Nonpeaked Discriminant Analysis for Data Representation

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.

Two-level mixed-effects height to crown base model for moso bamboo (Phyllostachys edulis) in Eastern China

Height to crown base (HCB) is an important predictor variable for forest growth and yield models and is of great significance for bamboo stem utilization. However, existing HCB models built so far on the hierarchically structured data are for arbor forests, and not applied to bamboo forests. Based on the fitting of data acquired from 38 temporary sample plots of Phyllostachys edulis forests in Yixing, Jiangsu Province, we selected the best HCB model (logistic model) from among six basic models and extended it by integrating predictor variables, which involved evaluating the impact of 13 variables on HCB. Block- and sample plot-level random effects were introduced to the extended model to account for nested data structures through mixed-effects modeling. The results showed that bamboo height, diameter at breast height, total basal area of all bamboo individuals with a diameter larger than that of the subject bamboo, and canopy density contributed significantly more to variation in HCB than other variables did. Introducing two-level random effects resulted in a significant improvement in the accuracy of the model. Different sampling strategies were evaluated for response calibration (model localization), and the optimal strategy was identified. The prediction accuracy of the HCB model was substantially improved, with an increase in the number of bamboo samples in the calibration. Based on our findings, we recommend the use of four randomly selected bamboo individuals per sample to provide a compromise between measurement cost, model use efficiency, and prediction accuracy.

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.

Multiview Learning With Robust Double-Sided Twin SVM

Multiview learning (MVL), which enhances the learners' performance by coordinating complementarity and consistency among different views, has attracted much attention. The multiview generalized eigenvalue proximal support vector machine (MvGSVM) is a recently proposed effective binary classification method, which introduces the concept of MVL into the classical generalized eigenvalue proximal support vector machine (GEPSVM). However, this approach cannot guarantee good classification performance and robustness yet. In this article, we develop multiview robust double-sided twin SVM (MvRDTSVM) with SVM-type problems, which introduces a set of double-sided constraints into the proposed model to promote classification performance. To improve the robustness of MvRDTSVM against outliers, we take L1-norm as the distance metric. Also, a fast version of MvRDTSVM (called MvFRDTSVM) is further presented. The reformulated problems are complex, and solving them are very challenging. As one of the main contributions of this article, we design two effective iterative algorithms to optimize the proposed nonconvex problems and then conduct theoretical analysis on the algorithms. The experimental results verify the effectiveness of our proposed methods.

Position-Aware Participation-Contributed Temporal Dynamic Model for Group Activity Recognition

Group activity recognition (GAR) aiming at understanding the behavior of a group of people in a video clip has received increasing attention recently. Nevertheless, most of the existing solutions ignore that not all the persons contribute to the group activity of the scene equally. That is to say, the contribution from different individual behaviors to group activity is different; meanwhile, the contribution from people with different spatial positions is also different. To this end, we propose a novel Position-aware Participation-Contributed Temporal Dynamic Model (P2CTDM), in which two types of the key actor are constructed and learned. Specifically, we focus on the behaviors of key actors, who maintain steady motions (long moving time, called long motions) or display remarkable motions (but closely related to other people and the group activity, called flash motions) at a certain moment. For capturing long motions, we rank individual motions according to their intensity measured by stacking optical flows. For capturing flash motions that are closely related to other people, we design a position-aware interaction module (PIM) that simultaneously considers the feature similarity and position information. Beyond that, for capturing flash motions that are highly related to the group activity, we also present an aggregation long short-term memory (Agg-LSTM) to fuse the outputs from PIM by time-varying trainable attention factors. Four widely used benchmarks are adopted to evaluate the performance of the proposed P2CTDM compared to the state of the art.

Research into influencing factors in user experiences of university mobile libraries based on mobile learning mode

Purpose

The purpose of this study is to analyse and discuss the influencing factors of user experience in university mobile libraries and the improvement path of user experience in the context of mobile learning.

Design/methodology/approach

The study adopted the grounded theory research method, and the sample included 28 students from five universities, with mobile libraries as the research objects and semi-structured interview as data acquisition method. A step-by-step coding analysis of the original interview materials was conducted, which comprehensively identified the main concerns and problems encountered by users of the university mobile library apps especially in the mobile learning behaviour mode, and then a theoretical model of the influencing factors of the app user experience of the university mobile library was constructed.

Findings

A theoretical model of influencing factors was constructed, which determined that system quality, interaction quality, content quality, interface quality and function quality were the key elements of mobile library user experiences. Furthermore, based on the research results and user feedback obtained in the research process, the content and key points relating to the user experience can be elaborated in detail. In addition, this study was able to determine users' perspectives and their behavioural characteristics when engaging in mobile learning.

Originality/value

This study establishes a theoretical model of the factors influencing of the user experience of university mobile libraries based on mobile learning, which could provide a valuable reference for the design of other programs and strategies to promote user learning experiences of mobile library app in colleges and universities.

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.

The Core Industry Manufacturing Process of Electronics Assembly Based on Smart Manufacturing

This research takes a case study approach to show the development of a diverse adoption and product strategy distinct from the core manufacturing industry process. It explains the development status in all aspects of smart manufacturing, via the example of ceramic circuit board manufacturing and electronic assembly, and outlines future smart manufacturing plans and processes. This research proposed two experiments using Artificial Intelligence and deep learning are used to demonstrate the problems and solutions regarding methods in manufacturing and factory facilities, respectively. In the first experiment, a Bayesian network inference is used to find the cause of the problem of metal residues between electronic circuits through key process and quality correlations. In the second experiment, a Convolutional Neural Network (CNN) is used to identify false defects that were over-inspected during Automatic Optical Inspection. This improves the manufacturing process by enhancing yield rate and reducing cost. The contributions of the study in circuit board production. Smart manufacturing, with the application of a Bayesian network to an IoT setup, has addressed the problem of residue and redundant conductors on the edge of the ceramic circuit board pattern, and has improved and prevented leakage and high-frequency interference. CNN and deep learning were used to improve the accuracy of the AOI system, reduce the current manual review ratio, save labour costs and provide defect classification as a reference for pre-process improvement.

Estimating Fractional Vegetation Cover Changes in Desert Regions Using RGB Data

Fractional vegetation cover (FVC) is an important indicator of ecosystem changes. Both satellite remote sensing and ground measurements are common methods for estimating FVC. However, desert vegetation grows sparsely and scantly and spreads widely in desert regions, making it challenging to accurately estimate its vegetation cover using satellite data. In this study, we used RGB images from two periods: images from 2006 captured with a small, light manned aircraft with a resolution of 0.1 m and images from 2019 captured with an unmanned aerial vehicle (UAV) with a resolution of 0.02 m. Three pixel-based machine learning algorithms, namely gradient enhancement decision tree (GBDT), k-nearest neighbor (KNN) and random forest (RF), were used to classify the main vegetation (woody and grass species) and calculate the coverage. An independent data set was used to evaluate the accuracy of the algorithms. Overall accuracies of GBDT, KNN and RF for 2006 image classification were 0.9140, 0.9190 and 0.9478, respectively, with RF achieving the best classification results. Overall accuracies of GBDT, KNN and RF for 2019 images were 0.8466, 0.8627 and 0.8569, respectively, with the KNN algorithm achieving the best results for vegetation cover classification. The vegetation coverage in the study area changed significantly from 2006 to 2019, with an increase in grass coverage from 15.47 ± 1.49% to 27.90 ± 2.79%. The results show that RGB images are suitable for mapping FVC. Determining the best spatial resolution for different vegetation features may make estimation of desert vegetation coverage more accurate. Vegetation cover changes are also important in terms of understanding the evolution of desert ecosystems.

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.

Using Artificial Intelligence Assisted Learning Technology on Augmented Reality-Based Manufacture Workflow

The manufacturing process is defined by the synchronous matching and mutual support of the event logic and the task context, so that the work task can be completed perfectly, by executing each step of the manufacturing process. However, during the manufacturing process of the traditional production environment, on-site personnel are often faced with the situation that on-site advice is required, due to a lack of experience or knowledge. Therefore, the function of the manufacturing process should be more closely connected with the workers and tasks. To improve the manufacturing efficiency and reduce the error rate, this research proposes a set of manufacturing work knowledge frameworks, to integrate the intelligent assisted learning system into the manufacturing process. Through Augmented Reality (AR) technology, object recognition technology is used to identify the components within the line of sight, and the assembly steps are presented visually. During the manufacturing process, the system can still feedback to the user in animation, so as to achieve the function equivalent to on-the-spot guidance and assistance when a particular problem is solved by a specialist. Research experiments show that the operation of this intelligent assisted learning interface can more quickly recognize how the manufacturing process works and can solve problems, which greatly resolves the issue of personnel with insufficient experience and knowledge.

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.

Nonlinear Mixed-Effects Height to Crown Base Model for Moso Bamboo (Phyllostachys heterocycla (Carr.) Mitford cv. Pubescens) in Eastern China

Height to crown base (HCB) is an important variable used as a predictor of forest growth and yield. This study developed a nonlinear, mixed-effects HCB model through inclusion of plot-level random effects using data from 29 sample plots distributed across a state-owned Yixing forest farm in Jiangsu province, eastern China. Among several predictor variables evaluated in the analyses, bamboo height, canopy density, and total basal area of bamboo with a diameter larger than that of the subject bamboo individual contributed significantly to the HCB variations. The inclusion of random effects improved the prediction accuracy of the model significantly, indicating that the HCB variations within and across the sample plots were substantial. The model was localized using four sampling strategies, and the study identified that using two medium-sized bamboos by diameter at breast height per sample plot resulted in the smallest prediction error. This strategy, which would balance both measurement cost and potential error, may be applied to estimate the random effects and localization of the nonlinear mixed-effects HCB model for moso bamboo in eastern China.

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.

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.

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.

Learning Robust Discriminant Subspace Based on Joint L₂,ₚ- and L₂,ₛ-Norm Distance Metrics

Recently, there are many works on discriminant analysis, which promote the robustness of models against outliers by using L₁- or L_2,1-norm as the distance metric. However, both of their robustness and discriminant power are limited. In this article, we present a new robust discriminant subspace (RDS) learning method for feature extraction, with an objective function formulated in a different form. To guarantee the subspace to be robust and discriminative, we measure the within-class distances based on [Formula: see text]-norm and use [Formula: see text]-norm to measure the between-class distances. This also makes our method include rotational invariance. Since the proposed model involves both [Formula: see text]-norm maximization and [Formula: see text]-norm minimization, it is very challenging to solve. To address this problem, we present an efficient nongreedy iterative algorithm. Besides, motivated by trace ratio criterion, a mechanism of automatically balancing the contributions of different terms in our objective is found. RDS is very flexible, as it can be extended to other existing feature extraction techniques. An in-depth theoretical analysis of the algorithm's convergence is presented in this article. Experiments are conducted on several typical databases for image classification, and the promising results indicate the effectiveness of RDS.

Emotion-Aware and Intelligent Internet of Medical Things Toward Emotion Recognition During COVID-19 Pandemic

The Internet of Medical Things (IoMT) is a brand new technology of combining medical devices and other wireless devices to access to the healthcare management systems. This article has sought the possibilities of aiding the current Corona Virus Disease 2019 (COVID-19) pandemic by implementing machine learning algorithms while offering emotional treatment suggestion to the doctors and patients. The cognitive model with respect to IoMT is best suited to this pandemic as every person is to be connected and monitored through a cognitive network. However, this COVID-19 pandemic still remain some challenges about emotional solicitude for infants and young children, elderly, and mentally ill persons during pandemic. Confronting these challenges, this article proposes an emotion-aware and intelligent IoMT system, which contains information sharing, information supervision, patients tracking, data gathering and analysis, healthcare, etc. Intelligent IoMT devices are connected to collect multimodal data of patients in a surveillance environments. The latest data and inputs from official websites and reports are tested for further investigation and analysis of the emotion analysis. The proposed novel IoMT platform enables remote health monitoring and decision-making about the emotion, therefore greatly contribute convenient and continuous emotion-aware healthcare services during COVID-19 pandemic. Experimental results on some emotion data indicate that the proposed framework achieves significant advantage when compared with the some mainstream models. The proposed cognition-based dynamic technology is an effective solution way for accommodating a big number of devices and this COVID-19 pandemic application. The controversy and future development trend are also discussed.

Spatial-Spectral Network for Hyperspectral Image Classification: A 3-D CNN and Bi-LSTM Framework

Recently, deep learning methods based on the combination of spatial and spectral features have been successfully applied in hyperspectral image (HSI) classification. To improve the utilization of the spatial and spectral information from the HSI, this paper proposes a unified network framework using a three-dimensional convolutional neural network (3-D CNN) and a band grouping-based bidirectional long short-term memory (Bi-LSTM) network for HSI classification. In the framework, extracting spectral features is regarded as a procedure of processing sequence data, and the Bi-LSTM network acts as the spectral feature extractor of the unified network to fully exploit the close relationships between spectral bands. The 3-D CNN has a unique advantage in processing the 3-D data; therefore, it is used as the spatial-spectral feature extractor in this unified network. Finally, in order to optimize the parameters of both feature extractors simultaneously, the Bi-LSTM and 3-D CNN share a loss function to form a unified network. To evaluate the performance of the proposed framework, three datasets were tested for HSI classification. The results demonstrate that the performance of the proposed method is better than the current state-of-the-art HSI classification methods.

Research on knowledge dissemination in smart cities environment based on intelligent analysis algorithms: a case study on online platform

In developing smart cities, the implementation of social connections, collaboration, innovation, exchange of views by observing, exploiting and integrating various types of knowledge is required. The smart cities concept that employs knowledge sharing mechanism can be defined as the concept of a city that utilizes information technology to increase citizens' awareness, intelligence as well as community's participation. The knowledge dissemination via online sharing platforms has been becoming more popular in recent years, especially during the epidemic of infectious diseases. Thus, the social network and emotional analysis method based on intelligent data analysis algorithms is proposed to study the speaker relationship and comment sentiment tendency of a Chinese popular speech (knowledge dissemination) platform: YiXi. In our research, 690 speakers' information and 23,685 comments' information are collected from YiXi website as the data source. The speaker relationship network construction algorithm and emotional analysis algorithm are designed in details respectively. Experiments show that speakers who have the same profession can deliver different types of speeches, indicating that selection of YiXi platform in the invitation of speakers is diversified. In addition, overall sentiment tendency of comments on speeches seem to be slightly positive and most of them are the personal feelings according to their experience after watching speech videos instead of the direct evaluations of speech quality. The research aims to gain an insight into the popular knowledge sharing phenomenon and is expected to provide reference for knowledge dissemination platforms in order to improve the knowledge sharing environment in smart cities.

SSCNN-S: A Spectral-Spatial Convolution Neural Network with Siamese Architecture for Change Detection

In this paper, a spectral-spatial convolution neural network with Siamese architecture (SSCNN-S) for hyperspectral image (HSI) change detection (CD) is proposed. First, tensors are extracted in two HSIs recorded at different time points separately and tensor pairs are constructed. The tensor pairs are then incorporated into the spectral-spatial network to obtain two spectral-spatial vectors. Thereafter, the Euclidean distances of the two spectral-spatial vectors are calculated to represent the similarity of the tensor pairs. We use a Siamese network based on contrastive loss to train and optimize the network so that the Euclidean distance output by the network describes the similarity of tensor pairs as accurately as possible. Finally, the values obtained by inputting all tensor pairs into the trained model are used to judge whether a pixel belongs to the change area. SSCNN-S aims to transform the problem of HSI CD into a problem of similarity measurement for tensor pairs by introducing the Siamese network. The network used to extract tensor features in SSCNN-S combines spectral and spatial information to reduce the impact of noise on CD. Additionally, a useful four-test scoring method is proposed to improve the experimental efficiency instead of taking the mean value from multiple measurements. Experiments on real data sets have demonstrated the validity of the SSCNN-S method.

Visual attentional-driven deep learning method for flower recognition

As a typical fine-grained image recognition task, flower category recognition is one of the most popular research topics in the field of computer vision and forestry informatization. Although the image recognition method based on Deep Convolutional Neural Network (DCNNs) has achieved acceptable performance on natural scene image, there are still shortcomings such as lack of training samples, intra-class similarity and low accuracy in flowers category recognition. In this paper, we study deep learning-based flowers' category recognition problem, and propose a novel attention-driven deep learning model to solve it. Specifically, since training the deep learning model usually requires massive training samples, we perform image augmentation for the training sample by using image rotation and cropping. The augmented images and the original image are merged as a training set. Then, inspired by the mechanism of human visual attention, we propose a visual attention-driven deep residual neural network, which is composed of multiple weighted visual attention learning blocks. Each visual attention learning block is composed by a residual connection and an attention connection to enhance the learning ability and discriminating ability of the whole network. Finally, the model is training in the fusion training set and recognize flowers in the testing set. We verify the performance of our new method on public Flowers 17 dataset and it achieves the recognition accuracy of 85.7%.

CF2PN: A Cross-Scale Feature Fusion Pyramid Network Based Remote Sensing Target Detection

In the wake of developments in remote sensing, the application of target detection of remote sensing is of increasing interest. Unfortunately, unlike natural image processing, remote sensing image processing involves dealing with large variations in object size, which poses a great challenge to researchers. Although traditional multi-scale detection networks have been successful in solving problems with such large variations, they still have certain limitations: (1) The traditional multi-scale detection methods note the scale of features but ignore the correlation between feature levels. Each feature map is represented by a single layer of the backbone network, and the extracted features are not comprehensive enough. For example, the SSD network uses the features extracted from the backbone network at different scales directly for detection, resulting in the loss of a large amount of contextual information. (2) These methods combine with inherent backbone classification networks to perform detection tasks. RetinaNet is just a combination of the ResNet-101 classification network and FPN network to perform the detection tasks; however, there are differences in object classification and detection tasks. To address these issues, a cross-scale feature fusion pyramid network (CF2PN) is proposed. First and foremost, a cross-scale fusion module (CSFM) is introduced to extract sufficiently comprehensive semantic information from features for performing multi-scale fusion. Moreover, a feature pyramid for target detection utilizing thinning U-shaped modules (TUMs) performs the multi-level fusion of the features. Eventually, a focal loss in the prediction section is used to control the large number of negative samples generated during the feature fusion process. The new architecture of the network proposed in this paper is verified by DIOR and RSOD dataset. The experimental results show that the performance of this method is improved by 2–12% in the DIOR dataset and RSOD dataset compared with the current SOTA target detection methods.

Multiscale Weighted Adjacent Superpixel-Based Composite Kernel for Hyperspectral Image Classification

This paper presents a composite kernel method (MWASCK) based on multiscale weighted adjacent superpixels (ASs) to classify hyperspectral image (HSI). The MWASCK adequately exploits spatial-spectral features of weighted adjacent superpixels to guarantee that more accurate spectral features can be extracted. Firstly, we use a superpixel segmentation algorithm to divide HSI into multiple superpixels. Secondly, the similarities between each target superpixel and its ASs are calculated to construct the spatial features. Finally, a weighted AS-based composite kernel (WASCK) method for HSI classification is proposed. In order to avoid seeking for the optimal superpixel scale and fuse the multiscale spatial features, the MWASCK method uses multiscale weighted superpixel neighbor information. Experiments from two real HSIs indicate that superior performance of the WASCK and MWASCK methods compared with some popular classification methods.