Search results

The purpose of this paper is to model and predict suitable gait trajectories of lower-limb exoskeleton for wearer during rehabilitation walking. Lower-limb exoskeleton is widely used for assisting walk in rehabilitation field. One key problem for exoskeleton control is to model and predict suitable gait trajectories for wearer.

In this paper, the authors propose a Deep Spatial-Temporal Model (DSTM) for generating knee joint trajectory of lower-limb exoskeleton, which first leverages Long-Short Term Memory framework to learn the inherent spatial-temporal correlations of gait features.

With DSTM, the pathological knee joint trajectories can be predicted based on subject’s other joints. The energy expenditure is adopted for verifying the effectiveness of new recovery gait pattern by monitoring dynamic heart rate. The experimental results demonstrate that the subjects have less energy expenditure in new recovery gait pattern than in others’ normal gait patterns, which also means the new recovery gait is more suitable for subject.

Long-Short Term Memory framework is first used for modeling rehabilitation gait, and the deep spatial–temporal relationships between joints of gait data can obtained successfully.

The purpose of this paper is to present an automatic approach for mesh sizing field generation of complicated  computer-aided design (CAD) models.

In this paper, the authors present an automatic approach for mesh sizing field generation. First, a source point extraction algorithm is applied to capture curvature and proximity features of CAD models. Second, according to the distribution of feature source points, an octree background mesh is constructed for storing element size value. Third, mesh size value on each node of background mesh is calculated by interpolating the local feature size of the nearby source points, and then, an initial mesh sizing field is obtained. Finally, a theoretically guaranteed smoothing algorithm is developed to restrict the gradient of the mesh sizing field.

To achieve high performance, the proposed approach has been implemented in multithreaded parallel using OpenMP. Numerical results demonstrate that the proposed approach is remarkably efficient to construct reasonable mesh sizing field for complicated CAD models and applicable for generating geometrically adaptive triangle/tetrahedral meshes. Moreover, since the mesh sizing field is defined on an octree background mesh, high-efficiency query of local size value could be achieved in the following mesh generation procedure.

How to determine a reasonable mesh size for complicated CAD models is often a bottleneck of mesh generation. For the complicated models with thousands or even ten thousands of geometric entities, it is time-consuming to construct an appropriate mesh sizing field for generating high-quality mesh. A parallel algorithm of mesh sizing field generation with low computational complexity is presented in this paper, and its usability and efficiency have been verified.

Automatic mesh generation is still a challenge problem for combustion fluid dynamics simulations because of the high-quality requirement and complexity of geometries. This paper aims to find an efficient automatic analysis model creation and mesh generation method to save the time for pre-processing in numerical simulations.

Based on the previous work, we explore effective model processing and mesh generation methods from practical engineering applications. Considering the automation and high quality requirement, we construct an automatic mesh generation procedure for combustion fluid dynamics problems.

The numerical results show that the procedure we proposed in this paper can automatically generate high quality mesh for combustion fluid dynamics simulations. The strategy of fluid model construction is time-saving and with high-precision. The mesh generation method in our procedure is automatic and efficient.

The procedure proposed in this paper is applicable to the practical engineering application model, such as aircraft simulation, aeroengine simulation and so on. The procedure has been integrated into an numerical simulation software.

The method proposed in this paper has very practical application value. It can be used in the practical application and saves a lot of manual processing time for numerical stimulation specialists.

In the digital era, creativity is pivotal in marketing, particularly in advertising, where mobile short-video advertising (MSA) has surged in popularity. However, the mechanism of how advertising creativity influences consumer decision-making remains understudied. We scrutinize how MSAs’ creativity influences consumers' purchase and sharing intentions.

This study uses 40 selected creative MSAs to collect a total of 666 valid questionnaires.

The results show that the exertion of creativity in MSAs positively impacts consumer intentions through perceived surprises and mental simulation, with the optimal stimulus level moderating these effects.

Our findings provide practical recommendations for brands and advertisers, mainly in terms of the impact of advertising creativity on advertising content strategy, helping them to create effective advertising to capture market and traffic by focusing on the content (relevance) and format (novelty) of advertising.

This study conducted in-depth research using the cognitive-affective-behavior (CAB) paradigm, integrated with mental simulation theory and the optimum stimulation level theory. Innovatively, we developed a model of the consumer decision-making process based on creativity, which enhances the research on the mechanisms underlying the consumer decision-making process.

Perception has been identified as the main cause underlying most autonomous vehicle related accidents. As the key technology in perception, deep learning (DL) based computer vision models are generally considered to be black boxes due to poor interpretability. These have exacerbated user distrust and further forestalled their widespread deployment in practical usage. This paper aims to develop explainable DL models for autonomous driving by jointly predicting potential driving actions with corresponding explanations. The explainable DL models can not only boost user trust in autonomy but also serve as a diagnostic approach to identify any model deficiencies or limitations during the system development phase.

This paper proposes an explainable end-to-end autonomous driving system based on “Transformer,” a state-of-the-art self-attention (SA) based model. The model maps visual features from images collected by onboard cameras to guide potential driving actions with corresponding explanations, and aims to achieve soft attention over the image’s global features.

The results demonstrate the efficacy of the proposed model as it exhibits superior performance (in terms of correct prediction of actions and explanations) compared to the benchmark model by a significant margin with much lower computational cost on a public data set (BDD-OIA). From the ablation studies, the proposed SA module also outperforms other attention mechanisms in feature fusion and can generate meaningful representations for downstream prediction.

In the contexts of situational awareness and driver assistance, the proposed model can perform as a driving alarm system for both human-driven vehicles and autonomous vehicles because it is capable of quickly understanding/characterizing the environment and identifying any infeasible driving actions. In addition, the extra explanation head of the proposed model provides an extra channel for sanity checks to guarantee that the model learns the ideal causal relationships. This provision is critical in the development of autonomous systems.

This study aims to elucidate the causal relationship between corporate greenwashing and celebrity leaders.

This study considers winning the National Model Worker Award as an external shock for producing celebrity leaders and conducts a difference-in-difference (DID) estimation with listed companies from 2009 to 2022 in the Chinese context.

The findings indicate an increase in greenwashing of companies with celebrity leaders in the post-award period. Stakeholder pressure can moderate the effect of celebrity leaders on corporate greenwashing.

This study enriches the research on the antecedents of greenwashing and the impacts of celebrity leaders. The findings advance the understanding of the real effect of celebrity leaders on environmental, social and governance (ESG) efforts and provide new insights into how celebrities respond to legitimacy pressures.

This study examines whether common directors are guilty of contagion of corporate frauds from the customer side and, if so, how contagion occurs. Moreover, it explores a way to mitigate it, which is the increased digital orientation of firms.

Secondary data analysis is applied in this paper. We extract supply chain relations from the China Stock Market and Account Research (CSMAR) database as well as corporate fraud data from the same database and the official website of the China Securities Regulatory Commission (CSRC). Digital orientations are estimated through text analysis. Poisson regression is conducted to examine the moderating effect of common directors and the moderated moderating effect of the firms’ digital orientations.

By analysing the 2,096 downstream relations from 2000 to 2021 in China, the study reveals that corporate frauds are contagious through supply chains, while only customers’ misconduct can contagion to upstream firms. The presence of common directors strengthens such supply chain contagion. Additionally, the digital orientation can mitigate the positive moderating effect of common directors on supply chain contagion.

This study highlights the importance of understanding supply chain contagion through corporate fraud by (1) emphasising the existence of the contagion effects of corporate frauds; (2) understanding the potential channel in the process of contagion; (3) considering how digital orientation can mitigate this contagion and (4) recognising that the effect of contagion comes only from the downstream, not from the upstream.

The purpose of this study is to generate insight into the effects of entrepreneurship education in China by conducting a preliminary scoping study of the enterprising tendency of university students studying business.

This study used a self-administered questionnaire based on the General Measure of Enterprising Tendency v2 (GET2) test to measure the enterprising tendency of a group of Chinese university students. Decision trees, using the Chi-square automatic interaction detector (CHAID) approach, and multiple regression analyses were used to investigate the enterprising tendency of respondents.

The findings from this study indicate that the students have an overall medium level of enterprising tendency and strengths in some enterprising characteristics. The findings reveal that gender, family business, hometown and entrepreneurship education are significantly related to enterprising tendency but that age, household income, parents’ education and occupation are not.

Although the study is based on a relatively small sample taken from just one university in Beijing, the findings suggest that the enterprising tendency of students can be encouraged by entrepreneurship education. Combined with evidence that entrepreneurship education is at a relatively early stage of development in China, this finding suggests considerable scope to increase student’s enterprising tendency by extending, creating a more favourable environment for and improving the methods used to deliver entrepreneurship education. Enterprising tendency can be argued to naturally result in entrepreneurial intention; however, this extension is beyond the scope of this study, which is restricted to the analysis of enterprising tendency.

This study makes an original contribution to knowledge as it is one of the first studies to explore enterprising tendency among university students in China. It has value for government, policymakers and university program designers in that it provides direction for entrepreneurship education in China.

Internet marketing underground industry users refer to people who use technology means to simulate a large number of real consumer behaviors to obtain marketing activities rewards illegally, which leads to increased cost of enterprises and reduced effect of marketing. Therefore, this paper aims to construct a user risk assessment model to identify potential underground industry users to protect the interests of real consumers and reduce the marketing costs of enterprises.

Method feature extraction is based on two aspects. The first aspect is based on traditional statistical characteristics, using density-based spatial clustering of applications with noise clustering method to obtain user-dense regions. According to the total number of users in the region, the corresponding risk level of the receiving address is assigned. So that high-quality address information can be extracted. The second aspect is based on the time period during which users participate in activities, using frequent item set mining to find multiple users with similar operations within the same time period. Extract the behavior flow chart according to the user participation, so that the model can mine the deep relationship between the participating behavior and the underground industry users.

Based on the real underground industry user data set, the features of the data set are extracted by the proposed method. The features are experimentally verified by different models such as random forest, fully-connected layer network, SVM and XGBOST, and the proposed method is comprehensively evaluated. Experimental results show that in the best case, our method can improve the F1-score of traditional models by 55.37%.

This paper investigates the relative importance of static information and dynamic behavior characteristics of users in predicting underground industry users, and whether the absence of features of these categories affects the prediction results. This investigation can go a long way in aiding further research on this subject and found the features which improved the accuracy of predicting underground industry users.

In the era of big data, various industries are generating large amounts of text data every day. Simplifying and summarizing these data can effectively serve users and improve efficiency. Recently, zero-shot prompting in large language models (LLMs) has demonstrated remarkable performance on various language tasks. However, generating a very “concise” multi-document summary is a difficult task for it. When conciseness is specified in the zero-shot prompting, the generated multi-document summary still contains some unimportant information, even with the few-shot prompting. This paper aims to propose a LLMs prompting for multi-document summarization task.

To overcome this challenge, the authors propose chain-of-event (CoE) prompting for multi-document summarization (MDS) task. In this prompting, the authors take events as the center and propose a four-step summary reasoning process: specific event extraction; event abstraction and generalization; common event statistics; and summary generation. To further improve the performance of LLMs, the authors extend CoE prompting with the example of summary reasoning.

Summaries generated by CoE prompting are more abstractive, concise and accurate. The authors evaluate the authors’ proposed prompting on two data sets. The experimental results over ChatGLM2-6b show that the authors’ proposed CoE prompting consistently outperforms other typical promptings across all data sets.

This paper proposes CoE prompting to solve MDS tasks by the LLMs. CoE prompting can not only identify the key events but also ensure the conciseness of the summary. By this method, users can access the most relevant and important information quickly, improving their decision-making processes.