External Feature Research Articles

A Deep Multi-Task Learning Model for OD Traffic Flow Prediction Between Highway Stations

The rapid development of highways greatly affects the flow of people, finance, goods, and information between cities, and monitoring the OD flow of travel has become a very important task for intelligent transportation systems (ITS). The temporal dynamics and complex spatial correlations of OD traffic distribution, as well as the sparsity and incompleteness of data caused by uneven traffic distribution, make OD traffic prediction complex and challenging. This paper proposes a multi-task prediction model for OD traffic between highway stations. The model adopts a hard parameter shared multi-task learning network structure, which is divided into sub-task learning inflow trend modules, sub-task learning outflow trend modules, and main task learning modules for OD traffic. At the same time, the attraction intensity matrix between stations is constructed using the population density data as the external feature of the sub-task module for outlet outflow flow, and stronger constraints between tasks are introduced to achieve better fitting results. Finally, an OD flow prediction case experiment was conducted between stations on highways in Sichuan Province. The experimental results showed that the proposed model not only had higher accuracy in predicting results than other baseline models, but also had better effectiveness and robustness.

Smile or Not Smile: The Effect of Virtual Influencers' Emotional Expression on Brand Authenticity, Purchase Intention and Follow Intention

ABSTRACTVirtual influencer (VI) has become a new tool for brand promotion. The existing researches mainly focus on VI's external feature cues, such as identity, appearance, and sensory factors. In addition to carefully curated images, VI can also display emotions like a human influencer. Emotional expression as a non‐verbal social cue, is a key factor influencing consumers. This research focuses on VI's emotional cues and their impact on consumers' behavioral intentions. Based on emotional contagion theory (ECT) and elaboration likelihood model (ELM), this paper discusses the emotional contagion effect of VI emotional display (smiling vs. non‐smiling) and its matching effect with brand stereotypes. The results of three online experiments (N = 691) show that: firstly, VI's smiling emotion has a stronger primitive emotional contagion. Secondly, VI emotional expression has a positive impact on brand authenticity, purchase intention, and follow intention through affective empathy and cognitive empathy. Finally, this study found that VI's smile does not always produce a more positive effect than not smiling. In advertising situations that highlight brand competence, VI without a smile is more persuasive. Our results provide a new explanation mechanism for the influence of VI emotional expression on consumers' behavioral intention and provide a new perspective and advertising strategy for VI marketing practice.

Long–Short Observation-driven Prediction Network for pedestrian crossing intention prediction with momentary observation

Pedestrian crossing intention prediction aims to predict whether the pedestrian will cross the road, which is crucial for the decision-making of intelligent vehicles and ensuring traffic safety. Existing methods just rely on long-term observation and rarely consider it challenging to obtain sufficiently long and precise observation in real-world scenarios. Focus on momentary observation, which only contains two frames of the preceding and current time, we propose a novel Long–Short Observation-driven Prediction Network (LSOP-Net). LSOP-Net comprises two critical components, the Momentary Observation feature Extraction Module (MOE-Module) and the Multimodal Long–Short-term feature Fusion Module (MLSFusion). Utilizing a hybrid training strategy and an external long-term feature pool, the MOE-Module is proposed to extract features with long-term patterns from momentary observations, which effectively mitigates feature deficiency arising from momentary observations. Based on a feature selection fusion mechanism, the MLSFusion is proposed to explicitly model the importance relationship between various modalities’ long–short-term features and the output, which adaptively fuses the long–short-term features from various modalities. Experimental results on the JAAD and PIE datasets demonstrate that our approach achieves superior performance in pedestrian crossing intention prediction with momentary observation.

Population Distribution Forecasting Based on the Fusion of Spatiotemporal Basic and External Features: A Case Study of Lujiazui Financial District

Predicting the distribution of people in the time window approaching a disaster is crucial for post-disaster assistance activities and can be useful for evacuation route selection and shelter planning. However, two major limitations have not yet been addressed: (1) Most spatiotemporal prediction models incorporate spatiotemporal features either directly or indirectly, which results in high information redundancy in the parameters of the prediction model and low computational efficiency. (2) These models usually incorporate certain basic and external features, and they can neither change spatiotemporal addressed features according to spatiotemporal features nor change them in real-time according to spatiotemporal features. The spatiotemporal feature embedding methods for these models are inflexible and difficult to interpret. To overcome these problems, a lightweight population density distribution prediction framework that considers both basic and external spatiotemporal features is proposed. In the study, an autoencoder is used to extract spatiotemporal coded information to form a spatiotemporal attention mechanism, and basic and external spatiotemporal feature attention is fused by a fusion framework with learnable weights. The fused spatiotemporal attention is fused with Resnet as the prediction backbone network to predict the people distribution. Comparison and ablation experimental results show that the computational efficiency and interpretability of the prediction framework are improved by maximizing the scalability of the spatiotemporal features of the model by unleashing the scalability of the spatiotemporal features of the model while enhancing the interpretability of the spatiotemporal information as compared to the classical and popular spatiotemporal prediction frameworks. This study has a multiplier effect and provides a reference solution for predicting population distributions in similar regions around the globe.

Pattern of Drowning among Autopsies Conducted at Baroda Medical College and S.S.G Hospital

Drowning kills at least 3,72,000 people every year and is the 3rd leading cause of unintentional deaths. In addition to the human tragedy, drowning represents a huge economic problem with direct and indirect costs, including many Disability-Adjusted Life Years. In India, there is limited knowledge about the epidemiology of drowning.The objective of the study was to study the incidence, manner and epidemiology of deaths due to drowning in and around Vadodara region.The present study was conducted from May 2022 to April 2023 in Government Medical College, Baroda on 82 cases to study the various epidemiological parameters of drowning. In this study period, 1989 cases of post-mortem examination were done out of which 82 cases were of drowning deaths. A maximum number of cases were seen in the age group of 21–30 years with 43% cases of males, dominating the study population. 62% of deaths were accidental in nature and occurred during the rainy season. The most common place of occurrence of drowning was river (38%) followed by water canal (31%). Soddening of hands and feet was the most common external feature of drowning followed by the presence of froth at mouth and nostril. Drowning is a most ignored public hazard worldwide with serious implications for the society. Public awareness regarding safety measures and drowning prevention strategies suitable to the needs of geographical region should be adapted.

Short-Term Prediction of Origin–Destination Passenger Flow in Urban Rail Transit Systems with Multi-Source Data: A Deep Learning Method Fusing High-Dimensional Features

Short-term origin–destination (OD) passenger flow forecasting is crucial for urban rail transit enterprises aiming to optimise transportation products and increase operating income. As there are large-scale OD pairs in an urban rail transit system, OD passenger flow cannot be obtained in real time (temporal hysteresis). Additionally, the distribution characteristics are also complex. Previous studies mainly focus on passenger flow prediction at metro stations, while few methods solve the OD passenger flow prediction problems of an urban rail transit system. In view of this, we propose a novel deep learning method fusing high-dimensional features (HDF-DL) with multi-source data. The HDF-DL method is combined with three modules. The temporal module incorporates the time-varying, trend, and cyclic characteristics of OD passenger flow, while the latest OD passenger flow time sequence (within 1 h) is excluded from the time-varying characteristics. In the spatial module, the K-means and K-shape algorithms are used to classify OD pairs from multiple perspectives and capture the spatial features, reducing the difficulty of OD passenger flow predictions with large-scale and complex characteristics. Weather factors are considered in the external feature module. The HDF-DL method is tested on a large-scale metro system in China, in which eight baseline models are designed. The results show that the HDF-DL method achieves high prediction accuracy across multiple time granularities, with a mean absolute percentage error of about 10%. OD passenger flow in every departure time interval can be predicted with high and stable accuracy, effectively capturing temporal characteristics. The modular design of HDF-DL, which fuses high-dimensional features and employs appropriate neural networks for different data types, significantly reduces prediction errors and outperforms baseline models.

Variable‐weight combined forecasting model with causal analysis and clustering for refined oil sales forecasting

AbstractForecasting refined oil sales is essential in energy supply chain management. However, accurate forecasting is limited by several factors, including multiple influences of external features, heterogeneity of different gasoline stations, and difficulty in balancing linear and nonlinear forecasting. To address these issues, we propose a novel variable‐weight combined forecasting model. In the first stage, the model incorporates causal analysis and clustering methods to provide a quantitative description of multiple effects of external features and highly correlated aggregation of homogeneous data. Subsequently, based on the patterns of external feature influences learned from historical data, variable‐weight combined forecasting is realized to balance linear and nonlinear forecasting dynamically. Experiments based on real sales data procured from several regions demonstrate that the proposed model outperforms other benchmark and widely used models in terms of forecasting accuracy and statistical significance. The ablation experimental results confirm the significance of causal analysis, clustering, and variable‐weight combined forecasting in improving the balance between linear and nonlinear forecasting. Moreover, our results indicate that improving the quality of clustering can yield greater benefits than improving the amount of training data. Finally, we also explore whether the forecasting superiority translates into better inventory control, and our results show that the proposed optimization model can effectively balance inventory cost and service level, while also better suppress the bullwhip effect.

HGEE: Learning for Trajectory Prediction with Heterogeneous Graph Interaction and External Embedding of Unmanned Swarm Systems in Adversarial Environment

Trajectory prediction of unmanned swarm systems, serving as the foundation for behavioral and intentional cognition, has attracted extensive attention and made considerable progress in adversarial research. The influence of heterogeneous interaction relationships and external factors is crucial for trajectory prediction. Consequently, this paper proposes the Heterogeneous Graph with External Embedding (HGEE) network. We model the latent variables as multi-layer heterogeneous graphs based on prior knowledge of different interaction relationships and propose a method for calculating edge embeddings for heterogeneous graphs. Furthermore, we introduce a method that combines external environmental feature with historical observational trajectory data as the input for the decoder, enabling the model to learn the impacts of obstacles, targets, and desired formations on trajectories. We demonstrate that our approach surpasses state-of-the-art models in interaction inference and trajectory prediction through experiments on our proposed formation datasets based on consensus theory, across five evaluation metrics.

Mobile traffic prediction with attention-based hybrid deep learning

Mobile data consumption is ever-increasing due to the continuous emergence of bandwidth-hungry mobile applications as well as the drastic increase in number of mobile terminals resulted from the pervasive adoption of Internet of Things. In the 5G+ era, network operators have to deal with new technical challenges on network management, resource optimization and mobility scheduling, which require the ability to perform efficient mobile traffic prediction. Traditional prediction methods using convex optimization, Markov model and linear equations cannot describe the various nonlinearity changes of network traffic. In this paper, we propose a novel traffic prediction algorithm for mobile networks by introducing a hybrid deep learning method equipped with the attention mechanism, which analyzes the traffic in cellular zones to determine the spatiotemporal characteristics in the residential community. The hybrid deep learning model includes autoregressive integrated moving average mode (ARIMA) preprocessing with decomposition ability for time series, external spatial feature variables, sequence-to-sequence (seq2seq; attention-based CNN-LSTM) pretraining and extreme gradient boosting (XGBoost) optimization processing for integrating nonlinear relationships. The CNN method shows good nonlinear generalization ability to mine deep features of community traffic and capture the nonlinear trend. Our proposed approach first decomposes the community traffic data into linear and residual parts through ARIMA and then seizes the deep features of community traffic through the constructed pretraining seq2seq framework. Finally, the pretraining outcomes are further adjusted by the XGBoost method. Simulation results show that the proposed solution improves the accuracy of prediction apparently.

Cytological, Phytohormone, and Transcriptome Analyses Provide Insights into Persimmon Fruit Shape Formation (Diospyros kaki Thunb.).

Fruit shape is an important external feature when consumers choose their preferred fruit varieties. Studying persimmon (Diospyros kaki Thunb.) fruit shape is beneficial to increasing its commodity value. However, research on persimmon fruit shape is still in the initial stage. In this study, the mechanism of fruit shape formation was studied by cytological observations, phytohormone assays, and transcriptome analysis using the long fruit and flat fruit produced by 'Yaoxianwuhua' hermaphroditic flowers. The results showed that stage 2-3 (June 11-June 25) was the critical period for persimmon fruit shape formation. Persimmon fruit shape is determined by cell number in the transverse direction and cell length in the longitudinal direction. High IAA, GA4, ZT, and BR levels may promote long fruit formation by promoting cell elongation in the longitudinal direction, and high GA3 and ABA levels may be more conducive to flat fruit formation by increasing the cell number in the transverse direction and inhibiting cell elongation in the longitudinal direction, respectively. Thirty-two DEGs related to phytohormone biosynthesis and signaling pathways and nine DEGs related to cell division and cell expansion may be involved in the persimmon fruit shape formation process. These results provide valuable information for regulatory mechanism research on persimmon fruit formation.

The Extraction of Roof Feature Lines of Traditional Chinese Village Buildings Based on UAV Dense Matching Point Clouds

Traditional Chinese buildings serve as a carrier for the inheritance of traditional culture and national characteristics. In the context of rural revitalization, achieving the 3D reconstruction of traditional village buildings is a crucial technical approach to promoting rural planning, improving living environments, and establishing digital villages. However, traditional algorithms primarily target urban buildings, exhibiting limited adaptability and less ideal feature extraction performance for traditional residential buildings. As a result, guaranteeing the accuracy and reliability of 3D models for different types of traditional buildings remains challenging. In this paper, taking Jingping Village in Western Hunan as an example, we propose a method that combines multiple algorithms based on the slope segmentation of the roof to extract feature lines. Firstly, the VDVI and CSF algorithms are used to extract the building and roof point clouds based on the MVS point cloud. Secondly, according to roof features, village buildings are classified, and a 3D roof point cloud is projected into 2D regular grid data. Finally, the roof slope is segmented via slope direction, and internal and external feature lines are obtained after refinement through Canny edge detection and Hough straight line detection. The results indicate that the CSF algorithm can effectively extract the roofs of I-shaped, L-shaped, and U-shaped traditional buildings. The accuracy of roof surface segmentation based on slope exceeds 99.6%, which is significantly better than the RANSAC algorithm and the region segmentation algorithm. This method is capable of efficiently extracting the characteristic lines of roofs in low-rise buildings within traditional villages. It provides a reference method for achieving the high-precision modeling of traditional village architecture at a low cost and with high efficiency.

Multi-channel high-order network representation learning research.

The existing network representation learning algorithms mainly model the relationship between network nodes based on the structural features of the network, or use text features, hierarchical features and other external attributes to realize the network joint representation learning. Capturing global features of the network allows the obtained node vectors to retain more comprehensive feature information during training, thereby enhancing the quality of embeddings. In order to preserve the global structural features of the network in the training results, we employed a multi-channel learning approach to perform high-order feature modeling on the network. We proposed a novel algorithm for multi-channel high-order network representation learning, referred to as the Multi-Channel High-Order Network Representation (MHNR) algorithm. This algorithm initially constructs high-order network features from the original network structure, thereby transforming the single-channel network representation learning process into a multi-channel high-order network representation learning process. Then, for each single-channel network representation learning process, the novel graph assimilation mechanism is introduced in the algorithm, so as to realize the high-order network structure modeling mechanism in the single-channel network representation learning. Finally, the algorithm integrates the multi-channel and single-channel mechanism of high-order network structure joint modeling, realizing the efficient use of network structure features and sufficient modeling. Experimental results show that the node classification performance of the proposed MHNR algorithm reaches a good order on Citeseer, Cora, and DBLP data, and its node classification performance is better than that of the comparison algorithm used in this paper. In addition, when the vector length is optimized, the average classification accuracy of nodes of the proposed algorithm is up to 12.24% higher than that of the DeepWalk algorithm. Therefore, the node classification performance of the proposed algorithm can reach the current optimal order only based on the structural features of the network under the condition of no external feature supplementary modeling.

Трансформация признаков документа в электронной среде

The article deals with one of the main theoretical problems of document science related to the definition of document features. This problem is also of applied importance, since when formulating the definition of the concept of «document», it usually reflects its properties and features. In the context of the revision of the national terminological standard GOST R 7.0.8 – 2013. «Record keeping and archival business. Terms and definitions» it is advisable to turn once again to the question of the features of the document for their correct reflection in the concept of the term «document». The urgency of the problem is also due to the fact that these signs should be universal for both paper and electronic documents. In document science, the material carrier of the document and its form are traditionally considered as features of the document. As for the material carrier of the document, its use as a feature of the document was due to the need for physical isolation of the recorded information for the purpose of subsequent processing, transmission and storage. The material carrier acted primarily as an object that allows you to select a document from among others, and ensures its integrity. With the advent of electronic documents, this condition has ceased to be observed. Electronic media, which is generally understood as a technical device. Moreover, the features of recording information on this type of media allow you to transmit information without transferring the media, so the electronic media is fundamentally different. In this regard, it is not advisable to use it to identify a specific document as an object in an electronic environment. In this connection, the feature of the document "material carrier" in the electronic environment ceases to be essential, one of the main external features of the document. At the same time, its second external feature is preserved – a form that ensures the integrity of the document within the framework of its use in the interaction of subjects of public relations. However, it also undergoes some transformation, since in the electronic environment it ceases to reflect information about the management process, some of the document details are contained as information in the information system. These changes related to the features of the document in the electronic environment force us to turn to the search for new features, as well as to revise from a scientific point of view the definition of the concept of «document», which would reflect the common essential characteristics of the traditional document and the document in the electronic environment, primarily related to the social functions that the document performs in society.

A ranking-based multi-scale feature calibration network for nuclear cataract grading in AS-OCT images

Anterior Segment Optical Coherence Tomography (AS-OCT) is an important imaging technique for the grading of nuclear cataract. However, due to the complex interdependencies among 6 clinically-defined levels of cataract severity, it presents significant challenges to classify neighboring severity levels accurately and expeditiously, whether by human experts or computer-aided approaches. Existing deep learning-based models usually obtain 3 grades of nuclear cataract severity only, and often struggle to capture vital information related to the progression of neighboring severity levels, leading to inaccuracies in grading. In this paper, we introduce a novel method called Ranking-MFCNet, which utilizes both a ranking-based framework and a Multi-scale Feature Calibration network (MFCNet). To bolster the model’s capability for discriminating between neighboring severities that are prone to confusion, we treat the multi-category severity classification as a collection of distinct binary classification patterns. This strategy facilitates a systematic implementation of fine-grained nuclear cataract severity grading on an individual basis. Within each binary classification pattern, we propose an external attention-augmented Multi-scale Feature Calibration (eaMFC) module, which effectively captures the multi-scale characteristics inherent to the lens nucleus. Additionally, eaMFC allows for the calibration of shared attributes extracted by the external attention layer, thereby enhancing the model’s proficiency in modeling the distinctive traits related to opacity and sclerosis of the lens nucleus. We trained and validated our model on a dataset that contains 1608 AS-OCT images, and the extensive experiments have verified the effectiveness and superiority of our method over state-of-the-art cataract grading methods.

Research on the vision system of lychee picking robot based on stereo vision

In this study, we propose a development scheme of litchi robot vision system based on stereo vision. The system includes three components: image acquisition, image analysis, and image processing. The obtained image can be corrected according to the light environment conditions with the corresponding algorithm for image color, calculate the Hue color layer, analyze the external characteristics and positional data (2D) of litchi, obtain the 3D coordinate information of fruits and vegetables, and provide to the running device for route planning and vegetable and fruit picking claw tools for picking. The integration test results for the robot arm and claw tool demonstrate the following: (1) Using image acquisition, the system can acquire high-quality images in real-time via a combination of automatic exposure and white balance conversion. (2) Using image analysis techniques such as background separation, edge detection, and external feature search, it is possible to successfully calculate the location coordinates of the litchi's tip, center, and bottom. (3) Using image processing, the claw of the picking machine can determine the condition of overlapping lychees and their state of ripening based on the depth information of feature points used in the picking operation. (4) Under the working range of 18.4 cm × 33.6 cm, the success rate of picking litchi with a diameter of 28 mm, 34 mm, and 42 mm was 93.3%, 91.1 %, and 84.4%, respectively, exceeding the design expectation level.

An enhanced interval-valued decomposition integration model for stock price prediction based on comprehensive feature extraction and optimized deep learning

For the purpose of managing financial risk and making investment decisions, interval stock price forecasting is essential. Currently, decomposition integration frameworks are widely used in point-valued stock price forecasting studies, mainly focusing on mining internal information. However, point forecasts are difficult to adequately capture price uncertainty and may suffer from loss of volatile information. Therefore, this paper proposes an enhanced interval-valued decomposition integration model for stock price prediction based on comprehensive feature extraction and optimized deep learning. Firstly, the interval variational modal decomposition with feedback mechanism (FIVMD) is proposed to extract internal features and can decompose interval values into interval trend and residual. FIVMD not only solves the interval decomposition challenge, but also helps to improve the internal feature extraction capability. Secondly, while considering the influencing factors more comprehensively, appropriate feature selection and compression techniques can effectively achieve external feature extraction, obtain the best influencing factors, and improve the modeling capability of high-dimensional data. Finally, the final prediction results are obtained by modeling the interval trend and residuals separately through the optimization algorithm and deep learning model to improve the prediction accuracy. The results of the empirical analysis reveal that the proposed interval decomposition integrated model has the smallest of the three evaluation metrics, where the values of interval mean average percentage errors (IMAPE) are 1.8188%, 1.1244%, 1.9001%, and 2.1542% respectively. This shows that the model is significantly more accurate and stable than the other comparative models, and it is a successful model for predicting interval-valued stock prices.

Extraction of Roof Feature Lines Based on Geometric Constraints from Airborne LiDAR Data

Airborne LiDAR (Light Detection and Ranging) is an active Earth observing system, which can directly acquire high-accuracy and dense building roof data. Thus, airborne LiDAR has become one of the mainstream source data for building detection and reconstruction. The emphasis for building reconstruction focuses on the accurate extraction of feature lines. Building roof feature lines generally include the internal and external feature lines. Efficient extraction of these feature lines can provide reliable and accurate information for constructing three-dimensional building models. Most related algorithms adopt intersecting the extracted planes fitted by the corresponding points. However, in these methods, the accuracy of feature lines mostly depends on the results of plane extraction. With the development of airborne LiDAR hardware, the point density is enough for accurate extraction of roof feature lines. Thus, after acquiring the results of building detection, this paper proposed a feature lines extraction strategy based on the geometric characteristics of the original airborne LiDAR data, tracking roof outlines, normal ridge lines, oblique ridge lines and valley lines successively. The final refined feature lines can be obtained by normalization. The experimental results showed that our methods can achieve several promising and reliable results with an accuracy of 0.291 m in the X direction, 0.295 m in the Y direction and 0.091 m in the H direction for outlines extraction. Further, the internal feature lines can be extracted with reliable visual effects using our method.

Metro Station functional clustering and dual-view recurrent graph convolutional network for metro passenger flow prediction

The metro system is indispensable for alleviating traffic congestion in the urban transportation system. Precise metro passenger flow (MPF) prediction is crucial in ensuring smooth operations of the metro system. Recently, the graph convolutional network (GCN), which is effective in the spatial feature extraction, has been applied in traffic prediction. However, most existing GCN-based methods construct the empirical graphs based on distance and adjacency, which cannot fully express the correlations of metro stations. This paper proposes a novel MPF prediction method consisting of three parts: K-means-based metro station functional clustering (KMSFC), external feature fusion, and dual-view recurrent GCN (DVRGCN). The KMSFC identifies the metro stations both having similar MPF changing tendencies and being located in similar urban functional areas. Furthermore, the DVRGCN is designed to simultaneously capture the spatiotemporal and external features. The dual-view GCN module in the DVRGCN captures both explicit and implicit spatial features of the metro traffic network. To demonstrate the capability for making accurate MPF predictions, the experiments using a real-world metro traffic dataset are conducted. The ablation experiments are also performed to prove the contribution of each module in the proposed method. The experimental results show that the proposed method outperforms other state-of-the-art traffic prediction methods.

Theoretical analysis and model manufacturing of innovative mortise and tenon hollow spherical joint

One of the main challenges for free-form surface reticulated shell structure recently is the development of a new joint that is able to implement complex-shaped curvature and fulfill the required loading capacity, whilst also meeting various important requirements such as convenient on-site assembly and suitability for connecting members with various cross-sectional forms. This article draws inspiration from the construction idea of Chinese traditional mortise and tenon structure and proposes a new type of mortise and tenon hollow spherical joint. To investigate the joint’s mechanical performance, the detailed numerical models of 29 mortise and tenon hollow spherical joints with different size parameters are established by SolidWorks and Ansys, and the effects of the hollow spherical wall thickness, tooth width, tooth spacing, tooth height and tenon face width on the joint bearing performance are analyzed. The joint failure modes under bending limit states are discussed, and the calculation formulas for the initial and elastic-plastic stage rotational stiffness are derived. The results show that the joint initial rotational stiffness is increased by 34.45%, 4.69%, 4.29%, and 3.25%, respectively, after the parameter optimization analysis of the hollow spherical wall thickness, tooth width, tooth spacing and tenon face width. The mortise and tenon hollow spherical joint has good mechanical performance, and possesses the advantages of simple and beautiful appearance, fast construction speed and high positioning accuracy. Finally, a reduced-scale model of the mortise and tenon hollow spherical joint is manufactured using 3D printing technology to visually showcase its external feature and validate its assembly characteristic.

Pose-guided self and external attention feature matching and aggregation network for person re-identification

Traditional methods that use pose information for person re-identification (ReID) often focus only on relationships between different parts of the same sample and ignore the correlation between poses of different samples, which hinders further improvement in recognition accuracy. In view of this, this paper proposes a pose-guided self and external attention feature matching and aggregation net which contains a visual context self and external attention module and a pose-guided feature matching and aggregation module. It can divide global features into local features without strict spatial feature alignment, and enables the model to focus on pose correlation between different samples. Thus, it not only learns pose-related identity identification features, but also avoids interference from the samples with large pose changes. The visual context self and external attention module realizes feature embedding through a transformer-based image classification model ViT and a human pose estimation model. Also, it extracts encoder features and local features containing rich pose information by adding an external attention. The pose-guided feature matching and aggregation module obtains a learnable part semantic view through a transformer decoder and pose heat maps. Then, it matches and aggregates with local features, adaptively learns pose-related features, and enhances the robustness of the model to background and occlusion. In this paper, experiments are conducted based on three data sets, including Market-1501, DukeMTMC-reID and MSMT17. The Rank-1 values are 95.3%, 90.1%, and 82.5%, respectively, and the mAP values are 88.3%, 81.1%, and 64.1%, respectively. In conclusion, our method introduces an external attention into the ReID task, and the ReID model can obtain more accurate results by extracting pose-related identity identification features and avoiding interference from samples with large pose changes.