Search

Chip pad inspection is of great practical importance for chip alignment inspection and correction. It is one of the key technologies for automated chip inspection in semiconductor manufacturing. When applying deep learning methods for chip pad inspection, the main problem to be solved is how to ensure the accuracy of small target pad detection and, at the same time, achieve a lightweight inspection model. The attention mechanism is widely used to improve the accuracy of small target detection by finding the attention region of the network. However, conventional attention mechanisms capture feature information locally, which makes it difficult to effectively improve the detection efficiency of small targets from complex backgrounds in target detection tasks. In this paper, an OCAM (Object Convolution Attention Module) attention module is proposed to build long-range dependencies between channel features and position features by constructing feature contextual relationships to enhance the correlation between features. By adding the OCAM attention module to the feature extraction layer of the YOLOv5 network, the detection performance of chip pads is effectively improved. In addition, a design guideline for the attention layer is proposed in the paper. The attention layer is adjusted by network scaling to avoid network characterization bottlenecks, balance network parameters, and network detection performance, and reduce the hardware device requirements for the improved YOLOv5 network in practical scenarios. Extensive experiments on chip pad datasets, VOC datasets, and COCO datasets show that the approach in this paper is more general and superior to several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

With the wave of artificial intelligence and deep learning sweeping the world, there are many algorithms based on deep learning for image defog research. However, there is still serious color distortion, contrast reduction, incomplete fog removal, and other problems. To solve these problems, this paper proposes an improved image defogging network based on the traditional cycle-consistent adversarial network. We add the self-attention module and atrous convolution multi-scale feature fusion module on the basis of the traditional CycleGAN network to enhance the feature extraction capability of the network. The perceptual loss function is introduced into the loss function of the model to enhance the texture sense of the generated image. Finally, by comparing several typical defogging algorithms, the superiority of the defogging model proposed in this paper is proved qualitatively and quantitatively. Among them, on the indoor synthetic data set, the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measurement (SSIM) of the network designed by us can reach 23.22 and 0.8809, respectively. On the outdoor synthetic data set, the PSNR and SSIM of our designed network can be as high as 25.72 and 0.8859, respectively. On the real data set, the PSNR and SSIM of our designed network can reach 21.02 and 0.8166, respectively. It is proved that the defogging network in this paper has good practicability and universality. [ABSTRACT FROM AUTHOR]

Machine learning-based malware (malicious software) detection methods have a wide range of real-world applications. However, these types of approaches suffer from the fatal problem of "model aging", in which the validity of the model decreases rapidly as the malware continues to evolve and variants emerge continuously. The model aging problem is usually solved by model retraining, which relies on lots of labeled samples obtained at great expense. To address this challenge, this paper proposes a semi-supervised continuous learning malware detection model based on Transformer. Firstly, this model improves the lifelong semi-supervised mixture algorithm to dynamically adjust the weighted combination of new sample sequences and historical ones to solve the imbalance problem. Secondly, the Learning with Local and Global Consistency algorithm is used to iteratively compute similarity scores for the unlabeled samples in the mixed samples to obtain pseudo-labels. Lastly, the Multilayer Perceptron is applied for malware classification. To validate the effectiveness of the model, this paper conducts experiments on the CICMalDroid2020 dataset. The experimental results show that the proposed model performs better than existing deep learning detection models. The F1 score has an average improvement of 1.27% compared to other models when conducting binary classification. And, after inputting hybrid samples, including historical data and new data, four times, the F1 score is still 1.96% higher than other models. [ABSTRACT FROM AUTHOR]

Object tracking based on Siamese networks has achieved great success in recent years, but increasingly advanced trackers are also becoming cumbersome, which will severely limit deployment on resource-constrained devices. To solve the above problems, we designed a network with the same or higher tracking performance as other lightweight models based on the SiamFC lightweight tracking model. At the same time, for the problems that the SiamFC tracking network is poor in processing similar semantic information, deformation, illumination change, and scale change, we propose a global attention module and different scale training and testing strategies to solve them. To verify the effectiveness of the proposed algorithm, this paper has done comparative experiments on the ILSVRC, OTB100, VOT2018 datasets. The experimental results show that the method proposed in this paper can significantly improve the performance of the benchmark algorithm. [ABSTRACT FROM AUTHOR]

In the foggy environment, the images collected outdoors are prone to problems, such as low contrast and loss of details. In order to solve this problem, this paper proposes an algorithm based on multiscale parallel-depth separable convolutional neural network (MSP-DSCNN) to remove fog from foggy images and improve image quality. The multiscale feature extraction module extracts texture feature details from fog images at different scales and extracts high-dimensional and low-dimensional features from fog images by using parallel depth and shallow channels. In order to further optimize the network model, a split convolution method is proposed, which can split the feature graph into two categories, one is the main feature and the other is the secondary feature. The key information is extracted from the main features with high complexity, and the compensation information is extracted from the minor features with low complexity. Experiments show that compared with other algorithms, the model constructed in this paper has obvious advantages in defogging effect, natural color of restored images, good detail retention, and dominant indicators. It effectively solves the problems of incomplete haze, color offset, and poor visibility of detail maintenance in the current image. [ABSTRACT FROM AUTHOR]

In order to solve the problem of large model computing power consumption, this paper proposes a novel model compression algorithm. Firstly, this paper proposes an interpretable weight allocation method for the loss between a student network (a network model with poor performance), a teacher network (a network model with better performance) and real label. Then, different from the previous simple pruning and fine-tuning, this paper performs knowledge distillation on the pruned model, and quantifies the residual weights of the distilled model. The above operations can further reduce the model size and calculation cost while maintaining the model accuracy. The experimental results show that the weight allocation method proposed in this paper can allocate a relatively appropriate weight to the teacher network and real tags. On the cifar-10 dataset, the pruning method combining knowledge distillation and quantization can reduce the memory size of resnet32 network model from 3726 KB to 1842 KB, and the accuracy can be kept at 93.28%, higher than the original model. Compared with similar pruning algorithms, the model accuracy and operation speed are greatly improved. [ABSTRACT FROM AUTHOR]

Detection and recognition of traffic signs are the keys to creating advanced driving assistance systems. Making highly precise maps also requires the identification and extraction of such road elements as traffic signs. Traditional detection and recognition methods no longer meet today's needs, and object recognition algorithms based on deep learning have become the mainstream solution. However, current algorithms have limitations. The recognition speed of one-stage strategy algorithms is fast, but recognition accuracy is not satisfactory especially for small objects. The accuracy of two-stage algorithms is higher, but the recognition speed is extremely slow. This paper solves these problems with a proposed parallel attention convolution module, a channel attention pyramid network, and a loss function diagonal and center point IoU based on the YOLOv3 algorithm. The improved models in this paper are compared with SSD, YOLOv3, and Faster RCNN. Experimental results show that the proposed models have some improvement over the above models: the mAP of the models with PACM, CAFPN, and DCPIoU was 76.02%, compared with SSD300, SSD500, Faster RCNN, and YOLOv3, which had improvements of 9.27%, 6.93%, 2.94, and 5.3%, respectively. And the FPS of the improved model is basically the same as the original YOLOv3, without reducing the real-time performance. [ABSTRACT FROM AUTHOR]

In numerous scientific disciplines and practical applications, addressing optimization challenges is a common imperative. Nature-inspired optimization algorithms represent a highly valuable and pragmatic approach to tackling these complexities. This paper introduces Dendritic Growth Optimization (DGO), a novel algorithm inspired by natural branching patterns. DGO offers a novel solution for intricate optimization problems and demonstrates its efficiency in exploring diverse solution spaces. The algorithm has been extensively tested with a suite of machine learning algorithms, deep learning algorithms, and metaheuristic algorithms, and the results, both before and after optimization, unequivocally support the proposed algorithm's feasibility, effectiveness, and generalizability. Through empirical validation using established datasets like diabetes and breast cancer, the algorithm consistently enhances model performance across various domains. Beyond its working and experimental analysis, DGO's wide-ranging applications in machine learning, logistics, and engineering for solving real-world problems have been highlighted. The study also considers the challenges and practical implications of implementing DGO in multiple scenarios. As optimization remains crucial in research and industry, DGO emerges as a promising avenue for innovation and problem solving. [ABSTRACT FROM AUTHOR]

To solve the problem of low accuracy in the traditional FunkSVD recommendation algorithm, an improved FunkSVD algorithm (RM-FS) is proposed. RM-FS is an improvement of the traditional FunkSVD algorithm, using RMSProp, a deep learning optimization algorithm. The RM-FS algorithm can not only solve the problem of reduced accuracy of the traditional FunkSVD algorithm because of iterative oscillations but also alleviate the impact of data sparseness on the accuracy of the algorithm, achieving the effect of improving the accuracy of the traditional algorithm. The experimental results show that the RM-FS algorithm proposed in this paper effectively improves the accuracy of the recommendation algorithm, which is better than the traditional FunkSVD recommendation algorithm and other improved FunkSVD algorithms. [ABSTRACT FROM AUTHOR]

To provide reliable input for obstacle avoidance and decision-making, unmanned surface vehicles (USV) need to have the function of sensing the position of other USV targets in the process of cooperation and confrontation. Due to the small size of the target and the interference of the water and sky background, the current algorithms are prone to missed detection and drift problems when detecting and tracking USV. Therefore, in this paper, we propose a fusion algorithm of detection and tracking for USV targets. To solve the problem of vague features in the single-frame image, high-resolution and deep semantic information are obtained through a cross-stage partial network, and the anchor and convolution structure in the network has been improved given the characteristics of USV; besides, to meet the real-time requirements, the detected target is quickly tracked through correlation filtering, and the correlation characteristics of multi-frame images are obtained; then, the correlation characteristics are used to significantly reduce missed detection, and the tracking drift problems are corrected, combined with high-resolution semantic features of a single frame. Finally, the fusion algorithm is designed. In this paper, we constructed a picture dataset and a video dataset to test the effect of detection, tracking, and fusion algorithm separately, which proves the superiority of the fusion algorithm in this paper. The results show that, compared with a single detection algorithm and tracking algorithm, the fusion one can increase the success rate by more than 10%. [ABSTRACT FROM AUTHOR]

In the paper, we proposed a deep learning-based industrial equipment detection algorithm ROMS R-CNN (Rotation Occlusion Multi-Scale Region-CNN). It can solve the problem of inaccurate detection of industrial equipment under complex working conditions such as multi-scale ratio, rotation tilt, occlusion and overlap. The method proposed in this paper first is to construct the MobileNetV2 as the feature pyramid network, and then to combine high semantic information with high resolution information solved industrial equipment detection of different scales. Secondly, a specific rotation anchor scheme is proposed, and the data set is clustered through the k-means algorithm to obtain a specific aspect ratio. Combined with the rotation angle, a rotation anchor of any direction and size is generated to solve the problem of easy tilting of industrial equipment. Finally, a Non-Maximum Suppression algorithm with penalty factors is introduced to solve the overlapping in industrial equipment detection. The experimental results in common industrial equipment detection show that this method is better than other algorithms, significantly improves the missed detection and false detection, and the mAP reaches 0.939. [ABSTRACT FROM AUTHOR]

Infrared image target detection technology has been one of the essential research topics in computer vision, which has promoted the development of automatic driving, infrared guidance, infrared surveillance, and other fields. However, traditional target detection algorithms for infrared images have difficulty adapting to the target's multiscale characteristics. In addition, the accuracy of the detection algorithm is significantly reduced when the target is occluded. The corresponding solutions are proposed in this paper to solve these two problems. The final experiments show that this paper's infrared image target detection model improves significantly. [ABSTRACT FROM AUTHOR]

With the development of deep learning, target detection from vision sensor has achieved high accuracy and efficiency. However, small target detection remains a challenge due to inadequate use of semantic information and detailed texture information of underlying features. To solve the above problems, this paper proposes a small target detection algorithm based on Mask R-CNN model which integrates transfer learning and deep separable network. Firstly, the feature pyramid fusion structure is introduced to enhance the learning effect of low-level and high-level features, especially to strengthen the information channel of low-level feature and meanwhile optimize the feature information of small target. Secondly, the ELU function is used as the activation function to solve the problem that the original activation function disappears in the negative half axis gradient. Finally, a new loss function F-Softmax combined with Focal Loss was adopted to solve the imbalance of positive and negative sample proportions. In this paper, self-made data set is used to carry out experiments, and the experimental results show that the proposed algorithm makes the detection accuracy of small targets reach 66.5%. [ABSTRACT FROM AUTHOR]

With the rapid development of deep learning, in recent years, many excellent deep learning models have been developed to solve the problem of video frame prediction. Among them, most models directly generate predicted target frames. However, the predicted frames obtained in this way are often fuzzy and not realistic enough. In order to solve this problem, this paper first attempts to integrate the attention mechanism with Convolutional Long Short-Term Memory, and correspondingly proposes a new deep learning model, abbreviated as AttConvLSTM. One prominent and original characteristic of this newly constructed model is that, each of its layer calculates the attention weight of the obtained information, focusing on the information key part. Although the proposed AttConvLSTM model effectively improves the prediction accuracy, it still does not solve the problem that the prediction frames directly generated by classical deep learning models are often fuzzy and not realistic. Therefore, inspired by the concept of optical flow, this work further develops a novel Deep Pixel Restoration AttConvLSTM (DPRAConvLSTM) model. This model cleverly uses the input frames and the end-to-end characteristics of deep learning. We innovatively restore the pixels of the input frames to the predicted frames, thereby avoiding the defects that typical deep learning models can easily cause, when directly generating the predicted frames. The experimental results effectively confirm that the finally formed DPRAConvLSTM model can not only improve the accuracy of prediction, but also obtain clearer and more realistic prediction frames. [ABSTRACT FROM AUTHOR]

With the advent of the era of big data and the rapid development of deep learning and other technologies, people can use complex neural network models to mine and extract key information in massive data with the support of powerful computing power. However, it also increases the complexity of heterogeneous network and greatly increases the difficulty of network maintenance and management. In order to solve the problem of network fault diagnosis, this paper first proposes an improved semisupervised inverse network fault diagnosis algorithm; the proposed algorithm effectively guarantees the convergence of generated against network model, makes full use of a large amount of trouble-free tag data, and obtains a good accuracy of fault diagnosis. Then, the diagnosis model is further optimized and the fault classification task is completed by the convolutional neural network, the discriminant function of the network is simplified, and the generation pair network is only responsible for generating fault samples. The simulation results also show that the fault diagnosis algorithm based on network generation and convolutional neural network achieves good fault diagnosis accuracy and saves the overhead of manually labeling a large number of data samples. [ABSTRACT FROM AUTHOR]

With the rapid development of computer hardware in the past three decades, various classic algorithms such as neural computing and bionic optimization computing have been widely used in practical problems. This paper extended the new bionic algorithm-flock algorithm proposed in 2014 and obtained a multi-objective flock algorithm to solve the multi-objective problem. This study used aggregate functions to define social ranks, and simulated the foraging behavior of chickens in the process of searching for food in the objective space and found the balance between diversity and convergence when looking for the best Pareto solution. The algorithm took five types of bi-objective functions and four types of three-objective functions as objects and compared it with four more widely used algorithms in multi-objective problems. The results demonstrate that the MOCSO (multi-objective chicken swarm optimization) algorithm shows better results in the optimization of multi-objective problems. [ABSTRACT FROM AUTHOR]

The evaluation of the effects of artificial precipitation enhancement remains one of the most important and challenging issues in the fields of meteorology. Rainfall is the most important evaluation metric for artificial precipitation enhancement, which is mainly achieved through physics-based models that simulate physical phenomena and data-driven statistical models. The series of effect evaluation methods requires the selection of a comparison area for effect comparison, and idealized assumptions and simplifications have been made for the actual cloud precipitation process, leading to unreliable quantitative evaluation results of artificial precipitation effects. This paper proposes a deep learning-based method (UNET-GRU) to quantitatively evaluate the effect of artificial rainfall. By comparing the residual values obtained from inverting the natural evolution grid rainfall of the same area under the same artificial rainfall conditions with the actual rainfall amount after artificial rainfall operations, the effect of artificial rainfall can be quantitatively evaluated, effectively solving the problem of quantitative evaluation of artificial precipitation effects. Wuhan and Shiyan in China are selected to represent typical plains and mountainous areas, respectively, and the method is evaluated using 6-min resolution radar weather data from 2017 to 2020. During the experiment, we utilized the UNET-GRU algorithm and developed separate algorithms for comparison against common persistent baselines (i.e., the next-time data of the training data). The prediction of mean squared error (MSE) for these three algorithms was significantly lower than that of the baseline data. Moreover, the indicators for these algorithms were excellent, further demonstrating their efficacy. In addition, the residual results of the estimated 7-h grid rainfall were compared with the actual recorded rainfall to evaluate the effectiveness of artificial precipitation. The results showed that the estimated rainfall was consistent with the recorded precipitation for that year, indicating that deep learning methods can be successfully used to evaluate the impact of artificial precipitation. The results demonstrate that this method improves the accuracy of effect evaluation and enhances the generalization ability of the evaluation scheme. [ABSTRACT FROM AUTHOR]

The paper summarizes the research progress on critical region recognition and deep metric learning to achieve accurate clothing image retrieval in cross-domain situations. Critical region recognition is of great value for the clothing feature extraction, effectively improving retrieval accuracy. The accuracy will decrease when solving difficult samples with similar features but different categories. Nowadays, deep metric learning is an effective way to solve this problem, which utilizes the optimization of different loss functions and ensemble network to strengthen the discrimination of clothing features. Therefore, through comparison of the experimental results of different algorithms and analysis of the accuracy of cross-domain clothing retrieval, it is demonstrated that the improvement of the retrieval accuracy in the future mainly depends on clothing important feature extraction and clothing feature discrimination. [ABSTRACT FROM AUTHOR]

At present, the UAV (Unmanned Aerial Vehicle) has been widely used both in civilian and military fields. Most of the current object detection algorithms used to detect UAVs require more parameters, and it is difficult to achieve real-time performance. In order to solve this problem while ensuring a high accuracy rate, we further lighten the model and reduce the number of parameters of the model. This paper proposes an accurate and lightweight UAV detection model based on YOLOv4. To verify the effectiveness of this model, we made a UAV dataset, which contains four types of UAVs and 20,365 images. Through comparative experiments and optimization of existing deep learning and object detection algorithms, we found a lightweight model to achieve an efficient and accurate rapid detection of UAVs. First, from the comparison of the one-stage method and the two-stage method, it is concluded that the one-stage method has better real-time performance and considerable accuracy in detecting UAVs. Then, we further compared the one-stage methods. In particular, for YOLOv4, we replaced MobileNet with its backbone network, modified the feature extraction network, and replaced standard convolution with depth-wise separable convolution, which greatly reduced the parameters and realized 82 FPS and 93.52% mAP while ensuring high accuracy and taking into account the real-time performance. [ABSTRACT FROM AUTHOR]

Single-pixel imaging (SPI) is a promising imaging scheme based on compressive sensing. However, its application in high-resolution and real-time scenarios is a great challenge due to the long sampling and reconstruction required. The Deep Learning Compressed Network (DLCNet) can avoid the long-time iterative operation required by traditional reconstruction algorithms, and can achieve fast and high-quality reconstruction; hence, Deep-Learning-based SPI has attracted much attention. DLCNets learn prior distributions of real pictures from massive datasets, while the Deep Image Prior (DIP) uses a neural network′s own structural prior to solve inverse problems without requiring a lot of training data. This paper proposes a compressed reconstruction network (DPAP) based on DIP for Single-pixel imaging. DPAP is designed as two learning stages, which enables DPAP to focus on statistical information of the image structure at different scales. In order to obtain prior information from the dataset, the measurement matrix is jointly optimized by a network and multiple autoencoders are trained as regularization terms to be added to the loss function. Extensive simulations and practical experiments demonstrate that the proposed network outperforms existing algorithms. [ABSTRACT FROM AUTHOR]

Visual inspection of photovoltaic modules using electroluminescence (EL) images is a common method of quality inspection. Because human inspection requires a lot of time, object detection algorithm to replace human inspection is a popular research direction in recent years. To solve the problem of low accuracy and slow speed in EL image detection, we propose a YOLO‐based object detection algorithm YOLO‐PV, which achieves 94.55% of AP (average precision) on the photovoltaic module EL image data set, and the interference speed exceeds 35 fps. The improvement of speed and accuracy benefits from the targeted design of the network architecture according to the characteristics of EL image. First, we weaken the backbone's ability to extract deep‐level information so that it can focus on extracting the low‐level defect information. Second, the PAN network is used for feature fusion in the Neck part. But, only the single‐size feature map output is retained, which significantly reduces the amount of calculation. Also, we analyze the impact of data enhancement methods on model overfitting and performance. Finally, we give effective data enhancement methods. The results show that the object detection algorithm in this paper can meet the requirements for high‐precision and real‐time processing on the PV module production line. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN) is now widely applied in bearing fault diagnosis, but the design of network structure or parameter tuning is time-consuming. To solve this problem, a particle swarm optimization (PSO) algorithm is used to optimize the network structure and a self-adaptive CNN is proposed in this paper. In the proposed method, a theoretical method is used to automatically determine the window size of short-time Fourier transform (STFT). To reduce the computation time, PSO is only applied to obtain the optimal key parameters in CNN with a small number of training samples and a small epoch number. To simplify the CNN structure, a fitness function considering the numbers of kernels and neuron nodes is used in PSO. According to the verification experiments for two well-known public datasets, the proposed method can get higher accuracy than other state-of-art methods. Furthermore, the parameters that are required to be input only involve the bearing parameters, so the proposed method can be applied in industry readily. [ABSTRACT FROM AUTHOR]

In terms of small objects in traffic scenes, general object detection algorithms have low detection accuracy, high model complexity, and slow detection speed. To solve the above problems, an improved algorithm (named YOLO-MXANet) is proposed in this paper. Complete-Intersection over Union (CIoU) is utilized to improve loss function for promoting the positioning accuracy of the small object. In order to reduce the complexity of the model, we present a lightweight yet powerful backbone network (named SA-MobileNeXt) that incorporates channel and spatial attention. Our approach can extract expressive features more effectively by applying the Shuffle Channel and Spatial Attention (SCSA) module into the SandGlass Block (SGBlock) module while increasing the parameters by a small number. In addition, the data enhancement method combining Mosaic and Mixup is employed to improve the robustness of the training model. The Multi-scale Feature Enhancement Fusion (MFEF) network is proposed to fuse the extracted features better. In addition, the SiLU activation function is utilized to optimize the Convolution-Batchnorm-Leaky ReLU (CBL) module and the SGBlock module to accelerate the convergence of the model. The ablation experiments on the KITTI dataset show that each improved method is effective. The improved algorithm reduces the complexity and detection speed of the model while improving the object detection accuracy. The comparative experiments on the KITTY dataset and CCTSDB dataset with other algorithms show that our algorithm also has certain advantages. [ABSTRACT FROM AUTHOR]

Adversarial sample generation problem is a hot issue in the security field of deep learning. Evolutionary algorithm has been widely used to solve this problem in recent years because of its good global search ability. However, existing methods still suffer from the "curse of dimensionality" when attacking high-resolution images. In this paper, a two-stage frequency domain generation algorithm of black-box adversarial samples based on differential evolution is proposed. In the first stage, a representative image-guided differential evolution method is proposed to quickly generate a universal adversarial perturbation with a high attack success rate in the frequency-domain. In the second stage, a space reduction strategy based on frequency-domain pixel blocks is designed to reduce the search space and alleviate the problem of "curse of dimensionality". In addition, a new space–frequency interaction sensitivity measure is introduced to evaluate the similarity between the adversarial samples and the original images. The adversarial perturbations obtained by the measure are more in line with the subjective perception of the human eye. Finally, compared with several typical black-box adversarial sample generation algorithms, experimental results show that the proposed algorithm can achieve higher attack success rate with less prediction times. • Proposing a two-stage evolutionary generation framework of adversarial samples. • Developing a space–frequency interaction sensitivity measure. • Presenting a representative image-guided differential evolutionary algorithm. • Designing an individual adversarial perturbation generation algorithm. [ABSTRACT FROM AUTHOR]

Cameras, especially those carried by drones, are the main tools used to detect wildfires in forests because cameras have much longer detection ranges than smoke sensors. Currently, deep learning is main method used for fire detection in images, and Transformer is the best algorithm. Swin Transformer restricts the computation to a fixed-size window, which reduces the amount of computation to a certain extent, but to allow pixel communication between windows, it adopts a shift window approach. Therefore, Swin Transformer requires multiple shifts to extend the receptive field to the entire image. This somewhat limits the network's ability to capture global features at different scales. To solve this problem, instead of using the shift window method to allow pixel communication between windows, we downsample the feature map to the window size after capturing global features through a single Transformer, and we upsample the feature map to the original size and add it to the previous feature map. This way, there is no need for multiple layers of stacked window Transformers; global features are captured after each window Transformer operation. We conducted experiments on the Corsican fire dataset captured by ground cameras and on the Flame dataset captured by drone cameras. The results show that our algorithm performs the best. On the Corsican fire dataset, the mIoU, F1 score, and OA reached 79.4%, 76.6%, and 96.9%, respectively. On the Flame dataset, the mIoU, F1 score, and OA reached 84.4%, 81.6%, and 99.9%, respectively. [ABSTRACT FROM AUTHOR]

Small object detection is one of the challenging tasks in computer vision. Most of the existing small object detection models cannot fully extract the characteristics of small objects within an image, due to the small coverage area, low resolution and unclear detailed information of small objects in the image; hence, the effect of these models is not ideal. To solve this problem, a simple and efficient reinforce feature pyramid network R-FPN is proposed for the YOLOv5 algorithm. The learnable weight is introduced to show the importance of different input features, make full use of the useful information of different feature layers and strengthen the extraction of small object features. At the same time, a channel space mixed attention CSMA module is proposed to extract the detailed information of small objects combined with spaces and channels, suppress other useless information and further improve the accuracy of small object detection. The experimental results show that the proposed method improves the average accuracy AP, AP50 and AR100 of the original algorithm by 2.11%, 2.86% and 1.94%, respectively, and the detection effect is better than the existing small object detection algorithms, which proves the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In order to solve the problems of poor region delineation and boundary artifacts in Chinese style migration of images, an improved Variational Autoencoder (VAE) method for dress style migration is proposed. Firstly, the Yolo v3 model is used to quickly identify the dress localization of the input image, then, the classical semantic segmentation algorithm (FCN) is used to finely delineate the desired dress style migration region twice, and finally, the trained VAE model is used to generate the migrated Chinese style image. The results show that, compared with the traditional style migration model, the improved VAE style migration model can obtain finer synthetic images for dress style migration and can adapt to different Chinese traditional styles to meet the application requirements of dress style migration scenarios. We evaluated several deep learning-based models and achieved a BLEU value of 0.6 on average. The transformer-based model outperformed the other models, achieving a BLEU value of up to 0.72. [ABSTRACT FROM AUTHOR]

Recently, studies on early-exit mechanisms have emerged to reduce the computational cost during the inference process of deep learning models. However, most existing early-exit architectures simply determine early exiting based only on a target confidence level in the prediction, without any consideration of the computational cost. Such an early-exit criterion fails to balance accuracy and cost, making it difficult to use in various environments. To address this problem, we propose a novel, cost-effective early-exit architecture in which an early-exit criterion is designed based on the Markov decision process (MDP). Since the early-exit decisions within an early-exit model are sequential, we model them as an MDP problem to maximize accuracy as much as possible while minimizing the computational cost. Then, we develop a cost-effective early-exit algorithm using reinforcement learning that solves the MDP problem. For each input sample, the algorithm dynamically makes early-exit decisions considering the relative importance of accuracy and computational cost in a given environment, thereby balancing the trade-off between accuracy and cost regardless of the environment. Consequently, it can be used in various environments, even in a resource-constrained environment. Through extensive experiments, we demonstrate that our proposed architecture can effectively balance the trade-off in different environments, while the existing architectures fail to do so since they focus only on reducing their cost while preventing the degradation of accuracy. [ABSTRACT FROM AUTHOR]

Deep neural networks have played a crucial role in the field of deep learning, achieving significant success in practical applications. The architecture of neural networks is key to their performance. In the past few years, these architectures have been manually designed by experts with rich domain knowledge. Additionally, the optimal neural network architecture can vary depending on specific tasks and data distributions. Neural Architecture Search (NAS) is a class of techniques aimed at automatically searching for and designing neural network architectures according to the given tasks and data. Specifically, evolutionary-computation-based NAS methods are known for their strong global search capability and have aroused widespread interest in recent years. Although evolutionary-computation-based NAS has achieved success in a wide range of research and applications, it still faces bottlenecks in training and evaluating a large number of individuals during optimization. In this study, we first devise a multi-objective evolutionary NAS framework based on a weight-sharing supernet to improve the search efficiency of traditional evolutionary-computation-based NAS. This framework combines the population optimization characteristic of evolutionary algorithms with the weight-sharing ideas in one-shot models. We then design a bi-population MOEA/D algorithm based on the proposed framework to effectively solve the NAS problem. By constructing two sub-populations with different optimization objectives, the algorithm can effectively explore network architectures of various sizes in complex search spaces. An inter-population communication mechanism further enhances the algorithm's exploratory capability, enabling it to find network architectures with uniform distribution and high diversity. Finally, we conduct performance comparison experiments on image classification datasets of different scales and complexities. Experimental results demonstrate the effectiveness of the proposed multi-objective evolutionary NAS framework and the practicality and transferability of the introduced bi-population MOEA/D-based NAS method compared to existing state-of-the-art NAS methods. [ABSTRACT FROM AUTHOR]

Planetary soft landing has been studied extensively due to its promising application prospects. In this paper, a soft landing control algorithm based on deep reinforcement learning (DRL) with good convergence property is proposed. First, the soft landing problem of the powered descent phase is formulated and the theoretical basis of Reinforcement Learning (RL) used in this paper is introduced. Second, to make it easier to converge, a reward function is designed to include process rewards like velocity tracking reward, solving the problem of sparse reward. Then, by including the fuel consumption penalty and constraints violation penalty, the lander can learn to achieve velocity tracking goal while saving fuel and keeping attitude angle within safe ranges. Then, simulations of training are carried out under the frameworks of Deep deterministic policy gradient (DDPG), Twin Delayed DDPG (TD3), and Soft Actor Critic (SAC), respectively, which are of the classical RL frameworks, and all converged. Finally, the trained policy is deployed into velocity tracking and soft landing experiments, results of which demonstrate the validity of the algorithm proposed. [ABSTRACT FROM AUTHOR]

One of the biggest challenge in the field of deep learning is the parameter selection and optimization process. In recent years different algorithms have been proposed including bio-inspired solutions to solve this problem, however, there are many challenges including local minima, saddle points, and vanishing gradients. In this paper, we introduce the Whale Optimisation Algorithm (WOA) based on the swarm foraging behavior of humpback whales to optimise neural network hyperparameters. We wish to stress that to the best of our knowledge this is the first attempt that uses Whale Optimisation Algorithm for the optimisation task of hyperparameters. After a detailed description of the WOA algorithm we formulate and explain the application in deep learning, present the implementation, and compare the proposed algorithm with other well-known algorithms including widely used Grid and Random Search methods. Additionally, we have implemented a third dimension feature analysis to the original WOA algorithm to utilize 3D search space (3D-WOA). Simulations show that the proposed algorithm can be successfully used for hyperparameters optimization, achieving accuracy of 89.85% and 80.60% for Fashion MNIST and Reuters datasets, respectively. [ABSTRACT FROM AUTHOR]

Aiming at solving the problem that the recognition effect of rare slot values in spoken language is poor, which affects the accuracy of oral understanding task, a spoken language understanding method is designed based on deep learning. The local features of semantic text are extracted and classified to make the classification results match the dialogue task. An intention recognition algorithm is designed for the classification results. Each datum has a corresponding intention label to complete the task of semantic slot filling. The attention mechanism is applied to the recognition of rare slot value information, the weight of hidden state and corresponding slot characteristics are obtained, and the updated slot value is used to represent the tracking state. An auxiliary gate unit is constructed between the upper and lower slots of historical dialogue, and the word vector is trained based on deep learning to complete the task of spoken language understanding. The simulation results show that the proposed method can realize multiple rounds of man-machine spoken language. Compared with the spoken language understanding methods based on cyclic network, context information, and label decomposition, it has higher accuracy and F1 value and has higher practical application value. [ABSTRACT FROM AUTHOR]

Gesture serves as a crucial means of communication between individuals and between humans and machines. In football matches, referees communicate judgment information through gestures. Due to the diversity and complexity of referees' gestures and interference factors, such as the players, spectators, and camera angles, automated football referee gesture recognition (FRGR) has become a challenging task. The existing methods based on visual sensors often cannot provide a satisfactory performance. To tackle FRGR problems, we develop a deep learning model based on YOLOv8s. Three improving and optimizing strategies are integrated to solve these problems. First, a Global Attention Mechanism (GAM) is employed to direct the model's attention to the hand gestures and minimize the background interference. Second, a P2 detection head structure is integrated into the YOLOv8s model to enhance the accuracy of detecting smaller objects at a distance. Third, a new loss function based on the Minimum Point Distance Intersection over Union (MPDIoU) is used to effectively utilize anchor boxes with the same shape, but different sizes. Finally, experiments are executed on a dataset of six hand gestures among 1,200 images. The proposed method was compared with seven different existing models and 10 different optimization models. The proposed method achieves a precision rate of 89.3%, a recall rate of 88.9%, a mAP@0.5 rate of 89.9%, and a mAP@0.5:0.95 rate of 77.3%. These rates are approximately 1.4%, 2.0%, 1.1%, and 5.4% better than those of the newest YOLOv8s, respectively. The proposed method has right prospect in automated gesture recognition for football matches. [ABSTRACT FROM AUTHOR]

Solving combinatorial problems on complex networks represents a primary issue which, on a large scale, requires the use of heuristics and approximate algorithms. Recently, neural methods have been proposed in this context to find feasible solutions for relevant computational problems over graphs. However, such methods have some drawbacks: (1) they use the same neural architecture for different combinatorial problems without introducing customizations that reflects the specificity of each problem; (2) they only use a nodes local information to compute the solution; (3) they do not take advantage of common heuristics or exact algorithms. Following this interest, in this research we address these three main points by designing a customized attention-based mechanism that uses both local and global information from the adjacency matrix to find approximate solutions for the Minimum Vertex Cover Problem. We evaluate our proposal with respect to a fast two-factor approximation algorithm and a widely adopted state-of-the-art heuristic both on synthetically generated instances and on benchmark graphs with different scales. Experimental results demonstrate that, on the one hand, the proposed methodology is able to outperform both the two-factor approximation algorithm and the heuristic on the test datasets, scaling even better than the heuristic with harder instances and, on the other hand, is able to provide a representation of the nodes which reflects the combinatorial structure of the problem. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) has emerged as a crucial tool in healthcare with the primary aim of improving patient outcomes and optimizing healthcare delivery. By harnessing machine learning algorithms, natural language processing, and computer vision, AI enables the analysis of complex medical data. The integration of AI into healthcare systems aims to support clinicians, personalize patient care, and enhance population health, all while addressing the challenges posed by rising costs and limited resources. As a subdivision of computer science, AI focuses on the development of advanced algorithms capable of performing complex tasks that were once reliant on human intelligence. The ultimate goal is to achieve human-level performance with improved efficiency and accuracy in problem-solving and task execution, thereby reducing the need for human intervention. Various industries, including engineering, media/entertainment, finance, and education, have already reaped significant benefits by incorporating AI systems into their operations. Notably, the healthcare sector has witnessed rapid growth in the utilization of AI technology. Nevertheless, there remains untapped potential for AI to truly revolutionize the industry. It is important to note that despite concerns about job displacement, AI in healthcare should not be viewed as a threat to human workers. Instead, AI systems are designed to augment and support healthcare professionals, freeing up their time to focus on more complex and critical tasks. By automating routine and repetitive tasks, AI can alleviate the burden on healthcare professionals, allowing them to dedicate more attention to patient care and meaningful interactions. However, legal and ethical challenges must be addressed when embracing AI technology in medicine, alongside comprehensive public education to ensure widespread acceptance. [ABSTRACT FROM AUTHOR]

• This paper proposes an unsupervised deep learning model. • This paper proposes an optimized sparse representation method. • This paper proposes a new image fusion algorithm based on unsupervised deep learning-optimized sparse representation. The image fusion method based on deep learning has problems such as the supervised learning of the model, the edge and noise of the fused image, and the setting of the image fusion weight map. To solve these problems, this paper proposes an end-to-end unsupervised deep learning model that performs one-to-many focus image fusion. It solves the training problem encountered by supervised deep learning models while avoiding the unreasonable image fusion weight maps. In addition, this paper proposes an optimized sparse representation method that divides an image into a target area and a background area. Then, it uses super complete dictionary learning to obtain a sparse representation of the image background area. This approach makes the proposed unsupervised deep learning image fusion method robust to noise. Finally, using this method to carry out image fusion experiments, the results show that the quality evaluation indicators of the fused image obtained by this method substantially outperform those of both mainstream machine learning and deep learning image fusion methods. [ABSTRACT FROM AUTHOR]

There is tremendous demand for marine environmental observation, which requires the development of a multi-agent cooperative observation algorithm to guide Unmanned Surface Vehicles (USVs) and Unmanned Aerial Vehicles (UAVs) to observe isotherm data of the mesoscale vortex. The task include two steps: firstly, USVs search out the isotherm, navigate independently along the isotherm, and collect marine data; secondly, a UAV takes off, and in its one round trip, the UAV and USVs jointly perform the task of the UAV reading the observation data from USVs. In this paper, aiming at the first problem of the USV following the isotherm in an unknown environment, a data-driven Deep Deterministic Policy Gradient (DDPG) control algorithm is designed that allows USVs to navigate independently along isotherms in unknown environments. In addition, a hybrid cooperative control algorithm based on a multi-agent DDPG is adopted to solve the second problem, which enables USVs and a UAV to complete data reading tasks with the shortest flight distance of the UAV. The experimental simulation results show that the trained system can complete this tas, with good stability and accuracy. [ABSTRACT FROM AUTHOR]

Attribute reduction is a crucial research area within concept lattices. However, the existing works are mostly limited to either increment or decrement algorithms, rather than considering both. Therefore, dealing with large-scale streaming attributes in both cases may be inefficient. Convolution calculation in deep learning involves a dynamic data processing method in the form of sliding windows. Inspired by this, we adopt slide-in and slide-out windows in convolution calculation to update attribute reduction. Specifically, we study the attribute changing mechanism in the sliding window mode of convolution and investigate five attribute variation cases. These cases consider the respective intersection of slide-in and slide-out attributes, i.e., equal to, disjoint with, partially joint with, containing, and contained by. Then, we propose an updated solution of the reduction set for simultaneous sliding in and out of attributes. Meanwhile, we propose the CLARA-DC algorithm, which aims to solve the problem of inefficient attribute reduction for large-scale streaming data. Finally, through the experimental comparison on four UCI datasets, CLARA-DC achieves higher efficiency and scalability in dealing with large-scale datasets. It can adapt to varying types and sizes of datasets, boosting efficiency by an average of 25%. [ABSTRACT FROM AUTHOR]

Under the background of intelligent manufacturing, in order to solve the complex problems of manual detection of metallurgical saw blade defects in enterprises, such as real-time detection, false detection, and the detection model being too large to deploy, a study on a metallurgical saw blade surface defect detection algorithm based on SC-YOLOv5 is proposed. Firstly, the SC network is built by integrating coordinate attention (CA) into the Shufflenet-V2 network, and the backbone network of YOLOv5 is replaced by the SC network to improve detection accuracy. Then, the SIOU loss function is used in the YOLOv5 prediction layer to solve the angle problem between the prediction frame and the real frame. Finally, in order to ensure both accuracy and speed, lightweight convolution (GSConv) is used to replace the ordinary convolution module. The experimental results show that the mAP@0.5 of the improved YOLOv5 model is 88.5%, and the parameter is 31.1M. Compared with the original YOLOv5 model, the calculation amount is reduced by 56.36%, and the map value is increased by 0.021. In addition, the overall performance of the improved SC-YOLOv5 model is better than that of the SSD and YOLOv3 target detection models. This method not only ensures the high detection rate of the model, but also significantly reduces the complexity of the model and the amount of parameter calculation. It meets the needs of deploying mobile terminals and provides an effective reference direction for applications in enterprises. [ABSTRACT FROM AUTHOR]

To solve the problem that the deep learning‐based image matting algorithm cannot balance accuracy and model size, a lightweight image matting algorithm based on deep learning is proposed. Considering the limitation of memory and computing resources, and aiming at lightweight. We construct a network and gradually improved it. Firstly, apply deep detachable convolution to deep image matting networks to form faster and stronger encoder and decoder networks. The simultaneous use of depth‐separable convolution can also reduce the number of corresponding model parameters and computation. And then attention mechanism is integrated into the model and SE Block was used to assign different weights to feature channels to improve the accuracy of the model. Finally, knowledge distillation scheme is designed in part of the encoder‐decoder structure, the corresponding loss function is proposed, and the method of knowledge distillation is used to improve the feature learning ability of the lightweight neural network. Compared with the original deep image matting model, the number of parameters in the new model is greatly reduced without too much loss of accuracy. [ABSTRACT FROM AUTHOR]

Falling represents one of the most serious health risks for elderly people; it may cause irreversible injuries if the individual cannot obtain timely treatment after the fall happens. Therefore, timely and accurate fall detection algorithm research is extremely important. Recently, a number of researchers have focused on fall detection and made many achievements, and most of the relevant algorithm studies are based on ideal class-balanced datasets. However, in real-life applications, the possibilities of Activities of Daily Life (ADL) and fall events are different, so the data collected by wearable sensors suffers from class imbalance. The previously developed algorithms perform poorly on class-imbalanced data. In order to solve this problem, this paper proposes an algorithm that can effectively distinguish falls from a large amount of ADL signals. Compared with the state-of-the-art fall detection algorithms, the proposed method can achieve the highest score in multiple evaluation methods, with a sensitivity of 99.33%, a specificity of 91.86%, an F-Score of 98.44% and an AUC of 98.35%. The results prove that the proposed algorithm is effective on class-imbalanced data and more suitable for real-life application compared to previous works. [ABSTRACT FROM AUTHOR]

To solving the problems that the existing image inpainting methods lack authenticity, do not deal with the information of missing and non-missing regions flexibly, and do not deal with the image feature information on different stages effectively, we propose an image restoration method combining Semantic Priors and Deep Attention Residual Group. The image restoration method mainly consists of Semantic Priors Network, Deep Attention Residual Group, and Full-scale Skip Connection. The Semantic Priors Network learns the complete semantic prior information of the visual elements in the missing regions and completes the missing regions with the learned semantic information. The deep attention residual set allows the generator to focus more on not only the missing regions of the image but also to learn the features of each channel adaptive. The full-scale jump joins can combine the low-level feature maps containing image boundaries with the high-level feature maps containing image textures and details to repair the missing regions. In this paper, a full comparison experiment is conducted on the CelebA-HQ and the Paris StreetView datasets, and the experimental results show that proposed method outperforms the current representative state-of-the-art image restoration methods. [ABSTRACT FROM AUTHOR]

In the manufacturing of chips, the accurate and effective detection of internal bubble defects of chips is essential to maintain product reliability. In general, the inspection is performed manually by viewing X-ray images, which is time-consuming and less reliable. To solve the above problems, an improved bubble defect detection model YOLO-Xray based on the YOLOv5 algorithm for chip X-ray images is proposed. First, the chip X-ray images are preprocessed by image segmentation to construct the chip X-ray defect dataset, namely, CXray. Then, in the input stage, the K-means++ algorithm is used to re-cluster the CXray dataset to generate the anchors suitable for our dataset. In the backbone network, a micro-scale detection head is added to improve the capabilities for small defect detection. In the neck network, the bi-direction feature fusion idea of BiFPN is used to construct a new feature fusion network based on the improved backbone to fuse the semantic features of different layers. In addition, the Quality Focal Loss function is used to replace the cross-entropy loss function to solve the imbalance of positive and negative samples. The experimental results show that the mean average precision (mAP) of the YOLO-Xray algorithm on the CXray dataset reaches 93.5%, which is 5.1% higher than the original YOLOv5. Meanwhile, the YOLO-Xray algorithm achieves state-of-the-art detection accuracy and speed compared with other mainstream object detection models. This shows the proposed YOLO-Xray algorithm can provide technical support for bubble defect detection in chip X-ray images. The CXray dataset is also open and available at CXray. [ABSTRACT FROM AUTHOR]

For the last 40 years, actigraphy or wearable accelerometry has provided an objective, low-burden and ecologically valid approach to assess real-world sleep and circadian patterns, contributing valuable data to epidemiological and clinical insights on sleep and sleep disorders. The proper use of wearable technology in sleep research requires validated algorithms that can derive sleep outcomes from the sensor data. Since the publication of the first automated scoring algorithm by Webster in 1982, a variety of sleep algorithms have been developed and contributed to sleep research, including many recent ones that leverage machine learning and / or deep learning approaches. However, it remains unclear how these algorithms compare to each other on the same data set and if these modern data science approaches improve the analytical validity of sleep outcomes based on wrist-worn acceleration data. This work provides a systematic evaluation across 8 state-of-the-art sleep algorithms on a common sleep data set with polysomnography (PSG) as ground truth. Despite the inclusion of recently published complex algorithms, simple regression-based and heuristic algorithms demonstrated slightly superior performance in sleep-wake classification and sleep outcome estimation. The performance of complex machine learning and deep learning models seem to suffer from poor generalization. This independent and systematic analytical validation of sleep algorithms provides key evidence on the use of wearable digital health technologies for sleep research and care. [ABSTRACT FROM AUTHOR]

The traditional single-shot multiBox detector (SSD) for the recognition process in sea cucumbers has problems, such as an insufficient expression of features, heavy computation, and difficulty in application to embedded platforms. To solve these problems, we proposed an improved algorithm for sea cucumber detection based on the traditional SSD algorithm. MobileNetv1 is selected as the backbone of the SSD algorithm. We increase the feature receptive field by receptive field block (RFB) to increase feature details and location information of small targets. Combined with the attention mechanism, features at different depths are strengthened and irrelevant features are suppressed. The experimental results show that the improved algorithm has better performance than the traditional SSD algorithm. The average precision of the improved algorithm is increased by 5.1%. The improved algorithm is also more robust. Compared with YOLOv4 and the Faster R-CNN algorithm, the performance of this algorithm on the P-R curve is better, indicating that the performance of this algorithm is better. Thus, the improved algorithm can stably detect sea cucumbers in real time and provide reliable feedback information. [ABSTRACT FROM AUTHOR]

Point cloud registration is a key task in the fields of 3D reconstruction and automatic driving. In recent years, many learning-based registration methods have been proposed and have higher precision and robustness compared to traditional methods. Correspondence-based learning methods often require that the source point cloud and the target point cloud have homogeneous density, the aim of which is to extract reliable key points. However, the sparsity, low overlap rate and random distribution of real data make it more difficult to establish accurate and stable correspondences. Global feature-based methods do not rely on the selection of key points and are highly robust to noise. However, these methods are often easily disturbed by non-overlapping regions. To solve this problem, we propose a two-stage partially overlapping point cloud registration method. Specifically, we first utilize the structural information and feature information interaction of point clouds to predict the overlapping regions, which can weaken the impact of non-overlapping regions in global features. Then, we combine PointNet and the self-attention mechanism and connect features at different levels to efficiently capture global information. The experimental results show that the proposed method has higher accuracy and robustness than similar existing methods. [ABSTRACT FROM AUTHOR]

The spatial optimization method between combinatorial optimization problems and GIS has many geographical applications. The p-center problem is a classic NP-hard location modeling problem, which has essential applications in many real-world scenarios, such as urban facility locations (ambulances, fire stations, pipelines maintenance centers, police stations, etc.). This study implements two methods to solve this problem: an exact algorithm and an approximate algorithm. Exact algorithms can get the optimal solution to the problem, but they are inefficient and time-consuming. The approximate algorithm can give the sub-optimal solution of the problem in polynomial time, which has high efficiency, but the accuracy of the solution is closely related to the initialization center point. We propose a new paradigm that combines a graph convolution network and greedy algorithm to solve the p-center problem through direct training and realize that the efficiency is faster than the exact algorithm. The accuracy is superior to the heuristic algorithm. We generate a large amount of p-center problems by the Erdos–Renyi graph, which can generate instances in many real problems. Experiments show that our method can compromise between time and accuracy and affect the solution of p-center problems. [ABSTRACT FROM AUTHOR]

Information extraction (IE), which aims to retrieve meaningful information from plain text, has been widely studied in general and professional domains to support downstream applications. However, due to the lack of labeled data and the complexity of professional mechanical, electrical and plumbing (MEP) information, it is challenging to apply current common deep learning IE methods to the MEP domain. To solve this problem, this paper proposes a rule-based approach for MEP IE task, including a "snowball" strategy to collect large-scale MEP corpora, a suffix-based matching algorithm on text segments for named entity recognition (NER), and a dependency-path-based matching algorithm on dependency tree for relationship extraction (RE). 2 ideas called "meta linking" and "path filtering" for RE are proposed as well, to discover the out-of-pattern entities/relationships as many as possible. To verify the feasibility of the proposed approach, 65 MB MEP corpora have been collected as input of the proposed approach and an MEP semantic web which consists of 15,978 entities and 65,110 relationship triples established, with an accuracy of 81% to entities and 75% to relationship triples, respectively. A comparison experiment between classical deep learning models and the proposed rule-based approach was carried out, illustrating that the performance of our method is 37% and 49% better than the selected deep learning NER and RE models, respectively, in the aspect of extraction precision. • We proposed a snowball strategy to collect large-scale MEP corpora from the web. • We proposed a rule-based approach for the MEP named entity recognition (NER) and relationship extraction (RE). • Linking/filtering strategy is presented to discover out-of-pattern entity/relationships. • An MEP semantic web is constructed with a considerable size. • The performance of our method is about 40% better than deep learning models. [ABSTRACT FROM AUTHOR]

As an essential subproblem in the face recognition field, occluded face recognition has received considerable attention in recent years. However, satisfactory recognition accuracy for occluded faces has not been achieved. Therefore, in order to solve this problem, this paper proposes a convolutional neural network that has multidimensional serial feature extraction modules for occluded faces and uses the deep learning method to improve the recognition rate. In order to improve the expression ability of the network, the method extracts features from two dimensions — space and channel — and built a multidimensional serial feature extraction module. By "multiscale" and "dependence" processing features, the generalization ability was significantly improved. Through the experimental test, the recognition accuracy of the multidimensional feature network (MFNet) reached 90.35%. This accuracy is 17.89% (72.36%) better than that of the traditional algorithm. Meanwhile, compared with other convolutional neural networks, this network has different degrees of improvement, which are 0.68% (ArcFace), 2.14% (Visual Geometry Group Face), and 4.83% (DeepID3). [ABSTRACT FROM AUTHOR]

The intestine is an important organ of the human body, and its internal structure always needs to be observed in clinical applications so as to provide a basis for accurate diagnosis. However, due to the limited intestinal data obtained by a single institution, deep learning cannot effectively train the intestines, and the effect is not satisfied. For this reason, we propose a distributed training method to carry out federated learning to alleviate the situation of patient sample data shortage, not shared and uneven data distribution. And the blockchain is introduced to enhance the interaction between networks, to solve the problem of a single point of failure of the federated learning server. Fully excavate the multiscale features of samples, to construct a fusion enhancement model and intestinal segmentation module for accurate positioning. At the local end, the centerline extraction algorithm is optimized, with the edge as the main and the source as the auxiliary to realize centerline extraction. [ABSTRACT FROM AUTHOR]