Search

Folk paper-cut art is one of the bright pearls, with a wide range of shapes and a long history, that serves as a model for modern visual communication design in China and encourages designers to think creatively. Integrating emotional elements into a design not only can elicit an emotional response from the viewer but also can make works created using traditional rational thinking more vivid, energetic, and touching. The main focus of this research is on the path and method of incorporating folk paper-cut emotion into visual communication design. The research status of various feature extraction methods and image recognition methods at home and abroad is examined in depth in this paper. For the recognition of distorted images that are not transformed by mathematics, some effective methods are proposed. They are used to recognize artistic images of paper-cut patterns because they can extract effective features that are not affected by translation, rotation, scale change, or small deformation. Experiments have shown that they have a positive impact. The use of folk paper-cut art in visual communication design not only improves the quality of design work but also generates new ideas for the transmission and development of other traditional Chinese cultures. [ABSTRACT FROM AUTHOR]

As a commonly used mode of transportation in people's daily lives, the normal operation of railway transportation is crucial. The track circuit, as a key component of the railway transportation system, is prone to malfunctions due to environmental factors. However, the current method of inspecting track circuit faults still relies on the experience of on-site personnel. In order to improve the efficiency and accuracy of fault diagnosis, we propose to establish an intelligent fault diagnosis system. Considering that the fault data are a one-dimensional time series, this paper presents a fault diagnosis method based on the UNet-LSTM network (ULN). The LSTM network is established on the basis of fault data and used for ZPW-2000A track circuit fault diagnosis. However, the use of a single LSTM network has a high error rate in the common fault diagnosis of track circuits. Therefore, this paper proposes a feature extraction method based on the UNet network. This method is used to extract the features of the original data and then input them into the LSTM network for fault diagnosis. Through experiments with on-site fault data, it has been verified that this method can accurately classify seven common track circuit faults. Finally, the superiority of the method is verified by comparing it with other commonly used fault classification methods. [ABSTRACT FROM AUTHOR]

Vehicle detection and tracking from unmanned aerial vehicles (UAVs) aerial images are among the main tasks of intelligent traffic systems. Especially in tasks with long distances, extensive backgrounds, and small objects, it increases the difficulty of localization and regression, which can easily lead to missed detections and false positives. This paper proposes a detection-based small-scale vehicle tracking framework that integrates an improved YOLOX network and the DeepSORT algorithm to address these issues. Based on the original YOLOX network, a shallow feature extraction network, 160 × 160 pixels, is added to enhance the ability to extract small-scale object features. A convolutional block attention module (CBAM) is inserted in front of the neck network to select crucial information for vehicle detection tasks while suppressing noncritical ones. EIoU_Loss is introduced as the bounding box regression loss function in training to speed up their convergence and improve the localization accuracy of the small objects. Furthermore, an image segmentation method is proposed to effectively reduce missed and false detection events. It divides the original high-definition image into multiple subimages, first detected and then reassembled. Finally, the improved YOLOX network is used as the detector of the DeepSORT to perform small-scale vehicle detection and tracking tasks in various traffic scenarios. Experiments show that the proposed method can significantly improve the detection accuracy of the network and effectively solve the problems of missed detection and false positives in small-scale vehicle tracking tasks in high-resolution aerial images captured by high-altitude UAVs. Significantly, the algorithm proposed in this paper has sufficient robustness for small-scale tracking tasks of aerial videos captured at different altitudes. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative approach, Deep Multiscale Soft-Threshold Support Vector Data Description (DMS-SVDD), designed for the detection of anomalies and prediction of faults in heavy-duty gas turbine generator sets (GENSETs). The model combines a support vector data description (SVDD) with a deep autoencoder backbone network framework, integrating a multiscale convolutional neural network (M) and soft-threshold activation network (S) into the Deep-SVDD framework. In comparison with conventional methods, such as One-Class Support Vector Machine (OCSVM) and autoencoder (AE), DMS-SVDD demonstrates improvements in accuracy (by 22.94%), recall (by 32%), F1 score (by 12.02%), and smoothness (by 39.15%). The model excels particularly in feature extraction, denoising, and early fault detection, offering a proactive strategy for maintenance. Furthermore, the DMS-SVDD demonstrated enhanced training efficiency with a reduction in the convergence rounds by 66% and overall training times by 34.13%. The study concludes that DMS-SVDD presents a robust and efficient solution for gas turbine anomaly detection, with practical advantages for decision support in turbine maintenance. Future research could explore additional refinements and applications of the DMS-SVDD model across diverse industrial contexts. [ABSTRACT FROM AUTHOR]

Uneven water-air media distribution or irregular liquid flow can cause changes in light propagation, leading to blurring and distortion of the extracted image, which presents a challenge for object recognition accuracy. To address these issues, this paper proposes a repair network to correct object image distortion in water-air cross-media. Firstly, convolutional combination performs feature extraction on water-air cross-media images, which retains the same features at the same scale and marks feature points with large differences. Then, an attention correction module for geometric lines is proposed to correct geometric lines in water-air cross-media images by comparing and sensing the marked feature points with large differences and utilizing the line similarity in positive and negative samples. Finally, the blurring artifact elimination module eliminates artifacts caused by image blurring and geometric line correction by using multiscale fusion of individual U-Net information streams. This completes the image restoration of object distortion under water-air cross-media. The proposed method is feasible and effective for restoring aberrated objects in water-air cross-media environments, with numerous experiments conducted on water-air cross-media image datasets. [ABSTRACT FROM AUTHOR]

Machine learning (ML) algorithms are increasingly used in power systems applications. One important application is the classification and localization of various types of transmission line faults. Using voltage and current measurements from phasor measurement units (PMUs), a number of useful features can be extracted, which can form the basis of a ML-based prediction of the fault type, line, and distance on the line. This paper proposes a technique to find the optimal number and placement of PMUs by performing thorough feature selection. The features are selected to maximize the accuracy of the ML classification and regression algorithms. The results show that for the IEEE 14 bus system, the use of only five PMUs is sufficient to obtain high levels of accuracy. For example, a testing accuracy of 99.0% and 97.1% can be achieved for the fault type and fault line location, respectively. As for the fault distance along the line, the testing MAE of 3.1% can be obtained along with an R 2 score of 94.4%. Adding more PMUs does not provide any additional value in terms of accuracy. [ABSTRACT FROM AUTHOR]

The stable operation of the process industrial system, which is integrated with various complex equipment, is the premise of production, which requires the condition monitoring and diagnosis of the system. Recently, the continuous development of deep learning (DL) has promoted the research of intelligent diagnosis in process industry systems, and the sensor system layout has provided sufficient data foundation for this task. However, these DL-driven approaches have had some shortcomings: (1) the output signals of heterogeneous sensing systems existing in process industry systems are often high-dimensional coupled and (2) the fault diagnosis model built from pure data lacks systematic process knowledge, resulting in inaccurate fitting. To solve these problems, a graph feature fusion-driven fault diagnosis of complex process industry systems is proposed in this paper. First, according to the system's prior knowledge and data characteristics, the original multisource heterogeneous data are divided into two categories. On this basis, the two kinds of data are converted to physical space graphs (PSG) and process knowledge graphs (PKG), respectively, according to the physical space layout and reaction mechanism of the system. Second, the node features and system spatial features of the subgraphs are extracted by the graph convolutional neural network at the same time, and the fault representation information of the subgraph is mined. Finally, the attention mechanism is used to fuse the learned subgraph features getting the global-graph representation for fault diagnosis. Two publicly available process chemistry datasets validate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Deep learning has recently received extensive attention in the field of rolling-bearing fault diagnosis owing to its powerful feature expression capability. With the help of deep learning, we can fully extract the deep features hidden in the data, significantly improving the accuracy and efficiency of fault diagnosis. Despite this progress, deep learning still faces two outstanding problems. (1) Each layer uses the same convolution kernel to extract features, making it difficult to adaptively select convolution kernels based on the features of the input image, which limits the network's adaptability to different input features and leads to weak feature extraction. (2) Large number of parameters and long training time. To solve the above problems, this paper proposes an integrated deep neural network that combines an improved selective kernel network (SKNet) with an enhanced Inception-ResNet-v2, named SIR-CNN. First, based on the SKNet, a new three-branch SKNet was designed. Second, the new SKNet is embedded into a depthwise separable convolution network such that the model can adaptively select convolution kernels of different sizes during training. Furthermore, the convolution structure in the Inception-ResNet-v2 network was replaced by the improved depthwise separable convolution network to achieve effective feature extraction. Finally, the time-frequency maps of the raw vibration signals are obtained through short-time Fourier transform (STFT) and then sent to the proposed SIR-CNN network for experiments. The experimental results show that the proposed SIR-CNN achieves superior performance compared to other methods. [ABSTRACT FROM AUTHOR]

Accurate fault detection in high-voltage direct current (HVDC) transmission lines plays a pivotal role in enhancing operational efficiency, reducing costs, and ensuring grid reliability. This research aims to develop a cost-effective and high-performance fault detection solution for HVDC systems. The primary objective is to accurately identify and localize faults within the power system. In pursuit of this goal, the paper presents a comparative analysis of current and voltage characteristics between the rectifier and inverter sides of the HVDC transmission system and their associated alternating current (AC) counterparts under various fault conditions. Voltage and current features are extracted and optimized using a metaheuristic approach, specifically Harris Hawk's optimization method. Leveraging machine learning (ML) and artificial neural networks (ANN), this technique demonstrates its effectiveness in generating a fault locator with exceptional accuracy. With a substantial volume of data employed for learning and training, the Harris Hawks optimization method exhibits faster convergence compared to other metaheuristic methods examined in this study. The research findings are applied to simulate diverse fault types and unknown fault locations at multiple system points. Evaluating the fault detection system's effectiveness, quantified through metrics such as specificity, accuracy, F1 score, and sensitivity, yields remarkable results, with percentages of 99.01%, 98.69%, 98.64%, and 98.67%, respectively. This research underscores the critical role of accurate fault detection in HVDC systems, offering valuable insights into optimizing grid performance and reliability. [ABSTRACT FROM AUTHOR]

Software defect prediction (SDP) is designed to assist software testing, which can reasonably allocate test resources to reduce costs and improve development efficiency. In order to improve the prediction performance, researchers have designed many defect-related features for SDP. However, feature redundancy (FR) and irrelevance caused by the increasing dimensions of data will greatly degrade the performance of defect prediction. In order to solve the problems, researchers have proposed various data dimensionality reduction methods. These methods can be simply divided into two categories of methods: feature selection and feature extraction. However, the two categories of methods have their own advantages and limitation. In this paper, we propose a Hybrid Feature Dimensionality Reduction Approach (HFDRA) for SDP, which combines the two different kinds of methods, to improve the performance of SDP. HFDRA approach can be divided into two stages: feature selection and feature extraction. First, HFDRA divides the original features into several feature subsets through a clustering algorithm in the feature selection stage. Then, in the feature extraction stage, kernel principal component analysis (KPCA) is used to reduce the dimensionality of each feature subset. Finally, the reduced-dimensional data is used to build the prediction model. In the empirical study, we use 22 projects from AEEEM, SOFTLAB, MORP, and ReLink as experiment object. In this paper, we first compare our approach with seven baseline methods and three state-of-the-art methods. Then, we analyze the relationship between FR and prediction performance. Experiment results show that our approach outperforms the state-of-the-art data dimensionality reduction methods for defect prediction. [ABSTRACT FROM AUTHOR]

With people's higher and higher spiritual requirements, fiber art is more common in people's lives. From ordinary fiber materials to handicrafts and daily necessities, there are shadows of fiber art. This paper aims to study the application of two-dimensional images in the visual and tactile dimensions of fiber art design. This paper proposes a three-dimensional simulation of two-dimensional images of art based on deep learning technology to achieve the purpose of convenient display and also analyzes the feature extraction in fiber art. In order to comprehensively compare the performance of the algorithms, this paper compares the performance of four categories: reconstruction speed, number of reconstructed point clouds, diversity of reconstructable categories, and reconstruction stability. The experimental results show that the number of point clouds obtained by the algorithm proposed in this paper far exceeds the other two reconstruction processes, and the average time is 34.4 min. This also shows that such algorithmic processes are more robust to clothing diversity. [ABSTRACT FROM AUTHOR]

Pins are essential connecting components in power transmission lines. Their extensive use yet leads to frequent defects. Given the small size of a pin and many similar components, the detection of such defects is not ideal, which is a technological problem in the identification and diagnosis of power defects. In response to the large size, complex background, and on-site requirements, such as real-time detection, of power transmission lines, this paper proposes a method to detect pin defects based on TPH-MobileNetv3 (Transformer prediction Head Mobilenetv3). This paper modifies and adds a self-attention layer to MobilNetV3-Small to improve the feature extraction capability of small targets after downsampling. A feature fusion structure with layers of self-attention and a convolutional block attention module (CBAM) is added to the neck network, and a transformer prediction head are added to the head network so that different scale characteristics can be fused and focused from space and channels to strengthen the detection of small targets. Compared with the traditional MobileNetV3, the detection accuracy of the algorithm in this paper has been raised by 24%, as shown in the detection results of measured data. Moreover, compared with the mainstream algorithms with the same detection accuracy, this algorithm not only reduces the model size and significantly enhances detection efficiency but also satisfies the requirement of edge image processing of power inspection. [ABSTRACT FROM AUTHOR]

The problem of intrusion detection has new solutions, thanks to the widespread use of machine learning in the field of network security, but it still has a few issues at this time. Traditional machine learning techniques to intrusion detection rely on expert experience to choose features, and deep learning approaches have a low detection efficiency. In this paper, an intrusion detection model based on feature selection and improved one-dimensional convolutional neural network was proposed. This model first used the extreme gradient boosting decision tree (XGboost) algorithm to sort the preprocessed data, and then it used comparison to weed out 55 features with a higher contribution. Then, the extracted features were fed into the improved one-dimensional convolutional neural network (I1DCNN), and this network training was used to complete the final classification task. The feature selection and improved one-dimensional convolutional neural network (FS-I1DCNN) intrusion detection model not only solved the traditional machine learning method of relying on expert experience to extract features but also improved the detection efficiency of the model, reduced the training time while reducing the dimension, and increased the overall accuracy. In comparison to the I1DCNN model without feature extraction and the conventional one-dimensional convolutional neural network (1DCNN) model, the experimental results demonstrate that the FS-I1DCNN model's overall accuracy increases by 0.67% and 2.94%, respectively. Its accuracy, precision, recall, and F 1 -score were significantly better than those of the other intrusion detection models, including SVM and DBN. [ABSTRACT FROM AUTHOR]

The convolution neural network (CNN) not only has high fault tolerance but also has high computing capacity. The image classification performance of CNN has an important relationship with its network depth. The network depth is deeper, and the fitting ability of CNN is stronger. However, a further increase in the depth of CNN will not improve the accuracy of the network but will produce higher training errors, which will reduce the image classification performance of CNN. In order to solve the above problems, this paper proposes a feature extraction network, AA-ResNet with an adaptive attention mechanism. The residual module of the adaptive attention mechanism is embedded for image classification. It consists of a feature extraction network guided by the pattern, a generator trained in advance, and a complementary network. The feature extraction network guided by the pattern is used to extract different levels of features to describe different aspects of an image. The design of the model effectively uses the image information of the whole level and the local level, and the feature representation ability is enhanced. The whole model is trained as a loss function, which is about a multitask problem and has a specially designed classification, which helps to reduce overfitting and make the model focus on easily confused categories. The experimental results show that the method in this paper performs well in image classification for the relatively simple Cifar-10 dataset, the moderately difficult Caltech-101 dataset, and the Caltech-256 dataset with large differences in object size and location. The fitting speed and accuracy are high. [ABSTRACT FROM AUTHOR]

Dynamic-vibration-based structural damage identification (SDI) represents the main target for structural health monitoring (SHM). It is significant to consider the unavoidable uncertainties arising from both the structure and measuring noise. On the other hand, nonuniform measurement conditions often appear in actual SHM applications, which consist of two parts, i.e., spatial nonuniform characteristics for noises are induced by various intensities of input noise in every single sampling channel and multisensor stays in a damaged state. This paper proposes a new method for the SDI considering uncertainties in nonuniform measurement conditions integrating convolutional neural network (CNN). Herein, the great ability of feature extraction from the measurement associated with the convolutional network is used to handle the input data, and the mapping connection between the selected features and damage states is established. Time histories of structural responses, such as acceleration, are applied for damage identification. The application and accuracy of the CNN, which is trained with input uncertain parameters contaminated by stochastic noises, are verified by the finite element numerical and experimental results. Both uncertain parameters and measurement conditions are considered in the verification. The responses obtained from the numerical and experimental approach show that the proposed neural network model can identify the structural damage with high accuracy. The great robustness of the proposed method is examined by studying the influence of uncertainties, even considering the nonuniform measurement condition. [ABSTRACT FROM AUTHOR]

Railway axle box bearing fault signal contains high Q-factor resonance and low Q-factor transient shock components with periodic transient shock features that can characterize bearing faults. However, extracting fault features is usually difficult due to noise, transmission paths, and high-amplitude accidental shocks. Therefore, to address the abovementioned problems, the multilevel feature extraction method for adaptive fault diagnosis of railway axle box bearing was proposed. This paper used the maximum second-order cyclostationary blind convolution (CYCBD) to weaken the influence of disturbances, enhancing weak transient shock components. Resonant sparse decomposition(RSSD) is used for the selection of quality factor Q due to its excellent fault feature separation property. Considering the strict fault frequency component periodicity in the envelope spectrum, the envelope spectrum multipoint kurtosis (ESMK) is proposed as a metric. The Q factor is optimized using the gray wolf optimization algorithm (GWO) to obtain an adaptive sparse decomposition method (GWO-RSSD) for extracting bearing transient fault shocks to eliminate the signal effects of high-amplitude disturbance shocks and background noise. The simulation results and measured signal analysis of railway axle box bearing show that ESMK can effectively measure periodic transient shocks under strong shock interference compared with the MED-RSSD method. Thus, GWO-RSSD can adaptively separate the optimal low-Q resonance components, verifying the methods' effectiveness and superiority. [ABSTRACT FROM AUTHOR]

Transformer model is being gradually studied and applied in bearing fault diagnosis tasks, which can overcome the feature extraction defects caused by long-term dependencies in convolution neural network (CNN) and recurrent neural network (RNN). To optimize the structure of existing transformer-like methods and improve the diagnostic accuracy, we proposed a novel method based on the multiscale time-frequency sparse transformer (MTFST) in this paper. First, a novel tokenizer based on shot-time Fourier transform (STFT) is designed, which processes the 1D format raw signals into 2D format discrete time-frequency sequences in the embedding space. Second, a sparse self-attention mechanism is designed to eliminate the feature mapping defect in naive self-attention mechanism. Then, the novel encoder-decoder structure is presented, the multiple encoders are employed to extract the hidden feature of different time-frequency sequences obtained by STFT with different window widths, and the decoder is used to remap the deep information and connect to the classifier for discriminating fault types. The proposed method is tested in the XJTU-SY bearing dataset and self-made experiment rig dataset, and the following work is conducted. The influences of hyperparameters on diagnosis accuracy and number of parameters are analysed in detail. The weights of the attention mechanism (AM) are visualized and analysed to study the interpretability, which explains the partly working pattern of the network. In the comparison test with other existing CNN, RNN, and transformer models, the diagnosis accuracy of different methods is statistically analysed, feature vectors are presented via the t-distributed stochastic neighbor embedding (t-SNE) method, and the proposed MTFST obtains the best accuracy and feature distribution form. The results demonstrate the effectiveness and superiority of the proposed method in bearing fault diagnosis. [ABSTRACT FROM AUTHOR]

Artificial intelligence and deep learning have attracted much attention from researchers in industry and academia. The volleyball movement standardization and recognition model involve the application of artificial intelligence and deep learning. In order to solve the problem that human action in volleyball video is continuous and effective spatial and temporal features need to be extracted from the video stream, the Inception module is decoupled and heterogeneous, replacing the original 5 × 5 convolutional structures with two 3 × 3 convolutional structures, as well as replacing the 3 × 3 convolutional structures with 1 × 3 and a 3 × 1 convolutional structure with internal parameter optimization to ensure the accuracy of recognition. The model uses the input motion video RGB map as the spatial input and the optical flow map as the temporal input, and the two are weighted 1 : 1 for feature fusion. Experiments are conducted on the volleyball action video and homemade dataset in UCF101, and the experimental data show that the accuracy of the DNet volleyball action standardization recognition model proposed in this paper is 94.12%, which proves that the method improves the recognition ability of the model while speeding up the training speed. The research presented in this paper provides important theoretical guidance for artificial intelligence and deep learning. [ABSTRACT FROM AUTHOR]

Due to millimeter‐wave (MMW) has a strong ability to penetrate clothing, MMW holographic imaging technology can conduct a non‐contact inspection of the human body's surface. Therefore, it is of great significance to study the security inspection equipment and target recognition technology based on millimeter wave imaging. In this paper, an active and passive hybrid millimeter wave imaging target recognition method based on multi‐feature fusion is proposed, which improves the ability of the imaging system to identify different dangerous targets. First, active and passive millimeter wave imaging techniques are discussed, the reconstruction algorithm of active millimeter wave holographic imaging is derived in detail, and the measured optical photos and data of active and passive imaging are obtained. Secondly, the image preprocessing technology applied to active and passive millimeter wave imaging is studied, which can effectively highlight the target, eliminate background interference, and clearly describe the target contour. Then the methods of image feature extraction, data feature extraction and multi‐feature fusion are studied. On this basis, a multi‐feature fusion method based on weighted series fusion is proposed to obtain the fusion feature vector form of active and passive MMW imaging. Finally, this paper proposed the target recognition method applied to millimeter wave imaging, and concludes that the fusion feature vector is better than the original feature vector, which provides an idea for the fusion of active and passive millimeter wave imaging at the feature level. It also provides a theoretical basis for the application of security equipment. [ABSTRACT FROM AUTHOR]

Nowadays, the verification of handwritten signatures has become an effective research field in computer vision as well as machine learning. Signature verification is naturally formulated as a machine-learning task. This task is performed by determining if the signature is genuine or forged. Therefore, it is considered a two‐class classification issue. Since handwritten signatures are widely used in legal documents and financial transactions, it is important for researchers to select an efficient machine-learning technique for verifying these signatures and to avoid forgeries that may cause many losses to customers. So far, great outcomes have been obtained when using machine learning techniques in terms of equal error rates and calculations. This paper presents a comprehensive review of the latest studies and results in the last 10 years in the field of online and offline handwritten signature verification. More than 20 research papers were used to make a comparison between datasets, feature extraction, and classification techniques used in each system, taking into consideration the problems that occur in each. In addition, the general limitations and advantages of machine-learning techniques that are used to classify or extract signature features were summarized in the form of a table. We also present the general steps of the verification system and a list of the most considerable datasets available in online and offline fields. [ABSTRACT FROM AUTHOR]

The development of industry is inseparable from the support of steel materials, and the modern industry has increasingly high requirements for the quality of steel plates. But the process of steel plate production produces many types of defects, such as roll marks, scratches, and scars. These defects will directly affect the quality and performance of the steel plate, so it is necessary to effectively detect them. Steel plate surface defects are characterized by their types, shape, and size: the same defect can have different morphologies, and similarities can exist between different defects. In this paper, industrial steel plate surface defect samples are analyzed, and a sample set is established by screening the collected defect images. Then, annotation and classification are performed. A multilayer feature extraction framework is developed in experiments to train a neural network on the sample set of defects. To address the problems of low automation, slow detection speed, and low accuracy of the traditional defect detection methods, the attention graph convolution network (AGCN) is investigated in this paper. Firstly, faster R-CNN is used as the basic network model for defect detection, and the visual features are jointly refined by combining attention mechanism and graph convolution neural network. The latter network enriches the contextual information in the visual features of steel plates and explores the semantic association between vision and defect types for different kinds of defects using the attention mechanism to achieve intelligent detection of defects, thus enabling our method to meet the practical needs of steel plate production. [ABSTRACT FROM AUTHOR]

With the continuous development of digital technology, music, as an important form of media, and its digital audio technology is also constantly developing, forcing the traditional music industry to start the road of digital transformation. What kind of method can be used to automatically retrieve music information effectively and quickly in vocal singing has become one of the current research topics that has attracted much attention. Aiming at this problem, it is of great research significance for the field of timbre feature recognition. With the in-depth research on timbre feature recognition, the research on timbre feature extraction by machine learning in vocal singing has also been gradually carried out, and its performance advantages are of great significance to solve the problem of automatic retrieval of music information. This paper aims to study the application of feature extraction algorithm based on machine learning in timbre feature extraction in vocal singing. Through the analysis and research of machine learning and feature extraction methods, it can be applied to the construction of timbre feature extraction algorithms to solve the problem of automatic retrieval of music information. This paper analyzed vocal singing, machine learning, and feature extraction, experimentally analyzed the performance of the method, and used related theoretical formulas to explain. The results have showed that the method for timbre feature extraction in the vocal singing environment was more accurate than the traditional method, the difference between the two was 24.27%, and the proportion of satisfied users was increased by 33%. It can be seen that this method can meet the needs of users for timbre feature extraction in the use of music software, and the work efficiency and user satisfaction are greatly improved. [ABSTRACT FROM AUTHOR]

Many IP (intellectual property) will also be infringed, and it will become more and more serious, causing huge economic losses to people or groups who own IP. If punitive damages can be made for intentional but intentional infringement of IP, it will help to stop intentional infringement of IP, and it can also give due compensation to the obligee's loss. Based on this, this paper analyzes the introduction and implementation of punitive damages in IP law. In this paper, a relatively efficient text classification method is realized by using the method of deep learning and model design. Similar texts in the training set are grouped into a group, and each group is considered as a common text vector. Then, a threshold is set to deal with clusters higher than the threshold, and the training set is reformed. Through the experimental results, the feature extraction effect of this model is improved, the classification accuracy is constantly improved, and the final convergence rate of this model reaches 95%. It has been verified that the system can realize the automatic classification of basic Chinese patent texts. [ABSTRACT FROM AUTHOR]

Bearing fault is a process of gradual development and deepening. In the early stage of the fault, if it can be found out in time and taken reasonable prevention and elimination measures, we can avoid serious losses and safety accidents. Therefore, the feature extraction and analysis of early weak fault has important practical significance. In this paper, an improved multiscale permutation entropy (IMPE) method was proposed to overcome the shortcomings in the coarse-grained process. In order to solve the problem that only considering a single coarse-grained sequence under a certain scale may lead to the loss of feature information, this paper proposed to calculate the time series with equal overlapping segments, that was to consider all coarse-grained sequences under the same scale to reflect the feature information of fault signals more comprehensively. In order to solve the problem that feature extraction is not refined enough when using the first-order moment mean value calculation in traditional MPE calculation, a calculation method based on the skewness of the third-order moment was proposed. The calculation method is more sensitive to the complexity and fluctuation of signals and can better describe the feature details and extract the fault features effectively. IMPE was applied to feature extraction of early weak fault of rolling bearing and input into Support Vector Machines (SVMs) for faults classification. Aiming at SVM parameter optimization problem, an improved chaos firefly optimization algorithm was proposed. Experimental results show that the new method of early weak fault identification based on IMPE-SVM was effective in detecting rolling bearing faults with different severity. [ABSTRACT FROM AUTHOR]

This paper designs a feature extraction-based physical characteristics and kinematic analysis of collegiate martial arts Sanda athletes by profoundly studying the model of athletes' action feature extraction and constructing physical characteristics and kinematic model of collegiate martial arts Sanda athletes. This paper provides feature extraction category support by describing the data types of clustered objects, calculating behavioral operator distances, identifying multiple behaviors occurring in collegiate martial arts Sanda tactics, and delineating the correct thresholds for operator identification. A comparison experiment is designed to verify that the proposed method can improve the accuracy of feature extraction for athletes' technical and tactical use and is more applicable to the comprehensive assessment of athletes' behaviors. The underlying features of the athletes' motion technique forming image features are analyzed, the image features are regionally divided, the feature sets of different levels of developing actions are obtained, and the image features are allowed to map to the corresponding feature dimension space. The AdaBoost algorithm filters out the feature data of the athletes' action images that contribute most to the intelligent visual analysis. It is used as training samples for training and recognition to complete the extraction of athlete action image features. The action times of the five different phases of side kick up, knee lift, kick strike, and strike: recovery is 0.2986 s, 0.1819 s, 0.1322 s, 0.0708 s, and 0.9986 s, respectively, which reflects that the time of different action phases of athletes with extra body weight is more related to the athletes' weight, strength, flexibility, and coordination. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles (UAVs), commonly known as drones, have been progressively prevalent due to their capability to operate quickly and their vast range of applications in a variety of real-world circumstances. The utilization of UAVs in precision farming has lately gained a lot of attention from the scientific community. This study addresses with the assistance of drones in the precision agricultural area. This paper makes significant contributions by analyzing communication protocols and applying them to the challenge of commanding a fleet of drones to protect crops from parasite infestations. In this research, the effectiveness of nine powerful deep neural network models is measured for the detection of plant diseases using diverse methodologies. These deep neural networks are adapted to the immediate situation using transfer learning and deep extraction of features approaches. The presented study takes into account the used pretrained deep learning model for extracting features and fine-tuning. The deep feature extraction characteristics are subsequently categorized using support vector machines (SVMs) and extreme learning machines (ELMs). For measuring performance, the precision, sensitivities, specific, and F1-score are all evaluated. Deep feature extraction and SVM/ELM classification generated better outcomes than transfer learning, according to the analysis result. Furthermore, the analysis of the various methodologies tries to assess their effectiveness and costs. The different approaches, for example, confront difficulties such as investigating the region in the shortest possible time feasible, while eliminating the same region being searched by more drones, detecting parasites, and stopping their spread by applying the appropriate number of pesticides. Simulation models are a significant aid to researchers in conducting to evaluate these technologies and creating specific tactics and coordinating procedures capable of effectively supporting farms and achieving the aim. The main objective of this paper is to compare the search techniques of two distinct methods of parasitic to identify performance. [ABSTRACT FROM AUTHOR]

This paper designs a multimodal convolutional neural network model for the intelligent analysis of the influence of music genres on children's emotions by constructing a multimodal convolutional neural network model and profoundly analyzing the impact of music genres on children's feelings. Considering the diversity of music genre features in the audio power spectrogram, the Mel filtering method is used in the feature extraction stage to ensure the effective retention of the genre feature attributes of the audio signal by dimensional reduction of the Mel filtered signal, deepening the differences of the extracted features between different genres, and to reduce the input size and expand the model training scale in the model input stage, the audio power spectrogram obtained by feature extraction is cut the MSCN-LSTM consists of two modules: multiscale convolutional kernel convolutional neural network and long and short term memory network. The MSCNN network is used to extract the EEG signal features, the LSTM network is used to remove the temporal characteristics of the eye-movement signal, and the feature fusion is done by feature-level fusion. The multimodal signal has a higher emotion classification accuracy than the unimodal signal, and the average accuracy of emotion quadruple classification based on a 6-channel EEG signal, and children's multimodal signal reaches 97.94%. After pretraining with the MSD (Million Song Dataset) dataset in this paper, the model effect was further improved significantly. The accuracy of the Dense Inception network improved to 91.0% and 89.91% on the GTZAN dataset and ISMIR2004 dataset, respectively, proving that the Dense Inception network's effectiveness and advancedness of the Dense Inception network were demonstrated. [ABSTRACT FROM AUTHOR]

In the field of mechanical and electrical equipment, the motor rolling bearing is a workpiece that is extremely prone to damage and failure. However, the traditional fault diagnosis methods cannot keep up with the development pace of the times because they need complex manual pretreatment or the support of specific expert experience and knowledge. As a rising star, the data-driven fault diagnosis methods are increasingly favored by scholars and experts at home and abroad. The convolutional neural network has been widely used because of its powerful feature extraction ability for all kinds of complex information and its outstanding research results in image processing, target tracking, target diagnosis, time-frequency analysis, and other scenes. Therefore, this paper introduces a convolutional neural network and applies it to motor-bearing fault diagnosis. Aiming at the shortcomings of fault signal and convolutional neural network, a large-scale maximum pooling strategy is proposed and optimized by wavelet transform to improve the fault diagnosis efficiency of motor bearing under high-voltage operation. Compared with other machine learning algorithms, the convolution neural network fault diagnosis model constructed in this paper not only has high accuracy (up to 0.9871) and low error (only 0.032) but also is simple to use. It provides a new way for motor bearing fault diagnosis and has very important economic and social value. [ABSTRACT FROM AUTHOR]

The entire auditing process is complicated and tedious and requires a lot of human resources. Therefore, the intelligent development of auditing is the general trend. In order to improve the audit quality, this paper establishes an intelligent financial audit model that can predict the audit opinion of the consolidated financial statements. This paper proposes an audit opinion prediction model based on the fusion of deep belief neural network (DBN) and long-short term memory (LSTM). First, an indicator system is established for audit opinions, and multiple financial parameters are used to describe possible audit opinions. On this basis, a DBN network is designed to complete deep feature extraction and used for LSTM training. According to the prediction model obtained by training, the subsequent audit opinion can be scientifically predicted. In the experiment, the method in this paper is tested based on financial audit related data sets and compared with the prediction results of traditional multilayer perceptron (MLP), convolutional neural network (CNN), and LSTM models. The results verify the validity and reliability of the model in this paper. [ABSTRACT FROM AUTHOR]

This paper analyses the design of a healthy interior environment using big data intelligence. The application of big data intelligence in the design of healthy interior environments is necessary because the traditional interior design approaches consume a lot of energy and other problems. Benefited by its strong ability of computation and analytics, artificial intelligence can well improve a series of problems in the field of interior design. The proposal summarizes the sources, classifications, and expressions of behavioral data in interior spaces, carries out analysis and research on behavioral data from two aspects: display space and supermarket space, summarizes the interior methods based on behavioral data, and analyses the visualization application of behavioral data in different interior scenes, to explore the application value of behavioral data in interior design. In contrast to it is the unconscious behavioral response, the biggest characteristic of which is that it is regulated by the behavioral subject's physiological factors or habits of the behavior issuer. In this paper, we convert the layout recommendation problem of a space into a functional classification problem of segmented segments and household segments on a plane. The scene layout features are extracted by binary coding, the abstraction of the cross features between the vector segments is achieved by using a word embedding algorithm, the feature matrix is reduced in dimensionality, and finally, the segmentation network model and the layout network model are constructed, respectively, by using a bidirectional LSTM. The experiments show that the accuracy of the layout recommendation model in this paper is 98%, which can meet the demand for real-time online layouts. [ABSTRACT FROM AUTHOR]

Facial expression recognition based on residual networks is important for technologies related to space human-robot interaction and collaboration but suffers from low accuracy and slow computation in complex network structures. To solve these problems, this paper proposes a multiscale feature fusion attention lightweight wide residual network. The network first uses an improved random erasing method to preprocess facial expression images, which improves the generalizability of the model. The use of a modified depthwise separable convolution in the feature extraction network reduces the computational effort associated with the network parameters and enhances the characterization of the extracted features through a channel shuffle operation. Then, an improved bottleneck block is used to reduce the dimensionality of the upper layer network feature map to further reduce the number of network parameters while enhancing the network feature extraction capability. Finally, an optimized multiscale feature lightweight attention mechanism module is embedded to further improve the feature extractability of the network for human facial expressions. The experimental results show that the accuracy of the model is 73.21%, 98.72%, and 95.21% on FER2013, CK+ and JAFFE, respectively, with a covariance of 10.14 M. Compared with other networks, the model proposed in this paper has faster computing speed and better accuracy at the same time. [ABSTRACT FROM AUTHOR]

This paper proposed a hybrid approach for the identification of encrypted traffic based on advanced mathematical modeling and computational intelligence. Network traffic identification is the premise and foundation of improving network management, service quality, and application security. It is also the focus of network behavior analysis, network planning and construction, network anomaly detection, and network traffic model research. With the increase in user and service requirements, many applications use encryption algorithms to encrypt traffic during data transmission. As a result, traditional traffic classification methods classify encrypted traffic on the network, which brings great difficulties and challenges to network monitoring and data mining. In our article, a nonlinear modified DBN method is proposed and applied to encrypted traffic identification. Firstly, based on Deep Belief Networks (DBN), this paper introduces the proposed Eodified Elliott (ME)-DBN model, analyzes the function image, and presents the ME-DBN learning algorithm. Secondly, this article designs an encrypted traffic recognition model based on the ME-DBN model. Feature extraction is carried out by training the ME-DBN model, and finally, classification and recognition are carried out by the classifier. The experimental results on the ISCX VPN-non-VPN database show that the MEDBN method proposed in this article can enhance the classification and recognition rate and has better robustness to encrypt traffic recognition from different software. [ABSTRACT FROM AUTHOR]

The rapid development of the internet and multimedia technology in recent years has continued to push foreign language education in the direction of modern education. Multimodal education is becoming more and more important in the field of English education as an advanced educational concept in the field of language education. As a result, many English teachers have begun to emphasize the use of multimodal teaching theory in their classrooms. This paper investigates a multimodal model that incorporates text and image features, based on multimodal discourse theory, systemic functional linguistics theory, and foreign language teaching theory. This paper develops a multimodal model that can search for images and texts from various perspectives. We use an image feature bias term in the log-bilinear natural language model to influence the probability of predicting the next word based on the context, resulting in a multimodal model. The experimental results show that the proposed model, as an image-text relationship evaluation index system, has a slower search speed than other models but better search accuracy. [ABSTRACT FROM AUTHOR]

In order to improve the recognition accuracy of action poses for athletes in martial arts competitions, it is considered that a single frame pose does not have the temporal features required for sequential actions. Based on deep learning, this paper proposes an image arm movement analysis technology in martial arts competitions. The motion features of the arm are extracted from the bone sequence. Taking human bone motion information as temporal dynamic information, combined with RGB spatial features and depth map, the spatiotemporal features of arm motion data are formed. In this paper, we set up a slow frame rate channel and a fast frame rate channel to detect sequential motion of images. The deep learning model takes 16 frames from each video as samples. The softmax classifier is used to get the classification result of which action category the human action in the video belongs to. The test results show that the accuracy and recall rate of the arm motion analysis technology based on deep learning in martial arts competitions are 95.477% and 92.948%, respectively, with good motion analysis performance. [ABSTRACT FROM AUTHOR]

Vulnerability detection technology has become a hotspot in the field of software security, and most of the current methods do not have a complete consideration during code characterizing, which leads to problems such as information loss. Therefore, this paper proposes one class of Scalable Feature Network (SFN), a composite feature extraction method based on Continuous Bag of Words and Convolutional Neural Network. In addition, to characterize the source code more comprehensively, we construct multiscale code metrics in terms of semantic-, line-, and function granularity. In order to verify the effectiveness of the SFN, this paper builds a Scalable Vulnerability Detection Model (SVDM) by combining SFN with Bi-LSTM. The experimental results show that the proposed SVDM can obtain precision over 84.3% and recall at 83.4%, respectively, while both FNR and FPR are less than 17%. [ABSTRACT FROM AUTHOR]

In the current battlefield space, with the massive application of electromagnetic equipment, the electromagnetic environment in the battlefield space tends to be complex, which can lead to the electromagnetic equipment and personnel in the battlefield space receiving interference from the electromagnetic environment signal. To protect the safety of personnel and equipment quality, it is necessary to evaluate the complexity of the electromagnetic environment signal research, to use the corresponding measures. However, there is still little research related to the evaluation of the complexity of electromagnetic environmental signals. In this paper, a feature extraction method for electromagnetic environmental signals based on adaptive multiscale morphological gradient filtering and a nonnegative matrix factorization algorithm is proposed. First, the electromagnetic environment signal is filtered by AMMG, and then the filtered signal is processed by NMF for feature extraction. Finally, the complex electromagnetic environment signals after feature extraction are evaluated and classified by the SVM method. The results show that the evaluation results have good classification accuracy, and this paper provides an effective feature extraction method for the complexity of electromagnetic environment signals. [ABSTRACT FROM AUTHOR]

In actual concrete arch dam engineering scenarios, the dynamic data obtained by the health monitoring system of an arch dam are incomplete. The data acquired typically depend on the state of the dam structure, that is, whether it is intact or incomplete. Besides, the future environmental loads of the structure are unpredictable. Thus, environmental noise is also uncertain. In practical engineering, the use of a damage identification model constructed based on incomplete information is problematic in scenarios with variable loads. Consequently, detecting the water level in actual arch dam projects after an earthquake and determining the impact of environmental uncertainty are necessary. Accordingly, this paper proposes a denoising contractive sparse deep autoencoder (DCS-DAE) model based on domain adaptation. The core idea of the proposed method is to constrain the data probability distribution of feature spaces in the source and target domains using maximum mean discrepancy. This fusion enables the DCS-DAE model to be capable of feature extraction. Moreover, it resolves the problem in which the objective function cannot be applied to other similar scenarios because of the lack of consistency constraints of feature spaces in the source and target domains. Four working conditions are designed to reproduce the uncertainty of structural modeling and the variability of water levels. The conditions are based on the postseismic water level detection requisites of dams in practical engineering. The results show that the proposed anomaly detection model enhances the generalization performance of the DCS-DAE in terms of feature design. Hence, the constructed model can "infer other things from one fact." The results of this study are meaningful for the real-time cross-domain monitoring of structures under variable load conditions, providing a driving force to apply similar methods to practical arch dam projects. [ABSTRACT FROM AUTHOR]

The typical pretrained model's feature extraction capabilities are insufficient for medical named entity identification, and it is challenging to express word polysemy, resulting in a low recognition accuracy for electronic medical records. In order to solve this problem, this paper proposes a new model that combines the BERT pretraining model and the BilSTM-CRF model. First, word embedding with semantic information is obtained by pretraining the corpus input to the BERT model. Then, the BiLSTM module is utilized to extract further features from the encoded outputs of BERT in order to account for context information and improve the accuracy of semantic coding. Then, CRF is used to modify the results of BiLSTM to screen out the annotation sequence with the largest score. Finally, extensive experimental results show that the performance of the proposed model is effectively improved compared with other models. [ABSTRACT FROM AUTHOR]

Online advertising has become one of the most important strategies used by companies. They get the valuable results from Internet marketing and communication strategies. Therefore, it is necessary to study the click-through rate (CTR) model to search the potential audiences in online advertising. The advertisers desire to search for potential candidates through a large number of queries for audiences in programmatic advertising. Facing such a large corpus, the most common method is that using two-tower model to learn user's queries and ad representations, and then the similarity function is applied to match the feature representation to get the potential audiences related to the ad. However, in the process of feature extraction, there is a lack of information interaction between the two towers, resulting in the loss of details in the representation. In order to alleviate the lack of information interaction between the networks in the two-tower model during feature extraction. In this paper, we propose a novel model named Feature Dual Supervision Model (FDSM), which integrates by Feature Expression Unit (FEU) and Feature Supervision Unit (FSU). The FEU is used to extract ads or users features, and FSU generates a weight vector to supervise the working process of the FEU. In addition, we propose a feature cross-layer with bridge connections in FDSM to achieve effective feature interaction between ad and user representations. Finally, we conduct experiments on the Tencent Lookalike and MovieLens datasets. The experimental results indicate that the FDSM model outperforms other state-of-the-art CTR prediction models in audience expansion. [ABSTRACT FROM AUTHOR]

From the cassette era to the CD era to the digital music era, the quantity of music has grown rapidly. People cannot easily search for the desired music without classifying enormous music resources and developing a successful music retrieval system. By examining users' historical listening patterns for personalised recommendations, the music recommendation algorithm can lessen message fatigue for users and enhance user experience. Relying on manual labelling is how traditional music is classified. It would be inefficient and unrealistic to attempt to classify music using manual labelling in the age of big data. Feature extraction and neural networks are the tools employed in this paper. The model's parameters can be trained using conventional gradient descent techniques, and the model's trained convolution neural network can learn the image's features and finish the extraction and classification of the features. This algorithm is 12 percent superior to the conventional algorithm, according to the research in this paper. It has strong ability and is appropriate for widespread implementation with the same number of iterations. [ABSTRACT FROM AUTHOR]

The study of plantar pressure has become a research consensus in the field of biomechanics. The purpose of this paper is to study some lower limb movements in the daily activities of ice and snow athletes to obtain relevant data so as to carry out gait recognition analysis research. This paper selects the average foot pressure, forefoot foot pressure, front and rear foot pressure, foot pressure, toe pressure, 2–5 toe pressure, standing with eyes closed, x- and y-axes speed, foot length, foot width, and other actions of ice and snow athletes. Therefore, correlation analysis, work analysis, and curve fitting analysis were carried out on the joint motion in a single gait cycle. The collection and application of foot pressure and foot posture information are also analyzed. According to the plantar structure, the sole is divided into four parts. The maximum pressure point and coordinates of each part, the pressure center point, the ratio of the width and height of the sole of the foot, and so on are extracted as the haptic features of the gait. The experimental data shows that it can be seen that if the plantar area is divided in advance and the weight of each area is marked, whether standing, walking, or standing with one leg closed eyes can achieve better recognition results, and the accuracy rate is all more than 90 percent. The average recognition accuracy rate using the method of dividing four regions is only about 80%, and the accuracy rate of recognition using the method of dividing eight regions is 82%. It can be seen that the features extracted by the FCM model proposed in this paper contain more information of the plantar pressure image, and the accuracy rate is higher in the classification and recognition. [ABSTRACT FROM AUTHOR]

Diabetes mellitus is a common chronic noncommunicable disease, the main manifestation of which is the long-term high blood sugar level in patients due to metabolic disorders. However, due to excessive reliance on the clinical experience of ophthalmologists, our diagnosis takes a long time, and it is prone to missed diagnosis and misdiagnosis. In recent years, with the development of deep learning, its application in the auxiliary diagnosis of diabetic retinopathy has become possible. How to use the powerful feature extraction ability of deep learning algorithm to realize the mining of massive medical data is of great significance. Therefore, under the action of computer-aided technology, this paper processes and analyzes the retinal images of the fundus through traditional image processing and convolutional neural network-related methods, so as to achieve the role of assisting clinical treatment. Based on the admission records of diabetic patients after data analysis and feature processing, this paper uses an improved convolutional neural network algorithm to establish a model for predicting changes in diabetic conditions. The model can assist doctors to judge the patient's treatment effect by using it based on the case records of inpatient diagnosis and treatment and to predict the risk of readmission of inpatients after discharge. It also can help to judge the effectiveness of the treatment plan. The results of the study show that the model proposed in this paper has a lower probability of misjudging patients with poor recovery as good recovery, and the prediction is more accurate. [ABSTRACT FROM AUTHOR]

This paper solves the problem of difficulty in achieving satisfactory results with traditional methods of bearing fault diagnosis, which can effectively extract the fault information and improve the fault diagnosis accuracy. This paper proposes a novel artificial intelligence fault diagnosis method by integrating complementary ensemble empirical mode decomposition (CEEMD), energy entropy (EE), and probabilistic neural network (PNN) optimized by a sparrow search algorithm (SSA). The vibration signal of rolling bear was firstly decomposed by CEEMD into a set of intrinsic mode functions (IMFs) at different time scales. Then, the correlation coefficient was used as a selection criterion to determine the effective IMFs, and the signal features were extracted by EE as the input of the diagnosis model to suppress the influence of the redundant information and maximize the retention of the original signal features. Afterwards, SSA was used to optimize the smoothing factor parameter of PNN to reduce the influence of human factors on the neural network and improve the performance of the fault diagnosis model. Finally, the proposed CEEMD-EE-SSA-PNN method was verified and evaluated by experiments. The experimental results indicate that the presented method can accurately identify different fault states of rolling bearings and achieve better classification performance of fault states compared with other methods. [ABSTRACT FROM AUTHOR]

This paper presents an in-depth study of a statistical system using image feature extraction technology for cultural heritage tourism information. Based on the specificity of the tourism industry, it combines the technical architecture, framework of image feature extraction, GIS basic design, database design, and other related theories; realizes visual mapping through relevant tourism statistics in GIS; and uses the spatial analysis capability of ArcGIS software to complete the statistical scheme of cultural heritage tourism information data in the context of Internet big data. In this paper, the image preprocessing process is accelerated by the parallel optimization of the filtering operation and down-sampling operation in the relevant image preprocessing algorithm. The preprocessed images can effectively improve the recognition effect of the image feature extraction and classification stage. Based on cultural heritage tourism information mining results, the design and development of the tourism information statistics platform are carried out. The platform is built and developed using GIS secondary development technology and HTML + CSS front-end development technology API, Echarts, and other image feature components. The platform enables the massive and disorganized tourism text information to be displayed in a way that is easier to understand in both maps and text. This paper's research on critical technologies provides technical support for image feature extraction of tourism statistics, which has specific practical value. Implementing the cultural heritage tourism platform offers a visual operating environment for tourism, enabling cultural heritage tourism businesses to tap into user preferences so that users can effectively access the travel options that interest them, which is conducive to promoting the development of travel recommendation platforms. [ABSTRACT FROM AUTHOR]

With the continuous development of social economy, English learning plays an increasingly important role in daily communication. However, the update speed of English textbooks is far lower than the development speed of English. How to reconstruct the text of English textbooks in colleges and universities to improve the learning effect of college English has become an urgent problem to be solved. In order to solve this problem more effectively, this paper proposes a text reconstruction method for college English textbooks from the perspective of language images. First, this paper proposes a text reconstruction network model for college English textbooks, which includes two self-network models, namely, a text feature extraction network and an image feature extraction network. Second, text designs an English text feature reconstruction network to fuse image features and text features to guide the generation of new English texts according to the generated emotions. Finally, through a large number of experiments, it is proved that the text reconstruction method of college English textbooks from the perspective of language images can effectively generate new texts of college English textbooks, enhance the emotional color of college textbooks, and improve the effect of English learning. [ABSTRACT FROM AUTHOR]

Many steel mills currently rely on thermal spray codes to carry and convey information about the steel plate at different stages of production. Thermal inkjet codes are patterns of numbers, letters, and symbols formed by continuous spraying of high-temperature resistant coatings on the surface of billets, so it is especially important to identify thermal inkjet code information accurately and timely during the processing stage of steel plates. Most of the existing mainstream identification methods rely on manual visual observation and traditional image recognition to obtain them, with low recognition efficiency and poor recognition effect. In this paper, a lightweight YOLO with ResNet18 as the backbone network is used as the detection and recognition framework, and deformable convolution and text feature extraction techniques are purposefully added to detect the location of thermal inkjet codes images to achieve accurate and fast positioning and segmentation of thermal spray codes. Meanwhile, an attention mechanism-based character recognition module is added to quickly infer the content within the ROI location of thermal inkjet codes. The experimental results show that the thermal inkjet code character recognition method proposed in this paper has a high recognition rate and fast recognition speed, which meets the practical application requirements of relevant enterprises. [ABSTRACT FROM AUTHOR]

In order to improve the effect of e-sports training, this paper combines the intelligent gesture recognition technology to construct an e-sports training system and judges the training effect of players through the recognition of players' gestures. Moreover, this paper studies the commonly used feature extraction algorithms and proposes an improved SLC-Harris feature extraction algorithm, and the feasibility of this algorithm is verified by the experimental results on the EUROC data set. In addition, this paper uses the KLT optical flow algorithm to track the extracted feature points and calculates the pure visual pose through epipolar geometry, triangulation, and PnP algorithms. The experimental research results show that the electronic economic training system based on intelligent gesture recognition proposed in this paper has certain effects. [ABSTRACT FROM AUTHOR]

Aiming at the problem of insufficient details of retinal blood vessel segmentation in current research methods, this paper proposes a multiscale feature fusion residual network based on dual attention. Specifically, a feature fusion residual module with adaptive calibration weight features is designed, which avoids gradient dispersion and network degradation while effectively extracting image details. The SA module and ECA module are used many times in the backbone feature extraction network to adaptively select the focus position to generate more discriminative feature representations; at the same time, the information of different levels of the network is fused, and long-range and short-range features are used. This method aggregates low-level and high-level feature information, which effectively improves the segmentation performance. The experimental results show that the method in this paper achieves the classification accuracy of 0.9795 and 0.9785 on the STARE and DRIVE datasets, respectively, and the classification performance is better than the current mainstream methods. [ABSTRACT FROM AUTHOR]

Landslides in nature are harmful to economic development and people's lives and cause irreparable losses to the environment. With the application of image detection technology and intelligent algorithm, a new way for landslide detection is proposed to achieve effective detection and identification of hazards. This paper takes the landslide as the data set, carries on the noise reduction, the image expansion, and the image segmentation processing to the image, and extracts the object region information. The quantitative description of the azimuth displacement and displacement change of the crack curve is completed in this paper. This method is suitable for 3D simulation model, sand and stone model, soil model, and the sliding test results of Panzhihua Flight Field, which proves that the design method is effective. Experiments show that when sliding occurs, the texture and color become chaotic, the usual mountain becomes more in the regular state, and the extraction of features is very different. The method has better recognition effect for the hillside covered with vegetation, the recognition time is short, and the recognition rate can reach 90%. [ABSTRACT FROM AUTHOR]

The cultural tourism industry combines the similarities of the cultural industry and tourism industry, which can be the most effective way to meet people's spiritual and cultural needs as well as their leisure needs simultaneously, and has a vast development potential. However, there are numerous and dispersed areas where the market value of cultural tourism resources is clustered, and frequently, each city has the clustering area with the highest market value concentration of cultural tourism resources. This feature of the spatial distribution of the market value of cultural tourism resources is significant for promoting the development of cultural tourism as a whole and constructing the industry's overall structure. It has broad application potential for extracting and differentiating cultural tourism industry characteristics. Texture feature extraction is typically performed using dual-tree complex wavelet transform (DT-CWT) and Gabor wavelet. In this paper, we propose a multiscale DT-CWT and Gabor-based method for identifying the cultural tourism industry. The method first decomposes the images of cultural tourism into multiscale space using a Gaussian pyramid, then extracts the multiscale features of the images using DT-CWT and Gabor, and lastly achieves feature fusion. Using a support vector machine (SVM) classifier to achieve classification, the effectiveness of the feature extraction method is determined. The experimental findings demonstrate that the method proposed in this paper can achieve a high rate of recognition. [ABSTRACT FROM AUTHOR]