Search

In view of the problems of data sparsity and the diversity in academic paper recom-mender systems,based on CONVNCF, this paper proposed an algorithm of convolution with word and heterogeneous information network for academic paper recommendation ( WN -APR) . Firstly, WN -APR algorithm learned user and paper' s diverse features from different semantics to alleviate the sparsity problem. Then it designed an outer product fusing way to seamlessly combine user features with paper features. Replacing of 2D CNN, this algorithm applied 3 D convolution to mine the influence of different features on the performance. Finally, it modified the BPR loss function to enhance diversity in recommendations. Experimental results on CiteULike-a and CiteULike-t datasets show that WN-APR improves the performance of accuracy and diversity over the baseline models. [ABSTRACT FROM AUTHOR]

Objectives: The quality of network structure is the key to obtain excellent classification performance. Most of existing deep models are designed by the trial-and-error method. When the same model processes different hyperspectral images (HSIs), different network hyperparameters need to be set artificially to adapt to the data characteristics of different images, greatly increasing the difficulty of network design. Aiming at the problem of deep learning model design in hyperspectral image classification, this paper proposes an automatic network structure search method for HSI classification. Methods: In the proposed method, the differentiable structure search technology is first used to search the network structure on the source HSI data sets, then the deep network model is constructed by stacking cells, and finally the classification performance is evaluated on the target HSIs. It should be pointed out that, the proposed method only conducts one search on the source HSI data sets, and the obtained deep model can be applied to other target HSI classification tasks, which can effectively improve the utilization rate of the model. To improve the generalization ability and classification accuracy of the model, multi-source and multi-resolution HSIs are employed to construct the precollected data set, and the partial channel connection operation is introduced to further improve the search efficiency. Results: Three HSIs inculding Houston, Chikusei and Pavia Center are selected as source data. Four HSIs including University of Pavia, Indian Pines, Salinas and Houston 2018 are selected as the target HSIs. The source data is used to determine the network model and the target HSIs are used to evaluate the classification performance. Experimental results show that the proposed method can automatically search out a universal deep network model suitable for HSI classification task, and this model can achieve better classification performance than the conventional deep learning models. The overall classification accuracies of University of Pavia, Indian Pines, Salinas and Houston 2018 are 98.15%, 98.74%, 97.30% and 74.47%, respectively. Conclusions: Compared with other deep models, the model in this paper is automatically determined by differentiable architecture search algorithm according to the data characteristics of HSIs, effectively improving the classification accuracy of target HSIs while avoiding complex network design. Extensive experiments verify the applicability and effectiveness of the proposed method in HSI classification. [ABSTRACT FROM AUTHOR]

In order to alleviate the inherent information differences between different user social spaces and interest spaces in recommendation systems and the problem of ignoring high-order neighbors, this paper proposed AGCRSR. Firstly, the algorithm used a mapping matrix in the embedding layer to convert the initial feature vectors into adaptive embedding. Secondly, it intro- duced an attention mechanism to aggregate different aspects of user embeddings, and used a graph convolutional network to li- nearly learn the potential representations of users and items. Finally, it used the adaptive module to aggregate user representations and predict the final recommendation results of users for the project using the inner product function. This paper conducted comparative experiments on the LastFM and Ciao datasets and compared with other baseline algorithms. The experimental results show that the recommendation performance of the AGCRSR is significantly improved compared to other algorithms. [ABSTRACT FROM AUTHOR]

Since the objects in remote sensing images have the characteristics of arbitrary direction, dense distribution and large scale differences, object detection in remote sensing images has become a challenging problem. Aiming at this problem, this paper systematically reviewed the work related to rotating object detection in deep learning remote sensing images in recent three years. Firstly, this paper introduced the representation method and characteristics of rotated bounding box. Then, it analyzed the existing methods of rotating object detection in remote sensing images from four aspects: the feature extraction network, the generation of rotating anchor and candidate bounding box, the label allocation and sampling strategy, and the loss function. Next, it introduced the commonly used remote sensing image datasets for rotated object detection, and compared the performance of different algorithms. Finally, this paper prospected rotating object detection in remote sensing images. [ABSTRACT FROM AUTHOR]

To improve the problem that existing stereo matching algorithms have difficulty in maintaining a good balance between higher parallax estimation accuracy and faster model inference speed, this paper proposed an efficient and accurate multi-layer cascaded recurrent stereo-matching network. Firstly, this paper designed a multilayer network to introduce position encoding and self-attention mechanisms on the higher resolution feature maps, then updated the disparity values using the disparity refinement strategies of hierarchical recurrent refinement, cascaded refinement, and recurrent refinement to recover the detailed information of stereo images better. In addition, this paper improved the method of disparity iterative update by using a light- weight group correlation layer at a low scale and an adaptive group correlation layer at a large scale to update the disparity values, which reduced the computational effort of parallax iterative update and improved the inference speed of the model. The experimental results show that the proposed algorithm has a faster model inference speed than others while achieving a competitive parallax estimation accuracy. [ABSTRACT FROM AUTHOR]

Aiming at the high computational cost of traditional compressed sensing algorithms, this paper proposed a sparse imaging algorithm based on depth expansion model from the perspective of sparse signal recovery. Firstly, it constructed a complex sparse reconstruction network VAMP-Net. In VAMP-Net, it divided complex regressive echo signal into real part and imaginary part as input. Secondly, it substituted the input into the iterative block based on VAMP algorithm. Finally, it carried out the optimal nonlinear sparse transformation by convolutional neural module to obtain the recovered real part and imaginary part signals, and then merged them to obtain the restored target image. As for the proposed algorithm, this paper used artificial data sets to conduct simulation experiments under different target density, iteration times and noise environment, and compared with the traditional iterative shrinkage threshold algorithm and deep learning reconstruction algorithm. Then it used the measured data with different sparsity for field measurement verification. Experimental results show that the image reconstructed by this algorithm has better performance in NMSE, TBR, reconstruction speed and memory usage. [ABSTRACT FROM AUTHOR]

Underwater image quality degradation has seriously hindered the development of marine engineering technology. Aiming at the problems of underwater image color distortion, low contrast and uneven brightness, in order to solve the special underwater imaging environment cause the above degradation problems, and facilitate the subsequent research work based on underwater images, this paper proposed an underwater image enhancement network model based on self-calibrated illumination framework. The network model integrated self-calibrated illumination module on the basis of convolutional neural network, which could brighten images quickly and flexibly. The method established a cascaded lighting learning process with weight sharing in the self-calibrated illumination module to process underwater images. Considering the computational burden of cascaded pattern, the method also constructed a self-calibrated module to realize the convergence of the results of each stage. This self-calibrated module reduced the computational cost greatly and realized the automatic adjustment of underwater image brightness. Finally, this paper analyzed the experimental results qualitatively and quantitatively, and compared eight advanced enhancement algorithms. The results show that the proposed method is obviously superior to other compared algorithms. The results of the proposed method improve the contrast, correct the color, improve the uneven brightness, and enhance the visual effect. The qualitative and quantitative analysis results show the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Congenital heart disease is one of the main causes of infant mortality. Echocardiography is the preferred inspection method, but its complexity and repeatability often affect the quality of screening and preoperative diagnosis. Based on deep learning The artificial intelligence method has recently become a research hotspot in the diagnosis of congenital heart disease by echocardiography. This paper reviews the application progress of deep learning in the diagnosis of pediatric congenital heart disease by echocardiography [ABSTRACT FROM AUTHOR]

Most of the Encryption-then-Compression (ETC) methods can only obtain several limited fixed compression ratios. However, arbitrary encryption compression ratios instead of limited fixed compression ratios are more suitable for practical requirements. To this end, this paper proposed a lossy compression algorithm for encrypted color images with arbitrary compression ratios. It combines the uniform and random downsampling to compress the encrypted images, obtaining arbitrary compression ratios of an encrypted image. The receiver receives the compressed sequence of the encrypted image and obtains the decrypted image by decompression and decryption. The proposed scheme then characterizes the lossy reconstruction of the original image from the decrypted image as an optimization problem with the downsampling compression-based constraint. This scheme designs a convolutional neural network-based image reconstruction model for lossy ETC to resolve this problem, which is denoted the ETC-oriented Reconstruction Network (ETRN). ETRN consists of shallow feature extraction (SFE), residual in residual (RIR), residual content supplementation (RCS), and down-sampling constraint (DC). The experimental simulation results show that the encrypted color image lossy compression algorithm proposed in this paper can obtain excellent compression and reconstruction performance, which fully demonstrates the feasibility and effectiveness of this method. [ABSTRACT FROM AUTHOR]

This paper proposed a self-supervised training method based on inter-frame consistency to solve the problem that the current inverse rendering supervised learning method is challenging to obtain labels and has poor generalization ability. Due to the ill-posed nature of the inverse rendering problem, this paper introduced additional albedo consistency loss and cross-rendering loss to strengthen the self-supervised network, the main idea of which was to enforce inter-frame consistency constraints on image sequences with continuous illumination changes. The method performed image projection and warping between adjacent frames through pose maps and depth maps between image frames. This method established constraints between adjacent frames and used Siamese training to ensure photometric invariance consensus estimate. This paper used a fully convolutional neural network to recover geometry, reflectivity, and illumination from indoor video sequences. The method trained the self-supervised network using a collection of unlabeled consecutive frame images and incorporating a differentiable renderer, making the network learn in a self-supervised manner. Compared with other mainstream methods, quantitative and qualitative experimental results show that the proposed method performs better on multiple benchmarks. [ABSTRACT FROM AUTHOR]

Although high-quality and high-resolution depth maps can significantly improve the performance of computer vision tasks in various natural scenes, the limitations of depth camera hardware make the depth maps captured by consumer-level depth cameras have problems such as low resolution, poor quality, invalid holes, etc. Depth super-resolution reconstruction (DSR) is a kind of technology that can effectively improve the resolution and quality of depth maps, and DSR has become a research hot-spot in the field of computer vision. Firstly, this paper introduced the definition of DSR and the research progress of DSR algorithm at home and abroad in recent years, and then mainly stated and analyzed deep learning DSR reconstruction algorithms. Next, it introduced the depth image quality evaluation criteria. Finally, this paper prospected the application fields of DSR and the challenges as well as the opportunities in the future. [ABSTRACT FROM AUTHOR]

Objective To understand the research hotspots and research trends about convolutional neural networks in the field of oncology imaging diagnosis by analyzing the characteristics of published literature at home and abroad over the past decade. Methods The SCI-E database was used as the data source to retrieve literature about convolutional neural networks in the field of oncology imaging diagnosis published from 2012 to 2022. The distribution characteristics of countries, institutions, journals, co-cited authors, and keywords of the studies were analyzed by CiteSpace software. Results A total of 1088 papers were eventually included, and they were mostly from China, the United States, and India. A total of 39 papers were published by Sun Yat-sen University, the research institution with the highest number of publications. Radiology Nuclear Medicine Medical Imaging was the journal with the highest number of publications. A total of 25 high-frequency keywords and 15 burst keywords were obtained. The formation of 12 author co-citation clusters such as image segmentation and lung nodule, as well as 11 keyword clusters such as automatic segmentation and breast cancer, was observed. Conclusion Current research on convolutional neural networks for oncology imaging diagnosis focuses on oncology segmentation, lung-nodule recognition, assisted diagnosis of breast cancer, and other high-frequency oncology. [ABSTRACT FROM AUTHOR]

The function of protein is crucial for understanding the mechanisms of cellular and biological activities, as well as for studying the mechanisms of diseases. Traditional experimental and sequence alignment methods are insufficient to support large-scale protein functional annotation when in the face of the rapid growth of sequence databases. For this situation, this paper proposed EGnet（Evolutionary Graph Network） model, which utilized the protein pre-training language model ESM2 and One-hot encoding to obtain the protein sequence encoding. The model integrated the coevolutionary information between residues, including PI（Paired Interaction） and SPI（Strong Paired Interaction）, through sequence self-attention and physical calculations. Subsequently, the two types of coevolutionary information and the sequence encoding used in inputs for a multi-layered cascaded graph convolutional network to learn the node features of the sequence encoding and achieve end-to-end protein function prediction. Compared with earlier methods, EGnet achieved better performance on the EC（Enzyme Commission） category labels in the ENZYME database, which reached 0.89 in the F-score and 0.91 in the AUPR. The results indicate that EGnet can achieve good performance by using only a single sequence to predict protein function, providing a rapid and effective method for protein function annotation. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the traditional deep learning fish recognition method has a low accuracy rate and the parameters cannot be determined adaptively during the model training process. This paper proposes an improved ShuffleNet fish identification method based on Particle Swarm Optimization( PSO) and Transfer Learning(TL). The research takes 20 species of fish as the object, uses the particle swarm algorithm to take the model's loss function as the fitness function, optimizes the two hyperparameters of batch size and learning rate, and uses the transfer learning method for training to construct TL-PSO-ShuffleNet model. The research shows that compared with the models of AlexNet, MobileNet, and ShuffleNet, the recognition accuracy rate is increased by 57. 89%, 30. 43% and 23. 28%, respectively. The fish identification method proposed in this paper has the characteristics of high accuracy and self-adaptive parameter setting, which provides a reference for the research on automatic fish identification. [ABSTRACT FROM AUTHOR]

Most of the existing sound event detection researches analyzes from recorded audio, and these models had massive parameters with low efficiency, which is not suitable for real-time detection. This paper proposed an efficient convolutional neural networks model for multi-task and real-time sound event detection. The model considered triggering and detecting task as multi-task learning mission, and its structure combined densely connection, ghost module and SE block. Moreover, this paper proposed a data augmentation method that combined with audio shifting, random cropping and SpecAugment. The experimental results show that the mean prediction accuracies of the model on ESC-10 and Urbansound8K datasets are at least 2% higher than latest baseline models, but also has better robustness as well as less parameters and memory. Additionally, multi-task learning saves computation, and due to the reusing of feature maps, the model can quickly and accurately feedback the results. Compared with the traditional data augmentation methods, the proposed model achieves better performance and robustness. [ABSTRACT FROM AUTHOR]

Generative adversarial network (GAN), as an emerging generative model, has been gradually developed and applied in the fields of image generation, 3D reconstruction, cross-modal conversion, etc. It effectively solves the problem of inefficiency of conventional convolutional neural networks in image-generating tasks and fills the shortage of deep learning in the field of image generation. In order to help subsequent researchers quickly and comprehensively understand GAN, this paper sorted out the improved model of GAN based on the literature in recent years. It firstly introduced the basic principles of GAN from two perspectives of network structure and objective function, then elaborated and summarized various derivative models of GAN from two major perspectives of improvement and application types. Secondly it summarized and analyzed the quality and diversity of generated images from the perspectives of subjective qualitative, objective quantitative and task-specific evaluation. Finally, this paper discussed some core issues and latest research progress of GAN series models in recent years and analyzed the future development trend. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the existing single image super segmentation reconstruction methods are difficult to capture complete and effective information in the image, this paper proposed a joint image-frequency supervised image super-resolution reconstruction algorithm, which aimed to utilize the complementary information between multiple domains, thereby obtaining a more complete image feature representation. Firstly, by analyzing the characteristics of image pixels after converting to frequency domain space, this paper proposed a new frequency domain distance supervision loss according to its complex representation, which effectively applied spectral information to the optimization process of convolutional neural networks. Based on the characterization characteristics of different frequency bands in the domain, this paper constructed the spectral weighting loss on the basis of the distance loss in the frequency domain, and applied it to the two frequency bands of low frequency and high frequency respectively. Finally, combined with the supervision of the image domain, it formed a joint optimization of multiple domains and got good performance. The results on Setl4, BlOO and Kodak show that the PSNR and SSIM of the proposed algorithm reach 33.47 dB and 0.985 9, respectively, and the proposed algorithm achieves the best performance compared with several image super-resolution methods. [ABSTRACT FROM AUTHOR]

Traffic flow prediction is an important and challenging task in building smart city. Accurate forecasting requires consideration of spatio-temporal characteristics consisting of multiple influences such as holiday, similar node, and weather. In order to accurately capture the spatio-temporal characteristics of road network intersections, this paper proposed a prediction model based on graph convolutional neural network, temporal algorithm Prophet and Pearson correlation coefficient to achieve accurate prediction of intersection traffic considering spatial structure, similar nodes, holidays and other influencing factors. Firstly, it introduced pearson correlation coefficient to reduce the influence of similar nodes to improve the temporal algorithm for capturing temporal features. Secondly, it used the graph convolution neural network to capture spatial features; Finally, it determined the fusion weights of the graph convolutional network and the temporal algorithm by linear regression to obtain the results of spatio-temporal fusion prediction. This paper finally extracted the intersection traffic data based on the analysis of Chengdu taxi trajectory data and conducted traffic prediction experiments. The results show that the accuracy of the model proposed in this paper is better than that of most existing baseline methods, compared with the T-GCN, ASTGCN, and AGCRN models, the MAE is reduced by 1.623, 0.724, 0.161, respectively, and the accuracy is improved by 0. 144, 0. 068, and 0. 021, respectively, which verifies the effectiveness of the model in traffic intersection flow prediction. [ABSTRACT FROM AUTHOR]

To solve the problem of inaccurate description and unreliable relation inference in group activity recognition, this paper focused on constructing a scene relationship graph for three aspects: individual, group, and scene, and proposed a scene relationship graph network（SRGN） for group activity recognition. This method included a feature extraction module, a scene relation graph inference module, and a classification module. The feature extraction module extracted individual features, group features, and scene features by convolutional neural network. To fully explore the impact of scene on individual and group descriptions, the scene relation graph inference module learnt individual features and group features by building individual-scene and group-scene relationship graphs in a two-branch framework. Scene graph inference took into account the influence of individual on group and introduced a cross-branch module. It used the classification module to classify individual features and group features for prediction. The experimental results show that the group recognition accuracy of the proposed method on volleyball and collective activity data sets is improved by 1. 1% and 0. 5%,respectively. It verifies the validity of the scene graph in describing individual feature and group feature. [ABSTRACT FROM AUTHOR]

This paper proposed a parallel deep convolutional neural network optimization algorithm based on Spark and AMPSO (PDCNN-SAMPSO), aiming to address several issues encountered by parallel DCNN algorithms in big data environments, such as excessive redundant parameters, slow convergence speed, easy to fall into local optimal, and low parallel efficiency. Firstly, the algorithm designed a kernel pruning strategy based on importance and similarity (KP-IS) to address the problem of excessive redundant parameters by pruning the redundant convolution kernels in the model. Secondly, it proposed a model parallel training strategy based on adaptive mutation particle swarm optimization algorithm (MPT-AMPSO) to solve the slow convergence speed and easy to fall into local optimal issues of parallel DCNN algorithms by initializing the model parameters using adaptive mutation particle swarm optimization algorithm (AMPSO) . Finally, the algorithm proposed a dynamic load balancing strategy based on node performance (DLBNP) to balance the load of each node in the cluster and improve the parallel efficiency. Experiments show that, when using 8 computing nodes to process the CompCars dataset, the runtime of PDCNN-SAMPSO is 22%, 30%, 37% and 27% lower than that of Dis-CNN, DS-DCNN, CLR-Distributed-CNN and RS-DCNN, respectively, the speedup ratio is higher by 1.707, 1.424, 1.859, and 0.922, respectively, and the top-1 accuracy is higher by 4.01%, 4.89%, 2.42%, 5.94%, indicating that PDCNN-AMPSO has good classification performance in the big data environment and is suitable for parallel training of DCNN models in the big data environment. [ABSTRACT FROM AUTHOR]

[Objectives] Under the high-density breeding mode, broilers in cages are prone to respiratory diseases, which are difficult to prevent. In this paper, a cough detection method for whole-life cycle cough of white-feathered broiler based on vocalization characteristics and deep learning was designed to automatically monitor the cough vocalization of broilers and provide early warning information in time. [Methods] Digital filtering, spectral subtraction denoising and endpoint detection were performed on the vocalization signals of broilers at three different growth stages: 10-19 days old, 20-29 days old and after 30 days of age, and the filter bank (FBank), Mel-frequency cepstral coefficients (MFCC) features and their respective first-order and second-order differences were used as the input of the VGG16 and ResNet18 neural networks to complete the three-category model training of cough, tweet and other vocalizations. [Results] The recognition models constructed by using different vocalization features and neural networks in each age group could accurately realize the vocalization classification, and the FBank-VGG16 model was better at 10-19 days old and 20-29 days old, and the accuracy rates were respectively 94.29% and 97.65%. The accuracy rate of the MFCC-ResNet18 model after 30 days was higher than other models at 98.66%. As the age increased, the overall recognition accuracy of each model increased, ranging from 3% to 7%. [Conclusions] This experimental method could quickly and accurately identify the cough sounds of broilers at different life stages in the actual production environment, and provided technical support for the early detection of respiratory diseases in caged broilers. [ABSTRACT FROM AUTHOR]

Existing lip-reading algorithms for Chinese sentences are inadequate at feature extraction and visual ambiguity resolution, which leads to low accuracy. Aiming at this problem, this paper proposed a lip-reading algorithm for Chinese sentences based on temporal convolutional network and 3D convolutional neural network（3DT-CHLipNet）.Firstly, it used a Temporal Convolutional Network to extract long-term features from lip dynamics sequences, which has a much larger receptive field than the Long Short Term Memory Network. Secondly, in order to minimize the visual ambiguity in Chinese lipreading, it adopted a Transformer model with the self-attention mechanism to capture the context information and improve the accuracy of sentence prediction. Finally, it introduced a temporal masking data augmentation strategy in the data preprocessing to further reduce the error rate of the algorithm. Comparison experiments on CMLR, the largest open-source Sequence-to-Sequence Chinese Mandarin Lip Reading dataset, show that the improvement in accuracy over representative lip reading algorithms for Chinese sentences ranges from 2.17%to 23.99%. [ABSTRACT FROM AUTHOR]

To solve the problem of combustion state recognition in solid oxide fuel cell (SOFC) combustor, this paper proposed a combustion state recognition method based on attention mechanism and image feature pyramid. The method adopted the adaptive gamma correction with weighting distribution (AGCWD) to standardize the input images. It combined two single full connections with 1×1 convolution to replace the squeeze and excitation structure, and proposed a hybrid attention structure combined with spatial attention structure to enhance the ability of feature extraction. To provide multi-scale information communication capability, it constructed the multi-scale bidirectional fusion pyramid by means of bidirectional computation and multi-scale fusion. The experimental results show that the proposed method reaches 99.22% accuracy under the premise of 3.98 M parameters and 397 M floating point operations (FLOPs), and effectively identifies the combustion state in SOFC combustor. [ABSTRACT FROM AUTHOR]

In previous knowledge graph relationship prediction tasks, the main approach is straightforward reasoning, which couldn’t use a priori knowledge to deal with inductive learning in the case of unseen entities and relations. This paper proposed a relationship prediction method based on BERT and path contrast learning, called BPCL. Firstly, it used the convolutional neural network to capture the contextual neighborhood information of the target triplet of the subgraph, and linearized the subgraph into a relational path. And it used BERT to initialize edge features. Secondly, it introduced the comparative learning of positive and negative relational paths. Finally, it carried out the relationship prediction by combining contrast learning and supervised training. This paper verifies the improved prediction accuracy of the model on a common benchmark dataset applicable to inductive inference methods. [ABSTRACT FROM AUTHOR]

Aiming at the current hand pose estimation which doesn’t fully use 2D information to assistance 3D hand mesh reconstruction, this paper further introduced HOG feature of the RGB image based on the use of hand Mask and 2D heatmaps. This paper designed the framework of multi task learning CNN to extract the 2D information, and used the topology of the hand to fused the relevant information. In order to solve two problems: the consistency of hidden Embeddings dimensions in Transformer Encoder as well as requires heavy computational resources, the model introduced a new MLP (Multi-Layer Perception) module into transformer encoder to increase the length of Embeddings and decrease the dimensions of Embeddings, thereby the hand Mesh was completed in the way from coarse to fine. The new method proposed in this paper has achieves better results in two Frei-HAND and RHD datasets. [ABSTRACT FROM AUTHOR]

In order to expand the prediction range of spatio-temporal graph convolutional networks and apply them to the multivariate time series prediction problems in the scenario of unknown correlation, this paper proposed a graph learning based spatio-temporal graph convolutional networks（GLB-STGCN）. The graph learning layer learned the graph adjacency matrix from the time series with the help of cosine similarity, then the graph convolution networks captured the interaction between multi-variables, and finally the multi-kernel time convolution networks captured the periodic characteristics of the time series for precise prediction. To verify the effectiveness of GLB-STGCN, this paper used 4 public datasets from astronomy, electricity, transportation and economy and 1 industrial production dataset for the prediction experiments. The results showed that GLB-STGCN outperforms the comparison methods, especially on astronomical datasets, with prediction errors reduced by 6.02%, 8.01%, 6.72%, and 5.31%, respectively. The experimental results proved that GLB-STGCN has a wider application range and better prediction effect, especially for time series prediction problems with obvious natural cycles. [ABSTRACT FROM AUTHOR]

In order to solve the problem of strong popularity bias in recommendation lists generated by Bayesian personalized ranking algorithm under the condition of unbalanced data, this paper designed a hybrid recommendation algorithm based on feature embedding to remove popularity bias. Firstly, this paper used convolutional neural network to extract user and item features, determine user preferences, and fill original unbalanced data according to user preferences. Secondly, this paper embedded the user preference features extracted from convolutional neural network into the Bayesian personalized ranking algorithm for hybrid recommendation. Finally, it trained the mixed recommendation model with score filled data, and obtained the personalized ranking list without popularity bias. In order to verify the performance of the algorithm, it conducted the analysis and comparison experiments on Movielens-100 K and Movielens-1 M. And the experimental results show that the popularity bias is reduced by about 50%～60% and the accuracy is improved by about twice. [ABSTRACT FROM AUTHOR]

In order to solve the disadvantage that the ViT cannot change the input patch size and the input patches are all single-scale information, this paper proposed an image classification network based on Transformer called MultiFormer. MultiFormer embeds small patches with different scales of input at each stage into large patches with rich semantic information through the AWS（Attention With Scale） module; and captures local and global attention alternately through the GLA-P（Global-Local Attention With Patch） module, preserving both fine-grained and coarse-grained features during embedding. This paper designed MultiFormer-Tiny,-Small and-Base networks of three different sizes to achieve 81.1%, 82.2% and 83.2% Top-1 accuracy respectively in ImageNet image classification experiments, the latter two models improve by 3.1% and 3.4% compared to the same volume of convolutional neural networks ResNet-50 and ResNet-101; MultiFormer-Base offers a 2.1% improvement with far fewer parameters and computational effort than the ViT-Base/16 model, and without the need for extensive data pre-training. [ABSTRACT FROM AUTHOR]

The U-turn task is one of the contents of autonomous driving research, and most of the solutions under the standard roads in cities cannot be implemented on non-standard roads. Aiming at solving this problem, this paper establishes a vehicle U-turn dynamical model and designs a multi-scale convolutional neural network to extract feature maps as the input of the agent. In addition, for the sparse reward problem in the U-turn task, this paper proposes a hierarchical proximal policy optimization algorithm that combines hierarchical reinforcement learning and proximal policy optimization algorithm. In experiments with simple and complex scenarios, this algorithm learns policies faster and has a higher success rate of U-turn compared to other algorithms. [ABSTRACT FROM AUTHOR]

Action recognition (AR) is a hot research area in computer vision field, and has an extensive application prospect for security monitoring, autopilot, production safety etc. Firstly, this paper analysed the connotation and denotation of AR and put forward the technical challenges; Secondly, the paper analysed and compared the working principles of AR from three aspects: time feature extraction, efficient optimization and long-term feature capture; Thirdly, in order to select suitable AR models for different application scenarios, this paper compared the performance characterization of 43 benchmark AR methods in recent ten years based on UCF101, HMDB51, Something-Something and Kinetics400 data sets. Finally, this paper pointed out the future development direction of AR field, and the research results can provide theoretical reference and technical support for video feature extraction and visual content understanding. [ABSTRACT FROM AUTHOR]

Most existing text classification algorithms based on graph neural network ignore the problem of over-smoothing, and ignore the problem of information loss due to graph topology, resulting in poor classification performance. To solve this problem, this paper proposed a method to measure the smoothness of multiple text graph representations WACD and a regularization term RWACD to suppress over-smoothing. Subsequently, this paper proposed an attention and residual-based network structure ARS to compensate for the loss of textual information due to graph topology differences. Finally, this paper proposed a graph convolutional neural network text classification algorithm RA-GCN. RA-GCN used ARS to fuse text representations in the graph representation learning layer, and used RWACD in the readout layer to suppress over-smoothing. This paper conducted experiments on 6 Chinese and English datasets. The experimental results demonstrate the classification performance of RA-GCN, and the effects of RWACD and ARS are verified through multiple comparative experiments. [ABSTRACT FROM AUTHOR]

Existing short-term demand prediction models for public bikes ignored the difference in the nature of the impacts of different environmental factors on user demand as well as the temporal dependency of variable environmental factors. this paper distinguished environmental factors into the invariable factors that have been internalized into user demand and the variable factors that need to be considered separately, and then proposed a model called GCNN-LSTM-E in this paper. In the model, this paper used graph convolutional neural network(GCNN) to capture the non-euclidean spatial dependency of user demand, used long short-term memory (LSTM) network to capture the temporal dependencies of user demand and variable environmental factors, and applied vector concatenation and fully connected network to impose the influence of variable environmental factors on user demand. Experimental results showed that the GCNN-LSTM-E model has the best prediction performance and outperforms all benchmark models under 1 h time granularity. It indicates that the design of the model is reasonable and effective, and 1 h is the most appropriate time granularity. [ABSTRACT FROM AUTHOR]

Semantic segmentation is one of the important techniques in remote sensing image analysis. Existing methods, such as methods based on deep convolutional neural networks, etc., have made significant progress in semantic segmentation, but these methods often require a large amount of training data. The Markov random field model（MRF） based on the graph model proposed an idea of unsupervised semantic segmentation that did not rely on training data, which could effectively describe the spatial relationship of objects, and analyze the spatial distribution of objects. However, the existing MRF model methods were usually based on a single granularity primitive based on pixels or objects, and it is difficult to make full use of image information, resulting in poor semantic segmentation. Aiming at the above problems, this paper introduced the alternative direction method of multipliers（ADMM） and discretized it, then proposed an unsupervised semantic segmentation method（MRF-ADMM） based on the pixel and object primitives collaborative MRF model. Firstly, it constructed two probability maps of pixel primitive and object primitive, in which the pixel primitive probability map was used to describe the detailed information of the image and maintain the boundary of semantic segmentation. And the object primitive probability map was used to describe a large range of spatial relationships and deal with the high heterogeneity inside the remote sensing images. In the process of model solving, according to the characteristics of pixels and object primitives, it proposed a discretized ADMM method, and used it to transfer and update of the two primitive category labels. Compared with the existing MRF models, the experimental results of semantic segmentation of different types of remote sensing images in different databases such as Gaofen-2 and aerial images can effectively synergize the advantages of different granularity primitives and optimize semantics results. [ABSTRACT FROM AUTHOR]

In recent years, single device sound scene classification has achieved good results, however, progress in multi-device sound scene classification has been slow. To solve the problem of large differences in the number of multi-device samples, this paper proposed a pairwise feature fusion algorithm. By calculating the differences in the spectrogram for each pair of paired samples and averaging these differences after accumulation, obtaining the average spectral characteristics of each device for the conversion of device samples. The algorithm effectively improved the generalization ability of the model while increasing the number of device samples. Meanwhile, in order to obtain global information, it proposed a lightweight attention module, which could make the model focus on the training of the whole sound sequence information on the basis of reduced computation by performing self-attention operations on the input features after compression in the frequency domain. The experimental results show that the proposed algorithm has better advantages in terms of model size and classification accuracy compared with other methods. [ABSTRACT FROM AUTHOR]

In order to solve the problems of high computational complexity, large computational cost and large number of parameters, this paper proposed the parallel group convolution algorithm based on the domestic SW26010P multi-core processor. The core idea was to use the unique data layout, through the multi-core mapping processing, parallel computing. Experimental results show that compared with single-core serial algorithm, the proposed parallel group convolution algorithm can achieve the highest speed-up ratio of 79.5 and the maximum effective computing power of 186.7MFLOPS. After data parallel optimization of the parallel group convolution algorithm by SIMD instruction, the algorithm obtains the highest speed-up ratio of 10.2 compared with the parallel group convolution algorithm before optimization. [ABSTRACT FROM AUTHOR]

Aiming at the lack of global dependency mining of users in traditional information prediction models research, this paper proposed an information diffusion prediction model based on hypergraph attention mechanism and graph convolution network (HGACN）. Firstly, it constructed the subgraph of user social relationship, and obtained the subcascade sequence by sampling, and learnt the structural features of user social relationship by graph convolutional neural network. Secondly, considering the global dependence between users and cascades, it used the hypergraph attention mechanism (HGAT) to learn the interaction characteristics of users at different time intervals. Finally, it captured the learned user representation into the embedded module, and used the gating mechanism to fuse it to obtain a more expressive user representation, and used the multi-head attention mechanism with mask for information prediction. The experimental results on Twitter and other five datasets show that the proposed HGACN model is improved by 4.4% in hits@N and 2.2% in map@N, which are significantly better than the existing diffusion prediction models such as MS-HGAT, proving that the proposed HGACN model is reasonable and effective. It is of great significance for HGACN to monitor rumors and detect malicious accounts. [ABSTRACT FROM AUTHOR]

Considering the complex characteristics of low contrast, blurred boundaries, and irregular shapes in the lesion area and surrounding mucus in colorectal polyp images, most of the existing algorithms cannot achieve high-precision segmentation of colorectal polyps. In view of the above difficulties, this paper proposed a colorectal polyp segmentation algorithm combining PVTv2 and multi-scale boundary polymerization. Firstly, using PVTv2 to extract the lesion features in the intestinal polyp image layer by layer, to solve the problem that the traditional convolutional neural network has insufficient ability to extract the features of the lesion area. It constructed a multi-scale context space awareness module at the network skip connection. Then, it designed a multi-scale extrusion adaptation fusion module to aggregate the feature information of different scales to reduce the semantic difference of each scale feature. Finally, in order to further strengthen the edge detail features recognition ability, creatively constructed residual axial double boundary refinement module. The algorithm verified by a large number of experiments on the Kvasir-SEG dataset and the CVC-ClinicDB dataset, the similarity coefficients were 93. 29% and 94. 52%, and the average intersectional merge ratio was 88. 36% and 89. 88% respectively. The experimental results show that the segmentation accuracy of the proposed model has been greatly improved for the complex lesion area and the blurred lesion boundary. [ABSTRACT FROM AUTHOR]

Expert recommendation is one of the research hotspots in the online Q&A community. However, the majority of the currently used algorithms concentrate on matching user's static interest and question information, ignoring the efficient capture of user' s dynamic interest representation information, which results in a lack of recommendation accuracy. In order to address the aforementioned issues, this paper proposed an expert recommendation algorithm for the Q&A community that incorporated multi-head self-attention. Firstly, this algorithm built out question encoders of convolutional neural networks and attention mechanisms to process target question and user' s historically answered questions, in order to extract the corresponding question representations. Secondly, it treated the sequence of user's historically answered questions as a time series and used the multi-head self-attention mechanism to learn the dynamic interest representations hidden in the sequence, and combined with the user' s static interest representations to obtain the user' s comprehensive interest representations. Finally, it calculated the similarity between the target question representation and the comprehensive user representation to generate recommendation results. Based on the real data from the Zhihu Q&A community, the experimental results show that the performance of this algorithm is significantly better than the current popular expert recommendation algorithm. [ABSTRACT FROM AUTHOR]

Current intent recommendation researches extract users' intents are flat, which ignore the hierarchical relationship between intents. In order to solve the above problem, this paper proposed the hierarchical intent disentangling for graph convolution neural network recommendation model ( HIDR), which divided the user-item interaction graph into multiple dynamic interaction sub-graphs to depict the hierarchy of user intent from fine-grained to coarse-grained. Firstly, in each intent interaction sub-graph, the model adaptive fused information from high-order neighborhoods according to the high-order connectivity of nodes, and extracted the fine-grained intent representations of users by disentangling. Then, it built coarse-grained intents based on the similarities between the fine-grained intents in low-level relationships and high-level network super-nodes to explicitly model the intent hierarchy from fine-grained to coarse-grained. Finally, it aggregated the high-quality representations of user and item for inner product predictive and iterative optimization by the hierarchical intent vectors. The experimental results on the two datasets of Gowalla and Amazon-book show that the recall rate of HIDR is improved by an average of 10. 82% and 6. 63%, and the normalized damage cumulative gain increases by an average of 14. 65% and 9. 63%, and the precision increases by an average of 10. 46% and 7. 73 %, respectively, compared with optimal benchmark model CLSR. [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]

In order to accurately predict the short-term passenger flow of urban rail transit for multiple stations, this paper proposed a deep learning model, SAE-ConvLSTM, combining convolutional long short-term memory ( ConvLSTM) and stack autoencoder (SAE) . This paper considered thirteen external factors related to passenger flow, whose features would be extracted by SAE with successive layers and thus obtain more representative features. It proposed ConvLSTM to extract spatiotemporal features of passenger flow, which was combined with the resulting external factors to predict short-term passenger flow of multiple stations simultaneously. And it developed latent action Monte Carlo tree search ( LA-MCTS) to optimize the parameters of SAE. Compared with genetic algorithm( GA), particle swarm optimization ( PSO), simulated annealing algorithm (SA) and tabu search (TS), LA-MCTS performed best in terms of effect and efficiency. This paper conducted extensive experiments. The results show that SAE-ConvLSTM works better than shallow machine learning model-back propagation neural network ( BPNN), support vector regression mode(SVR),autoregressive integrated moving average model ( ARIMA ),and deep learning modellong and short time memory network ( LSTM), convolutional neural network (CNN) and Conv LSTM without external features, ConvLSTM external features without SAE, CNN + LSTM and CNN + LSTM with external features, in terms of root mean square errors ( RMSE), mean absolute errors ( MAE) and mean absolute percentage errors ( MAPE), and the goodness of fit ( R² ) . [ABSTRACT FROM AUTHOR]

Entity relationship extraction is a key task of natural language processing and knowledge graph construction. The existing few-hot relation extraction methods can't effectively obtain and make full use of more text semantic information. For this reason, this paper proposed a semantic enhancement-based multi-feature fusion relationship extraction method (SMPC), and applied it to few-shot tasks. The method constructed a piecewise convolution al neural network that integrated information such as position, part of speech, and syntactic dependence to maximize semantic features. The model extracted fine-grained semantic information from Wikipedia and integrated it into word embedding to improve the common learning of model context . This paper made experiments on different baseline methods in two scenarios. It achieves a maximum ac curacy improvement of 4 % and 10 %, and proves the effectiveness of the method [ABSTRACT FROM AUTHOR]

Objectives: The registration of remote sensing image data and GIS ( geographic information system ) vector data is the basis of the integration of remote sensing and GIS, which is widely used in the fields of map data update, city monitoring, map change detection and so on. At present, the key to the registration of remote sensing images and vector data is the extraction of remote sensing image features. However, the existing remote sensing image feature extraction has problems such as incomplete feature extraction, which leads to registration failure or low accuracy. This paper proposes a registration method for remote sensing images and vector data based on Mask region -based convolutional neural network (Mask R -CNN). Methods: Firstly, we select the road intersection as the distinctive feature of the same name in the remote sensing image and vector data, and create a road intersection image data set to train Mask R -CNN model. Secondly, according to the geometric topological relationship, the vector data road intersections are selected as vector control points. And take the intersection control point of the vector data as the center, we use 400 × 400 pixels window to crop the remote sensing image data and input it into the Mask R-CNN model, extract the border of the road intersection in the image. The control points of the same name are determined according to the Euclidean distance between the remote sensing image and the vector data control points, and the control points of the same name are cleaned using the density-based spatial clustering of applications with noise algorithm. Finally, the affine transformation parameters are calculated according to the filtered control points of the same name to realize the registration of remote sensing image and vector data. The registration data of Shanghai vector data and Gaofen-2 image data were selected for registration experiment. Results: Experimental results show that the average deviations of the experimental data before were 15. 34 m and 1. 44 m, before and after registration based on Mask R -CNN. This method can correctly register remote sensing images and vector data, and the proposed method has better application prospects in urban data registration, and has the characteristics of strong robustness and high accuracy. Conclusions: The proposed method in this paper can automatically register remote sensing images and vector data from different sources in areas such as mountains, grasslands, and deserts. In the next step, the amount of sample data of remote sensing images will be increased, including types of remote sensing images and types of features. [ABSTRACT FROM AUTHOR]

Aiming at the problem of how to build a high-performance model with low number of parameters and calculation, this paper proposed a lightweight multi-information graph convolutional neural network (LMI-GCN). LMI-GCN performed information fusion by encoding four different information of joint coordinates, joint speed, bone edge, and bone edge speed into a high-dimensional space, and introduced a multi-channel adaptive graph that could aggregate important features and a shunt temporal convolution block to reduce the amount of model parameters. At the same time, this paper proposed a random pool data preprocessing method. Compared with the baseline method SGN(semantics-guided neural networks) on the NTU-RGB + Dl20 dataset, the two evaluation settings cross-subject and cross-setup increase by 5.4% and 4. 7%. Experimental results show that the performance of the LMI-GCN is better than that of the SGN. [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]

This paper proposed a natural language sentence matching method that combined high-level and low-level semantic information to solve the problems about current natural language sentence matching method fail to integrate common semantic information and it is difficult to capture deep-semantic information. First of all, the method used pre-trained word vector GloVe and character-level word vector to obtained the word embedding representation of sentence P and sentence Q. Secondly, this paper encode red P and Q with bidirectional LSTM, then it contained low-level semantic information through preliminary fusion of P and Q. Thirdly, this paper calculated bidirectional attention between P and Q, then spliced them together to get semantic representation, afterwards it calculated its self-attention to obtained high-level semantic information. Finally, this paper used a heuristic fusion function to fuse the low-level semantic information with the high-level semantic information to obtain the final semantic representation, and it used a convolutional neural network to prediction answers. This paper evaluated the proposed model on two tasks, such as recognition textual entailment, paraphrase recognition. This paper conducted experiments on the SNLI dataset and the Quora dataset. The results show that the accuracy of the proposed algorithm on the SNLI test set is 87. 1%, and the accuracy of the Quora test set is 86. 8%, which verifies the effectiveness of the algorithm in the task of natural language sentence matching. [ABSTRACT FROM AUTHOR]

Facial local detail information plays an important role in facial expression recognition（FER）.However, most of the existing methods only focus on the high-level semantic information of facial expressions, while ignoring the fine-grained information of local facial regions. To solve this problem, this paper proposed a deep convolutional neural network fusing local feature and two-stage attention weight learning（FLF-TAWL）,which could adaptively capture important facial regions to improve the effectiveness of facial expression recognition. The FLF-TAWL model was composed of a dual-branch framework, one branch extracted local features from image blocks, and the other branch extracted global features from the entire expression image. Firstly, this paper proposed a two-stage attention weight learning strategy. In the first stage, it roughly learned the importance weights of global and local features, in the second stage, it further refined the attention weight, and fused the local and global features. Secondly, the model used a region-biased loss function to encourage the most important regions to obtain higher attention weights. Finally, this paper carried out extensive experiments on FERPlus, Cohn-Kanada（CK+） and JAFFE datasets to obtain accuracy rates of 90.92%,98.90% and 97.39% respectively. The experimental results verify the effectiveness and feasibility of the FLF-TAWL model. [ABSTRACT FROM AUTHOR]

Most of the existing steganalysis methods have weak generalization ability and cannot effectively detect unknown steganalysis algorithms, which makes the accuracy of their classification greatly reduced in the practical application process. To solve this problem, this paper proposed an image steganalysis method based on group convolution and snapshot ensembling（Snapshot Ensembling steganalysis network, SENet）. Firstly, residual convolution block and group convolution block are used to extract the features of the image. Secondly, the model with the best performance is obtained as the snapshot model in each training period. Finally, the selected snapshot models are integrated to classify the images. This method uses the techniques of group convolution and snapshot ensembling to avoid the high training cost of traditional integration methods and the limited generalization ability of a single classifier. Experimental results show that this method can improve the accuracy of steganographic analysis model, and can effectively classify when the training set and test set are mismatched, and has high model generalization ability. [ABSTRACT FROM AUTHOR]

Aiming at the problems of too many long-tail entities and existing knowledge and the scarcity of labeled data in the current entity alignment tasks in the tourism domain, this paper proposed an entity alignment method based on the combination of multi-view knowledge representation and neural network. It used a pre-trained model to complete the knowledge representation learning of multiple views, obtained the structural embedding, relationship embedding and description information embed-ding of the entity, and then used the convolutional neural network to calculate the similarity of the comprehensive embedding of the entities combined with the three views. The experimental accuracy rate reached 91.4%, the recall rate reached 87.9%, and the comprehensive index F1 value reached 89.6%. The results show that the method effectively completes the entity alignment task in the tourism domain. [ABSTRACT FROM AUTHOR]

In order to reduce the cost of manual operation, this paper proposed a fully convolutional neural network model for 6DoF pose and size estimation of targets with small data sets for 6DoF pose and size estimation that required collecting and labeling a large amount of data to train neural networks. Firstly, it combined the attention mechanism with the feature pyramid to extract the region of interest through the region suggestion network, and the region was input into the parallel fusion full convolution network to obtain the mask map. Secondly, it enriched the feature information after each convolution by adding jump connections, which were fused and classified to obtain the predicted normalization coordinate space map. Finally, it obtained the 6DoF pose and size of the target by 3D point cloud registration between the obtained mask image and the normalization coordinate space image. Experiments show that compared with PVN3D method, this method improves the accuracy by about 2. 6% and GPVPose method by about 1% in small data sets. [ABSTRACT FROM AUTHOR]