined to develop a new flame detector abbreviated as FIRE-DET,which was then trained on self-built dataset and tested on internet videos.The experimental results showed that the FIRE-DET outperformed mainstream algorithms by its flame recognition accuracy of 97% and frame rate of 85 FPS,thus provides a more common solution to solve the flame detection. [ABSTRACT FROM AUTHOR]

In the large data environment, there are many problems in the parallel deep convolution neural network（DCNN） algorithm, such as excessive data redundancy, slow convolution layer operation and poor convergence of loss function. This paper proposed a parallel deep convolution neural network optimization algorithm based on the Im2 col method. First, the algorithm proposed a parallel feature extraction strategy based on Marr-Hildreth operator to extract target features from data as input of convolution neural network, which can effectively avoid the problem of excessive data redundancy. Secondly, the algorithm designed a parallel model training strategy based on the Im2 col method. The redundant convolution kernel is removed by designing the Mahalanobis distance center value, and the convolution layer operation speed is improved by combining the MapReduce and Im2 col methods. Finally, the algorithm proposed an improved small-batch gradient descent strategy, which eliminates the effect of abnormal data on the batch gradient and solves the problem of poor convergence of the loss function. The experimental results show that IA-PDCNNOA algorithm performs well in deep convolution neural network calculation under large data environment and is suitable for parallel DCNN model training of large datasets. [ABSTRACT FROM AUTHOR]

In this paper, a recognition method is proposed based on the time-frequency domain and PE features of ship radiated noise. The empirical mode decomposition (EMD) method is used to decompose the original signal into multiple Intrinsic modal function (IMF) and screen them combined with the reverse weighted permutation entropy (RWPE). By taking the weighted average instantaneous frequency and weighted permutation entropy (WPE) of effective IMF as inputs the LSTM neural network is used for training. The experimental results show that the recognition rate can reach 99.40%, compared with the ship-single-feature-based recognition method. [ABSTRACT FROM AUTHOR]

Objectives: Few corresponding points can easily affect the calculation of image pose information, increase the difficulty of constructing a regional network in an aerial triangulation solution, so that lead to problems such as image stitching misalignment, incorrect bundle adjustment results or even failure. In order to better complete the matching of unmanned aerial vehicle (UAV) images, this paper proposes a robust UAV image matching algorithm considering log-polar description and position scale distance. Methods: Firstly, a Gaussian multi-scale image collection is established and feature points are extracted. Secondly, the descriptors are constructed using log-polar coordinates, and a descriptor suitable for UAV image characteristics is established. Then, the feature matching is performed by the distance function of position and scale constraints. Finally, the mode seeking and fast sample consensus method are used to eliminate the outliner and complete the extraction of correspondence. Results: The image obtained by four-rotor UAV is used as the data source, and a comparison experiment of image matching with scale invariant feature transform (SIFT) algorithm and synthetic aperture radar-scale invariant feature transform (SARSIFT) algorithm is carried out. The experimental results show that a 210-dimensional log-polar coordinate descriptor is constructed through the gradient location and orientation histogram. The descriptor can better describe the feature points in 10 directions through the circular neighborhood, making the matching results more robust. The position scale Euclidean distance matching function established by integrating factors such as position and scale can better calculate the UAV image matching relationship, and match more correct corresponding points. In terms of the number of correct corresponding points extracted under the same parameter settings, the proposed algorithm is significantly more than the other two algorithms, and in terms of the root mean square error of the matching results, the algorithm in this article is also significantly better than the two compared algorithms. Conclusions: The proposed algorithm can better extract the corresponding points of UAV images. [ABSTRACT FROM AUTHOR]

When traditional convolutional neural networks are used in mineral species identification, due to their large parameters and the limitations of fixed input image resolution, sufficient computing resources and image preprocessing are required, which are difficult to deploy in actual exploration. For this reason, based on the depth separable convolution,combined with the attention mechanism, this paper constructs a mineral intelligent recognition model through dense connection, and this model can train multi-resolution mineral images. Ex perimental results show that the model's memory usage is only 20 Mb, the verification accuracy and the test accuracy are both higher than 90 %, the classification effect is better than the classic convolutional neural network, and it shows excellent ability to distinguish positive and negative samples. These results show that the proposed model h as fewer parameters and low memory footprint which is suitable for portable devices. This model can successfully identify mineral images with different resolutions, which has good generalization and potential application. [ABSTRACT FROM AUTHOR]

To predict aircraft taxiing estimated time of arrival（ETA），reduce conflicts，and improve the efficiency of the airport，this paper uses the Kalman filter algorithm to preprocess historical trajectory data of an airport. In order to measure the distance between trajectory samples， three kinds of features are synthesized for clustering of airport historical trajectory data，including the aircraft taxiing period and the number of surface aircraft. In addition ，we refer to the dynamic time warp（DTW）algorithm to extract the difference features of the trajectory. The Euclidean distance of two sample features is taken as their similarity. Initial clustering center is determined based on the divided difference maximum principle. The K⁃means algorithm is used to cluster samples，and the cluster with the highest matching degree is selected according to the time period of the aircraft to be planned and the number of aircraft operating on the surface. The trajectory sequence of the cluster’s center sample and the static path planned by the tower are combined to predict the aircraft taxiing ETA. By comparing and analyzing the actual trajectory data with the predicted taxiing ETA， the good performance of predicting the aircraft taxiing ETA in this paper is verified. [ABSTRACT FROM AUTHOR]

Aiming at the problem of inaccurate locating of traditional iris locating algorithms, an improved YOLOV3 iris locating model is proposed to improve the accuracy of iris locating and make it better applied to production practice. Using the Densenet-121 model as the feature extraction module, and on the basis of it, the auxiliary network is obtained by copying the backbone network to make it more conducive to the detection of small targets, and the non-local attention mechanism is used to enhance the semantic information of the features obtained by the image. The YOLOV3 model, Daugman model and Wilde model based on DarkNet-53 are used for comparative experiments. The experimental results show that the accuracy of the experimental model in this paper is as high as 97. 1 % in iris locating, which has obvious advantages compared with other iris locating models. [ABSTRACT FROM AUTHOR]

Sitophilus oryzae is a weevil growing on diet of wheat grain. Its timely identification and control is essential to safeguarding wheat production. This paper proposes a computer vision-based method to diagnose its larval development inside wheat grain. After Sitophilus oryzae infects grains, its subsequent development is divided into egg stage, juvenile stage, elder stage, pupal stage and adult stage. We acquired a sequence of micro-CT projection images of the infested grains and then reconstructed the 2D images using the FDK algorithm. The larvae in the images were mapped out using segmentation and morphological method. Overall, we extracted 26 features to characterize a larva and its development, including morphological features, 3D features, invariant moment and texture features. The metamorphosis of Sitophilus oryzae was differentiated based on larval height, larval volume, its cross-sectional area, the minimum rectangle method, surficial area and perimeter of the cross section. The partial features simulated using the annealing algorithm composed of optimal features which were calculated by the fitness function, with the initial temperature T set at 150, drop rate at 0.9 and the end temperature at 1.0. Ten features were determined after 10 optimizations and the associated maximum fitness was 90.214 3%. The penalty factor c and the kernel function parameter g in the support vector machine (SVM) were optimized by the artificial bee colony (ABC) algorithm, in which the initial bee colony size was 20, the times of updates was set to be 50 and the maximum number of iterations was 50. Two parameters were optimized in the range of 0.01-100, and the algorithm was repeated twice to check robustness of the program. We used 250 images to train and test the model. The model correctly identified 97% of the larvae at different developmental stages when the parameters the penalty factor c=96.44, and the kernel function parameter g=0.01. The results showed that the height of Sitophilus oryzae larva had been in increase in the experiment; its volume, cross-sectional area, size of the minimum rectangle, surficial area and perimeter of cross-section had all asymptotically increased up to the pupal stage, followed by a decline after that. In addition, ABC-SVM correctly identified 97 images. The results presented in this paper indicated that computer vision can be used to identify larval development of Sitophilus oryzae in wheat grain. [ABSTRACT FROM AUTHOR]

To improve the correct rate of image classification by convolutional neural network, this paper proposed a multimodel fusion convolutional neural network after research on the network structure. By extracting the output feature vectors of a single model and then fusing them, it obtained the new output feature vectors, and then set up a single classifier to classify the images, and improved the accuracy of the classification. By comparing the classification accuracy of single model and multimodel fusion, the class ification accuracy of multi-model fu sion convolutional neural network was improved. This paper analyzed the weight distribution of the last layer of the convolutional neural network, and found that the weight distribution curve of the same model on different data sets was similar and the weight distribution curve of the network model with better classification effect was more gentle. [ABSTRACT FROM AUTHOR]

Sketch retrieval (SBIR) is an extension of content-based image retrieval (CBIR), which is a flexible and convenient way to retrieve target images. How to minimize the difference between the sketch domain and the image domain is crucial to SBIR. The traditional methods extract the manual fea-tu res to achieve the approxima te conversion bet ween the sketch field and the image field, so as to reduce the domain difference. However, these methods cannot effectively fit the content of the two domains, resulting in low retrieval accuracy. Deep learning methods break through the limitations of traditional methods, which extract high-dimensional features from a large amount of data and have been proved to effectively solve the cross-domain modeling problems. This paper focuses on deep learning-based sketch retrieval methods, and covers several aspects such as the deep feature extraction model, public dataset, coarse-grained and fine-grained retrieval based on deep learning, deep hashing technology, category generalization, etc. Related works are reviewed and commented on. Then, a comparative experiment is conducted. For one hand, three existing public SBIR datasets such as Sketchy, TU-Berlin and QuickDraw are used for suitability evaluation. For the other hand, three latest SBIR deep learning models such as GRLZS model, SEM-PCYC model and SAKE model are selected for performance analysis and comparison. Finally, current challenges and future research trends of SBIR are summarized. [ABSTRACT FROM AUTHOR]

Capsule network emphasizes the encoding of image features' spatial relationship, while its feature extraction module has difficulty in handling complex scenarios. In order to improve the performance of CapsNet, this paper proposed a capsule network with a self-attention feature extraction module ( SA-CapsNet) to solve the above problem. At first, it improved CapsNet by reducing the dimension of the capsule and adding an intermediate layer. Then mapped the SA module to the feature extraction layer of the capsule network to increase feature extraction capability. The results worked on the MNIST, Fashion MNIST, and CIFARlO datasets show that the classification accuracy rates are 99. 67%, 92. 21 %, and 82. 51 %, respectively. Additionally, results demonstrate the effectiveness of this proposed network, and the overall performance has been dramatically improved compared with CapsNet [ABSTRACT FROM AUTHOR]

The traditional curvature calculation method is sensitive to local changes and noise in the discrete domain, which makes the corner detection accuracy and location deviate. In order to solve the above problems, a multi-scale discrete curvature is proposed to calculate the curvature and detect corners. Firstly, Canny edge detector was used to process the input image to obtain a binary edge image, then the edge contour was extracted from the edge image, the gap was filled along the contour, and T-shaped corners were detected and marked. Secondly, under three different smoothing scales, Gaussian function was used to smooth each plane curve, and then a new curvature measurement method was used to calculate the curvature of each point on each contour after smoothing, and the local maximum point of absolute curvature was taken as the candidate corner point of each scale. Finally, the curvature value of candidate corners was compared with the curvature threshold. The points greater than the curvature threshold were defined as candidate real corners, and the candidate corners that could be detected at three scales were regarded as real corners. The experimental results show that when the algorithm is used to detect the standard corner data laboratory image, the correct corner number is 159, the wrong corner number is 90, the missing corner number is 16, and the localization error is 1.257 2,and that when the standard corner data block image is tested, the detected correct corner number is 46, the wrong corner number is 13, the missing corner number is 1, and the localization error is 1.013 2.Compared with the existing three classical corner detection algorithms, the detection method in this paper has better corner detection performance. [ABSTRACT FROM AUTHOR]

In order to improve the correctness and efficiency of tree species recognition, to slow down the occurrence of overfitting, and to enhance the practicality of tree recognition techniques, this paper proposed a tree recognition method based on an improved convolutional neural network. The approach started with compressing the channel in the Xception framework to further exploit the average pool of global feature mapping, and changing the hybrid attention connection to parallel connection. Next, a randomly selected part of the feature map was normalized and re-entered into the neural network after using the attentional feature map cropping method. Finally, ablation experiment was performed and the accuracy of tree species recognition was up to 98.90% in the tree dataset when the learning rate was 0.1 and the iteration was 50 times. The study showed that the proposed improved convolutional neural network had better recognition effect on tree recognition. And the memory of the convolutional neural network architecture was reduced to 133.9 MB and the time consumed was only 458 ms. Using the improved convolutional neural network not only improved the accuracy of tree recognition, but also reduced the time cost. [ABSTRACT FROM AUTHOR]

The identification of encryption algorithms is the primary task of cryptanalysis. The current identification schemes cover the identification of block ciphers, the identification of stream ciphers, and the identification of hybrid algorithms of sym-metric ciphers and public key ciphers. With the popularization of Chinese national cryptographic algorithms, their security has also attracted much attention. For the national secret algorithm, this paper proposed the SM4 block cipher system identification based on random characteristics, and identified the national secret SM4 algorithm with the main international standard block cipher algorithm. It used the randomness test method to perform feature extraction on the ciphertext to obtain feature vectors. These feature vectors formed the feature space. Finally, it used machine learning algorithms to train and test the feature space. Experimental results show that the recognition rate of SM4 and other block cipher algorithms are over 90%. This work provides new possibilities for cryptanalysis and at the same time increases the diversity of password identification schemes. [ABSTRACT FROM AUTHOR]

Aiming at the problems of low accuracy and poor robustness of existing LiDAR odometry methods in outdoor dynamic road scene, this paper proposed a scheme of odometry and mapping based on 3D LiDAR and MEMS IMU. The scheme was consist of four sequential module, namely data preprocessing module,feature extraction considering dynamic obstacles module, laser odometry module and laser mapping module. By using the KITTI data and real scene data, it carried out the qualitative and quantitative accuracy evaluation of the improved scheme and the current popular LOAM and Lego-LOAM schemes. The test results show that the accuracy of the improved scheme is better than LOAM scheme under the real-time requirements of the system, which is equivalent to Lego-LOAM scheme. [ABSTRACT FROM AUTHOR]

As the bearing fault signal is non-stationary and non-linear in nature, this paper used the wavelet packet decomposition( WPD) and auto-regressive( AR) spectrum estimating method to extract features. In order to improve the accuracy of diagnosis, this paper proposed the deep believe network to train diagnostic models. Firstly, it used the WPD and AR spectrum estimating method to calculate the energy of different signal bands to realize the feature extraction of vibration signals. Then, it used the extracted eigenvalues as input vectors of the deep belief network to conduct model training. Finally, it used the trained model to carry out bearing fault diagnosis. In order to verify the effectiveness of the proposed method, used the rotating bearing data set provided by the Case Western Reserve University in the United States, the algorithm was compared with three fault diagnosis methods. Experimental results show that the proposed method has better diagnostic performance. [ABSTRACT FROM AUTHOR]

This paper introduced the t-SNE.a manifold learning algorithm.into the field of bionic olfaction,and proposed a method of odor classification and identification using t-SNE( t-distributed stochastic neighbor embedding) +LDA( linear discriminant analysis) technique. Odorant characteristic data were collected from PEN3 electronic nose. Then the method reduced these nonlinear and high-dimensional odorant response data to low-dimensional space by using t-SNE. Finally.it used LDA for classification and recognition in the low dimensional data. This paper implemented comparative experiments (t-SNE, PCA + LDA and t-SNE + LDA) of the classification and identification for five different ingredient textile material. The result shows that t-SNE + LDA has higher ability of distinguishing and recognizing common textile ingredient materials and according to the output t-SNE + LDA has smaller within-class scatter and larger between-class scatter. Consequently,t-SNE + LDA is supposed to be a new method for odor classification and identification in bionic olfaction. [ABSTRACT FROM AUTHOR]

Aiming at the shortcomings of the feature extraction method in the traditional underground target recognition algorithm, the convolutional neural network(CNN) in deep learning can automatically extract features from the data, but the classifier that comes with CNN can not solve nolinear classification problem well. Because SVM has good generalization classification ability, a CNN-SVM based underground target shape recognition method is proposed. In this paper, firstly, the method is used to identify underground circular and rectangular targets in the case of smooth surface. Then increasing the difficulty of the scene, the same method is used to recognize underground target shape under rough ground conditions. Compared with the traditional artificially designed feature classification method. The experimental results show that the algorithm uses the features extracted automatically by CNN, combined with SVM to improve the generalization ability and classification accuracy of CNN, and has higher underground targets recognition precision in both scenarios. [ABSTRACT FROM AUTHOR]

LGS algorithm extracts information from far pixels. It assigns weights without considering distance between surrounding pixels and center pixel. Thus, this paper proposed WCLGS. The algorithm defined a hybrid feature extract strategy. It constructed graph structure from four directions of central pixel. The structure caught symmetric and asymmetric information in vertical direction and diagonal direction respectively. WCLGS gave a larger weight to edges close to central pixel, and a smaller weight to edges far from central pixel. It paid close attention to differences of near neighbor elements and center pixel by extracting closer pixel information and reasonable weighting strategy. Information extracted on both sides of center point was more uniform and sufficient. Compared with existing local graph structure algorithms, WCLGS has better recognition rate and performance in ORL, AR and HD infrared face databases. [ABSTRACT FROM AUTHOR]

Predicting the future activity location and trajectory of residents can provide essential information for smart urban management such as epidemic control, traffic facilitation, public security, etc. However, the current personal location prediction methods generally focus on the mining of individual’s historical travel patterns, and seldom consider the feature of different travel stay points. This paper aims to propose a location prediction model utilizing stay point feature extraction. The model firstly constructs the historical trajectory links based on trajectory data, performs the location discovery rules to transform historical trajec⁃ tory links into stay point links and clusters the stay points to form clustering links. Secondly, the model ex⁃ tracts the feature information (entry time, departure time, weather and land use) from different stay points and extracts the space feature from clustering links. Finally, the cluster links with feature information is in⁃ troduced into long short ⁃ term memory (LSTM) network for customization to implement the personal loca⁃ tion prediction capability. By using a 23⁃day trajectory location data of more than 3 million volunteer users in Shenzhen city, China. The results show that the location prediction F⁃score of our proposed model is bet⁃ ter than variable order Markov model (about 5.5% performance gains) and the traditional N⁃order Markov model (about 7% performance gains). The model also introduces approximately 6.6% performance gains by utilizing the temporal and weather features of stay points. The model shows the capability of utilizing travel stay point feature for personal next location prediction. [ABSTRACT FROM AUTHOR]

The anti-jamming performance of radar is an important indicator to measure the pros and cons of a radar, which directly determines the performance of radar combat. Common anti-interference measures include sidelobe cancellation, pulse compression, moving target detection, constant false alarm processing. In this paper, a LASSO-based impulse compression anti-jamming measure is proposed. The method use the characteristics of sparsity of LASSO regression, and combines radar echo signals to set matching dictionary. Then, the data set is constructed by using redundant predictors. The LASSO model is constructed by cross validation, and predictors are identified to achieve the target detection. Compared with the pulse compression method, these simulation results show that the LASSO algorithm can obtain better target resolution without considering the influence of side lobes, and the target detection effect is better under the condition of smaller SNR. [ABSTRACT FROM AUTHOR]

Weed identification was the key to the site-specific weed management in the field. The machine vision method was adopted to realize automatic and rapid detection of weeds. This paper selected 6 weed species in paddy fields, including Alternanthera philoxeroides, Eclipta prostrata, Ludwigia adscendens, Sagittaria trifolia, Echinochloa crus-galli, and Leptochloa chinensis, which were captured in early growth stages with natural background and variable illumination. A total of 928 images were taken. The Alternanthera philoxeroides, Eclipta prostrata, and Ludwigia adscendens were dicotyledonous weeds which had large heart-shaped opposite leaves, and the other 3 weed species were monocotyledonous weeds which had narrow leaves. The image was 640×480 pixels and only a single seedling of weed was in the scene, and the acquisition format was color images of RGB (red, green, blue). The component with 1.1G-R was applied to gray level transformation of original RGB images. The OTSU adaptive segmentation method was adopted to realize the image segmentation of grayscale image. The morphological operation was used to fill vacancies in weed images. The noises and small target were eliminated based on area-reconstruction operator. The background was removed by masking algorithm between binary image and original RGB images. The 101-dimensional features were extracted from the foreground image of weed, including color, shape and texture feature. The color feature was composed of the first, second and third moments, the shape feature was composed of geometric features and improved moment invariant features, and the texture feature was composed of gray level co-occurrence matrix and local binary patterns (LBP) feature. The weighting matrix of color, shape and texture feature would be the input parameter after unitary processing. A three-step method for model updating consisting of model structure tuning, model parameter updating and model validation was presented in this article. Firstly, the deep belief networks (DBNs) of double hidden layers and single hidden layer were established. Secondly, the influence of the 3 types of constant, rising and descending nodes of double hidden layers in DBN was analyzed. The experimental result showed that the descending nodes of double hidden layers in DBN could learn the distributed characteristics of the original characteristic data better than the other node types of double hidden layers. In addition, the nodes in double hidden layers selected in different proportions of 2:1, 4:1 and 6:1 were analyzed. Finally, the testing optimization parameters of double hidden layers and single hidden layer were obtained by experiment. The recognition rate of double hidden layers of DBN was 83.55% when the number of nodes stood at 101-210-55-6, and the recognition rate of single hidden layer of DBN was 91.13% when the number of nodes stood at 101-200-6. The DBN structure of single hidden layer was better able to excavate the distribution rule of weed features than DBN with double hidden layer. The single color, shape, texture and fusion feature were used to construct 3 types of weed classification models, which were support vector machine (SVM), BP (back propagation) neural network and DBN. In the experiment, the recogniton accuracy of DBN model with single color and shape feature was lower than that of the SVM and BP neural network model. The dimensions of color and shape feature were relatively small, which could not reflect the advantage of characteristic representation with DBN. On the other hand, the recognition of DBN model with single texture and fusion feature was more accurate than that of the SVM and BP neural network model, and the recognition accuracy of DBN model reached 88.78% and 91.13% with single texture and fusion feature, respectively. The results demonstrate that the method put forward in the paper can improve the classification accuracy of weeds with the complex background and variable illumination in paddy fields. [ABSTRACT FROM AUTHOR]

In agricultural production, image mosaic plays an important role for a panorama view when images are collected by on-board real-time sensor. Most of the agricultural operation is outside, and traditional method of image mosaic based on SIFT (scale-invariant feature transform) algorithm is affected by uneven illumination or wind and some other factors, so image after mosaic presents dislocation or absence of information and other mistakes. It is difficult to meet the requirements of the reliability of agricultural vehicle applications by using image feature element method for image mosaic. Aiming at this problem, the paper proposes a new method of image mosaic based on the color and depth dual information feature source from Kinect. Firstly, depth information and color images are collected by Kinect sensor from 3 different angels. Kinect sensor is fixed on the slider, and when the motion slider moves at a constant speed of 0.5 m/s, the Kinect moves at the same speed. The Kinect is invoked to obtain color image and depth information and save them every 0.6 s through MATLAB. Three consecutive time points are selected in order, and the color images of 3 angles are taken as the mosaic images. Secondly, SIFT algorithm is used to get feature points from color images. SIFT algorithm can extract the feature points which have invariance for illumination, affine and projection transformation. It is helpful to reduce the number of feature points matching and improve the speed and accuracy of feature point matching. Thirdly, feature points matches are gotten by similarity measure, and the Euclidean distance with high efficiency is used as the similarity measure in the 2 pictures in this paper. A key point in an image is gotten, and the closest 2 key points in another image are found. If the ratio of the nearest distance to the next closest distance is less than a certain threshold, then the pair of matching points are received. But some wrong matches exist with this method. Too many mismatches may result in mosaic errors. Therefore, a solution is needed to remove mismatches to improve the accuracy of the matches. From the nature of Kinect, if Kinect moves horizontally, the depth data of a fixed point is the same. Based on this characteristic, some mismatches would be removed. If the depth data of these 2 feature points are the same, the match is retained, and otherwise they would be removed. As a result, the accuracy of matches is improved. Next, by RANSAC (random sample consensus) algorithm, projection transformation matrix can be found. The RANSAC algorithm uses the least possible points to estimate the model and then as far as possible to expand scope of the influence of the model. The projection transformation matrix is more accurate than traditional image mosaic method on account of the removing of mismatches. At last, through the best suture line algorithm, image fusion is relatively smooth. From indoor and outdoor test, the mosaic method based on color and depth dual information feature source has obvious advantages, and it can effectively overcome the influence of light, wind and other environmental factors and avoid mosaic errors such as the loss of image and the difference of brightness. In the indoor test, the mosaic method of this article takes 9.70 s, the accuracy of matches is 92.9%, while traditional method based on SIFT algorithm takes 13.04 s, the accuracy of matches is 88.1%. In the outdoor test, the mosaic method of this article takes 71.15 s, the accuracy of matches is 99.1%, while traditional method based on SIFT algorithm takes 77.67 s, the accuracy of matches is 92.1%. So the mosaic method in this article takes less time than the traditional method based on SIFT algorithm. The data of mosaic accuracy show that the average matching accuracy of the method in this article is 96.0%, and the average accuracy is 5.9% higher than the traditional image mosaic method based on SIFT. So, this method can be further applied in other occasions of image mosaic. It can realize precise spraying of drug fertilizers and the control of pests and diseases based on information collected by Kinect. [ABSTRACT FROM AUTHOR]

This paper designed and implemented the novel interactive solutions based on the touch screen of the smartphone and the built-in sensor considering the interaction of images as an information carrier's demanding to the environments. First, gesture information were acquired through smartphone built-in MEMS sensors and touch screens. Then the gestures information (angular velocity, acceleration ,touch screen data) were extracted in real time. The kinetic feature of gestures were analyzed. Meanwhile, the multivariate decision trees classifier was used to classify and identify gestures. Finally, this paper provided a prototype system. The experimental results show that the proposed method can meet the requirements of real-time human-computer interaction. [ABSTRACT FROM AUTHOR]

Knowledge graph is a useful tool when introducing it into the recommendation system as auxiliary information. It can effectively enhance the learning ability of the recommendation system, improving the system' s accuracy and user' s satisfaction. Aiming at the problem of the preference propagation on the knowledge graph, this paper proposed an entity recommendation model based on the user preference propagation of the knowledge graph. This model took the transmission intensity into consideration, while propagated the preference at the same time, thus improved the final effect of recommendation. It controlled the propagation intensity of user's preference on the knowledge graph by extracting the basic characteristics of different specific attributes, and iteratively calculated the historical preference data of each user to obtain the preference propagation model of user-item pair. Later, employing the sorting learning algorithm to get the top N recommendations. In the end, comparison experiments on three different kinds of datasets verified the effectiveness of the proposed model. This study shows that controlling the propagation intensity during the propagating process can significantly improve the accuracy rate, recall rate,as well as the F, value of the recommendation system, and this method also has strong flexibility and interpretability. [ABSTRACT FROM AUTHOR]

At present, most intrusion detection algorithm cannot achieve a good balance between intrusion detection rate and false positive rate, in order to effectively avoid such problems, this paper proposed an intrusion detection method based on ADEN. The method first initialized the parameters of the encoder part in the ADEN model by training the deep belief network, and initialized the parameters of the decoder part by using the normal distribution. Then it tuned the parameters of the asymmetric deep belief network model by calculating the reconstruction error, so that the model can obtain the optimal low-dimensional representation of the original data. Finally, it used the data obtained by the encoder as input data of the classifier and detected. The ADEN model can extract features that are more conducive to classification and save more test time in the model initialization phase. The experimental results show that the method can achieve better detection performance and achieve better detection accuracy for small categories of samples. [ABSTRACT FROM AUTHOR]

Face recognition has a wide range of applications, but it is vulnerable to spoofing attacks that affect security. How to design a method with high detection accuracy, strong generalization ability, and satisfying real-time requirements is the focus of current research. This paper divided the existing methods of face anti-spoofing into methods based on hand-crafted descriptor, deep learning and fusion strategy, and introduced the basic ideas, implementation steps and advantages and disadvantages of typical algorithms. Finally, it collated and explained the published databases of face anti-spoofing, summarized the development trend of face anti-spoofing and the problems that still further needed to be solved, which could provide reference for the future research of face anti-spoofing. [ABSTRACT FROM AUTHOR]

In practice, mechanical equipments usually working with the variable speed and load, and the vibration signal of the equipments is nonlinear and nonstationary. The traditional fault diagnosis methods are prone to misdiagnosis or missed diagnosis. In order to solve the problem of feature extraction and intelligent diagnosis of mechanical fault vibration signal under variable working conditions, a fault diagnosis method combining optimized Variational Mode Decomposition (VMD) and Deep Transfer Learning(DTL) was proposed in this paper. First, Multiple Population Differential Evolution (MPDE) algorithm and envelope entropy fitness function were used to optimize VMD to solve the problem that the decomposition number k and penalty factor α were difficult to be determined adaptively. Second, the intrinsic mode functions of VMD decomposition were reconstructed according to the average kurtosis criterion. Continuous wavelet transform was used to process the reconstructed signal, and the time-frequency characteristics of the reconstructed signal were obtained. Third, combining the Residual Network (ResNet) with Transfer Learning (TL) model, the edge distribution adaptive method was used to reduce the difference between the source domain data set and the target domain data set of mechanical fault signal, and a deep transfer learning model for mechanical fault diagnosis under variable working conditions was constructed. Finally, the MPDE-VMD+DTL method was compared with the traditional BP neural network, ResNet convolution neural network and transfer component analysis (TCA) in different rolling bearing experimental datasets which contained CWRU, XJTU-SY, IMS and MCVN dataset. The results showed that the accuracy of fault diagnosis of MPDE-VMD+DTL method was 84.36%, and that of the BP neural network, ResNet and TCA were 23.60%, 71.63% and 19.68% respectively. MPDE-VMD+DTL method realized the end-to-end mechanical fault intelligent diagnosis under different working conditions, and had good generalization ability and robustness. [ABSTRACT FROM AUTHOR]

Deep learning is hard to train with industrial product samples due to their features are non-obvious and amount is extremely rare. This paper proposed a neighboring difference filtering generative adversarial network ( NDF-GAN) _The combination of NDF-GAN extracted more features from real data and generated more samples, which could augment the real data. Experimental results reveal that, the proposed method can effectively provide more new samples to train the classifier and improve classification performance. In conclusion,NDF-GAN can augment industrial product samples . [ABSTRACT FROM AUTHOR]

BF (bilateral filtering) has been widely considered to be a simple and effective way for extracting HSI (hyperspectral image) features. The algorithm limits the influence of non ⁃ structural similar pixels on target pixel by weighting spatial proximity and pixels similarity. However, non⁃structral similar pixels with a close spatial distance will be assigned larger weights, thereby reducing the effect of weighted limit. Therefore, this paper proposed a COBF (classified optimization BF), it selects the pixels with the most similar category structure from neighbor pixel sets to form a new template, ensuring the neighbor pixels in the new template that applied to the weight distribution as similar as possible in order to improve the features extract result. The COBF algorithm has been successfully applied to the feature extraction of several real HSIs. In order to verify the effectiveness of the proposed algorithm, SVM (support vector machine) was used to classify the HSI features that were extracted by COBF. The experimental results show that the overall accuracy is high when the number of training samples is only 10. The overall accuracies of Indian Pines, Salinas and PaviaU are 83.8%, 96.0% and 90.6%, respectively. [ABSTRACT FROM AUTHOR]

Design structural matrix (DSM) has become a modeling and analytical tool for complex systems in the researches and practices of many areas. However, building DSM faces great difficulties, because the decomposition of each product and the different interpretation of the structural relationship are difficult to build in a standard model. This makes it difficult to realize the rapid generation of DSM and shorten its product design cycle. This paper introduces a new automatic DSM generation system based on CAD model. Firstly, the mates feature information of the top-level component in the structural feature tree of the CAD model in the SolidWorks platform is extracted by SolidWorks API technology. The extracted information is then arranged in a certain order and stored in the database. Secondly, the geometric relationship between the assembled components is analyzed in order to evaluate the degree of the influence of various types of mates on the connection relationship between the components. Thus, the corresponding rules of analysis and comparison are set up. Fin ally, the design of the automatic DSM generation system was successfully accomplished in Visual Basic. Meanwhile, some CAD models are used as examples to verify the feasibility and reliability of the developed system. [ABSTRACT FROM AUTHOR]