Multiview Learning With Robust Double-Sided Twin SVM

Multi-view learning with enhanced multi-weight vector projection support vector machine

Multi-view learning aims on learning from the data represented by multiple distinct feature sets. Various multi-view support vector machine methods have been successfully applied to classification tasks. However, the existed methods often face the problems of long processing time or weak generalization on some complex datasets. In this paper, two multi-view enhanced multi-weight vector projection support vector machine models are proposed. One is a ratio form of multi-view enhanced multi-weight vector projection support vector machine (R-MvEMV), while the other is a difference form (D-MvEMV). Instead of searching for specific classification hyperplanes, each proposed model tries to generate two projection matrices composed of a set of projection vectors for each view. A co-regularization term is added to maximize the consistency of different views. R-MvEMV and D-MvEMV can be simplified to two generalized eigenvalue problems and two eigenvalue problems, respectively. The optimal weight vector projections are the eigenvectors corresponding to the smallest eigenvalues. Some numerical tests are conducted to compare the proposed methods with the other state-of-art multi-view support vector machine methods. The numerical results show the better classification performance and higher efficiency of the proposed methods.

Convergence Analysis on Trace Ratio Linear Discriminant Analysis Algorithms

Linear discriminant analysis (LDA) may yield an inexact solution by transforming a trace ratio problem into a corresponding ratio trace problem. Most recently, optimal dimensionality LDA (ODLDA) and trace ratio LDA (TRLDA) have been developed to overcome this problem. As one of the greatest contributions, the two methods design efficient iterative algorithms to derive an optimal solution. However, the theoretical evidence for the convergence of these algorithms has not yet been provided, which renders the theory of ODLDA and TRLDA incomplete. In this correspondence, we present some rigorously theoretical insight into the convergence of the iterative algorithms. To be specific, we first demonstrate the existence of lower bounds for the objective functions in both ODLDA and TRLDA, and then establish proofs that the objective functions are monotonically decreasing under the iterative frameworks. Based on the findings, we disclose the convergence of the iterative algorithms finally.

Partial Multiview Representation Learning With Cross-View Generation

Multiview learning has made significant progress in recent years. However, an implicit assumption is that multiview data are complete, which is often contrary to practical applications. Due to human or data acquisition equipment errors, what we actually get is partial multiview data, which existing multiview algorithms are limited to processing. Modeling complex dependencies between views in terms of consistency and complementarity remains challenging, especially in partial multiview data scenarios. To address the above issues, this article proposes a deep Gaussian cross-view generation model (named PMvCG), which aims to model views according to the principles of consistency and complementarity and eventually learn the comprehensive representation of partial multiview data. PMvCG can discover cross-view associations by learning view-sharing and view-specific features of different views in the representation space. The missing views can be reconstructed and are applied in turn to further optimize the model. The estimated uncertainty in the model is also considered and integrated into the representation to improve the performance. We design a variational inference and iterative optimization algorithm to solve PMvCG effectively. We conduct comprehensive experiments on multiple real-world datasets to validate the performance of PMvCG. We compare the PMvCG with various methods by applying the learned representation to clustering and classification. We also provide more insightful analysis to explore the PMvCG, such as convergence analysis, parameter sensitivity analysis, and the effect of uncertainty in the representation. The experimental results indicate that PMvCG obtains promising results and surpasses other comparative methods under different experimental settings.

Multiview learning with twin parametric margin SVM

Multiview learning (MVL) seeks to leverage the benefits of diverse perspectives to complement each other, effectively extracting and utilizing the latent information within the dataset. Several twin support vector machine-based MVL (MvTSVM) models have been introduced and demonstrated outstanding performance in various learning tasks. However, MvTSVM-based models face significant challenges in the form of computational complexity due to four matrix inversions, the need to reformulate optimization problems in order to employ kernel-generated surfaces for handling non-linear cases, and the constraint of uniform noise assumption in the training data. Particularly in cases where the data possesses a heteroscedastic error structure, these challenges become even more pronounced. In view of the aforementioned challenges, we propose multiview twin parametric margin support vector machine (MvTPMSVM). MvTPMSVM constructs parametric margin hyperplanes corresponding to both classes, aiming to regulate and manage the impact of the heteroscedastic noise structure existing within the data. The proposed MvTPMSVM model avoids the explicit computation of matrix inversions in the dual formulation, leading to enhanced computational efficiency. We perform an extensive assessment of the MvTPMSVM model using benchmark datasets such as UCI, KEEL, synthetic, and Animals with Attributes (AwA). Our experimental results, coupled with rigorous statistical analyses, confirm the superior generalization capabilities of the proposed MvTPMSVM model compared to the baseline models. The source code of the proposed MvTPMSVM model is available at https://github.com/mtanveer1/MvTPMSVM.

A Joint Network of Edge-Aware and Spectral-Spatial Feature Learning for Hyperspectral Image Classification

Hyperspectral image (HSI) classification is a vital part of the HSI application field. Since HSIs contain rich spectral information, it is a major challenge to effectively extract deep representation features. In existing methods, although edge data augmentation is used to strengthen the edge representation, a large amount of high-frequency noise is also introduced at the edges. In addition, the importance of different spectra for classification decisions has not been emphasized. Responding to the above challenges, we propose an edge-aware and spectral-spatial feature learning network (ESSN). ESSN contains an edge feature augment block and a spectral-spatial feature extraction block. Firstly, in the edge feature augment block, the edges of the image are sensed, and the edge features of different spectral bands are adaptively strengthened. Then, in the spectral-spatial feature extraction block, the weights of different spectra are adaptively adjusted, and more comprehensive depth representation features are extracted on this basis. Extensive experiments on three publicly available hyperspectral datasets have been conducted, and the experimental results indicate that the proposed method has higher accuracy and immunity to interference compared to state-of-the-art (SOTA) method.

Multimodal Image Classification by Multiview Latent Pattern Extraction, Selection, and Correlation

The large amount of data available in the modern big data era opens new opportunities to expand our knowledge by integrating information from heterogeneous sources. Multiview learning has recently achieved tremendous success in deriving complementary information from multiple data modalities. This article proposes a framework called multiview latent space projection (MVLSP) to integrate features extracted from multiple sources in a discriminative way to facilitate binary and multiclass classifications. Our approach is associated with three innovations. First, most existing multiview learning algorithms promote pairwise consistency between two views and do not have a natural extension to applications with more than two views. MVLSP finds optimum mappings from a common latent space to match the feature space in each of the views. As the matching is performed on a view-by-view basis, the framework can be readily extended to multiview applications. Second, feature selection in the common latent space can be readily achieved by adding a class view, which matches the latent space representations of training samples with their corresponding labels. Then, high-order view correlations are extracted by considering feature-label correlations. Third, a technique is proposed to optimize the integration of different latent patterns based on their correlations. The experimental results on the prostate image dataset demonstrate the effectiveness of the proposed method.

An enhanced machine learning approach for effective prediction of IgA nephropathy patients with severe proteinuria based on clinical data

IgA Nephropathy (IgAN) is a disease of the glomeruli that may eventually lead to chronic kidney disease or kidney failure. The signs and symptoms of IgAN nephropathy are usually not specific enough and are similar to those of other glomerular or inflammatory diseases. This makes a correct diagnosis more difficult. This study collected data from a sample of adult patients diagnosed with primary IgAN at the First Affiliated Hospital of Wenzhou Medical University, with proteinuria ≥1 g/d at the time of diagnosis. Based on these samples, we propose a machine learning framework based on weIghted meaN oF vectOrs (INFO). An enhanced COINFO algorithm is proposed by merging INFO, Cauchy Mutation (CM) and Oppositional-based Learning (OBL) strategies. At the same time, COINFO and Support Vector Machine (SVM) were integrated to construct the BCOINFO-SVM framework for IgAN diagnosis and prediction. Initially, the proposed enhanced COINFO is evaluated using the IEEE CEC2017 benchmark problems, with the outcomes demonstrating its efficient optimization capability and accuracy in convergence. Furthermore, the feature selection capability of the proposed method is verified on the public medical datasets. Finally, the auxiliary diagnostic experiment was carried out through IgAN real sample data. The results demonstrate that the proposed BCOINFO-SVM can screen out essential features such as High-Density Lipoprotein (HDL), Uric Acid (UA), Cardiovascular Disease (CVD), Hypertension and Diabetes. Simultaneously, the BCOINFO-SVM model achieves an accuracy of 98.56%, with sensitivity at 96.08% and specificity at 97.73%, making it a potential auxiliary diagnostic model for IgAN.

CESA-MCFormer: An Efficient Transformer Network for Hyperspectral Image Classification by Eliminating Redundant Information

Hyperspectral image (HSI) classification is a highly challenging task, particularly in fields like crop yield prediction and agricultural infrastructure detection. These applications often involve complex image types, such as soil, vegetation, water bodies, and urban structures, encompassing a variety of surface features. In HSI, the strong correlation between adjacent bands leads to redundancy in spectral information, while using image patches as the basic unit of classification causes redundancy in spatial information. To more effectively extract key information from this massive redundancy for classification, we innovatively proposed the CESA-MCFormer model, building upon the transformer architecture with the introduction of the Center Enhanced Spatial Attention (CESA) module and Morphological Convolution (MC). The CESA module combines hard coding and soft coding to provide the model with prior spatial information before the mixing of spatial features, introducing comprehensive spatial information. MC employs a series of learnable pooling operations, not only extracting key details in both spatial and spectral dimensions but also effectively merging this information. By integrating the CESA module and MC, the CESA-MCFormer model employs a "Selection-Extraction" feature processing strategy, enabling it to achieve precise classification with minimal samples, without relying on dimension reduction techniques such as PCA. To thoroughly evaluate our method, we conducted extensive experiments on the IP, UP, and Chikusei datasets, comparing our method with the latest advanced approaches. The experimental results demonstrate that the CESA-MCFormer achieved outstanding performance on all three test datasets, with Kappa coefficients of 96.38%, 98.24%, and 99.53%, respectively.

FPIRST: Fatigue Driving Recognition Method Based on Feature Parameter Images and a Residual Swin Transformer

Fatigue driving is a serious threat to road safety, which is why accurately identifying fatigue driving behavior and warning drivers in time are of great significance in improving traffic safety. However, accurately recognizing fatigue driving is still challenging due to large intra-class variations in facial expression, continuity of behaviors, and illumination conditions. A fatigue driving recognition method based on feature parameter images and a residual Swin Transformer is proposed in this paper. First, the face region is detected through spatial pyramid pooling and a multi-scale feature output module. Then, a multi-scale facial landmark detector is used to locate 23 key points on the face. The aspect ratios of the eyes and mouth are calculated based on the coordinates of these key points, and a feature parameter matrix for fatigue driving recognition is obtained. Finally, the feature parameter matrix is converted into an image, and the residual Swin Transformer network is presented to recognize fatigue driving. Experimental results on the HNUFD dataset show that the proposed method achieves an accuracy of 96.512%, thus outperforming state-of-the-art methods.

VaBTFER: An Effective Variant Binary Transformer for Facial Expression Recognition

Existing Transformer-based models have achieved impressive success in facial expression recognition (FER) by modeling the long-range relationships among facial muscle movements. However, the size of pure Transformer-based models tends to be in the million-parameter level, which poses a challenge for deploying these models. Moreover, the lack of inductive bias in Transformer usually leads to the difficulty of training from scratch on limited FER datasets. To address these problems, we propose an effective and lightweight variant Transformer for FER called VaTFER. In VaTFER, we firstly construct action unit (AU) tokens by utilizing action unit-based regions and their histogram of oriented gradient (HOG) features. Then, we present a novel spatial-channel feature relevance Transformer (SCFRT) module, which incorporates multilayer channel reduction self-attention (MLCRSA) and a dynamic learnable information extraction (DLIE) mechanism. MLCRSA is utilized to model long-range dependencies among all tokens and decrease the number of parameters. DLIE's goal is to alleviate the lack of inductive bias and improve the learning ability of the model. Furthermore, we use an excitation module to replace the vanilla multilayer perception (MLP) for accurate prediction. To further reduce computing and memory resources, we introduce a binary quantization mechanism, formulating a novel lightweight Transformer model called variant binary Transformer for FER (VaBTFER). We conduct extensive experiments on several commonly used facial expression datasets, and the results attest to the effectiveness of our methods.

Maximal Margin Support Vector Machine for Feature Representation and Classification

High-dimensional small sample size data, which may lead to singularity in computation, are becoming increasingly common in the field of pattern recognition. Moreover, it is still an open problem how to extract the most suitable low-dimensional features for the support vector machine (SVM) and simultaneously avoid singularity so as to enhance the SVM's performance. To address these problems, this article designs a novel framework that integrates the discriminative feature extraction and sparse feature selection into the support vector framework to make full use of the classifiers' characteristics to find the optimal/maximal classification margin. As such, the extracted low-dimensional features from high-dimensional data are more suitable for SVM to obtain good performance. Thus, a novel algorithm, called the maximal margin SVM (MSVM), is proposed to achieve this goal. An alternatively iterative learning strategy is adopted in MSVM to learn the optimal discriminative sparse subspace and the corresponding support vectors. The mechanism and the essence of the designed MSVM are revealed. The computational complexity and convergence are also analyzed and validated. Experimental results on some well-known databases (including breastmnist, pneumoniamnist, colon-cancer, etc.) show the great potential of MSVM against classical discriminant analysis methods and SVM-related methods, and the codes can be available on https://www.scholat.com/laizhihui.

Prediction of p53 mutation status in rectal cancer patients based on magnetic resonance imaging-based nomogram: a study of machine learning

BACKGROUND

The current study aimed to construct and validate a magnetic resonance imaging (MRI)-based radiomics nomogram to predict tumor protein p53 gene status in rectal cancer patients using machine learning.

METHODS

Clinical and imaging data from 300 rectal cancer patients who underwent radical resections were included in this study, and a total of 166 patients with p53 mutations according to pathology reports were included in these patients. These patients were allocated to the training (n = 210) or validation (n = 90) cohorts (7:3 ratio) according to the examination time. Using the training data set, the radiomic features of primary tumor lesions from T2-weighted images (T2WI) of each patient were analyzed by dimensionality reduction. Multivariate logistic regression was used to screen predictive features, which were combined with a radiomics model to construct a nomogram to predict p53 gene status. The accuracy and reliability of the nomograms were assessed in both training and validation data sets using receiver operating characteristic (ROC) curves.

RESULTS

Using the radiomics model with the training and validation cohorts, the diagnostic efficacies were 0.828 and 0.795, the sensitivities were 0.825 and 0.891, and the specificities were 0.722 and 0.659, respectively. Using the nomogram with the training and validation data sets, the diagnostic efficacies were 0.86 and 0.847, the sensitivities were 0.758 and 0.869, and the specificities were 0.833 and 0.75, respectively.

CONCLUSIONS

The radiomics nomogram based on machine learning was able to predict p53 gene status and facilitate preoperative molecular-based pathological diagnoses.

Open data: an innovative learning resource for postgraduates

Purpose

With the continuous development of the global COVID-19 epidemic, mobile learning has become one of the most significant learning approaches. The mobile learning resource is the basis of mobile learning; it may directly affect the effectiveness of mobile learning. However, the current learning resources cannot meet users' needs. This study aims to analyze the influencing factors of accepting open data as learning resources among users.

Design/methodology/approach

Based on the technology acceptance model (TAM) and the unified theory of acceptance and use of technology (UTAUT), this study proposed a comprehensive theoretical research model. Data were obtained from 398 postgraduates from several universities in central China. Confirmatory factor analysis was used to determine the reliability and validity of the measurement model. Data has been analyzed using SPSS and AMOS software.

Findings

The results suggested that perceived usefulness, performance expectancy, social influence and facilitating conditions have a positive influence on accepting open data as learning resources. Perceived ease of use was not found significant. Moreover, it was further shown in the study that behavioural intention significantly influenced the acceptance of open data as learning resources.

Originality/value

There is a lack of research on open data as learning resources in developing countries, especially in China. This study addresses the gap and helps us understand the acceptance of open data as learning resources in higher education. This study also pays attention to postgraduates' choice of learning resources, which has been little noticed before. Additionally, this study offers opportunities for further studies on the continuous usage of open data in higher education.

Adversarial Patch Attacks on Deep-Learning-Based Face Recognition Systems Using Generative Adversarial Networks

Deep learning technology has developed rapidly in recent years and has been successfully applied in many fields, including face recognition. Face recognition is used in many scenarios nowadays, including security control systems, access control management, health and safety management, employee attendance monitoring, automatic border control, and face scan payment. However, deep learning models are vulnerable to adversarial attacks conducted by perturbing probe images to generate adversarial examples, or using adversarial patches to generate well-designed perturbations in specific regions of the image. Most previous studies on adversarial attacks assume that the attacker hacks into the system and knows the architecture and parameters behind the deep learning model. In other words, the attacked model is a white box. However, this scenario is unrepresentative of most real-world adversarial attacks. Consequently, the present study assumes the face recognition system to be a black box, over which the attacker has no control. A Generative Adversarial Network method is proposed for generating adversarial patches to carry out dodging and impersonation attacks on the targeted face recognition system. The experimental results show that the proposed method yields a higher attack success rate than previous works.

Research on the brand image of iOS and Android smart phone operating systems based on mixed methods

Introduction

To analyze the differences in system functions, interaction behaviors and user experience between iOS and Android smart phone operating system, and then study the differences in their brand images, so as to provide theory and research method for shaping corporate brand images from the perspective of product interaction design.

Methods

This study was divided into three stages. In the first stage, the functional information architecture of iOS and Android smart phone operating system are studied comparatively by using information visualization methods. In the second stage, the brand image differences between the two systems at the explicit, behavioral and semantic levels are analyzed comparatively by building the "explicit - behavioral - semantic" product brand gene model. In the third stage, the functions of "setting alarm clock", "sharing pictures" and "modifying passwords" were selected for interactive behavior analysis. First, analyze the user experience of the three system functions from the perspective of interaction process and information architecture, and present the analysis results using the method of information visualization.; Secondly, the user experience and brand image differences between the two systems are analyzed by setting up manipulation task experiments.

Results

The brand images of iOS and Android systems are similar in conciseness, clearness and efficiency; In terms of uniqueness, iOS system is more unique, while Android system has stronger applicability.

Discussion

This study constructs an "explicit-behavior-semantic" brand gene model to create a unique product brand image for software products such as operating systems through interactive design, so as to solve the problem of product brand image homogeneity caused by the convergence of function and interaction design.

Living Tree Moisture Content Detection Method Based on Intelligent UHF RFID Sensors and OS-PELM

Moisture content (MC) detection plays a vital role in the monitoring and management of living trees. Its measurement accuracy is of great significance to the progress of the forestry informatization industry. Targeting the drawbacks of high energy consumption, low practicability, and poor sustainability in the current field of living tree MC detection, this work designs and implements an ultra-high-frequency radio frequency identification (UHF RFID) sensor system based on a deep learning model, with the main goals of non-destructive testing and high-efficiency recognition. The proposed MC diagnostic system includes two passive tags which should be mounted on the trunk and one remote data processing terminal. First, the UHF reader collects information from the living trees in the forest; then, an improved online sequential parallel extreme learning machine algorithm (OS-PELM) is proposed and trained to establish a specific MC prediction model. This mechanism could self-adjust its neuron network structure according to the features of the data input. The experimental results show that, for the entire living tree dataset, the MC prediction model based on the OS-PELM algorithm can identify the MC level with a root-mean-square error (RMSE) of no more than 0.055 within a measurement range of 1.2 m. Compared with the results predicted by other algorithms, the mean absolute error (MAE) and RMSE are 0.0225 and 0.0254, respectively, which are better than the ELM and OS-ELM algorithms. Comparisons also prove that the prediction model has the advantages of high precision, strong robustness, and broad applicability. Therefore, the designed MC detection system fully meets the demand of forestry Artificial Intelligence of Things.

A Local and Nonlocal Feature Interaction Network for Pansharpening

Pansharpening based on deep learning (DL) has shown great advantages. Most convolutional neural network (CNN)-based methods focus on obtaining local features from multispectral (MS) and panchromatic (PAN) images, but ignore the nonlocal dependence on images. Therefore, Transformer-based methods are introduced to obtain long-range information on images. However, the representational capabilities of features extracted by CNN or Transformer alone are weak. To solve this problem, a local and nonlocal feature interaction network (LNFIN) is proposed in this paper for pansharpening. It comprises Transformer and CNN branches. Furthermore, a feature interaction module (FIM) is proposed to fuse different features and return to the two branches to enhance the representational capability of features. Specifically, a CNN branch consisting of multiscale dense modules (MDMs) is proposed for acquiring local features of the image, and a Transformer branch consisting of pansharpening Transformer modules (PTMs) is introduced for acquiring nonlocal features of the image. In addition, inspired by the PTM, a shift pansharpening Transformer module (SPTM) is proposed for the learning of texture features to further enhance the spatial representation of features. The LNFIN outperforms the state-of-the-art method experimentally on three datasets.

The Effect of Education Model in Physical Education on Student Learning Behavior

This research explores the effect of the sports education model implemented in physical education on college students' learning motivation and outcomes. The sports education model was compared with traditional physical education teaching as a control group. Participants were 60 college students in two classes. The ARCS (Attention, Relevance, Confidence, Satisfaction) Learning Motivation Scale, the Physical Education Affection Scale and a learning sheet were used for pre- and post-test comparison. Quantitative analysis was carried out on the post-test data using a dependent sample t-test and an independent sample t-test. The study found that: (1) the students in the sports education model group showed clear progress in learning motivation, affection, cognition and behavior, whereas the students in the traditional physical education group showed clear progress in cognition but no significant improvement in learning motivation, affection or behavior; (2) the sports education model group is clearly superior to the traditional physical education group in terms of learning motivation, affection, cognition, and behavior. This research shows that students are highly receptive to the sports education model, with a positive attitude and a high degree of motivation to learn to actively change their sports behavior. The sports education model brings several benefits: (1) it is an effective teaching method; (2) students' sense of responsibility, leadership and participation can be improved; (3) the preliminary homework and course structure descriptions take more time to compose, but can better guide students' motivation for learning physical education and can enhance teachers' professional growth.

Forest Fire Segmentation from Aerial Imagery Data Using an Improved Instance Segmentation Model

In recent years, forest-fire monitoring methods represented by deep learning have been developed rapidly. The use of drone technology and optimization of existing models to improve forest-fire recognition accuracy and segmentation quality are of great significance for understanding the spatial distribution of forest fires and protecting forest resources. Due to the spreading and irregular nature of fire, it is extremely tough to detect fire accurately in a complex environment. Based on the aerial imagery dataset FLAME, this paper focuses on the analysis of methods to two deep-learning problems: (1) the video frames are classified as two classes (fire, no-fire) according to the presence or absence of fire. A novel image classification method based on channel domain attention mechanism was developed, which achieved a classification accuracy of 93.65%. (2) We propose a novel instance segmentation method (MaskSU R-CNN) for incipient forest-fire detection and segmentation based on MS R-CNN model. For the optimized model, the MaskIoU branch is reconstructed by a U-shaped network in order to reduce the segmentation error. Experimental results show that the precision of our MaskSU R-CNN reached 91.85%, recall 88.81%, F1-score 90.30%, and mean intersection over union (mIoU) 82.31%. Compared with many state-of-the-art segmentation models, our method achieves satisfactory results on forest-fire dataset.

Major League Baseball Marketing Strategies and Industry Promotion Approaches

The sport of baseball is one of the chief pillars of the American sports industry. Major League Baseball (MLB) is the oldest professional sports league in the United States. It has long since formulated comprehensive marketing strategies and global industry promotion approaches that have proved exceptionally successful. Accordingly, the study of MLB's marketing strategies and industry promotion approaches will be crucial for the development of baseball in China and the establishment of an industrial chain. This study employed the literature consultation method, the comparative analysis method, and the inductive method to analyze MLB's localized marketing strategies and development trends in China and obtained the following insights concerning MLB's promotion and industry development efforts in China: (1) MLB has used a “family sport” concept to promote baseball culture and employed a project culture approach to promoting the universal spread of the sport of baseball; (2) MLB has sought to join baseball with school sports as a means of developing baseball talent; (3) MLB has promoted its brand, established a baseball industry chain, and engaged in comprehensive market cultivation; and (4) MLB has strengthened baseball infrastructure and encouraged baseball's rapid development.

Exploring the factors influencing users' learning and sharing behavior on social media platforms

Purpose

The research goal is to understand what factors affect users' knowledge and information learning and sharing on social media platforms. This study focuses on the impact of platform characteristics on users' behavior. Specifically, the purpose of this study is to investigate (1) what factors affect users' learning and dissemination of knowledge and information on social media platforms, (2) whether knowledge and information learning behavior will have a positive effect on sharing behavior and (3) try to establish an impact model of users' learning and sharing behavior about knowledge and information.

Design/methodology/approach

This study proposes an impact mechanism model to test these hypotheses. To achieve this, the authors collected data from 430 users who have used the social media platforms to acquire and share knowledge and information to test the hypothesis. The tools SPSS 26.0 and AMOS 23.0 were used to analyze the reliability, validity, model fits and structural equation modeling.

Findings

The results show that the learning of knowledge and information can influence the sharing behavior on social media platforms. Users' platform-based trust and platform-based satisfaction affect their knowledge and information learning and sharing on the platform. Factors affecting users' trust in social platforms include privacy protection effectiveness and network effects. And, perceived usefulness and perceived ease of use are related to users' satisfaction with social media platforms.

Originality/value

This study constructs an impact model on the learning and sharing of knowledge and information. The model takes the information system continuance model as the theoretical framework and integrates other factors, including the network effect, the effectiveness of privacy protection and trust. Most of the hypotheses of this research were confirmed. The conclusions provide practical guidance for the dissemination of knowledge information and platform management.

Smart Allocation of Standby Resources for Cloud Survivability in Smart Manufacturing Smart Allocation of Resources

With the development of virtualization technology, cloud computing has emerged as a powerful and flexible platform for various services such as online trading. However, there are concerns about the survivability of cloud services in smart manufacturing. Most existing solutions provide a standby Virtual Machine (VM) for each running VM. However, this often leads to huge resource waste because VMs do not always run at full capacity. To reduce resource waste, we propose a smart survivability framework to efficiently allocate resources to standby VMs. Our framework contains two novel aspects: (1) a prediction mechanism to predict the resource utilization of each VM in order to reduce the number of standby VMs; (2) a nested virtualization technology to refine the granularity of standby VMs. We will use an open-source cloud simulation platform named cloudsim, with real-world data, to verify the feasibility of the proposed framework and evaluate its performance. The proposed Smart Survivable Usable Virtual Machine (SSUVM) will predict resource utilization of VMs on Rack1 periodically. When errors happen in VMs, the framework will allocate standby resources according to the predicted result. The SSUVM will receive the latest running status of the failed VM and its mirror image to recover the VM's work.

A Research on Online Education Behavior and Strategy in University

After the reform and opening up in China, through a series of rapid developments in world, online education has grown both socially and economically. This area has become representative of the fast-growing economy. However, Guangfu culture as a crucial component of Cantonese traditional culture is gradually becoming less influential today. It is the college's responsibility and duty to protect, carry forward, and inherit this traditional culture. Especially during this cyber era, where networks have become a powerful source for communication and study, there are diversified methods of adaptive learning and various learning behaviors. This article aims to analyze the plausibility of adapting an online platform into the teaching arena and the needs of students under this teaching mode. A simulation of applying advanced technology and artificial intelligence into Guangfu culture innovation was also conducted. The contribution shows the users in this platform have a longer study time, compared with non-platform users, and are more interested in traditional culture knowledge than non-users; 21.5% higher in the performance's test.

Hyperspectral Image Super-Resolution Method Based on Spectral Smoothing Prior and Tensor Tubal Row-Sparse Representation

Due to the limited hardware conditions, hyperspectral image (HSI) has a low spatial resolution, while multispectral image (MSI) can gain higher spatial resolution. Therefore, derived from the idea of fusion, we reconstructed HSI with high spatial resolution and spectral resolution from HSI and MSI and put forward an HSI Super-Resolution model based on Spectral Smoothing prior and Tensor tubal row-sparse representation, termed SSTSR. Foremost, nonlocal priors are applied to refine the super-resolution task into reconstructing each nonlocal clustering tensor. Then per nonlocal cluster tensor is decomposed into two sub tensors under the tensor t-prodcut framework, one sub-tensor is called tersor dictionary and the other is called tensor coefficient. Meanwhile, in the process of dictionary learning and sparse coding, spectral smoothing constraint is imposed on the tensor dictionary, and L1,1,2 norm based tubal row-sparse regularizer is enforced on the tensor coefficient to enhance the structured sparsity. With this model, the spatial similarity and spectral similarity of the nonlocal cluster tensor are fully utilized. Finally, the alternating direction method of multipliers (ADMM) was employed to optimize the solution of our method. Experiments on three simulated datasets and one real dataset show that our approach is superior to many advanced HSI super-resolution methods.

The effectiveness of mobile learning strategies based on pervasive animated games: an example in a vocational technology college

Purpose

The author proposed a mobile learning model of pervasive animated games which allows college students to learn via games accessed through a smartphone. It can develop the process of field observation and self-reflection to enhance learning effectiveness, and the motivation, and attitude of students towards learning.

Design/methodology/approach

The author proposed a model for teaching via pervasive animated games. The author used SPSS software and Pearson's correlation coefficients to explore different mobile learning strategies and their relationship with learning attitudes and achievement. Participants were vocational technology college students, who each experienced animated games in individual and group learning settings.

Findings

The results found that the learning performance of students in the individual learning group was better than that of the group learning group. A higher level of digital experience was associated with better learning performance, and a more positive attitude towards using mobile phones was associated with better learning performance.

Research limitations/implications

The learning method still has its limitations, the learner's digital information level, learning mode, learning attitudes will have an impact on the student playing teaching pervasive animation games. Therefore, improving student information level is one of the important topics of teaching pervasive animation games and mobile learning.

Originality/value

The author proposed a mobile learning strategy based on pervasive animated games. The result in the strategy of mobile learning shows that the level of students' digital experience and the overall design of animated games are important criteria for successful implementation.

Compositional action recognition with multi-view feature fusion

Most action recognition tasks now treat the activity as a single event in a video clip. Recently, the benefits of representing activities as a combination of verbs and nouns for action recognition have shown to be effective in improving action understanding, allowing us to capture such representations. However, there is still a lack of research on representational learning using cross-view or cross-modality information. To exploit the complementary information between multiple views, we propose a feature fusion framework, and our framework is divided into two steps: extraction of appearance features and fusion of multi-view features. We validate our approach on two action recognition datasets, IKEA ASM and LEMMA. We demonstrate that multi-view fusion can effectively generalize across appearances and identify previously unseen actions of interacting objects, surpassing current state-of-the-art methods. In particular, on the IKEA ASM dataset, the performance of the multi-view fusion approach improves 18.1% over the performance of the single-view approach on top-1.

How to Use Artificial Intelligence to Improve Entrepreneurial Attitude in Business Simulation Games: Implications From a Quasi-Experiment

Business simulation games (BSGs) have been widely used in entrepreneurship education with positive effects. However, there are still some deficiencies in the BSGs, such as limited guidance, low uncertainty and limited simulation environment, which make it impossible to exert the maximum effect. Artificial intelligence (AI) can solve the above shortcomings. The combination of AI and BSGs is the possible development direction of BSGs. But how to effectively combine BSGs with AI is still an open question. Using a quasi-experimental design, this study uses fuzzy-set qualitative comparative analysis to analyze how participants' entrepreneurial attitude changes in BSGs. The results show that BSGs can effectively improve entrepreneurial attitude, and there are four types of promotion configurations. These four configurations consist of five antecedent conditions. According to the above conclusions, AI can improve entrepreneurial attitude in BSGs in various ways, such as simulating competitors, providing targeted feedback for failures, and improving game experience. The contribution of this paper is to highlight the possibility of combining AI with BSGs, and to provide suggestions on how AI can intervene in BSGs.

Construction of alternate peer teaching method for digital animation game design

Purpose

The purpose of this paper is to develop the teaching strategies of alternating peer teaching and progressive project-oriented learning, and apply them to the curriculum design of digital animation game production, and conduct teaching experimental research.

Design/methodology/approach

This research method under the teaching strategies of alternating peer teaching and progressive project-oriented learning, to the design of digital animation game and use teaching experiment animation game production tool was Game Maker animation game production software to develop the study. The production of learning history data was used in-game projects, to verify the digital animation game design effectiveness was used SPSS statistics method, and was to compare the learning effectiveness of the different teaching modes.

Findings

Through experimental design, learners can acquire the knowledge and skills of digital animation game production under the guidance of progressive project-oriented teaching strategies. In terms of the cognition and skills of animation game production, learners have acquired the skills of taking them in animation game design to be able to independently produce and design digital animation games. The research results can be used as a reference for future research on digital animation game teaching and curriculum development.

Originality/value

This study proposed a new approach to develop the teaching strategies of alternating peer teaching and progressive project-oriented learning, to design digital animation games. The research results show that effective teaching strategies guide successful learning, it can be used as a reference for future research on digital animation game teaching and curriculum development.

Research on the Influence of AI and VR Technology for Students’ Concentration and Creativity

The application of digital technology in teaching has triggered the evolution of traditional teaching. Students have different corresponding relationships under digital behavior. The interactive technology of artificial intelligence (AI) and virtual reality (VR) provides a new driving force for the development of art education and psychology. Firstly, this thesis analyzes the limitations and existing problems of traditional art education. Especially, the influence of the teaching mode of art education on the teaching of other disciplines develops a targeted student-centered digital education program. Secondly, the author used VR equipment and technology to let students experience the virtual world freely, and then, the relevant data model was established on the basis of analyzing the reasons affecting students’ creativity and concentration. Thirdly, the data model was applied to art education in order to improve students’ concentration and creativity. Then, the author compared and analyzed the data of the students under different teaching models through questionnaires. The results show that introducing VR and AI technology into art education and encouraging students to carry out deep learning can significantly improve student concentration and creativity. Finally, the influence reasons are analyzed from the perspective of psychology. VR interaction and Artificial Intelligence can be introduced into middle school fine art education which is to the benefit of students’ deep learning, thus students’ concentration and creativity can be improved.

Zero trust in edge computing environment: a blockchain based practical scheme

Edge computing offloads the data processing capacity to the user side, provides flexible and efficient computing services for the development of smart city, and brings many security challenges. Aiming at the problems of fuzzy boundary security protection and dynamic identity authentication in the edge computing environment in smart city, the zero trust architecture based on blockchain is studied, and a digital identity model and dynamic authentication scheme of edge computing nodes based on distributed ledger are proposed. Firstly, a digital identity model of two-way authentication between edge computing node and sensing terminal is established to realize fine-grained authorization and access control in edge computing. Secondly, based on the identity data and behavior log bookkeeping on the chain, the quantification of trust value, trust transmission and update are realized, and the traceability of security events is improved. Finally, based on the improved RAFT consensus algorithm, the multi-party consensus and consistency accounting in the authentication process are realized. Simulation results show that this scheme can meet the requirements of zero trust verification in edge computing environment, and has good efficiency and robustness.

Simultaneous Compatible System of Models of Height, Crown Length, and Height to Crown Base for Natural Secondary Forests of Northeast China

Individual trees are characterized by various sizes and forms, such as diameter at breast height, total height (H), height to crown base (HCB), crown length (CL), crown width, and crown and stem forms. Tree characteristics are strongly related to each other, and studying their relationships is very important. The knowledge of the compatibility and additivity properties of the major tree characteristics, such as H, CL, and HCB, is essential for informed decision-making in forestry. H can be used to represent site quality and CL represents biomass and photosynthesis of crown, which is the performance of individual tree vigor and light interception, and the longer the crown length (or shorter HCB) is, the more vigorous the tree would be. However, none of the studies have uncovered their inherent relationships quantitatively. This study attempts to explore such relationships through the application of appropriate modeling approaches. We applied seemingly unrelated regression, such as nonlinear seemingly unrelated regression (NSUR), which is commonly used for exploring the compatibility and additivity properties of the variables, for the proposes. The NSUR involves the variance and covariance matrices of the sub-models that are used for the interpretation of the correlations among the variables of interest. The data set acquired from Mongolian oak forest and spruce-fir forest in the Jingouling forest farm of the Wangqing Forest Bureau in the Northeast of China were used to construct two types of model systems: a compatible model system (the model system of H, CL, and HCB can be estimated simultaneously) and an additive model system (the sum of HCB and CL is H, the form of the H sub-model equals the sum of the HCB and CL sub-models) from the individual models of H, CL, and HCB. Among the various tree-level and stand-level variables evaluated, D (diameter at breast), Dg (quadratic mean diameter), DT (dominant diameter), CW (crown width), SDI (stand density index), and BAS (basal area of stand) contributed significantly highly to the variations of the response of the variables of interest in the model systems. Modeling results showed the existence of the compatibility and additivity of H, CL, and HCB simultaneously. The additive model system exhibited better fitting performance on H and HCB but poorer fitting on CL compared with the simultaneous model system, indicating that the performance of the additive model system could be higher than that of the simultaneous model system. Model tests against the validation data set also confirmed such results. This study contributes a novel approach to solving the compatibility and additivity of the problems of H, CL, and HCB models through the application of the robust estimating method, NSUR. The results and algorithm presented will be useful for constructing similar compatible and additive model systems of multiple tree-level models for other tree species.