Search

Objective To discuss the feasibility of directly processing paper-based ECG by using deep learning method, and to propose a method for identifying atrial fibrillation ( AF) from paper-based ECG rapidly and accurately. Methods The 12-lead ECG signals of 1 040 AF and 1 344 non-AF patients were selected from CPSC 2018 Challenge data, and were plotted as ECGs. These ECGs were printed out on papers, and rescanned into images. The paper-based ECGs with white background were obtained by a series of preprocessing. These paper-based ECGs were used to construct AF recognition dataset; the artificial intelligence algorithm (AIA) was trained, validated and tested using the real labels provided by the Challenge as the gold standard. Results The sensitivity, specificity and F1 score of the AIA based on paper-based ECGs are 0. 957, 0. 978 and 0. 969, respectively, and the area under receiver operating characteristic curve is 0. 994. The Grad-CAM based feature visualization results show that in paper-based ECGs, the position of P wave and F wave at the onset of AF provide main references for the algorithm to identify AF, which is consistent with the ECG diagnostic criteria of AF in clinical practice. Conclusion The AF recognition algorithm based on paper-based ECGs shows good performance. The visualization results verify the high efficiency and feasibility of directly analyzing paper-based ECGs by using AIA, which could provide guidance for clinical practice. [ABSTRACT FROM AUTHOR]

In recent years, there has been rapid development in intelligent aquaculture and fisheries resource conservation, leading to an increased demand for fish tracking technologies. Traditional fish tracking methods rely heavily on visual observation and tag tracking, which suffer from low efficiency, limited applicability, and low accuracy, hindering their widespread adoption. With the rapid advancement of deep learning in computer vision, deep learning-based fish-tracking technologies can provide accurate, objective, scalable, and automated tracking methods. Firstly, this paper introduces the tracking objects and four deep learning-based fish tracking methods:semantic segmentation, instance segmentation, object detection, and object classification. Secondly, it describes how fish tracking technologies capture fish trajectories, postures, fish quantities, and fish lengths, which are important tracking information for fish targets. Furthermore, the application of deep learning-based fish tracking technologies in fish diseases, fish feeding behavior, and fish health status is discussed. The paper also explores the main challenges of current deep learning-based fish tracking technologies, including low contrast and texture blurring, image color distortion, occlusion, and deformation, along with some corresponding solutions. Finally, the paper concludes and provides an outlook on the future development of deep learningbased fish-tracking technologies. It suggests that deep learning-based fish tracking technologies offer higher accuracy and objectivity, providing more solutions for practical applications in different scenarios. This technology is expected to play a more significant role in aquaculture management, fish scientific research, and marine environment conservation, offering more data and support to relevant fields. [ABSTRACT FROM AUTHOR]

[Objectives]Because of the limit of camera field, the walnut point cloud suffers from missing points, which detrimentally affects the accuracy of walnut phenotype analysis. To enhance the accuracy and expedite the efficiency of walnut grading and classification, this paper proposed a walnut external parameter estimation approach with three-dimensional reconstruction. [Methods]We introduced a coarse-grained realistic structure with the point cloud generation network(CGRSNet)to form a point cloud completion network with an encoding-decoding mechanism. Firstly, a new sampling algorithm was implemented to extract feature information of the original point cloud in different dimensions and thereby increased the feature extraction effectiveness of walnut phenotype. Afterward, the autoencoder was utilized to reconstruct the point cloud in multiple dimensions, and a complete walnut shape was eventually obtained. In the end, the parameters of the model were applied to estimate the volume of walnut. The walnut geometry model generated by multiple parameters was digitized into the point cloud data to feed CGRSNet and get a pre-trained walnut geometry model through shape completion. A fine-tuning process was then conducted with the real walnut point cloud data. [Results]The chamfer distance of the completion network for walnut data set was 0.196 cm. According to the linear regression analysis, the RMSE and R² score of the volume estimation were 2.47cm and 0.94, respectively, which were 0.88 cm and 0.01 higher than those of PF-Net, respectively. [Conclusions]The walnut external parameter estimation algorithm based on CGRSNet proposed in this paper presents satisfactory practicability and accuracy. [ABSTRACT FROM AUTHOR]

In industrial production, defects are treated differently based on their severity, so it is necessary to classify defects. However, in actual production, the classification accuracy is often insufficient due to the presence of few easily confused defects, which requires conservative treatment of all defects in production practice, resulting in significant human and economic costs. To solve this problem, this paper proposes a method for interactive separating easily confused defects. This method separates few easily confused defects from other defects, ensuring that the classification results of the remaining majority of defects can be directly used. This method selects easily confused defects from the training data as one or more new defect categories, called virtual defects, so that the trained network can distinguish between virtual defects and other defects. This paper designs a visual interface to assist users in interactively selecting easily confused defects to construct virtual categories. CMOS defect data from actual industrial sites are adopted for effectiveness verification, and the results show that the proposed method can quickly classify few confusing defects and ensure that the classification accuracy of remaining defects meets the requirements of industrial applications. [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]

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]

Implementing fast and accurate hand detection on embedded devices mainly face two challenges. Firstly, it is difficult for complex deep learning networks to achieve real-time hand detection. Secondly, the complexity of the scene leads to a decrease in the accuracy of hand detection algorithms based on RGB color images. Unlike mainstream RGB image based detection technologies, this paper adopted a lightweight hand detection algorithm based on ToF infrared images to attain precise and swift hand detection within the infrared images. Firstly, this paper gathered 22 419 static infrared images using this self-engineered equipment, thereby establishing an infrared dataset tailored for hand detection. Subsequently, it enhanced a general object detection algorithm to create a lightweight hand detection network known as Retina Hand, using two different lightweight networks, MobileNetV1 and Shuffle NetV2, as the backbone network of the model. Furthermore, this paper proposed an attention-enhanced feature pyramid structure called Attention-FPN. This structure integrated attention mechanisms to enhance the detection process. Ultimately, this paper conducted comparative experiments on the infrared dataset against conventional methods to validate the effectiveness of the method. [ABSTRACT FROM AUTHOR]

Voice conversion is a research topic in the fields of speech and artificial intelligence. The goal of voice conversion is to change the timbre of speech while preserving the content of the source speech, making it sounds like spoken by the target speaker. It is essential to ensure both the quality and naturalness of the converted speech. Voice conversion based on nonparallel data gains much attention currently, where models are trained using non-parallel multilingual speaker datasets, enabling many-to-many and any-to-any voice conversions. This paper provides a comprehensive summary and analysis of recent developments in non-parallel voice conversion. Firstly, we outline the early voice conversion techniques based on parallel corpus and their limitations. Then, we introduce and compare various approaches to voice conversion based on nonparallel data, providing a thorough analysis. Finally, a summary and outlook on voice conversion technology is provided. [ABSTRACT FROM AUTHOR]

Objectives: Recognition of building group patterns is an important part of the building generalization. Efficient methods for the recognition of building group patterns can effectively improve the quality of automated map generalization. Traditional recognition methods mainly include geometric methods and traditional machine learning methods, which are limited by the complex rule definitions and huge feature engineering. The graph convolution neural network (GCN) can overcome the limitations of traditional methods to some extent and has been successfully applied to the pattern analysis of buildings. However, there are few methods to recognize multiple building group patterns using GCN, and the existing GCN methods are almost based on spectral graph convolution, which do not consider local spatial information fully. Methods: As the spatial GCN is more efficient than the spectral GCN, this paper introduces a spatial GCN method DGCNN to recognize three building group patterns, including linear pattern, grid pattern and irregular pattern. The first step is to cluster the buildings into different groups, then some indices are selected to construct the feature vector of each group according to the Gestalt principles. Second, Delaunay triangulation (DT) and minimum spanning tree (MST) are chosen to construct graph structures of building groups. Finally, graph structures are used as input for the DGCNN model, and building group patterns are obtained after training. Results: The experiment selects the urban areas in Shanghai and we compare the accuracies with traditional spectral GCN method. The results show that the accuracy for the DGCNN model in the train set can reach 97.06%, and 95% for the test set. And the accuracies for the spectral GCN model in the train set is 90.90%, and 86.05% in the test set. Conclusions: The proposed method overcomes the limitations of spectral GCN, and it does not need graph Fourier transform. It can improve the recognition accuracy significantly and faces less difficulty in explaining the process of feature extraction. Hence it is an effective method for the recognition of building group patterns. [ABSTRACT FROM AUTHOR]

Deep learning is a machine learning method in the field of artificial intelligence, which simulates the workings of the neural network of the human brain to solve complex problems, and has been used in many important researches and applications in the field of medicine, such as diagnostic imaging, biomedical data processing, drug research and development, personalized medicine, etc., which improves the accuracy and efficiency of diagnosis and treatment. In the field of assisted reproduction, deep learning could efficiently identify well-grown embryos, suitable oocytes, or sperms during the intervention process, assisting medical staff to make more accurate choices to improve pregnancy rates and reduce the risk of multiple pregnancies. This paper summarizes the latest advances in the application of deep learning in the field of assisted reproduction technology in the past 5 years, and provides an outlook for future research. [ABSTRACT FROM AUTHOR]

In response to the existing gun sound recognition and positioning tasks, which require separate identification and positioning, resulting in time-consuming computation, system redundancy, and complex development processes, this paper proposes to use a two-stage CRNN deep learning network model to complete the gun sound recognition and positioning tasks. Firstly, perform a logarithmic Mel transform on the collected gunshot signal and calculate the generalized phase transition cross correlation spectrum as input to the network model. Secondly, in the first stage, the gunshot signal is identified through the CRNN network. Finally, in the second stage, the introduction of a mask is used to determine whether the CRNN network weight sharing is implemented for localization. The method proposed in this article can effectively solve the problems of separate recognition and positioning tasks, system redundancy, and complex development processes in traditional methods, and has certain application value in achieving joint recognition and positioning. [ABSTRACT FROM AUTHOR]

The radar echo extrapolation method is widely used in rainfall forecasting. Addressing the issue of insufficient prediction accuracy in radar echoes, this paper proposed a deep learning model DIPredRNN based on recurrent neural networks. This model combined long-term temporal and channel information by introducing a dual attention mechanism of space and channel, improved the long-term dependence of time memory. By introducing an interactive framework of hidden states and inputs, it retained more features and improved the short-term dependence of temporal memory. This model was experimentally compared with classical models and many advanced models on the HKO-7 and Sichuan datasets. The model achieved the best results in comparing multiple indicators such as extrapolated images, MSE, SSIM, CSI-30~50 dbz. The experiment proves that the proposed DIPredRNN network improves the radar echo prediction performance and has advanced performance. [ABSTRACT FROM AUTHOR]

The majority of current machine learning and deep learning solutions for ECG-based emotion recognition utilize fully-supervised learning methods. Several limitations of this approach are that large human-annotated datasets and computing resources are required. Furthermore, the feature representations learned by fully supervised methods tend to be task-specific with limited generalization capability. In response to these issues, this paper proposed an approach based on contrastive lear-ning for ECG-based emotion recognition, which consisted of two steps, such as pre-training and fine-tuning. The goal of pre-training was to learn representations from unlabeled EGG data through contrastive learning. Specifically, it designed two simple and efficient ECG signal augmentation methods, and used these two views to learn robust temporal representations in the time contrastive module, followed by learning discriminative feature representations in the context contrastive module. Fine-tuning used labelled data to learn emotion recognition. Experiments show that the proposed method has reached the maximum accuracy on three public ECG-based emotion recognition datasets. Additionally, the proposed method shows high efficiency under the semi-supervised settings. [ABSTRACT FROM AUTHOR]

Recognizing the phase transition of matter is an important problem in physics research. Convolutional neural network algorithm of confusion label scheme is used to identify quantum phase transition point of two- component Bose-Einstein condensates (BEC) in this paper. By calculating the output accuracy of neural net- work, the W-shape performance curve is obtained. The maximum value in the middle of W-shape performance curve corresponds to the critical point of quantum phase transition. The research results show that the critical point obtained by deep learning is consistent with the analytic calculation results. The deep learning method of confusion label scheme can be applied to the phase transition system of existing two phases. [ABSTRACT FROM AUTHOR]

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]

The intermittent, random and uncontrollable power generation characteristics of renewable energy pose challenges for the full utilization of green energy. The high energy consumption feature of the virtual power plant data center makes it an efficient absorption and regulation strategy for the intermittent (non-dispatchable) power in renewable energy. This paper proposes a method to predict the "source-load" dual-state of the virtual power plant using a long short-term memory network that incorporates time-embedded encoding. The results indicate that using the model presented in this paper can achieve proactive alerts for "power shortages" at 15-minute intervals, creating ample buffer time windows for container suspension and backup. Combined with container technology, it realizes dynamic energy consumption management in data centers, thereby enhancing the robustness of the virtual power plant data center against power supply-demand imbalances. This technology is of great significance for stabilizing grid operations, accelerating the application of green clean energy, constructing a service pattern for the energy ecosystem and speeding up the digital transformation of the grid. [ABSTRACT FROM AUTHOR]

The management of safety hazards in water conservancy engineering construction is transitioning towards informatization and intelligence. In order to efficiently mine valuable potential information from a large amount of unstructured construction safety hazard data, an intelligent recommendation system for construction safety hazard rectification based on deep learning is proposed. This paper is based on the TF-IDF algorithm to extract feature words of hidden danger, construct a safety hazard association Sankey diagram and display the information flow characteristics among construction sections, hazard features and hazard types. Then, this paper mines association rules in historical data based on the FP-Growth algorithm. In addition, the process of case retrieval recommendation is optimized by combining the sequence similarity matching algorithm and the Doc2Vec model. This paper uses 80 953 construction safety hazard information as the data source, which is recorded in the water resources allocation project of Pearl River Delta from 2019 to 2023. Example verification shows that the proposed method can match accurate rectification measures for current construction safety hazards, effectively assisting construction safety managers to identify and address hidden danger. [ABSTRACT FROM AUTHOR]

HD maps can provide accurate road information and rich semantic information, so that the automatic driving system can guide the vehicle to drive correctly. HD maps usually rely on manual labeling. The existing automatic labeling methods have low recognition accuracy in autonomous driving scenarios, resulting in low efficiency of HD map labeling. In order to solve this problem, this paper proposed a new semantic segmentation method for automatic labeling of HD maps called MapFormer. This paper proposed a multi-level feature fusion module, which enabled the model to aggregate different levels of detail and semantic information. Additionally, it proposed a novel boundary-decoupled joint decoder to improve the model's ability to handle intercategory boundaries. Experiments on the bird's-eye view dataset show that the proposed model not only achieves excellent performance in segmentation accuracy, but also has a clearer handling of category boundaries. The mIoU of MapFormer is 55.82%, which is higher than the SegFormer of 1.03%. The proposed method can improve the HD map labeling efficiency and labeling automation rate. [ABSTRACT FROM AUTHOR]

To address the problem of insufficient recommendation performance in session recommendation, this paper proposed a disentangled graph neural network model (GDST-GNN) using global graph diffusion and spatio-temporal awareness. Specifically, the model firstly constructed a global collaborative graph based on all sessions from a global perspective, and then employed graph diffusion as the message propagation paradigm for global representation learning of items to capture global information be- yond the current session. For the representation learning of the current session, this paper designed a disentangled spatio-temporal gated network modeling the complex transition pattern and temporal dependency pattern of items in the session, and then fused the learned global and local representations factor by factor. In addition, this paper employed a self-supervised task to achieve performance enhancement of the model. Finally, it generated session representations through attention networks to achieve accurate recommendation of items. Extensive experiments on four real-world datasets validate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Rice shrimp co-cultivation, as a circular agriculture model that integrates ecological, economic, and social benefits, has been widely applied in China. Accurately obtaining information on the planting area, spatial distribution, and changes of rice shrimp co-cultivation is of great significance for ensuring safe production, social supply of rice and shrimp, and formulating corresponding management and planning policies by government departments. Most of the existing methods for extracting rice shrimp farming fields used medium-resolution temporal images as data sources to analyze the characteristics of water or vegetation changes within a year to construct models. The accuracy of the extraction depended on the results of water or vegetation analysis, the boundaries were unclear and there was a lot of noise. To solve the problems of complex temporal analysis, low accuracy of extraction results, and incomplete boundaries in existing extraction methods, this paper used high-resolution images of a single temporal phase as the data source, without analyzing the temporal features of rice shrimp farming fields. Only the spatial features of rice shrimp farming fields on high-resolution images were used for high-precision extraction. We proposed a deep learning semantic segmentation model named EASNet (edge assisted segmentation network), which was mainly composed of three modules: feature extraction module (FE Module), edge assist module (EA Module), and information fusion Module (IF Module). The FE Module was used to extract multi-level and fused contextual semantic information features of the target object. The EA module used the unique edge "shrimp groove" of rice and shrimp farming fields as an auxiliary information for separate segmentation in the designed EA Module. The IF Module integrated the outputs of the FE Module and the EA Module, enabling the main task to not only enhanced the boundary structure information of rice shrimp farming fields but also learned the unique spatial and semantic information of rice shrimp farming fields. The experimental results showed that with the enhancement of the EA Module, the segmentation results of rice shrimp farming fields were more complete and the boundaries were clearer. The IoU (Intersection over Union) of semantic accuracy and the F1-Score of boundary accuracy were improved by 1.5% and 5.8%, respectively. The recall, IoU, and F1-Score of overall semantic accuracy reached 0.970, 0.964, and 0.930, respectively. The Recall and F1-Score of boundary accuracy reached 0.864 and 0.859, while the Recall and F1-Score of relaxed boundary accuracy reached 0.876 and 0.913. The trained EASNet model was applied to the whole area of Xuyi County, and the spatial distribution map of rice shrimp farming fields in Xuyi County in 2020 was obtained. In comparison with the results of rice shrimp breeding fields extracted by the traditional Water Seasonal Difference method and the Random Forest method, our method obtained the optimal results with an OA(overall accuracy) of 96.71% and a Kappa coefficient of 0.934. The method used in this paper has higher accuracy, lower missing rate, more regular boundaries, and fewer instances of similar integration in extracting results. It can provide a basis for natural resource surveys, and government departments to formulate corresponding rice shrimp breeding management and planning policies. [ABSTRACT FROM AUTHOR]

Objectives: The Mw 7.8 earthquake occurred in Turkey on February 6th, 2023, which is a rare powerful earthquake in recent years. Building collapse detection is an important part of post-earthquake damage assessment and emergency rescue. Facing the emergency rescue and post-earthquake disaster assessment, this paper aims to comprehensively utilize the intelligent interpretation technology of satellite remote sensing, coupled with high-resolution optical daily and night-time light remote sensing images, and to efficiently assess the collapsed buildings in the extreme disaster areas with low time and labor costs. Methods: In this paper, we present a multi-level rapid localization scheme for disaster-affected regions. First, the proposed approach involves the utilization of low- and medium-resolution night-time light data to estimate the extent of extreme disaster areas. Subsequently, high-resolution optical remote sensing imagery is employed to extract the collapsed buildings. By training a semi-supervised deep learning network with a small number of manually collected samples, the scheme automatically identifies collapse areas, thereby facilitating the precise localization of collapsed buildings. A high-resolution architecture network, HRNet, is employed in this study. HRNet has the advantages in both sematic and spatial feature representation, and can capture the collapsed buildings with muti-scale characteristics. Results: Six cities along the border between the Arab Plate and the Eurasian Plate are severely affected, from Adelman to Kahraman Marrash, and then to Antakia. A total of 2 377 collapsed buildings are detected in the extreme disaster areas. Except for Nurdaji and Antakia cities, where the proportion of collapsed buildings exceeded 2%, the proportion of collapsed buildings in the other four cities is close to 1%. After manual verification, the recall rate of the intelligent interpretation plan is between 74% and 93%. Conclusions: The efficiency and effectiveness of this approach are demonstrated through its application in assessing the building collapse situation after the Mw 7.8 earthquake in Turkey. The proposed work can serve as a timely reference for macro decision-making in post-earthquake emergency rescue operations. [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]

As a popular research direction in the field of artificial intelligence, Facial Expression Recognition (FER) is the most direct and effective way for computers to access human emotions. It occupies a key technical position in human-computer interaction, intelligent medical care, fatigue driving, and other R＆D topics. In order to meet the application requirements of high recognition rate, the structure of FER deep learning network becomes more and more complex, occupying a large amount of computing resources and storage space, which seriously affects the real-time requirements of the algorithm. This paper focuses on the problem of how to guarantee the accuracy of the model while effectively improving its computational speed. Firstly, it introduces the important datasets for expression recognition using lightweight networks; Secondly, it analyzes the classical lightweight network models used for facial expression recognition; Thirdly, it describes the principles, characteristics, and applicable scenarios of the main network lightweighting methods; Finally, it summarizes the problems and challenges of lightweight networks in facial expression recognition research and looks forward to the future research direction. [ABSTRACT FROM AUTHOR]

Objective: Deep convolutional neural network (DCNN) is widely used in automatic road extraction from high-resolution remote sensing images (HRSIs). However, the existing methods make it difficult to model the context relationship of pixels in the predicted results. To solve this problem, some studies have used fully connected conditional random field (FullCRF) to perform secondary optimization of semantic segmentation results combined with context information, but the discontinuity problem of road structure cannot be effectively improved. Methods: In order to improve the integrity of road structure, this paper proposes a short range conditional random filed (SRCRF) model combined with DCNN. SRCRF mainly includes a unary potential function based on road pre-segmentation, a binary potential function based on spectral spatial features, and a K-neighborhood mean field inference algorithm. First, the prior knowledge of road pre-segmentation results is obtained by using the powerful feature extraction capability of DCNN as the unary potential function of SRCRF. Then, the dependence of the binary potential function defined by the linear combination of Gaussian kernel functions on the surrounding nodes is modeled. The binary potential function enables the classification results to have local consistency,that is, adjacent pixels with similar spectral features have the same label. Finally, the K-neighborhood mean field inference algorithm based on the mean-field approximation inference algorithm optimizes the inference range to make full use of the spatial context information and spectral feature context information of the road, and then calculates the optimal label corresponding to each pixel based on the space and spectral feature to optimize the road accurately. The convolution method is adopted to control the inference range of SRCRF within the radius of K in order to improve the proportion of feature vectors. Results: The experimental results show that SRCRF not only alleviates the transition smoothness of FullCRF, but also alleviates the structural discontinuity and incompleteness in the road acquisition results of HRSIs. In Zimbawe-Roads dataset and Cheng-Roads dataset, F1-scores of SRCRF are increased by about 4.01% and 3.73% respectively compared with DCNN, and about 3.25% and 2.28% respectively compared with FullCRF. Conclusions: The proposed SRCRF combines the advantages of DCNN, optimizes the fully connected structure of traditional conditional random fields into the K-neighborhood structure, reduces the inference scope, and improves the proportion of feature vectors. Compared with FullCRF, SRCRF can make better use of image color features and spatial features to accurately optimize the road extraction results of deep learning output. The performance of SRCRF is improved compared with DCNN and FullCRF, and the time is shortened by one order of magnitude compared with FullCRF. In the future, we will further investigate the potential for learning Gaussian features and investigate more complex architecture of conditional random field to better capture global context information. Additionally, we are particularly interested in exploring the application potential of SRCRF in other fields, such as building extraction, vehicle extraction, lake extraction, etc. [ABSTRACT FROM AUTHOR]

In the past 20 years, the development of artificial intelligence has made rapid progress, and it is increasingly applied in the medical field, including medical image-assisted diagnosis and treatment, health management, disease risk prediction and so on. In this paper, the application status of artificial intelligence-assisted detection and diagnosis system based on deep learning in anorectal diseases is summarized, and the new methods related to the diagnosis and treatment of anorectal diseases at home and abroad are summarized. It mainly reviews the research progress of artificial intelligence technology in the diagnosis and treatment of anal fistula, perianal abscess, hemorrhoids and other anorectal diseases. [ABSTRACT FROM AUTHOR]

The large amount of medical information carried in the electronic medical record can help doctors better understand the situation of patients and assist doctors in clinical diagnosis. As the two core tasks of Chinese electronic medical record (EMR) information extraction, named entity recognition and entity relationship extraction have become the main research directions. Its main goal is to identify the medical entities in the EMR text and extract the medical relationships between the entities. This paper systematically expounds the research status of Chinese electronic medical record, points out the important role of named entity recognition and entity relationship extraction in Chinese electronic medical record information extraction, then introduces the latest research results of named entity recognition and relationship extraction algorithm for Chinese electronic medical record information extraction, and analyzes the advantages and disadvantages of each model in each stage. In addition, the current problems of Chinese EMR are discussed, and the future research trend is prospected. [ABSTRACT FROM AUTHOR]

The current research on the application of artificial intelligence techniques to the field of system architecture is promising, especially the research on applying deep learning to data prefetching in multicore architectures has become a research hotspot at home and abroad. This work studied the cache prefetching task based on deep learning and defined the deep learning cache prefetch model formally. Based on the introduction of current common multi-core cache architectures and prefetching techniques, this paper comprehensively analyzed the design ideas of existing typical cache prefetchers based on deep learning. The application of deep learning neural network in the field of multicore cache prefetching mainly adopts machine learning methods such as deep neural network, recurrent neural network, long and short-term memory network and attention mechanism. A comprehensive comparative analysis of existing deep learning-based data prefetching hierarchical neural models reveals that deep learning-based multicore cache prefetching techniques still have certain computational cost, model optimization, and practicality. In the future, there is still much room for research exploration and development prospect in adaptive prefetching models and the practicality of neural network prefetching models. [ABSTRACT FROM AUTHOR]

Atmospheric turbulence is a crucial factor that affects the quality of long-distance imaging. Though current deep learning models can effectively suppress geometric displacement and spatial blurring caused by atmospheric turbulence, such models require a large number of parameters and computational resources. To tackle this problem, this paper proposed a lightweight atmospheric turbulence degraded image restoration model based on generative inversion that entailed three core mo-dules: the DeBlur module, the remove shift module, and the turbulence regeneration module. The DeBlur module used high-dimensional feature mapping blocks, detail feature extraction blocks, and feature compensation blocks to suppress image blurring caused by turbulence. The remove shift module compensated for pixel displacement caused by turbulence using two convolutional layers. The turbulence regeneration module regenerated turbulence degraded images through convolutional operations. In the DeBlur module, it designed an attention-based feature compensation module that integrated the channel attention mechanism and the spatial mixed attention mechanism to focus on essential detail information in the image during training. The proposed model achieved peak signal-to-noise ratios of 19.94 dB and 23.51 dB, and structural similarity values of 0.688 2 and 0.752 1 on publicly available dataset Heat Chamber and self-built dataset Helen, respectively. Furthermore, it reduced the number of parameters and computational resources, compared to the current state-of-the-art(SOTA) method. The experimental results demonstrate the effectiveness of this method in restoring atmospheric turbulence degraded images. [ABSTRACT FROM AUTHOR]

The development of medical imaging technology has generated a massive amount of medical image data, which reflects the internal structural features of the human body. Medical image segmentation technology can improve the efficiency of medical diagnosis, making it an important assistive tool for modern medical diagnosis. However, noise or artifacts that are inevitably present in the imaging process bring great challenges to the segmentation work. In existing segmentation models, single-frame medical image semantic segmentation models do not consider the relationship between image frames, while video semantic segmentation models utilize temporal information but have some limitations in edge extraction. To address these issues, this paper proposes a U-Net-based temporal semantic segmentation model modified by optical flow. This model can extract optical flow information between consecutive frames and perform feature extraction and weight allocation on the current frame and optical flow for correction. Experiments show that the model obtains optimal results on three evaluation metrics, namely Dice similarity, pixel accuracy and cross-merge ratio, on different types of datasets, namely Drosophila electron micrographs, combined healthy abdominal organ segmentation and coronary angiogram, which validate the effectiveness and generalization of the proposed model. [ABSTRACT FROM AUTHOR]

For the problem of image degradation caused by raindrops attached to the lens or glass surface, this paper proposed a multi-stage progressive image raindrop removal method which divides the raindrop removal process into multiple stages to easily implement. First, the multi-scale fused encoder-decoder network at each stage designed to learn raindrop features. The constructed multi-scale dilated convolutions with gated recurrent units refined the internally transferred spatial features. In addition, the no dimensionality reduction channel attention module extracted channel information under specific spatial features. Finally, this paper adopted cross-stage feature fusion mechanism to strengthen the information exchange between the parts of each stage. Adding horizontal connections between the encoder-decoder networks in each stage to realize the horizontal transfer of feature information. And adding a supervised attention module to enhance the information transmission between different stages. The raindrop removal is progressively achieved. Experiments show that the proposed method can effectively remove raindrops. [ABSTRACT FROM AUTHOR]

Aiming at the problem that feature extraction is inaccurate and the reconstruction image is not natural enough in blind super-resolution reconstruction, this paper proposed an image blind super-resolution reconstruction based on degradation aware and sequence residuals. This paper proposed a mini-residual group combined degeneration aware and sequence residuals as the backbone network. Then the method constructed a symmetrical enhanced multi-scale residual block. In the image reconstruction part, this paper used the bottleneck attention module and the sub-pixel convolutional module to emphasize the multi-dimensional elements of the image. Finally, the method made a global residual connection. Compared with the current representative algorithm DASR, experiments show that the PSNR and SSIM of the proposed algorithm are improved 0.145dB and 0.0014 on Set14×2, and the PSNR of the proposed algorithm is improved 1.898dB and 0.252dB on Set14×3/4, respectively. The proposed algorithm achieves better performance than several current image super-resolution algorithms on five standard test sets. [ABSTRACT FROM AUTHOR]

In the detection of log volume, the accuracy and stability of the intelligent detection system are easily affected by the factors such as end cutting marks, cracks, shadows and so on. For a long time, the end face recognition and positioning is a difficult problem. For this reason, through the principle analysis and experimental verification of multiple YOLO version models, this paper has fused the advantages of multiple YOLO version models. On the basis of the yolo3 backbone network, using data enhancement, feature fusion, loss function and other optimization methods, an end-to-end depth learning model YOLO-Raw Wood (YOLO-RW) is constructed, which is more suitable for log detection and is used for accurate recognition and localization of log volume images. In order to test the performance of the YOLO-RW model, this paper has designed several sets of data experiments. The experimental results show that the YOLO-RW model has higher end face recognition accuracy and robustness than the benchmark model, and is 6. 95% and 2. 38% higher than the benchmark model in terms of preparation rate and recall rate. Therefore, the YOLO-RW model has a good application value in the field of log volume detection, and can also provide a reference for the research of related target recognition fields. [ABSTRACT FROM AUTHOR]

Objectives: It is difficult for the traditional traffic information acquisition method to obtain the real-time dynamic traffic flow information of large scope and full coverage. With urbanization, the increasing number of supertall buildings makes the city skyline a favorable platform for earth observation. This paper studies the urban remote sensing video production and traffic information extraction method using the urban skyline as the observation platform. Methods: First, the earth observation data shooting is carried out in the super-tall buildings. Then, the original oblique observation data is corrected by orthography, which is further fused with the satellite image to generate a large range of remote sensing video data of the city. Finally, we train a deep learning model and use it for vehicle classification and identification. The number and density of vehicles in the area are calculated based on the identification results. Results: This paper carries out data collection and processing analysis on the sightseeing floor of Ping, an Building in Shenzhen. Results show that the proposed method can produce low-cost, long-time, large-scale and high-quality urban remote sensing video. The vehicle detection based on the remote sensing video have high accuracy. Conclusions: The proposed framework can be used to effectively monitor the regional traffic flow and sever for the smart city management. Furthermore, based on its capability of long-time, high-resolution, full-coverage and real-time remote sensing, this method can also be applied to many other urban management fields, such as urban disaster emergency response, crowd monitoring, and construction site monitoring. [ABSTRACT FROM AUTHOR]

This paper analyzes and combs the application and research status of artificial intelligence technology in the field. of military intelligence, in order to provide reference for subsequent military intelligence research. This paper summarizes the development and application of artificial intelligence in military intelligence work from the aspects of intelligence analysis and military command decision-making. Based on the intelligence workflow, the military intelligence service model under artificial intelligence technology is analyzed. This paper systematically combs the research and development status of typical projects of intelligent intelligence systems in the United States, and analyzes the key development trends and technical difficulties of artificial intelligence in the military intelligence field. [ABSTRACT FROM AUTHOR]

Aiming at the problem of insufficient feature extraction ability of deep clustering algorithm on multivariate time series data( MTS), This paper proposes a new deep clustering structure model (MDTC. In order to extract the key features of MTS and realize dimensionality reduction, one-dimensional convolution learns the attribute and temporal dimension feature representation of MTS and the autoencoder structure composed of network layers such as recurrent neural network; To improve the model’s ability to represent temporal features, this paper proposes MCBAM temporal attention module, which is used to enhance the representation features of different time periods in the MTS sequence. This paper conducts experiments on nine publicly available UEA multivariate time series datasets, compared with other autoencoders, the autoencoder structure of the model improves by 2%-9% on 7 data sets; Compared with other attention modules, the MCBAM module of the model improves by 0.3%-2% on the six datasets. Experiments show the effectiveness of the MDTC model structure and MCBAM module, and the model has excellent performance compared with other clustering algorithms. [ABSTRACT FROM AUTHOR]

The level of face recognition technology continues to improve, and has achieved an ideal recognition rate in identity authentication, human-computer interaction and other industrial applications, and the market scale keeps growing. However, the occlusion problem in real scenes has not been completely solved. How to restrain or eliminate the negative impact of occlusion on key facial feature, is one of the hot spots in the field of face recognition. Aiming at the problem of lack of face structure information caused by occlusion, this paper reviews the occluded face recognition datasets and the occluded face recognition methods. Firstly, this paper introduces and analyzes some important new occluded face recognition datasets; Secondly, this paper summarizes the traditional learning methods and deep learning based methods to solve occlusion problems, and emphasizes the deep learning based robustness feature extraction and occluded facial information recovery. Finally, this paper summarizes and analyzes the advantages and disadvantages of relevant methods, points out the problems and challenges of occluded face recognition, and prospects the future research directions. [ABSTRACT FROM AUTHOR]

Video distortion mainly comes from the degradation of video quality caused by spatial and temporal distortion. Aiming at these two kinds of video quality degradation, this paper proposed a full-reference video quality assessment method STPFVQA combining spatio-temporal features and visual perception. Firstly, the method extracted spatial perceptual features from reference video and distorted video using ResNet50 convolutional network. Secondly, the method feeded the extracted spatial perceptual features into transformer’s encoder and decoder to construct the serialization relationship of the video, and at the same time to explore the effect of distortion on the video serialization relationship by comparing the reference video and distorted video Then, the method sent the output of the transformer to the prediction header to form a frame-level score Finally, in order to simulate the hysteresis of human visual system perception, this paper obtained the video quality score from the short-term, long-term and global memory effects. To verify the feasibility of the method, this paper conducted experiments on four datasets, respectively LIVE,IVC-IC,CSIQ,and IVPL. The experimental results show that the proposed method is more consistent with the perception of the human visual system. Compared with the state-of-the-art serial dependence model（SDM） on the IVC-IC and CSIQ datasets, the SROCC is 2.6% and 3.1% higher, the KROCC is 6.1% and 7.9% higher, and the PLCC is 2.3% and 5.5% higher. [ABSTRACT FROM AUTHOR]

In order to address the shortcomings of the facial landmarks detection models, which cannot model the relations between long-distance landmarks, this paper proposed a parallel multi-branch architecture combining with convolution and Transformer for facial landmarks tasks, called MCTN, it utilized the dynamic attention mechanism to model the long-distance relations between facial landmarks. The multi-branch parallel structure designing allowed MCTN to include shared weights, global information fusion and other merits. What’s more, this paper proposed the novel Transformer structure, Deformer, which could make the MCTN focused attention weights faster on sparse and meaningful locations and solved the problem of slow convergence of Transformer. MCTN reached 4.33%,3.12% and 3.15% normalized average error respectively on the WFLW,300W and COFW datasets, the results show that MCTN utilizes Transformer with CNN multi-branch parallel structure and Deformer structure to dramatically outperform other facial landmarks localization algorithms based on convolution network. [ABSTRACT FROM AUTHOR]

Long-tail characteristic of data has always been a great challenge in solving computer vision problems. To solve the difficulties brought to instance segmentation, image re-sampling, a simple and efficient method has always been used. However, there may be many classes in one image, it’s hard to balance different classes on the data level. This paper proposed a object-centric post-processable memory bank method. Firstly, it introduced a memory bank model and set up an object-based storage policy to address the number imbalance of categories. Then, in order to increase the predicted score for tail classes and common classes, it used a post-processing calibration to adjust the confidence score of each class. This paper verified the effectiveness of the proposed method by experiments on LVIS dataset. The accuracy can be improved by 2.2% compared to EQL method. [ABSTRACT FROM AUTHOR]

COVID-19 is spreading rapidly around the world. In order to diagnose it quickly and accurately and thus block the chain of epidemic transmission, the study proposed a deep learning-based classification network DLDA-A-DenseNet. Firstly, DenseNet-201 combined deep layer dense aggregation to aggregate feature information at different stages to enhance its ability to identify and localize lesions. Secondly, this paper proposed efficient multi-scale long-range attention to refine the aggregated features. Moreover, this paper used a balanced sampling training strategy to eliminate the bias for the class imbalance problem of CT image dataset. Testing on the China consortium of chest CT image investigation dataset, the method improved 2.24%,3.09%,2.09%,2.60% and 3.48% in accuracy, recall, precision, F1 score and Kappa coefficient compared with DenseNet-201,and achieved an optimal accuracy of 99.50% on COVID-CISet image dataset. The results show that the proposed COVID-19 CT image classification method can fully extract the lesion features of CT slices compared with other methods, and has higher classification accuracy and good generalizability. [ABSTRACT FROM AUTHOR]

Collaborative intrusion detection system (CIDS) can detect distributed cooperative attacks and deal with large-scale network intrusion. It has the advantages that traditional intrusion detection systems do not have. How to improve the detection performance while achieving decentralization is an important research topic. Through reviewing the research achievements of CIDS in recent years, this paper expounded the research progress and problems in detection methods, data aggregation, privacy protection and trust management, analyzed the challenges faced in decentralization, discussed the future development direction of CIDS based on blockchain technology. Finally this paper looked forward to the application prospects of CIDS in cloud computing, the Internet of Things and other emerging fields. [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]

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]

With the development of artificial intelligence, digital images have been widely used in various fields. However, due to the appearance of image editing software, a large number of images have been tampered with maliciously, which seriously affects the authenticity of image content. Different from the general object detection, the study of image tampering detection needs to pay more attention to the tamper information of the image itself, which is often manifested in a weak form. Therefore, the detection model needs to focus on learning more abundant tamper features. This paper proposes a dual-stream Faster R-CNN model that combines gradient edge information and attention mechanism, and the model can realize detection and location of regions with different tampering types. One of the two streams is the color stream, which uses the attention mechanism to extract the surface features of the image, such as brightness contrast, visual difference of tampering with the boundary, etc. The second of the two streams is a gradient stream. A Gradient high-pass filter is used to enhance the anomaly edge features between the real area and the tampered area, making it easier for the model to find faint tampered traces in the tampered image. Finally, the features of color stream and gradient stream are fused by means of compact bilinear pooling. Due to the relatively small size of publicly available image tampering data sets, the Pascal VOC 2012 is used to create an image tampering detection data set which containing 10 010 images for model pre-training. The experimental results on COVER, Columbia, and CASIA data sets show that the model proposed in this paper improves the detection accuracy by 7.1% to 9.6% compared to the latest models, and exhibits higher robustness under JPEG compression and image blur attacks. [ABSTRACT FROM AUTHOR]

The layout of document images is complex and distribution of object sizes is uneven, currently, most of detection methods ignore multimodal information and global dependencies. Therefore, this paper proposed a multi modal document object detection method based on vision and text. Firstly, this method explored the fusion strategy of multimodal features. In order to utilize textual features, it converted text sequence information of the image into two-dimensional representation. After the initial fusion of text features and visual features, it input the fused features to backbone network to extract multiscale features, and repeatedly integrated textual features during the extraction process, so as to realize deep fusion of multimodal features. Next, to ensure the detection accuracy of small and large objects, this paper designed a pyramid network. The lateral connection could concatenate feature maps of the same spatial size from the bottom-up pathway and the top-down pathway in channel, so as to achieve the propagation between high-level semantic information and low-level feature information. The experimental results on large public dataset PubLayNet show that the detection accuracy of this method reaches 95. 86%,and it has a higher accuracy than other methods. This method not only realizes the deep fusion of multi modal features, but also enriches the fused multimodal feature information, and it has good detection performance. [ABSTRACT FROM AUTHOR]

As a new research hotspot in deep learning, intermediate deep feature compression has gotten a great deal of attention and has been applied to edge-cloud intelligent collaboration. This paper summarized the current state of research on the intermediate deep feature compression and analyzed the problems in the current methods. Firstly, it introduced three kinds of intermediate deep feature compression from aspects of image/video coding framework, channel bit allocation and network units. Then it did the comparisons of the data set performance between the three intermediate deep feature compression. Finally, this paper discussed the existing challenges and solutions in intermediate deep feature compression and looked forward to the feature trends of intermediate deep feature compression. [ABSTRACT FROM AUTHOR]

Local feature information plays an important role in image segmentation, however, the referring image segmentation task is dependent on the text expression, so it is impossible to extract local feature information directly from the original reference image. In order to solve this problem, this paper proposes a specific noun-guided local feature extraction deep neural network model（NgLFNet). The NgLFNet model can automatically mine the local feature information of the object to be segmented according to the key nouns in the input text expression. Specifically, the model first obtains key nouns in text through sentence analysis; secondly, extracting corresponding features through text and image encoders, and using the key nouns to obtain local features of high-interest regions through the multihead attention mechanism; then the multi-modal features are gradually fused to learn; Finally, the decoding and correction module uses the obtained local features to perform more detailed corrections on the prediction mask to obtain the final result. The method in this paper is compared with a variety of mainstream referring segmentation methods and the experimental results show that the proposed method improves the accuracy of text-based instance segmentation task. [ABSTRACT FROM AUTHOR]

Object surface defect detection technology is an important subject in the field of industrial quality inspection, which is of great significance to industrial production. This paper mainly summarized the surface defect detection techniques based on machine vision in recent years. Firstly, it listed several application scenarios of defect detection in the industry. Secondly, from the perspective of feature extraction and classification algorithms, it expounded on traditional machine vision methods. Then, this paper focused on the classical neural network structure and the latest development of defect detection algorithms and introduced two commonly used optimization methods of the defect detection algorithm. Finally, it analyzed three major challenges in the field of defect detection; real-time problems, small sample problems and small target problems. The purpose was to provide useful references and context for the research of industrial surface defect detection. [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]

[Purpose/Significance] The development of the Internet has led to the rapid development of social networks, providing users with a convenient channel for the release, dissemination and acceptance of information. However, its low-threshold characteristics have also given rise to a group of the "Internet water army"・・online social spammers, who are paid to post online comments with particular content and spread false information on purpose. They have become a major problem for the Internet ecology. It is of great significance to detect the Internet water army, prevent their malicious attacks, and combat and eliminate their negative effects on the security of the online public opinion. [Method/Process] First, we analyzed the development process and characteristics of the online social spammers, summarized the algorithms used in previous studies and the characteristics mentioned, and sorted out three research starting points: text features, interaction features and graph structure features. Then, an online social spammer detection method based on deep learning was proposed. Combined with the three aspects of user basic information, historical remarks and interaction behavior, six types of features were extracted from the basic information, recent remarks, social intimacy, interaction behavior, microblog number and membership level. Through feature depth extraction and vector splicing and fusion, the user feature vectors were formed with the same length. Finally, a convolutional neural network was used as a classifier to build an automatic, high-precision and high-efficiency spammer detection model. Two Chinese online spammer datasets collected from the Sina Weibo platform were selected for the experiment. The features of the datasets were spliced and aligned to form the Weibo Spammer 2023 dataset as the model training dataset, which prevented the data features of a single dataset from being too discrete and reducing modle generalization. Considering the overfitting problem in the model training process, we solved the problem by adding abandoned layers. [Results/Conclusions] The online spammer detection model constructed in this experiment has significantly improved in terms of metrics such as precision and accuracy. At the same time, the ablation experiment shows that the six features extracted in this e迎eriment have a positive effect on the detection process. Through empirical analysis, the model constructed in this paper has a high detection accuracy and detection efficiency, which can provide certain technical support and theoretical guidance for online spammer identification. By using machine learning methods to actively identify online social spammer accounts, real-time monitoring and prevention of key spammer accounts can prevent the occurrence of malicious network events more timely and effectively and reduce the risk of illegal forces damaging the public opinion ecology. [ABSTRACT FROM AUTHOR]