Search

Traditional geological stratification methods usually rely on manual interpretation and empirical judgment, which have shortcomings such as cumbersome processes, heavy workload, and large impact from human factors. This paper aims to study the ideas and methods of regional engineering geological stratification based on machine learning, and convert the stratigraphic stratification problem into a sequence-to-sequence prediction task of geological body spatial units and a geological attribute feature classification task, so as to improve the accuracy of geological stratification. and efficiency. Based on in-depth research on the original data of engineering geology, this paper proposes to use deep learning methods to train and predict geological stratification of static cone test data, and use classification algorithms to stratify borrow hole soil samples and quantify them. The applicability of the relevant algorithms was evaluated. By comparing the results of traditional methods and machine learning methods, the advantages of machine learning in geological stratification are verified. This study provides a new geological layering idea for regional engineering geology research, which has important practical significance. [ABSTRACT FROM AUTHOR]

In the era of big data, with the continuous popularization of social media, various text data are growing in the network and in life. It is of great significance to analyze and manage text data using text classification technology. Text classification is a basic research field in the field of artificial intelligence natural language processing. Under the given criteria, it classifies text according to content. The application scenarios of text classification are very extensive, such as sentiment analysis, topic classification, relationship classification, etc. Deep learning is a method of representation learning based on data in machine learning, and it shows good classification effect in text data processing. Chinese text and English text have differences in form, sound, and image. Focusing on the uniqueness of Chinese text classification, this paper analyzes and expounds the deep learning methods used for Chinese text classification, and finally sorts out commonly used datasets for Chinese text classification. [ABSTRACT FROM AUTHOR]

Osteoporosis (OP) is one of the main problems affecting the health of middle-aged and elderly people, and its most serious complication is osteoporotic fracture (OPF), which also has a high disability and mortality rate. The accurate screening and diagnosis of OP mainly rely on imaging analysis, and the diagnosis result rely on the subjective judgment of doctors. Therefore, the traditional imaging method of OP have certain challenges to the accurate screening, diagnosis and differentiation of OP. The cross-fusion of machine learning (ML) and imaging images effectively improves the diagnostic efficiency of clinicians, while realizing the prediction of unknown diseases (such as OPF). Recently, significant progress has been made in the screening and diagnosis of OP and in the diagnosis and prediction of OPF. This paper will review the recent related studies on ML model-assisted screening and diagnosis of OP based on imaging data, so as to provide new ideas for accurate clinical diagnosis and treatment of OP. [ABSTRACT FROM AUTHOR]

In order to solve the problem that class-imbalance data of clinical medical tables tend to have an impact on the model and that the performance of deep learning framework is difficult to match that of traditional machine learning methods when processing scale data tasks, this paper proposed a layer by layer Transformer (LLT) network model based on cascaded under-sampling. LLT deleted the most types of data layer by layer by cascade under-sampling method to achieve the balance of data categories and reduced the impact of class-imbalance data on the classifier. Moreover, LLT used attention mechanism to carry out correlation evaluation on the features of the input data to achieve feature selection, refined the feature extraction abi-lity and improved the model performance. This paper used RA (rheumatoid arthritis) data as test samples. Experimental results show that, on the premise of not changing the sample distribution, the recognition rate of a few categories is increased by 6.1% by the proposed cascade under-sampling method, which is 1.4% and 10.4% higher than that of the commonly used NEARMISS and ADASYN respectively. The accuracy of the RA tabular data and the F1-score index of LLT reach 72.6% and 71.5%, the AUC value is 0.89, the mAP value is 0.79, and the performance exceeds the current mainstream tabular data classification models such as RF, XGBoost and GBDT. This paper also visualized the model process and analyzed the characteristics affecting RA. It has a good guiding significance for the clinical diagnosis of RA. [ABSTRACT FROM AUTHOR]

In recent years, various human action recognition algorithms have achieved excellent recognition performance based on a large number of labeled samples. However, in practical applications, acquiring training samples and their corresponding labels is time-consuming and laborious, which limits the actual implementation of the algorithm. This paper summarized the deep learning algorithms for action recognition under weak supervision and few-shot learning. Firstly, in the case of weak supervision, it classified and summarized the semi-supervised action recognition methods and unsupervised domain adaptation video action recognition methods separately. Then, it reviewed video action recognition algorithms based on few-shot learning in detail. Further, it summarized the relevant human behavior datasets and analyzed and compared the performance of various relevant video action recognition algorithms on these datasets. Finally, the paper summarized the full text and discusses the future development trend of human action recognition. [ABSTRACT FROM AUTHOR]

Machine learning, as a new technique combining statistics and computer science, has been widely used in crop information acquisition tasks in recent years. Traditional methods for obtaining crop information mainly rely on chemical detection methods, which is time-consuming and labor-intensive. Based on machine learning algorithms and hyperspectral remote sensing techniques, crop appearance and internal physical and chemical parameters can be quickly sensed in a non-destructive way, which has obvious application advantages and development prospects. First, the researches related to the hyperspectral remote sensing of crop information were systematically reviewed in this paper. Second, the application, advantages and disadvantages and uncertainties of different machine learning algorithms in hyperspectral sensing crop information were summarized. Finally, it was pointed out that the future development trends of hyperspectral sensing crop information were as follows: (1) complementary crop information acquisition methods could be realized through multi-source remote sensing collaborative observations. (2) The assimilation technologies of hyperspectral remote sensing and crop model as well as the deep integration technologies of hyperspectral remote sensing and artificial intelligence could be developed. (3) The intelligent acquisition of key information oriented to the whole growth period of crops and decision-making could be realized. [ABSTRACT FROM AUTHOR]

Objectives: To address the problem of internal inconsistency of classification targets in existing three dimensional(3D) point cloud data segmentation and classification methods. we propose a high-precision classification method for indoor point cloud jointly optimized by super voxel random forest and long short-term memory (LSTM) neural network. Methods: The method takes into account that the super voxel structure has the characteristics of internal feature consistency, divides the original point cloud into super voxels, and uses super voxels as the basic unit for multivariate feature calculation to build a super voxel random forest classification model for indoor point cloud to achieve coarse classification of point cloud data. On this basis, LSTM is introduced to train and predict the neural network model for the hyper voxel neighborhood connectivity of coarse classification to achieve the optimization of hyper voxel coarse classification results. The validity and accuracy of the proposed classification method are verified based on the open dataset. Results: The results show that the classification accuracy of the proposed classification method can reach 83.2% for 13 types of elements in the open dataset. The training data of the LSTM optimization network proposed in this paper used only the label information of region 1 for model training, while other deep learning frameworks used regions 1-5 for model training, so from the perspective of training data requirements, the point cloud data classification framework proposed in this paper can achieve a relatively better prediction result with a small portion of the training data set. The super voxel-based LSTM optimization method approach has high classification accuracy on objects with obvious set features such as ceiling, floor and wall, however, it is inferior to the deep learning algorithm RandLA-Net in classifying objects with complex structures such as chair, sofa and bookcase. Conclusions: In this paper, we consider the association characteristics between different types of elements embedded in the connection relations among super voxels, and introduce LSTM to train and predict the model for the coarse classification of super voxel neighborhood connection relations to achieve the optimization of coarse classification results of super voxels. The proposed method can achieve better classification accuracy when trained with small samples compared with the classical deep learning framework. [ABSTRACT FROM AUTHOR]

In recent years, the deep learning network model based on UNet and GAN (generative adversarial network) has shown unique advantages in the field of image restoration. But, there are still artifacts, blurring, degradation of texture details, difficult to repair large-area damage, and the repaired holes are incompatible with the background image. In order to solve the problems that the current existing models are not friendly to the repair of large-area damaged images and the degraded images after repair, this paper improved the Shift-UNet model by studying the existing methods. On the basis of U-Net and GAN, this paper added an improved attention mechanism Attention-UNet between each layer of encoder and decoder and integrated it into the Shift-UNet to form Attention-Shift-UNet. And through research, it changed the activation function of the original down-sampling part from Leaky＿ ReLU to SiLU. The improved model not only achieved good results on the 64×64 central cover, but also realized the random cover, and the cover area increased from 20 % to 80 %. The experimental results show that the repair effect of the proposed model is better, especially for the repair of large-area damaged images. After testing on CelebA, Paris Architecture and Paris Stree View datasets, the evaluation indexes have been significantly improved, and SSIM has increased from 0.944 5 to 0.947 1. PSNR is increased from 27.992 7 to 28.553 6. L2 loss is decreased from 0.001 7 to 0.001 5. [ABSTRACT FROM AUTHOR]

Aspect and opinion pair extraction aims to extract aspect and opinion items and match relations from a given sentence. However, related studies typically extract aspects and opinions independently without identifying the relationships. To identify the relationships of aspect and opinion item, this paper proposed a knowledge-augmented multi-task learning model for aspect and opinion pair extraction. First, it used the pre-trained language model to generate word vectors with semantic information for the text. In order to achieve the effect of knowledge enhancement, it used the masked attention mechanism to integrate the semantic information of the knowledge graph into the word vectors, and used the sequence labeling method based on the distance-based attention and conditional random fields to extract aspects and opinions. Finally, it matched the extracted aspects and opinions to predict the corresponding relationship. In order to strengthen the connection between the aspect and opinion extraction module and the matching module, the model adopted a shared coding layer to achieve joint training. In addition, in the training process, the matching module used the real labels as input, and used the result of the extraction module as input in the testing process. Finally, to demonstrate the effectiveness of the model, this paper used three general domain datasets for comparative experiments. The model achieves F, values of 66. 99%, 75. 17% and 67. 30% in aspect and opinion matching tasks respectively, and outperforms other comparative models. [ABSTRACT FROM AUTHOR]

Objectives: On 5th September 2022, an Ms 6.8 earthquake struck the Luding County, Ganzi Prefecture, Sichuan Province, China. This earthquake triggered extensive geological hazards in the moun‐ tainous area, leading to serious casualties. Rapidly and accurately obtaining the spatial distribution of the in‐ duced geological hazards is crucial for emergency decision-making and rescue after an earthquake. Methods: Based on the global coseismic landslide database and deep learning algorithm, this paper built a near real-time prediction model of spatial distribution probability of coseismic landslides, and obtained the prediction results of the geological hazards induced by the Luding earthquake within 2 hours after the event. Through the post-earthquake unmanned aerial vehicle （UAV） and satellite remote sensing images, ma‐ chine learning and deep learning algorithms were used to realize the automated recognition of large-scale geological hazards. A total of 3 633 earthquake-induced landslides with an area of 13.78 km2 were interpreted. Finally, the model was optimized by integrating these landslide data, and the prediction results of coseismic landslides with a broader area and higher accuracy were achieved. Results: The results show that the coseis‐ mic landslide prediction model can realize a rapid capture of spatial distribution of post-earthquake geologi‐ cal hazards, filling the blank period before the acquisition of post-earthquake remote sensing images and providing support for post-disaster emergency rescue. Conclusions: Intelligent identification technologies based on UAV and satellite remote sensing images are effective means to rapidly obtain the vital informa‐ tion of large-scale geological hazards. The achievements obtained in this paper played an important role in the emergency rescue after the Luding earthquake. [ABSTRACT FROM AUTHOR]

To address the problem of poor recommendation accuracy in the session recommendation model, this paper proposed a capsule-based graph convolutional disentanglement for session-aware recommendation (CGCD) method.Specifically, it used disentangled learning technique to transition item embedding into factor embedding based on multiple sub-channels. Then, it used a capsule dynamic fusion strategy to aggregate different factors to obtain a new item embedding.In addition, it used a multi-head attention mechanism to assign weights to each item in the session. Finally, it aggregated the item embedding with other items in the current session according to the assigned weights, and then generated an accurate session representation to achieve item recommendation. Experiments on two publicly available real datasets show that the proposed model can improve the Pre@10, Pre@20, MRR@10 and MRR@20 by 5.17%, 2.99%, 6.56% and 2.94% on average of the recommended performance, which verifies the effectiveness and efficiency of the method in this paper. [ABSTRACT FROM AUTHOR]

Osteoporosis (OP) is a kind of bone disease related to aging. Its onset is obscure and development is gradual. Patients are without obvious clinical manifestations in the early stage. However, with the progress of the disease, bone loss and bone tissue microstructure destruction occur, and bone pain, spine deformation, and even osteoporotic fracture (OPF) and other serious complications may develop. Dual-energy X-ray absorption method is the current gold standard for clinical diagnosis of OP. Because its diagnostic accuracy is affected by the factors of body weight, lumbar degenerative changes, and aortic wall calcification, a false negative diagnosis is possible. In recent years, artificial intelligence (AI) has developed rapidly in the medical field. At present, AI has been widely used in the research of OP. Its research in the field of OP screening, diagnosis, and prediction has become a new hot spot. This paper expounds the application status and advantages of AI in OP diagnosis and treatment from four aspects, i.e., OP early screening, medical imaging performance, clinical diagnosis and treatment data, and OPF risk prediction, so as to provide a new direction for the accurate diagnosis and treatment of OP. [ABSTRACT FROM AUTHOR]

【Objective】 Aiming at the problems of easy falling off and easy to cause pig infection in traditional pig breeding ear tag recognition, the paper used the improved YOLOv5s model to carry out non-invasive recognition of pig face.【Method】 Firstly, the distance of K-Means was changed to 1-IOU, which improved the adaptability of the target anchor frame of the model; Secondly, the CA coordinate attention mechanism was introduced to improve the model feature extraction; Finally, BiFPN feature fusion was introduced to effectively use the features to improve the detection ability of the model. The pig face dataset used in the experiment was divided into 5 categories, with 12 756 samples after data enhancement, and the training set and test set were divided into a ratio of 9∶1.【Result】 The improved algorithm reached 0.926, 0.897 and 0.955 in accuracy, recall, and average accuracy (IOU=0.5), which were 13.2%, 3.0% and 2.2%, while the improved algorithm has better generalization ability and high recognition accuracy in single, multiple, small target, dense, and occluded scenes. 【Conclusion】 Using deep learning algorithm can get the facial information of pigs and identify them accurately, reduce the situation of missed inspection and wrong inspection, and provide better technical support for intelligent management of pigs. [ABSTRACT FROM AUTHOR]

The classification performance of the existing multi-classification tasks of finger motor imagery EEG signals is difficult to achieve usable performance. On the basis of detailed analysis of multiple components on the time scale of EEG signals, this paper designed a self-supervised sub-network for signal sub-segment extraction, and then input the sub-segment into the next sub-network for signal classification, it synthesized the two sub-networks into a self-supervised hybrid multi-task deep network. In the training phase, the sub-segment extraction sub-network extracted different sub-segments for each EEG signal, and the subsequent classification sub-network judged whether the sub-segment was the best and automatically adjusted the position of the sub-segment. It weighted the total loss function by two loss functions of two sub-networks, and extracted the best sub-segment signal and obtained the best classification effect through the overall network learning algorithm. In the verification and testing phase, the sub-segment extraction sub-network automatically extracted the corresponding sub-segment input classification sub-network according to the parameters of the training for classification. It verified the network performance on the largest SCP data of Motor-Imagery data set and the Data sets 4 of BCI Competition IV. On the SCP dataset, the average test classification accuracy of all subjects’ three finger classification tasks is more than 70%, the average test classification accuracy of four finger classification tasks is about 60%, and the average test classification accuracy of five finger classification tasks is about 50%, which is significantly improved compared with the existing reports. It is confirmed that the network can effectively extract sub-segments of motor imagery EEG signals, and has good classification effect and generalization performance. [ABSTRACT FROM AUTHOR]

Discrete sequence generation is widely used in text generation, sequence recommendation and other fields. The current research work mainly focuses on improving the accuracy of sequence generation, but ignores the diversity of generation. To address this phenomenon, this paper proposed an adaptive sequence generation method ( ECoT), and designed a two-layer meta controller. In the data layer, the function of meta controller was to realize adaptive learning sampling, automatically balance the distribution of real data and generated data,and obtain mixed data distribution. At the model level, this paper added diversity constraints. The function of the meta controller was to adaptively learn the optimal update gradient to improve the generation diversity of the generation model. In addition, in order to improve the accuracy of the generation model, this paper proposed a method combining cooperative training and adversarial learning. Compared with the current mainstream models, the results show that the adaptive cooperative training sequence generation method has more balanced accuracy and diversity in terms of generation accuracy and diversity, and can effectively alleviate the pattern collapse of the generation model. [ABSTRACT FROM AUTHOR]

In dynamic gesture recognition methods based on deep learning, aiming at the problems of large network scale, simple dimension of extracted spatiotemporal features, and insufficient extraction ability of effective features, this paper proposed a deep network framework. Firstly, this paper applied a novel spatiotemporal convolution module based on multiscale information fusion in the time domain to improve the 3D residual network structure, greatly reduced the size of the network and obtained rich spatiotemporal receptive field characteristics. Then it introduced a spatiotemporal feature channel attention mechanism with global information synchronization, and used a few parameters to construct the global dependency between feature maps, and the module could obtain the key features of dynamic gestures more efficiently. The experimental results on the self-built gesture dataset SHC and the public gesture dataset SKIG show that the proposed gesture recognition method has fewer parameters and more powerful multiscale spatiotemporal feature extraction ability, and gains a higher recognition rate than the current mainstream algorithms. [ABSTRACT FROM AUTHOR]

To accomplish the task of aerial manipulator’s autonomous grasping, it is very important to recognize and locate the object. At present, most of the recognition algorithms of aerial manipulators use traditional feature extraction methods. In order to improve the accuracy and efficiency of object recognition and positioning, this paper designs a visual recognition and positioning algorithm based on YOLOv5 deep learning object detection algorithm and RGB‑D sensor. The algorithm can detect the object in real‑time and estimate its pose, which serves for the grasping task of aerial manipulator. At the same time, aiming at the problems that the deep learning algorithm has a huge amount of calculation and cannot achieve high‑performance real‑time detection in the embedded system, model quantization is introduced to optimize the algorithm, which can greatly improve the processing speed of the algorithm. This paper introduces the overall framework and implementation process of the algorithm and verifies the effectiveness of some algorithms of object detection and pose estimation by using the COCO dataset and motion capture system. [ABSTRACT FROM AUTHOR]

With the supervised deep learning algorithms, it is prone to generate artifacts when restoring the blurred solar speckle images taken by Yunnan Observatories, and it has a long training time and over-reliance on reference images, this paper proposed a weakly supervised method based on structural reparameterization combined with multi-branch module to reconstruct solar speckle images. First, deblurring model combined single-scale and multi-scale network to design, with constructing multi-branch modules to extract features of different scales, enhance detailed information, and reduce the generation of artifacts; second, each branch structure re-parameterized to make the reuse of structure parameters runs through the entire feature extraction process; after that, the deblurring model embedded in the weakly supervised training, the blurred image assorted firstly, then the degradation model used to learn different levels of degradation. Constituted paired dataset of corresponding levels, and the deblurring model used to inversely degenerate the dataset to reconstruct solar speckle images. Experimental results show that compared with the existing deblurring method, the proposed method has higher model training efficiency and less dependence on reference images, which can meet the high-resolution reconstruction requirements of solar speckle images. [ABSTRACT FROM AUTHOR]

As a key problem and hub link between problem discovery and problem solving, the current research on root cause analysis mainly includes two types of methods: data-driven and causality-driven. In view of the advantages of data-driven methods in narrowing the range of root causes, at present, root cause research mainly focusses on datadriven methods such as association rule mining, heuristic search, machine learning and deep learning. There are few root cause analysis from the perspective of causal knowledge, nor has it been based on method dimension. The inductive analysis of the root cause is carried out, and there is a lack of relevant research results. Therefore, this paper sorts out and summarizes the main results of root cause analysis in recent years, analyses the differences and advantages of root cause analysis under different method dimensions, and proposes a root cause analysis method that integrates causal knowledge, and combines asymmetric Shapley value with causal chain diagram to improve the accuracy of root cause analysis. Finally, the existing some research difficulties and development trends put forward scientific and meaningful future research directions. [ABSTRACT FROM AUTHOR]

Objectives: In recent years, the brain‑like navigation algorithm is a new research hotspot, which is expected to achieve autonomous navigation by imitating the ability of biological navigation. The core is‑ sue is how to improve generalization ability. Methods: This paper introduces the research background and theoretical basis of the brain‑like navigation algorithm. After investigation, we propose a computational framework of brain ‑ like navigation algorithm. The outstanding works in this field are discussed and analyzed under this framework, and we carried out experimental verification of some basic methods. Results： The main contributions of this paper are: (1) Comprehensively introduces and summarizes the theoretical basis and outstanding works in this field. (2) Proposes the computational framework of the brain‑like navigation algorithm, which scientifically defines the functions of different modules of the algorithm. (3) Through theoretical analysis and experimental verification, we summarized valuable conclusions and expectations. Conclusions: In terms of model design, mature methods of deep learning can also be applied to this problem, but need more modifications to further improve navigation capabilities; in terms of model training, combining the advantages of multiple learning algorithms is hopeful to further improve the generalization ability. [ABSTRACT FROM AUTHOR]

Aiming at the problem of fine-grained visual categorization, this paper proposed an effective algorithm to achieve end-to-end fine-grained visual categorization. The ECA module in ECA-Net was a channel attention mechanism with significant performance advantages. It model-fused with the classic network ResNet-50 to form the ResEca. Then, it used the object-level image positioning module and the part-level image generation module to generate object-level and part-level images. Those images combined with original images could be as the input of the new constructed network Tb-ResEca-Net. This paper trained the 95. 1% and 95. 3% respectively on the test set of the corresponding dataset. The experimental results show that this method has higher classification accuracy and stronger robustness compares with other traditional fine-grained classification methods, which is an effective fine-grained image classification method. [ABSTRACT FROM AUTHOR]

Loop closure detection is important for visual simultaneous localization and mapping (VSLAM) systems to reduce cumulative errors and perform re-localization. In order to shorten the loop closure detection online runtime while meeting the accuracy recall rate requirement, the paper proposed a fast loop closure detection algorithm using broad autoencoder (FLCD-BA). The algorithm improved broad learning architecture to learn feature representations autonomously from the input data in an unsupervised manner, and then accomplished loop closure detection tasks. Differing from the traditional deep learning methods, the network used a pseudo-inverse ridge regression algorithm to solve the weight matrix and achieved fast reconfiguration of the network by incremental learning without retraining the entire network. The proposed algorithm experimented on three public datasets without using GPU devices, and the training time of the network greatly reduced compared to bag-of-words models as well as deep learning methods. The experimental results show that the algorithm has high accuracy and recall in detecting loop closure, and the average running time per frame in the test is only 21 ms, which provides a new algorithm for loop closure detection in visual SLAM systems. [ABSTRACT FROM AUTHOR]

People have widely used air quality prediction models composed of traditional machine learning methods. However, such models still have shortage on data validity, especially the validity of spatial-temporal related data selection. In response to the input data validity of deep learning networks, this paper proposed a prediction model based on spatial-temporal similarity LSTM to select more effective data at the time and space level. STS-LSTM contained three modules, pre-order, middle-order and post-order module. The pre-order module was the time-space similar selection input module, which proposed the GCWDTW algorithm. This paper used it to select data with higher temporal and spatial similarity. The in-order module used LSTM as a deep. learning network for training. The post-order module selected different output groups for integration according to the characteristies of the target station. The STS-LSTM overall model improves the air quality prediction error by about 8% compared with the existing algorithm, and the data selected by the validity improves the accuracy of the model by up to 21%. The experimental results show that this model has achieved significant results in the effective data selection, and the data input and output method as a part of the applied deep learning network can effectively improve the final effect of the deep learning network. [ABSTRACT FROM AUTHOR]

When the scale of data is large, the deep learning model will encounter the problem of time-consuming weight adjustment and easy to fall into the local optimal solution. In order to solve these problems, broad learning system comes into being. The broad learning system not only has the advantages of simple structure, fast training speed and high accuracy, but also has the advantage of incremental learning. This paper firstly introduced the background and development of broad learning system, then described the basic theory and implementation method of broad learning system, and compared its similarities and differences with deep network. Then this paper introduced the improvement of broad learning system on image classification, numerical regression, EEG signal processing, and analyzed the advantages and disadvantages of these algorithms. Finally, it summarized the shortcomings of existing broad learning algorithms, and prospected the future research direction. [ABSTRACT FROM AUTHOR]

Aiming at the poor classification effect caused by complex background, large intra-class difference and high interclass similarity in remote sensing scene images, this paper proposed an attentional mechanism and residual contraction unit algorithm based on supervised contrast learning. Firstly, the algorithm improved the effective channel attention mechanism (ECA), and optimized the extraction of image features to be recognized. Then, the algorithm proposed a cooperative residual shrinkage unit algorithm, which is used to filter and eliminate redundant information of images. In addition, supervised contrast learning algorithm was used to enhance the generalization ability of the algorithm. Finally, experiments were carried out with remote sensing image data set and compared with the latest algorithms such as enhanced attention algorithm and scale attention mechanism algorithm. Experimental results show that the proposed algorithm improves the classification accuracy by 1.75% and 2.5% in AID Data Set with 20% training ratio. [ABSTRACT FROM AUTHOR]

Multi-contrast magnetic resonance imaging is a powerful imaging tool in clinical practice due to its ability to provide abundant contrast information. This paper proposes an efficient unsupervised deep learning algorithm in gradient domain (UDLGD) for reconstructing multi-contrast images of the same anatomical cross section from partially sampled K-space data. The present UDLGD consists of two consequent stages. At the prior learning stage, score-based generative model is utilized to train gradient domain prior information from single-contrast image dataset. After the prior knowledge is determined, it can be applied to multi-contrast reconstruction with various settings like different number of contrast images and sampling patterns. The data-consistency, gradient image and group sparsity are alternatively updated at the iterative reconstruction stage for achieving satisfactory result. Experimental results in in-vivo MRI data demonstrated that UDLGD can achieve lower reconstruction errors and better preserve image structures than competing methods. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the existing super-resolution algorithm based on deep learning didn't make full use of the feature information of each level, resulting in low reconstruction accuracy and large parameter quantity, this paper proposed a double dense connection structure named densely channel attention skip connection network. In the inner structure of the network, it improved the original dense cascade block to generate a channel separable dense cascade block. The outer structure adopted a densely residual connection and attention mechanism to fuse the features extracted by the dense block to achieve the goal that less convolution layer and higher precision effect. This paper tested the network models on several benchmark datasets . The results show the proposed model has higher accuracy and fewer parameters than the other models. [ABSTRACT FROM AUTHOR]

At present, multi-agent reinforcement learning algorithms mostly adopt frameworks that are centralized in learning and decentralized in action. These frameworks may take too long to converge or may not converge at all. In order to speed up the collective learning time of multi-agents, this paper proposed a novel multi-agent group learning strategy. It used recurrent neural network (RNN) to predict the grouping matrix of multi-agents to share the experience between them, resulting in improved learning efficiency within the multi-agents group. Meanwhile, this paper proposed the concept of information trace to remedy the problem that the agents could not share information brought by the grouping. In order to strengthen the retention of excellent experience within the group, this paper proposed the practice of delaying the death time of excellent agents in the group. Finally, the results show that, compared to MADDPG, the training time is reduced by 12% in the labyrinth experiment and by 17 % in capture the flag experiment. [ABSTRACT FROM AUTHOR]

Based on video action recognition, this paper firstly reviewed the traditional action recognition algorithms based on RGB, including traditional algorithms and deep learning algorithms. Because of the influence of background lighting, RGB-videobased action recognition is low accuracy, but it has rich color appearance information. Then this paper analyzed and summarized action recognition algorithms based on RGB-D, which was divided into depth sequence, bone and multi-feature fusion. RGB-D video has multiple modes and can provide more information for action recognition, which performs better than RGB video but also brings new challenges. Finally, this paper prospected the common data sets and the possible future development direction. [ABSTRACT FROM AUTHOR]

With the advancement of data acquisition technology, spatiotemporal data with geographic location information are growing rapidly, so it is urgent to explore effective spatiotemporal data modeling methods. Spatiotemporal sequence prediction is one of the basic methods in spatiotemporal data modeling and widely used in many fields. At present, there is no Chinese literature on its review, so it is of great significance to summarize these methods. For the spatiotemporal sequence prediction problem, this paper reviewed its application background and development history. Then it introduced some related definitions and characteristics. According to its category, the spatiotemporal sequence prediction methods, based on traditional methods, classical machine learning methods and deep learning methods are analyzed respectively as well as their application scope, advantages and disadvantages. Finally, this paper made a review and prospect over the research directions of spatiotemporal sequence prediction, laying a theoretical foundation for researchers to further study this problem [ABSTRACT FROM AUTHOR]

Aiming at the problem that the existing automatic image description generation models based on visual attention and text attention cannot describe the image details and the whole image at the same time, this paper proposed a model for image captioning which included three sub-modules, ie, an image encoder, an evolutionary neural network, and an adaptive merging decoder. The proposed model could effectively integrate both the visual information and text information, and automatically calculated the proportion of these two information at each time step. The experimental results on two public data sets, Flickr30k and COCO2014, show that the proposed EDLMIC model is superior to other baseline models in four indicators such as METEOR, ROUGE-L, CIDEr and SPICE, and has good performance in a variety of different life scenes. [ABSTRACT FROM AUTHOR]

Existing deep learning based single image super-resolution (SISR) models usually improve the fitting ability of the model by increasing the number of network layers, but fail to fully extract and reuse features, leading low quality of reconstructed images. To solve this problem, this paper proposed an image super-resolution model based on feature fusion and attention mechanism. This model used residual in residual (RIR) structure in feature extraction module. The feature extraction module of the network consisted of several residual groups. Each residual group consisted of several residual blocks. This module implemented local feature fusion in each residual group and global feature fusion between each group. In addition, this model introduced coordinate attention module into each residual block and spatial attention module into each residual group. It verifies that the model is able to fully extract features and reuse features. The final experimental results show that the model is superior to the existing models in objective evaluation indexes and subjective visual effect. [ABSTRACT FROM AUTHOR]

This paper proposed an optimization model of deep-knowledge tracking（KTSA-BiGRU） based on self-attention mechanism and bidirectional GRU neural networks owing to the existing deep-knowledge tracking models with weak capture of complex relationships between input exercises and inability to effectively handle long-sequence input data. Firstly, it mapped the learner’s historical learning interaction sequence data to the real value vector sequence. Then, it trained the bidirectional GRU neural network as input to model the learner’s learning process, and finally used, the self-attention mechanism to calculate the probability of the learner correctly answering the next question based on the hidden vectors of the bidirectional GRU neural network output and the attention weight. The performance analysis on the three public datasets can improve the prediction accuracy of deep knowledge tracking. [ABSTRACT FROM AUTHOR]

Occlusion in a real environment is one of the main obstacles to accurately analyze and recognize facial expressions. In recent years, researchers have used deep learning technology to solve the problem of high misrecognition rate of facial ex-pressions under occlusion conditions. It mainly summarized the deep learning algorithm of occlusion facial expression recognition and occlusion-related issues. Firstly, this paper summarized the development status of facial expression recognition under partial occlusion conditions, expression representation, and the data set used to study occlusion expression. Secondly, it re-viewed the occlusion expression identify the latest developments in deep learning methods and analyzed the impact of occlusion on expressions. Finally, it summarized the main technical challenges, research difficulties and possible coping strategies. The purpose is to provide a more useful reference and benchmark for future research on occlusion expression recognition. [ABSTRACT FROM AUTHOR]

In sound event detection tasks, the target event was susceptible to background noise, and wasn't present in a significantly high portion of sound signal flow. To solve the problem, this paper proposed a new method of sound event detection based on one-dimensional dense convolutional network (DenseNet ) with multi-level attention mechanism. Firstly, it used the one-dimensional DenseNet for frame-level detection, which was effective in finding the precise onset and offset time. Then, it introduced the multi-level attention mechanism in the one-dimensional DenseNet model, which made the attention-aware features from different modules change adaptively as layers went deeper. Therefore, the model could automatically select and attend on important frames for the targets while ignoring the unrelated parts (e. g. the background noise segments) . Finally, this paper evaluated the model using DCASE 2017 Task 2 development dataset. Results show that the overall performance of the proposed method has further improvement than the conventional deep learning method. [ABSTRACT FROM AUTHOR]

This paper proposed constrained deep reinforcement learning( CDRL) to compute the fastest route online using taxi drivers' experience in different time period. Firstly, this paper described the extraction of experiential road segment database (ERSD). Then it introduced CDRL method, which mainly comprised of two phase: bounded condition of route and deep Q-learning algorithm. In the first phase, the task was to generate alternative constrained road segments of OD pair. In the second phase, it devised deep Q-learning algorithm to learning the experience of taxi drivers, and computed the fastest route of a given OD according to their departure time. Lastly, this paper tested an empirical studies in CBD of Guangzhou. The results show that the routes computed by CDRL method is approximately equal to shortest route ( SR) and fastest route (FR) method in travel time and route length. Furthermore, the CDRL method notably outperforms FR and SR in computing efficiency, so it is more suitable for online fastest route computation. [ABSTRACT FROM AUTHOR]

In order to understand the development of SISR based on deep learning and grasp the hotspots and directions of the current research, this paper combed the existing model of SISR based on deep learning. Firstly, the paper introduced the related deep learning algorithm, these models based on deep learning and their evaluation index. In addition, it compared the performance of existing models through experiments, which aimed to understand the advantages of SISR model based on deep learning. Finally, the paper summarized the key issues of SISR, and prospected the future development trends. [ABSTRACT FROM AUTHOR]

Because convolutional neural networks( CNN) mostly focus on global feature learning and ignore local feature information containing more details, it is difficult to improve the accuracy of indoor scene recognition. To solve this problem, this paper proposed an indoor scene recognition method based on improved global-local attention network ( GLANet). Firstly, it used GIAN et to capture the global and local features of the scene image to increase the detail information of the image features. Then, it introduced a non-local attention module into the local network to further preserve the detail features of the image through the convolution of attention diagram and feature graph. Finally, it used various features of different stages of the network for classification. Through training and verification on the MIT lndoor67 and the SUN397 dataset, the recognition accuracy of the proposed method was increased by l. 98% and 3. 07% respectively compared with the LGN method. Experimental results show that the algorithm can effectively capture global semantic information and fine spatial details, and significantly improves the recognition accuracy. [ABSTRACT FROM AUTHOR]

The rectangle layout optimization problem with balance constraints is derived from the layout design of satellite module equipment. It belongs to combinatorial optimization problem. Deep reinforcement learning uses reward mechanism to realize high-performance decision optimization through data training. This paper proposed a new deep reinforcement learning algorithm DAR and its extension IDAR. The DAR algorithm output the optimized location sequence with a pointer network, and then used the positioning mechanism to give the layout results. The training of pointer network was realized by deep reinforcement learning. The time complexity of the DAR algorithm was O ( n ³ ). The IDAR algorithm was an iteration version of DAR, which had better results but with a time complexity of 0 ( n 4 ). The test results show that DAR algorithm has good learning ability, and the model obtained by small layout problems can be effectively applied to large-scale problems. The results on two typical large-scaled instances show that the proposed algorithms have achieved or approached to the current best results, so that they have advantages both in time and solution quality. [ABSTRACT FROM AUTHOR]

With the popularity and development of deep learning, the existence of adversarial samples is a serious threat to the security of the deep learning model. For the attack problem of adversarial samples in the physical world, this paper proposed a physical adversarial sample detection method based on attention mechanism. The method combined attention mechanism and feature compression to detect pertinently of local visual adversarial samples, excluded effects of non-major regions, and reduced calculation effort. It effectively combined multiple feature compression methods to deal with the main areas of the sample, which destroyed the structure of the antagonistic block and made them unaggressive. Perform defense tests on different adversarial attacked on the MNIST and CIFAR-10 data sets and compared with other countermeasures. The experimental results show that the defense accuracy of the method can reach more than 95%. This method is higher versatility and stronger stability than other local adversarial sample defense methods, and can effectively defense the attack of local visual adversarial samples. [ABSTRACT FROM AUTHOR]

When the deep reinforcement learning algorithm is trained in a complex dynamic environment, it is difficult for the agent to obtain useful information due to the partial observability of the environment, which leads to typical problems such as failure to learn good strategies and slow algorithm convergence speed. This paper proposed an improved DDPG algorithm based on LSTM and asymmetric actor-critic network. This method introduced the LSTM structure into actor-critic network to learn the hidden states in partially observable Markov through memory reasoning. At the same time, when the actor network only used RGB images as partially observable inputs, the critic network used the complete state of the simulation environment to train, which formed an asymmetric network and speeded up the training convergence. The simulation experiment of manipulator grasping in ROS shows that the proposed algorithm has higher success rate and faster convergence speed compared with DDPG, PPO and LSTM-DDPG. [ABSTRACT FROM AUTHOR]

Ocean mesoscale eddy is an important ocean mesoscale phenomenon that plays an important role in ocean circulation, mat erial and energy transport, and has an important impact on the safety of ship navigation and hydroacoustic communication. Efficient and accurate detection and identification of ocean mesoscale eddies are of great research value for both physical ocean cognition and ocean exploitation. Traditional eddy detection and identification methods rely on a single threshold designed by experts experiences. With the rise of deep learning, the current machine learning methods show certain advantages in the accuracy and automation of eddy detection and identification. This paper summarizes and comparatively analyzes the existing machine learning-based detection and identification methods to provide a systematic knowledge and reference basis for the development of ocean mesoscale eddy detection and identification research. [ABSTRACT FROM AUTHOR]

Cloud segmentation is a key task in applications of Landsat8 remote sensing images. At present, most existing deep learning based approaches usually adopt the U-type coder-encoder network structure. Although this structure can make use of spatial location information from the coding end effectively, the whole network has too many parameters and cause high computation cost. Meanwhile, the coding end only adopts simple convolution and subsampling operation, which makes it impossible to obtain high-quality contextual semantic feature information effectively. In view of the above situation, this paper proposed a new lightweight U-Net model for cloud segmentation. The whole model adopted a new U-shaped codec structure that jumped and connected the information between the shallow layer and the middle layer at the coding end, and also embedded novel optimization blocks consist of grouping convolution and attention mechanism in coding end. It also built context-semantic fusion connection to link corresponding layers in coding and decoding end. Experimental results on the common benchmark dataset 38-Cloud illustrates, compared with other mainstream cloud segmentation networks, the proposed new U-Net can achieve better segmentation precision with less model parameters. [ABSTRACT FROM AUTHOR]

Aiming at the problems of complex background, variety of change types, missing detection and rough boundary recognition in high-resolution remote sensing image of the same region, this paper proposed a high-resolution remote sensing image building change detection algorithm based on Siam-UNet++network. The algorithm used UNet++as the backbone extraction network. In the encoder phase, it applied the Siam-diff structure to extract the change features of the two sequential images, and employed the attention mechanism after the up sampling and lateral jump path connection in the decoding stage to highlight the building change features and inhibit the network learning from other types of features. Meanwhile, it used the MSOF strategy to weight and fuse feature information of different semantic levels, which improved the accuracy of building change detection. Finally, it adopted a sliding window method to predict large-scale remote sensing images, reducing the hole pattern generated by the change result map during the splicing process. The experimental results demonstrate that proposed algorithm shows better performance than other models. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the recommendation model cannot mine the diversity of user interest and capture the order information between the sequence of user behavior, and the interaction occurs at the element level rather than between the feature vectors, etc., based on multiple attention mechanism and location information, this paper proposed the x DMAL FM. Firstly, it extracted the feature depth from different subspaces by using the multi-head attention mechanism, and then location information could capture the sequential relationship between user behavior sequences. Finally, it used three public datasets to conduct comparative experiments and the AUC index to evaluate the results. The experimental results show that the proposed algorithm has better recommendation performance than the xDeepFM model and show the effectiveness and feasibility of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Since it is difficult to online measure the underflow concentration of the thickener in the thickening-dehydration process, a broad learning system(BLS) based soft sensor modeling method is proposed in this paper. The method has high precision and strong generalization capability. First, several pressure sensors are installed inside the thickener, and the historical dataset under normal operating conditions is established. Then, the soft sensor model is trained by employing the BLS method to online predict the underflow concentration of the thickener. Finally, the efficiency of the proposed method is verified by simulation experiments. Compared with other traditional machine learning methods, the BLS method has higher prediction accuracy. [ABSTRACT FROM AUTHOR]

In order to maintain security and reliability of operating system, this paper developed a universal framework for net-work intrusion detection system based on artificial intelligence( AI) model. This framework was capability of detecting all sorts of network traffic, catching out possible malicious connection or attack from Internet and identifying it. Firstly, this system pre-processed the network traffic data by sampling, one-hot encoding, feature selection and normalization for basic feature extrac-tion. Secondly,it utilized feature distribution in network connection instance to build a scoring mechanism for information ex-traction once again. Thirdly, it applied the different types of ML/DL models for different forms of network traffic to do final classification for extracted features. In experiments, this system applied three benchmark datasets, KDDCup99, UNSW-NB15 and CICIDS2017. The result of experiments shows it possesses exceedingly good performance and has better accuracy and F1 score than related works under these datasets. [ABSTRACT FROM AUTHOR]

In order to improve the information processing ability of the model in complex scenes, this paper proposed a dynamic selection mechanism based on attention, which selectively allocated weights according to the current information, effectively fused the feature outputs of deformation convolution and ordinary convolution, and adaptively balanced deformable convolution and standard convolution, so as to improve its representation ability. In addition, the learning ability of the model was further enhanced by means of iteration without additional parameters. It used seven different kinds of noises from Noise-X92 in TIMIT corpus, and carried out experiments in various SNR environments. The results show that the proposed algorithm outperforms other recent deep learning algorithms in terms of intelligibility and speech quality, regardless of SNR and whether noise appears in the training data set. [ABSTRACT FROM AUTHOR]

Objective: Develop a machine learning model, and to evaluate its accuracy in the diagnosis of primary bone tumor around the knee joint. Methods: In this paper, the deep learning method of deep convolutional neural network（DCNN） was applied to the imagomics analysis of knee X-ray images, its clinical value in assisting the diagnosis of primary bone tumor around the knee joint were explored. Results: The deep learning model showed excellent diagnostic accuracy in differentiating normal images from tumor images.The overall accuracy of 5 rounds of testing using the DCNN model was（99.8±0.4） %, while the positive predictive value and negative predictive value were（100.0±0.0） % and（99.6±0.8） % respectively. The area under the curve（AUC） of each dataset was 0.99, 1.00,1.00, 1.0 and 1.0 respectively, average AUC was（0.998±0.004). A further 10 rounds of testing using the DCNN model showed an overall accuracy of（71.2±1.6） % in differentiating benign from malignant bone tumors, and a strong positive predictive value（91.9±8.5） %was achieved in differentiating benign and malignant bone tumor, the AUC of each dataset was 0.63, 0.63, 0.58, 0.69, 0.55, 0.63, 0.54,0.57, 0.73, 0.63 respectively, average AUC was（0.62±0.06). Conclusion: This is the first study on the application of artificial intelligence technology in the imaging analysis of X-ray images for bone tumor diagnosis, Artificial intelligence imaging models can help doctors to automatically and quickly screen bone tumors and identify benign or malignant tumors, with a high positive predictive value. MoreReset [ABSTRACT FROM AUTHOR]

Aspect words consist of multiple words, averaging the word vectors of all words may lead to semantic errors or confusion, and different context words have different influence on the judgment of emotional polarity for aspect words. This paper proposed a text sentiment analysis model that integrated the left and right bilateral attention mechanisms. First, the model designed an internal attention mechanism to process aspect words, and designed a bilateral interactive attention mechanism based on aspect words and context words, and finally cascaded the three parts of the processing result of bilateral interactive attention and the aspect word processing value for classification. Experiments on the two datasets from SemEval2014 task 4 show that the proposed model achieves 81. 33% and 74. 22% accuracy respectively, and has achieved better results than models that combine machine learning or attention mechanisms. [ABSTRACT FROM AUTHOR]