Characterization inference based on joint-optimization of multi-layer semantics and deep fusion matching network

The Guanxi mediating role linking organizational justice to contextual performance with age as a moderator

Guanxi, a distinctive Chinese concept, reflects a shared vision of relationships and connections that include mutual understanding, trust, and a deep bond between individuals. Recognized for its potency in shaping the relationships that facilitate business undertakings and access to key resources, Guanxi is postulated as a potential mediator in the nexus between organizational justice and contextual work performance. The depth of Guanxi, intertwined with Chinese culture and values, may be perceived differently across age groups. Specifically, as Chinese millennials usually interact with global paradigms, generational disparities might emerge in valuing these traditional constructs. This study delves into how the dimensions of Guanxi-Ganqing (emotional connection), Renqing (reciprocity), and Xinren (loyalty)-mediate the relationship between organizational justice and contextual work performance, with chronological age as a moderator. The present study includes a convenience sample of 630 Chinese employees, aged 22-67 years, who participated in a quantitative online survey. The findings endorse the mediation role of Guanxi. The total influence of justice was found to be significant, as well as the indirect impacts, that were statistically salient. Although the age-moderated mediation was not wholly substantiated, the age-specific indirect effects of Renqing and Xinren did present significant variances between millennials and those above 42 years. The relevance of this study extends beyond the academic field, shedding light on the cultural dynamics at play within Chinese organizational settings. By unveiling the relationships between Guanxi, organizational justice, and performance, and by elucidating the age-specific variations therein, this research provides insights for organizational leaders and human resource professionals. Based on these findings, businesses can craft targeted interventions that capitalize on the strengths of Guanxi, ensuring fair practices and enhancing performance across diverse age groups. Further, recognizing the unique attributes and values of different generational cohorts can aid in fostering a harmonious, culturally attuned, and efficient workplace environment.

Research on consumers' purchase intention of cultural and creative products-Metaphor design based on traditional cultural symbols

Chinese traditional cultural symbols possess great aesthetic and cultural value, and are widely utilized in product design. In this study, we explore the relationship between metaphor design based on traditional cultural symbols, customer experience and cultural identity, and further estimate how these three variables stimulate consumers' perceived value to generate consumers' purchase intention. Based on existing traditional cultural literature and Stimulus-organism-response theory (SOR), we proposed a theoretical research model to characterize the relationship among metaphor design based on traditional cultural symbols, customer experience, cultural identity, perceived value and consumers' purchase intention. A research survey was conducted and 262 questionnaires were collected in total with 241 valid. We used Smart PLS graph version 3.0 for data analysis. Results indicate that the cognition of metaphor design based on traditional cultural symbols and customer experience has a direct and significant impact on the emotional value thereby, eliciting consumers' purchase intention, metaphor design based on traditional cultural symbols is directly and indirectly (i.e., through customer experience or perceived value) positively associated with consumers' purchase intention, also customer experience is directly and indirectly (i.e., through perceived value) associated with consumer purchase intention, cultural identity mediates the indirect effect of customer experience and perceived value on purchase intention, the moderating role of cultural identity between customer experience and perceived value is not significant. Our findings help to expand the existing literature on consumer purchase intentions by rationally using traditional cultural symbols in the product metaphor design.

Evaluation of student failure in higher education by an innovative strategy of fuzzy system combined optimization algorithms and AI

This research suggests two novel metaheuristic algorithms to enhance student performance: Harris Hawk's Optimizer (HHO) and the Earthworm Optimization Algorithm (EWA). In this sense, a series of adaptive neuro-fuzzy inference system (ANFIS) proposed models were trained using these methods. The selection of the best-fit model depends on finding an excellent connection between inputs and output(s) layers in training and testing datasets (e.g., a combination of expert knowledge, experimentation, and validation techniques). The study's primary result is a division of the participants into two performance-based groups (failed and non-failed). The experimental data used to build the models measured fourteen process variables: relocation, gender, age at enrollment, debtor, nationality, educational special needs, current tuition fees, scholarship holder, unemployment, inflation, GDP, application order, day/evening attendance, and admission grade. During the model evaluation, a scoring system was created in addition to using mean absolute error (MAE), mean squared error (MSE), and area under the curve (AUC) to assess the efficacy of the utilized approaches. Further research revealed that the HHO-ANFIS is superior to the EWA-ANFIS. With AUC = 0.8004 and 0.7886, MSE of 0.62689 and 0.65598, and MAE of 0.64105 and 0.65746, the failure of the pupils was assessed with the most significant degree of accuracy. The MSE, MAE, and AUC precision indicators showed that the EWA-ANFIS is less accurate, having MSE amounts of 0.71543 and 0.71776, MAE amounts of 0.70819 and 0.71518, and AUC amounts of 0.7565 and 0.758. It was found that the optimization algorithms have a high ability to increase the accuracy and performance of the conventional ANFIS model in predicting students' performance, which can cause changes in the management of the educational system and improve the quality of academic programs.

A novel ensemble approach for estimating the competency of bank telemarketing

Having a reliable understanding of bank telemarketing performance is of great importance in the modern world of economy. Recently, machine learning models have obtained high attention for this purpose. In order to introduce and evaluate cutting-edge models, this study develops sophisticated hybrid models for estimating the success rate of bank telemarketing. A large free dataset is used which lists the clients' information of a Portuguese bank. The data are analyzed by four artificial neural networks (ANNs) trained by metaheuristic algorithms, namely electromagnetic field optimization (EFO), future search algorithm (FSA), harmony search algorithm (HSA), and social ski-driver (SSD). The models predict the subscription of clients for a long-term deposit by evaluating nineteen conditioning parameters. The results first indicated the high potential of all four models in analyzing and predicting the subscription pattern, thereby, revealing the competency of neuro-metaheuristic hybrids. However, comparatively speaking, the EFO yielded the most reliable approximation with an area under the curve (AUC) around 0.80. FSA-ANN emerged as the second-accurate model followed by the SSD and HSA with respective AUCs of 0.7714, 0.7663, and 0.7160. Moreover, the superiority of the EFO-ANN is confirmed against several conventional models from the previous literature, and finally, it is introduced as an effective model to be practically used by banking institutions for predicting the likelihood of deposit subscriptions.

A fuzzy decision-making system for video tracking with multiple objects in non-stationary conditions

Computer vision remains challenged by tracking multiple objects in motion frames, despite efforts to improve surveillance, healthcare, and human-machine interaction. This paper presents a method for monitoring several moving objects in non-stationary settings for autonomous navigation. Additionally, at each phase, movement information between successive frames, including the new frame and the previous frame, is employed to determine the location of moving objects inside the camera's field of view, and the background in the new frame is determined. With the help of a matching algorithm, the Kanade-Lucas-Tomasi (KLT) feature tracker for each frame is determined. To get the new frame, we access the matching feature points between two subsequent frames, calculate the movement size of the feature points and the camera movement, and subtract the previous frame of moving objects from the current frame. Every moving object within the camera's field of view is captured at every moment and location. The moving items are categorized and segregated using fuzzy logic based on their mass center and length-to-width ratio. Our algorithm was implemented to investigate autonomous navigation surveillance of three types of moving objects, such as a vehicle, a pedestrian, a bicycle, or a motorcycle. The results indicate high accuracy and an acceptable time requirement for monitoring moving objects. It has a tracking and classification accuracy of around 75 % and processes 43 frames per second, making it superior to existing approaches in terms of speed and accuracy.

A comparative study of machine learning algorithms for predicting domestic violence vulnerability in Liberian women

Domestic violence against women is a prevalent in Liberia, with nearly half of women reporting physical violence. However, research on the biosocial factors contributing to this issue remains limited. This study aims to predict women's vulnerability to domestic violence using a machine learning approach, leveraging data from the Liberian Demographic and Health Survey (LDHS) conducted in 2019-2020. We employed seven machine learning algorithms to achieve this goal, including ANN, KNN, RF, DT, XGBoost, LightGBM, and CatBoost. Our analysis revealed that the LightGBM and RF models achieved the highest accuracy in predicting women's vulnerability to domestic violence in Liberia, with 81% and 82% accuracy rates, respectively. One of the key features identified across multiple algorithms was the number of people who had experienced emotional violence. These findings offer important insights into the underlying characteristics and risk factors associated with domestic violence against women in Liberia. By utilizing machine learning techniques, we can better predict and understand this complex issue, ultimately contributing to the development of more effective prevention and intervention strategies.

Digital technology and its application in supply chain management: new evidence from China's economy

The purpose of this article is to investigate the influence that practices using information technology (IT) have on the development of a competitive advantage across the supply chain. An organization has a competitive advantage when it has qualities that give the required foundations for it to separate itself from other organizations that are also in its industry. Pressure is applied to the corporate environment as a result of competition and ongoing changes, such as the introduction of new products and technical advancements, the decline of product lifestyles, and the proliferation of products. In order to maintain a competitive edge and achieve financial success in business, organizations are necessary for responding to changes in the market. Through the use of supply chain markets, companies are able to react quickly to unforeseen shifts in the market, and these shifts may be turned into lucrative business possibilities. One of the most significant things that firms can do to assist themselves is make use of information technology to improve their supply chain management agility. From March 2021 through January 2022, the area of China will have a total sample size of 247 persons fill out a questionnaire as part of the data collection process. In each and every questionnaire, the measurements were taken using a Likert scale with five points. The partial least square-structural equation modeling (PLS-SEM) approach is used to the causal model in order to assess the model's reliability and validity. This technique is used to evaluate the causal model. The findings indicate that information technology has a favorable impact on the adaptability of supply chain management systems. In addition, the findings that were collected have shown that there are four factors that influence the SCM systems. These factors are the IT skills and knowledge, the integration of IT-based systems, the IT infrastructure, and the design of global position system and geographic information systems. In addition, this research offers practitioners recommendations for implementing digital technology for supply chain management and building suitable business strategies at various stages of digitalization.

Sar Ship Detection Based on Convnext with Multi-Pooling Channel Attention and Feature Intensification Pyramid Network

The advancements in ship detection technology using convolutional neural networks (CNNs) regarding synthetic aperture radar (SAR) images have been significant. Yet, there are still some limitations in the existing detection algorithms. First, the backbones cannot generate high-quality multiscale feature maps. Second, there is a lack of suitable attention mechanisms to suppress false alarms. Third, the current feature intensification algorithms are unable to effectively enhance the shallow feature's semantic information, which hinders the detection of small ships. Fourth, top-level feature maps have rich semantic information; however, as a result of the reduction of channels, the semantic information is weakened. These four problems lead to poor performance in SAR ship detection and recognition. To address the mentioned issues, we put forward a new approach that has the following characteristics. First, we use Convnext as the backbone to generate high-quality multiscale feature maps. Second, to suppress false alarms, the multi-pooling channel attention (MPCA) is designed to generate a corresponding weight for each channel, suppressing redundant feature maps, and further optimizing the feature maps generated by Convnext. Third, a feature intensification pyramid network (FIPN) is specifically designed to intensify the feature maps, especially the shallow feature maps. Fourth, a top-level feature intensification (TLFI) is also proposed to compensate for semantic information loss within the top-level feature maps by utilizing semantic information from different spaces. The experimental dataset employed is the SAR Ship Detection Dataset (SSDD), and the experimental findings display that our approach exhibits superiority compared to other advanced approaches. The overall Average Precision (AP) reaches up to 95.6% on the SSDD, which improves the accuracy by at least 1.7% compared to the current excellent methods.

Assessing the supply chain management of waste-to-energy on green circular economy in China: an empirical study

One of the industries that makes a significant contribution to the overall amount of greenhouse gas emissions around the globe is agriculture. In this regard, the use of bioenergy in the agricultural and food processing industries might benefit from the implementation of circular economy techniques. Despite the fact that just roughly 9% of the global economy is circular, there have been worldwide efforts to improve that reality. The linear economy, commonly known as the "take-make-use-dispose" model, is in sharp contrast to the circular economy, also known as "grow-make-use-restore," which seeks to influence the flow of materials and energy in order to maximize the benefits to the environment and minimize any associated costs. Garbage-to-energy, also known as WTE, is the focus of both academics and businesses as a direct result of the increasingly diminishing number of energy supplies and the ever-increasing amount of garbage. This project intends to turn trash into profit, lessen the impact waste has on the environment, and generate energy from biowaste by conceptualizing a focus on the supply chain characteristics of waste-to-energy processing. The adoption of a waste-to-energy (WTE) supply chain as a district energy system should be a viable solution toward a circular industrial economy that can solve energy consumption, waste management, and greenhouse gas emission concerns all at once. In the framework of a "circular economy," this study investigates how the management of waste-to-energy supply chains impacts the performance of businesses. The present investigation makes use of life cycle assessments, technical innovation, waste-to-energy conversion, and capacities related to circular economies. The study makes use of data obtained from an online survey that was administered between March 2021 and November 2021 to employees of 285 representative samples drawn from 457 European enterprises and firms that have accepted the concepts of the circular economy. The data is examined using a technique known as partial least squares structural equation modeling (PLS-SEM for short). The findings indicate that waste-to-energy serves as a mediator between the life cycle assessment and the capabilities of the circular economy and that sustainable supply chain management, sustainable supply chain design, technological progress, and waste-to-energy all have positive effects on these metrics.

The multi-modal fusion in visual question answering: a review of attention mechanisms

Visual Question Answering (VQA) is a significant cross-disciplinary issue in the fields of computer vision and natural language processing that requires a computer to output a natural language answer based on pictures and questions posed based on the pictures. This requires simultaneous processing of multimodal fusion of text features and visual features, and the key task that can ensure its success is the attention mechanism. Bringing in attention mechanisms makes it better to integrate text features and image features into a compact multi-modal representation. Therefore, it is necessary to clarify the development status of attention mechanism, understand the most advanced attention mechanism methods, and look forward to its future development direction. In this article, we first conduct a bibliometric analysis of the correlation through CiteSpace, then we find and reasonably speculate that the attention mechanism has great development potential in cross-modal retrieval. Secondly, we discuss the classification and application of existing attention mechanisms in VQA tasks, analysis their shortcomings, and summarize current improvement methods. Finally, through the continuous exploration of attention mechanisms, we believe that VQA will evolve in a smarter and more human direction.

Evaluation Model of Physical Education Teaching Effect Based on AHP Algorithm

The multifaceted sources of physical education teaching factors and the uncertainty of evaluation have an impact on the qualitative and quantitative evaluation results of teaching effects. In order to improve the evaluation accuracy of the physical education teaching effect, the evaluation model of the physical education teaching effect was designed based on the AHP algorithm. The evaluation model is based on monitoring the whole process of teaching. Based on the multifaceted sources of physical education teaching factors and the uncertainty of evaluation, the overall objectives and selects three-level evaluation indicators were analyzed. The AHP algorithm was used to establish the hierarchical structure and obtained the total ranking and comprehensive score of the hierarchy. The test results show that the teaching evaluation model designed in this paper has an RMSE mean value of 1.923, which has higher evaluation accuracy and is conducive to the improvement of teaching quality.

Binary Classification Quantum Neural Network Model Based on Optimized Grover Algorithm

We focus on the problem that the Grover algorithm is not suitable for the completely unknown proportion of target solutions. Considering whether the existing quantum classifier used by the current quantum neural network (QNN) to complete the classification task can solve the problem of the classical classifier, this paper proposes a binary quantum neural network classifical model based on an optimized Grover algorithm based on partial diffusion. Trial and error is adopted to extend the partial diffusion quantum search algorithm with the known proportion of target solutions to the unknown state, and to apply the characteristics of the supervised learning of the quantum neural network to binary classify the classified data. Experiments show that the proposed method can effectively retrieve quantum states with similar features. The test accuracy of BQM retrieval under the depolarization noise at the 20th period can reach 97% when the depolarization rate is 0.1. It improves the retrieval accuracy by about 4% and 10% compared with MSE and BCE in the same environment.

The application of nature-inspired optimization algorithms on the modern management: A systematic literature review and bibliometric analysis

With the expanding adoption of technology and intelligent applications in every aspect of our life, energy, resource, data, and product management are all improving. So, modern management has recently surged to cope with modern societies. Numerous optimization approaches and algorithms are used to effectively optimize the literature while taking into account its many restrictions. With their dependability and superior solution quality for overcoming the numerous barriers to generation, distribution, integration, and management, nature-inspired meta-heuristic optimization algorithms have stood out among these methods. Hence, this article aims to review the application of nature-inspired optimization algorithms to modern management. Besides, the created clusters introduce the top authors in this field. The results showed that nature-inspired optimization algorithms contribute significantly to cost, resource, and energy efficiency. The genetic algorithm is also the most important and widely used method in the previous literature.

Couplet Analysis of Linguistic Topology Using Deep Neural Networks in Cognitive Linguistics

The work reported here primarily aims to realize the automatic generation of couplets using the linguistic topology of deep neural network (DNN). First, the symmetry, topology, and cognitive linguistics of language are explored to lay a theoretical foundation for subsequent model establishment and analysis. Then, the recurrent neural network (RNN) is employed to build the Seq2Seq model, and Liweng's Guide to Rhyme (an ancient Chinese enlightenment reading material to poetry creation) is imported into the Seq2Seq model as a basic corpus. Eventually, the entire system is implemented automatically on TensorFlow. The system undergoes tests of the five-character quatrain, the seven-character quatrain, the couplet, and the part-of-speech detection. Results demonstrate that both the first and the second lines of the couplet present an excellent correspondence regarding sentences and words. After some famous verses are entered, the second line of the couplet obtained is quite vivid and appropriate. Meanwhile, the results can be generated quickly and meet the requirements on rhyme and couplet matching. This model can input verses according to users' own needs and generate the second line of the couplet quickly, showing good correspondence in words, part-of-speech, and sentence pattern. Because the couplet belongs to Chinese traditional culture, it has a strong local Chinese cultural flavor. The system designed based on computer technology can help people learn and experience the charm of couplets.

Influence of Voice Interactive Educational Robot Combined with Artificial Intelligence for the Development of Adolescents

In the context of multicultural information, to explore and analyze the use effect of voice interactive educational robot in the classroom of adolescent students, and the physical and mental impact of movie characters on adolescent students, and to lay the foundation for studying the positive development of adolescents, under the guidance of positive psychology theory, the relationship between positive psychology and adolescent mental health is analyzed, the application of adolescent educational robot is discussed, and the relationship between adolescent educational robot combined with movies characters and positive development of adolescent is analyzed. The questionnaire is used to collect data, including the questionnaire on the influence of movie characters on the positive development of adolescents, the questionnaire of pre- and postpopularization of artificial intelligence in primary and secondary schools, and the satisfaction questionnaire of voice interactive educational robot. The reliability and validity of the questionnaire are analyzed. The results show that students who watch more than 20 movies are 20% in grade one and that is only 10% in grade three. 79% of the students think that the movie characters have an impact on themselves. The distribution of the number of the grade two students exposed to the movie is relatively uniform, 40% of them watch 10-20 movies, and 82% of them think that the movie characters have an impact on themselves; the Cronbach coefficient of classroom satisfaction questionnaire is 0.929 > 0.9, the average value of the correlation of total correction items of the corresponding item is 0.612 > 0.5, the Kaiser–Meyer–Olkin measurement value is 0.812 > 0.6, and the Sig value is 0.000 < 0.05, indicating that the reliability and validity of the questionnaire are very high and 92.3% of the students are very satisfied with the classroom. This shows that voice interactive educational robot combined with movie characters can promote the positive development of adolescents.

From developing to developed: Mechanisms of health inequalities among seniors in China and Japan under macro-field control

The behavioral characteristics, health statuses, and survival times of seniors in China and Japan using the fixed cohort method and constructed relationship models among capital, habitus, and health based on Pierre Bourdieu's social theory of practice. It was first found that capital, habitus, and health have a capital-based triangle generative structural relationship. Second, basic sources of health inequalities include the direct effect of capital and the indirect effect of capital through habitus, i.e., class habitus controlled by capital has class attributes and is also one of the sources of health inequalities. Third, time-space conversion of the field is not just the change in the total amount or composition of an individual's capital but also includes the development and improvement of the macro-social environment, causing altered intensities of the impacts of capital and habitus on health. Fourth, the macro-social structures of developing countries significantly differ. The direct effect of capital on health is far greater than the indirect effect of capital on health through habitus, and health inequalities are mainly derived from the direct role of capital. Fifth, with socioeconomic development and improvements in social welfare systems, health inequalities have been generally reduced but have not been eliminated, and the mechanism of health inequalities in developed countries has gradually shifted from the direct effect of capital to class habitus.

A comprehensive and bibliometric review on the blockchain-enabled IoT technology for designing a secure supply chain management system

Blockchain is a well-known prominent technology that has gotten a lot of interest beyond the financial industry, attracting researchers and practitioners from numerous businesses and fields. Specific uses of blockchain in supply chain management (SCM) are addressed in business practice. By combining two perspectives on blockchain in SCM, this study provides comprehensive knowledge in this field using a bibliometric approach. We will explore the worldwide research trend in related topic areas. By collecting data from the Web of Science, we collected 400 articles related to our research topic from 2016 until early 2021. We eliminated research in the form of technical reports, editorials, comments, and consultancy articles to maintain the quality of the data gathering. VOSviewer is used to create visualization maps based on text and bibliographic information. The examination uncovered helpful information, such as annual publishing and citation patterns, the top research topic, the top authors, and the most supporting funding organizations in this field.

University Archives Autonomous Management Control System under the Internet of Things and Deep Learning Professional Certification

The current work aims to meet the needs of the development of archives work in colleges and universities and the modernization of management to realize the standards and standardization of all aspects of archives business construction in colleges and universities, so as to improve the political and professional quality of archives cadres. First, the radio frequency identification (RFID) technology based on the Internet of things (IoT) digitizes the university archive labels. Meanwhile, the filing cabinet's intelligent security system preserves confidential files. Second, the convolutional neural network (CNN) algorithm under deep learning is introduced and college profile information is identified. Finally, the concept of professional certification is used to clarify the purpose of the university archives automation management system. Different activation functions are used to analyze the recognition accuracy loss and recognition accuracy of university archives. The identification error of You Only Look Once (YOLO) of the ReLU-convolutional neural network (R–CNN) of college archives is analyzed. The results show that the selection of rectified linear units (ReLU) activation function for CNN can effectively reduce the loss of identification accuracy of college archives and can improve the accuracy of identification of college archives. The algorithm based on the ReLU activation function has a smaller recognition error accuracy in college archives than that of the YOLO algorithm. The recognition error of the YOLO algorithm is slightly higher than that of the R–CNN. The font recognition error of archival information based on the R–CNN is relatively large. However, the conclusion is reasonable due to the recognition difficulties of handwritten archival fonts. The file positioning recognition error rate is 19.00%, the file printing font recognition error rate is 4.75%, and the image recognition error rate is 1.90%. These results have a certain reference value for the process of identifying information in the automatic management of university archives by CNN under different activation functions.

Interaction of Secure Cloud Network and Crowd Computing for Smart City Data Obfuscation

There can be many inherent issues in the process of managing cloud infrastructure and the platform of the cloud. The platform of the cloud manages cloud software and legality issues in making contracts. The platform also handles the process of managing cloud software services and legal contract-based segmentation. In this paper, we tackle these issues directly with some feasible solutions. For these constraints, the Averaged One-Dependence Estimators (AODE) classifier and the SELECT Applicable Only to Parallel Server (SELECT-APSL ASA) method are proposed to separate the data related to the place. ASA is made up of the AODE and SELECT Applicable Only to Parallel Server. The AODE classifier is used to separate the data from smart city data based on the hybrid data obfuscation technique. The data from the hybrid data obfuscation technique manages 50% of the raw data, and 50% of hospital data is masked using the proposed transmission. The analysis of energy consumption before the cryptosystem shows the total packet delivered by about 71.66% compared with existing algorithms. The analysis of energy consumption after cryptosystem assumption shows 47.34% consumption, compared to existing state-of-the-art algorithms. The average energy consumption before data obfuscation decreased by 2.47%, and the average energy consumption after data obfuscation was reduced by 9.90%. The analysis of the makespan time before data obfuscation decreased by 33.71%. Compared to existing state-of-the-art algorithms, the study of makespan time after data obfuscation decreased by 1.3%. These impressive results show the strength of our methodology.

The Fusion Application of Deep Learning Biological Image Visualization Technology and Human-Computer Interaction Intelligent Robot in Dance Movements

The paper aims to apply the deep learning-based image visualization technology to extract, recognize, and analyze human skeleton movements and evaluate the effect of the deep learning-based human-computer interaction (HCI) system. Dance education is researched. Firstly, the Visual Geometry Group Network (VGGNet) is optimized using Convolutional Neural Network (CNN). Then, the VGGNet extracts the human skeleton movements in the OpenPose database. Secondly, the Long Short-Term Memory (LSTM) network is optimized and recognizes human skeleton movements. Finally, an HCI system for dance education is designed based on the extraction and recognition methods of human skeleton movements. Results demonstrate that the highest extraction accuracy is 96%, and the average recognition accuracy of different dance movements is stable. The effectiveness of the proposed model is verified. The recognition accuracy of the optimized F-Multiple LSTMs is increased to 88.9%, suitable for recognizing human skeleton movements. The dance education HCI system’s interactive accuracy built by deep learning-based visualization technology reaches 92%; the overall response time is distributed between 5.1 s and 5.9 s. Hence, the proposed model has excellent instantaneity. Therefore, the deep learning-based image visualization technology has enormous potential in human movement recognition, and combining deep learning and HCI plays a significant role.

Exploring socioeconomic inequality in educational management information system: An ethnographic study of China rural area students

There is currently enough systematic literature presents about socioeconomic inequalities across different disciplines. However, this study relates socioeconomic inequality (SEI) to rural students educational management information systems (EMIS) in different schools in China. The dynamic force of information technology could not be constrained in the modern techno-based world. Similarly, the study was qualitative and ethnographic. Data were collected through an interview guide and analyzed with thematic scientific analysis. Ten male and ten female students were interviewed based on data saturation point. The purposive sampling technique was used for the rural school and students’ selection. This study summarizes the findings and brings together in-depth emic and etic findings based on new Marxist conflict theory, exploitation, and domination power lens. The study found that SEI creates disparities among EMIS. Household income inequality has influenced on educational achievements of rural areas’ students. Gender-based SEI was not present among students. Family wealth and SES-based exploitation are present regarding EMIS among male and female students. Household wealth is significant for the EMIS. The study put forward a recommendation to the policymakers that exploitation could be overcome among students if the government provides equal opportunities for access to the EMIS.

Cross-site scripting attack detection based on a modified convolution neural network

Cross-site scripting (XSS) attacks are currently one of the most threatening network attack methods. Effectively detecting and intercepting XSS attacks is an important research topic in the network security field. This manuscript proposes a convolutional neural network based on a modified ResNet block and NiN model (MRBN-CNN) to address this problem. The main innovations of this model are to preprocess the URL according to the syntax and semantic characteristics of XSS attack script encoding, improve the ResNet residual module, extract features from three different angles, and replace the full connection layer in combination with the 1*1 convolution characteristics. Compared with the traditional machine learning and deep learning detection models, it is found that this model has better performance and convergence time. In addition, the proposed method has a detection rate compared to a baseline of approximately 75% of up to 99.23% accuracy, 99.94 precision, and a 98.53% recall value.

Evaluation of College English Teaching Quality Based on Improved BT-SVM Algorithm

With the development of teaching evaluation program, colleges and universities have reformed according to the actual situation of the school. With the development of evaluation activities, many universities are eager to establish their own teaching quality evaluation system, so as to pre-evaluate the teaching quality of schools. SVM is one of the most widely used machine learning algorithms that enables efficient statistical learning with a very limited number of samples. Considering the excellent learning performance of SVM, it is very suitable for the teaching quality evaluation system. In this paper, we optimize the existing multiple classification algorithm for binary trees and propose a new method. Learning the popular teaching quality evaluation system in colleges and universities, the binary tree support vector machine classification algorithm, and design comparison experiment, the experimental results show that the evaluation model proposed in this paper has strong generalization ability and higher classification accuracy and better classification efficiency.

An Empirical Analysis on the Impact of Innovation Network Structure on Crossover Innovation Performance of Emerging Technologies

The crossover innovation springing up in emerging technologies has drawn wide attention from scholars. Innovation network, as an effective way for major innovation-driven entities towards less relevant risks and higher efficiency, can significantly affect the crossover innovation performance. This paper analyzes the evolution law of the innovation network of autonomous driving technology based on the Social Network Analysis (SNA) and by using the data on joint applications for invention patents of such technology during 2006–2020. Furthermore, the structural eigenvalues of the network evolution are calculated for the regression analysis of the relationship between network structure and crossover innovation performance. The empirical results show that network centrality, structural hole, and relationship intensity have a positive effect on crossover innovation performance of emerging technologies, while network clustering has a negative effect. Emerging technology enterprises should constantly improve their technological innovation ability, improve their status and influence in the innovation network, establish cooperation with appropriate innovation partners, further expand their own technical knowledge fields, and obtain innovation resources by optimizing the network structure so as to enhance the crossover innovation performance.

A comprehensive and systematic literature review on the employee attendance management systems based on cloud computing

Attendance is critical to the success of any business or industry. As a result, most businesses and institutions require a system to track staff attendance. On the other hand, cloud computing technology is being utilized in the human resource management sector. It may be an excellent option for processing and storing large amounts of data and improving management effectiveness to a desirable level. Hence, this paper examines cloud infrastructures for employee attendance management in which the articles are categorized into three groups. The results show that cloud infrastructure has a significant and positive impact on the management of employee attendance systems. Also, the results reveal that the radio frequency identification authentication protocol protects the privacy of tags and readers against database memory. When references operate properly, they help the people concerned and society by making workplaces more efficient and safer.

Construction of Emergency Procurement System and System Improvement Based on Convolutional Neural Network

At this stage, countries around the world have their own operating management model for the procurement system of emergency equipment. This article analyzes the influencing factors affecting the operation of the emergency procurement system through a convolutional neural network analysis method, and the contract management of the emergency procurement system is realized. Management and monitoring and balance of interests on supply and demand also meet the requirements of the construction and improvement of emergency procurement systems at this stage. During the construction and improvement of the emergency procurement system, through the monitoring and management of the procurement system, standardize the management of emergency procurement contracts, and implement the management of the memorandum of emergency procurement contracts to maximize the benefits of supply and demand of emergency equipment, and meet the requirements of different emergency levels in the future equipment procurement requirements.

A BERT-Based Aspect-Level Sentiment Analysis Algorithm for Cross-Domain Text

Cross-domain text sentiment analysis is a text sentiment classification task that uses the existing source domain annotation data to assist the target domain, which can not only reduce the workload of new domain data annotation, but also significantly improve the utilization of source domain annotation resources. In order to effectively achieve the performance of cross-domain text sentiment classification, this paper proposes a BERT-based aspect-level sentiment analysis algorithm for cross-domain text to achieve fine-grained sentiment analysis of cross-domain text. First, the algorithm uses the BERT structure to extract sentence-level and aspect-level representation vectors, extracts local features through an improved convolutional neural network, and combines aspect-level corpus and sentence-level corpus to form a sequence sentence pair. Then, the algorithm uses domain adversarial neural network to make the feature representation extracted from different domains as indistinguishable as possible, that is, the features extracted from the source domain and the target domain have more similarity. Finally, by training the sentiment classifier on the source domain dataset with sentiment labels, it is expected that the classifier can achieve a good sentiment classification effect in both source and target domain, and achieve sentence-level and aspect-level sentiment classification. At the same time, the error pooled values of the sentiment classifier and the domain adversary are passed backwards to realize the update and optimization of the model parameters, thereby training a model with cross-domain analysis capability. Experiments are carried out on the Amazon product review dataset, and accuracy and F1 value are used as evaluation indicators. Compared with other classical algorithms, the experimental results show that the proposed algorithm has better performance.

Research on Long Text Classification Model Based on Multi-Feature Weighted Fusion

Text classification in the long-text domain has become a development challenge due to the significant increase in text data, complexity enhancement, and feature extraction of long texts in various domains of the Internet. A long text classification model based on multi-feature weighted fusion is proposed for the problems of contextual semantic relations, long-distance global relations, and multi-sense words in long text classification tasks. The BERT model is used to obtain feature representations containing global semantic and contextual feature information of text, convolutional neural networks to obtain features at different levels and combine attention mechanisms to obtain weighted local features, fuse global contextual features with weighted local features, and obtain classification results by equal-length convolutional pooling. The experimental results show that the proposed model outperforms other models in terms of accuracy, precision, recall, F1 value, etc., under the same data set conditions compared with traditional deep learning classification models, and it can be seen that the model has more obvious advantages in long text classification.

Repertoire Construction for Critical Cross-Cultural Literacy of English Majors: Based on the Research Paradigm of Systemic Functional Linguistics

The ambiguous development trend of cultural globalization brings both opportunities and challenges to China's cultural development. English major in colleges and universities, a discipline of cross-cultural education, should look at the cultural communication of the target country dialectically based on the national consciousness of the home country. Since the end of the 20th century, administrators and scholars have paid attention to critical thinking, critical cultural awareness, and critical skills in cross-cultural communication, which are important components of the cross-cultural meaning system. Therefore, all these are collectively referred to as critical cross-cultural literacy (CCCL). On the basis of the research paradigm of systemic functional linguistics (SFL), a language is a semiotic system that creates meaning. Thus, to help students construct and improve their individual CCCL repertoire, teachers need to guide them to critically study and analyze the discourse purpose of the textbook author as well as their language methods and strategies to enrich their meaning potential.

Network Audio Data and Music Composition Teaching Based on Heterogeneous Cellular Network

With the rapid development of services such as Industry 4.0 and Internet of Vehicles, it is difficult for traditional cellular networks to meet the needs of network users for quantification, diversification, and greenness in the future. Various cellular networks expand multiple micro-cell nodes and relay nodes under macro-cells to form a multilayer network architecture. Based on this, in the process of data transmission, the links have been repeatedly reduced, and at the same time, the terminal power consumption has been reduced and the running system has been improved. This article will use the ratio of the capacity, energy consumption, and resource allocation of different cellular networks as the main means to optimize the cost. Using graph theory, auction theory, and multipurpose optimization algorithms, we have conducted in-depth research topics on upstream and downstream wireless resource allocation, network relay deployment and transmission scheduling, MMW large-scale multi-antenna transmission technology, and base station energy management. A series of optimization schemes and algorithms are proposed. This dissertation is based on the research of educational system design theory in the field of educational technology so as to carry out the research of music education system design theory suitable for the nature of music subjects and learning and education characteristics. Based on the necessity and importance of music education system design theory, the research framework of music education system design theory is constructed in advance. The voice data acquisition system collects voice data through a network grabber and real-time recording and uses signal processing and pattern recognition technology to automatically classify the collected voice data into three categories: voice, environmental sound, and music. After establishing the audio data deployment strategy, simulation method, and architecture design based on heterogeneous cellular network, this paper designs the corresponding music composition teaching system, mainly including score editing, viewing, and content display of the composition teaching system, and the final test shows that the system designed in this paper can be effectively used in various music school teaching combined with heterogeneous cellular networks.

Effect of cloud-based information systems on the agile development of industrial business process management

Business process management (BPM) has been the main driver behind company optimization and operational efficiency. However, the digitization era we live in necessitates that organizations be agile and adaptable. Delivering unprecedented rates of automation-fueled agility is necessary to be a part of this digital revolution. On the other hand, BPM automation cannot be done only by concentrating on procedure space and traditional planning methodologies. With the introduction of BPM, where the deployment of BPM with cloud computing has undergone enormous development lately, cloud computing has been considered a particularly active topic of study. Cloud computing points to the provision of dependable computing environments based on improved infrastructure availability and service quality without imposing a significant cost load. This research aims to discover the relationship between technical factors, financial factors, environmental factors, security of the cloud-based information systems, and the agile development of industrial BPM (IBPM). The present study aims to fill this gap and show how partial least squares structural equation modeling (SEM) can be employed in this field. Importance–performance map analysis (IPMA) evaluated the importance and performance of factors in the SEM. IPMA enables the identification of factors with relatively low performance but relatively high importance in shaping dependent variables. The empirical findings showed that four key factors (technical, financial, environmental, and security) positively influence the agile development of IBPM.

Trust of Information during the Dissemination of Popular Science Web Videos in the New Media Era

Web videos have gradually replaced text, voice, pictures, and other information carriers to become an important way of information dissemination in the new media era. As digital technology brings a new dissemination ecology, the original dissemination trust theory and its framework are facing the crisis of explanatory power failure. This paper considers the popular science web video as an object of study. It analyses and interprets the development of popular science web videos based on the evolution of dissemination form and the basic principle of social trust, from perspectives such as mediology, informatics, and sociology. To maintain or improve the trust relationship in web videos, it's necessary to find positive incentive and reverse punishment, and establish a trust certification and regulation mechanism. In this way, active dissemination and sharing of information can be promoted for a more vigorous society and culture. Moreover, this paper explores a new way of web video development from the perspective of trust.

Platformance-Based Cross-Border Import Retail E-Commerce Service Quality Evaluation Using an Artificial Neural Network Analysis

The transaction scale of cross-border import e-commerce has grown rapidly around the world. Platform-style cross-border e-commerce does not control the quality, source and transaction process of goods strictly and comprehensively. In terms of customer service quality, the seller's customer service often ignores the customer's problems, and some customer service solutions cannot solve the customer's problems. Serving customers through the network has changed the traditional offline service form without distance, and the service process has a time and space distance. This paper constructs an evaluation index system based on the development of cross-border e-commerce. Through questionnaires, relevant data were obtained and analyzed. Analyze the results based on the collected data on the factors that affect the quality of cross-border import e-commerce services. Responsiveness is the most important factor found by artificial neural networks. The descending order of importance of other factors is fulfillment, diversity, privacy, reliability, compensation, and ease of use.