Search results

Sparrow search algorithm (SSA) is a novel global optimization method, but it is easy to fall into local optimization, which leads to its poor search accuracy and stability. The purpose of this study is to propose an improved SSA algorithm, called levy flight and opposition-based learning (LOSSA), based on LOSSA strategy. The LOSSA shows better search accuracy, faster convergence speed and stronger stability.

To further enhance the optimization performance of the algorithm, The Levy flight operation is introduced into the producers search process of the original SSA to enhance the ability of the algorithm to jump out of the local optimum. The opposition-based learning strategy generates better solutions for SSA, which is beneficial to accelerate the convergence speed of the algorithm. On the one hand, the performance of the LOSSA is evaluated by a set of numerical experiments based on classical benchmark functions. On the other hand, the hyper-parameter optimization problem of the Support Vector Machine (SVM) is also used to test the ability of LOSSA to solve practical problems.

First of all, the effectiveness of the two improved methods is verified by Wilcoxon signed rank test. Second, the statistical results of the numerical experiment show the significant improvement of the LOSSA compared with the original algorithm and other natural heuristic algorithms. Finally, the feasibility and effectiveness of the LOSSA in solving the hyper-parameter optimization problem of machine learning algorithms are demonstrated.

An improved SSA based on LOSSA is proposed in this paper. The experimental results show that the overall performance of the LOSSA is satisfactory. Compared with the SSA and other natural heuristic algorithms, the LOSSA shows better search accuracy, faster convergence speed and stronger stability. Moreover, the LOSSA also showed great optimization performance in the hyper-parameter optimization of the SVM model.

The purpose of this paper is to deal with the practical challenge faced by modern logistics enterprises to accurately evaluate driving performance with high computational efficiency under the disturbance of road smoothness and to identify significantly associated performance influence factors.

The authors cooperate with a logistics server (G7) and establish a driving grading system by constructing real-time inertial navigation data-enabled indicators for both driving behaviour (times of aggressive speed change and times of lane change) and road smoothness (average speed and average vibration times of the vehicle body).

The developed driving grading system demonstrates highly accurate evaluations in practical use. Data analytics on the constructed indicators prove the significances of both driving behaviour heterogeneity and the road smoothness effect on objective driving grading. The methodologies are validated with real-life tests on different types of vehicles, and are confirmed to be quite effective in practical tests with 95% accuracy according to prior benchmarks. Data analytics based on the grading system validate the hypotheses of the driving fatigue effect, daily traffic periods impact and transition effect. In addition, the authors empirically distinguish the impact strength of external factors (driving time, rainfall and humidity, wind speed, and air quality) on driving performance.

This study has good potential for providing objective driving grading as required by the modern logistics industry to improve transparent management efficiency with real-time vehicle data.

This study contributes to the existing research by comprehensively measuring both road smoothness and driving performance in the driving grading system in the modern logistics industry.

With the continuous growth of online education, the quality issue of online educational videos has become increasingly prominent, causing students in online learning to face the dilemma of knowledge confusion. The existing mechanisms for controlling the quality of online educational videos suffer from subjectivity and low timeliness. Monitoring the quality of online educational videos involves analyzing metadata features and log data, which is an important aspect. With the development of artificial intelligence technology, deep learning techniques with strong predictive capabilities can provide new methods for predicting the quality of online educational videos, effectively overcoming the shortcomings of existing methods. The purpose of this study is to find a deep neural network that can model the dynamic and static features of the video itself, as well as the relationships between videos, to achieve dynamic monitoring of the quality of online educational videos.

The quality of a video cannot be directly measured. According to previous research, the authors use engagement to represent the level of video quality. Engagement is the normalized participation time, which represents the degree to which learners tend to participate in the video. Based on existing public data sets, this study designs an online educational video engagement prediction model based on dynamic graph neural networks (DGNNs). The model is trained based on the video’s static features and dynamic features generated after its release by constructing dynamic graph data. The model includes a spatiotemporal feature extraction layer composed of DGNNs, which can effectively extract the time and space features contained in the video's dynamic graph data. The trained model is used to predict the engagement level of learners with the video on day T after its release, thereby achieving dynamic monitoring of video quality.

Models with spatiotemporal feature extraction layers consisting of four types of DGNNs can accurately predict the engagement level of online educational videos. Of these, the model using the temporal graph convolutional neural network has the smallest prediction error. In dynamic graph construction, using cosine similarity and Euclidean distance functions with reasonable threshold settings can construct a structurally appropriate dynamic graph. In the training of this model, the amount of historical time series data used will affect the model’s predictive performance. The more historical time series data used, the smaller the prediction error of the trained model.

A limitation of this study is that not all video data in the data set was used to construct the dynamic graph due to memory constraints. In addition, the DGNNs used in the spatiotemporal feature extraction layer are relatively conventional.

In this study, the authors propose an online educational video engagement prediction model based on DGNNs, which can achieve the dynamic monitoring of video quality. The model can be applied as part of a video quality monitoring mechanism for various online educational resource platforms.

The purpose of this paper is to examine the prevalence of academic stress and exam anxiety among private secondary school students in India as well as the associations with socio-economic and study-related factors.

Participants were 400 adolescent students (52 percent male) from five private secondary schools in Kolkata who were studying in grades 10 and 12. Participants were selected using a multi-stage sampling technique and were assessed using a study-specific questionnaire.

Findings revealed that 35 and 37 percent reported high or very high levels of academic stress and exam anxiety respectively. All students reported high levels of academic stress, but those who had lower grades reported higher levels of stress than those with higher grades. Students who engaged in extra-curricula activities were more likely to report exam anxiety than those who did not engage in extra-curricula activities.

Private high school students in India report high levels of academic stress and exam anxiety. As such there is a need to develop effective interventions to help these students better manage their stress and anxiety.

This is the first study the authors are aware of that explores the academic stress levels of private secondary school students in India. The study identifies factors that may be associated with the experience of high levels of stress that need to be explored further in future research.

During the coronavirus disease 2019 (COVID-19) pandemic, ubiquitous social media has become a primary channel for information dissemination, social interactions and recreational activities. However, it remains unclear how social media usage influences nonpharmaceutical preventive behavior of individuals in response to the pandemic. This paper aims to explore the impacts of social media on COVID-19 preventive behaviors based on the theoretical lens of empowerment.

In this paper, survey data has been collected from 739 social media users in China to conduct structural equation modeling (SEM) analysis.

The results indicate that social media empowers individuals in terms of knowledge seeking, knowledge sharing, socializing and entertainment to promote preventive behaviors at the individual level by increasing each person's perception of collective efficacy and social cohesion. Meanwhile, social cohesion negatively impacts the relationship between collective efficacy and individual preventive behavior.

This study provides insights regarding the role of social media in crisis response and examines the role of collective beliefs in the influencing mechanism of social media. The results presented herein can be used to guide government agencies seeking to control the COVID-19 pandemic.

This paper aims to present a new intelligent wall-climbing welding robot system for large-scale steel structure manufacture, which is composed of robot body, control system and welding system.

The authors design the robot system according to application requirements, validate the design through simulation and experiments and use the robot in actual production.

Experimental results show that the robot system satisfies the demands of automatic welding of large-scale ferromagnetic structure, which contributes much to on-site manufacturing of such structures.

The robot can work with better quality and efficiency compared with manual welding and other semi-automatic welding devices, which can much improve large-scale steel structure manufacturing.

The robot system is a novel solution for large-scale steel structures welding. There are three major advantages: the robot body with reliable adsorption ability, large payload capability and good mobility which meet the requirements of welding; the control system with good welding seam tracking accuracy and intelligent automatic welding ability; and friendly human – computer interface which makes the robot easy to use.

The purposes of this study are to contribute to the limited green growth (GG) literature in emerging markets, to analyze GG from a financial economy perspective and to determine the contribution of financial development and innovation to GG in Brazil, Russian Federation, India, China and South Africa and Türkiye (BRICS-T). BRICS-T countries significantly impact the world population, international politics, energy resources and economy. In addition, BRICS-T countries are one of the leading countries in the world with their sustainability efforts. Investigating the GG model in these countries may contribute to structuring emerging economies around the principles of GG and advancing global green transformation efforts.

The authors applied panel data analysis from 2001 to 2019. GG is economic growth free from environmental depletion in the model. National income, personnel expenditure and foreign direct investments are macroeconomic variables. These variables measure economic development and promote economic and social progress, which is essential for GG. Capital accumulation and innovation are essential tools in GG transformation. Therefore, financial development and patent applications represent the moderating variables. The authors estimate the fixed effect model with Parks-Kmenta robust.

Empirical results show that national income growth and foreign direct investments positively affect GG. Personnel expenditure negatively affects GG. On the contrary, financial development and patent growth have little moderating role.

This study contributes to the literature on creating a GG model in emerging countries. The study is original in its model and sample.

In order to solve the current imbalance of academic resources within the discipline, this article builds a three-dimensional talent evaluation model based on the topic–author–citation based on the z index and proposes the ZAS index to evaluate scholars on different research topics within the discipline.

Based on the sample data of the CSSCI journals in the discipline of physical education in the past five years, the keywords were classified into 13 categories of research topics including female sports. The ZAS index of scholars on topic of female sports and so on was calculated, and quantitative indexes such as h index p index and z index were calculated. Comparative analysis of the evaluation effect was performed.

It is found that compared with the h index and p index, the z index achieves a better balance between the quantity, quality and citation distribution of scholars' results and effectively recognizes that the citation quality is higher and the number of citations of each paper is more balanced. In addition, compared to the z index, this article is based on a ZAS index model with an improved three-dimensional topic–author–citation relationship in research fields such as female sports.

It can identify some outstanding scholars who are engaged in small-scale or emerging topic research such as female sports and are excellent in different research areas. Talents create an objective and fair evaluation environment. At the same time, the ranking ability of ZAS indicators in the evaluation of talents is the strongest, and it is expected to be used in practical evaluations.

The post-COVID-19 era is characterised in the professional field by a deterioration in the psychological health of employees and by “The Great Resignation”. These phenomena require managers to rethink both organisational and HR strategies to protect their workers’ health, to retain them in their job and, in fine, to ensure the sustainability of the organisation. However, studies have demonstrated that high performance work systems (HPWS), which are currently the dominant approach in human resource management, are related to an intensification of work and consequently a deterioration of employees’ health (conflicting outcomes perspective). At the same time, workers’ well-being has been shown to be associated with numerous organisational outcomes, such as individual performance. However, relatively few articles have investigated win–win organisational practices or programmes that promote the well-being and consequently performance of workers. These include virtuous organisational practices (VOPs), which specifically aim to enhance employees’ well-being, considered not as a means to an end, but as an end in itself (mutual gains perspective). This paper aims to develop the general hypothesis that VOPs could increase employees’ performance by protecting their health and thus offer an alternative to HPWS.

We review relevant current research on psychological well-being and work performance and present innovative systems of organisational practices such as VOPs that create psychologically healthy workplaces and enhance workers’ optimal functioning (well-being and performance).

Based on theoretical arguments and empirical studies, we hypothesise that alternative practices such as VOPs can increase employees’ performance while protecting their health and encouraging them to stay in the organisation.

After this review, we discuss future avenues for research to encourage the scientific community to test this hypothesis.

Finally, we make a number of specific recommendations about how to (1) appraise, design and implement VOPs, (2) enhance organisational communication and managerial adherence to VOPs, and (3) train managers in R.I.G.H.T leadership behaviours.

Presentation of an original approach in this research field: the VOPs.

The objective of this paper is to evaluate whether the data from consignors, logistics service providers (LSPs) and consignees contribute to the prediction of air transport shipment delays in a machine learning application.

The research database contained 2,244 air freight intercontinental shipments to 4 automotive production plants in Latin America. Different algorithm classes were tested in the knowledge discovery in databases (KDD) process: support vector machine (SVM), random forest (RF), artificial neural networks (ANN) and k-nearest neighbors (KNN).

Shipper, consignee and LSP data attribute selection achieved 86% accuracy through the RF algorithm in a cross-validation scenario after a combined class balancing procedure.

These findings expand the current literature on machine learning applied to air freight delay management, which has mostly focused on weather, airport structure, flight schedule, ground delay and congestion as explanatory attributes.