Search results

In the COVID-19 era, sign language (SL) translation has gained attention in online learning, which evaluates the physical gestures of each student and bridges the communication gap between dysphonia and hearing people. The purpose of this paper is to devote the alignment between SL sequence and nature language sequence with high translation performance.

SL can be characterized as joint/bone location information in two-dimensional space over time, forming skeleton sequences. To encode joint, bone and their motion information, we propose a multistream hierarchy network (MHN) along with a vocab prediction network (VPN) and a joint network (JN) with the recurrent neural network transducer. The JN is used to concatenate the sequences encoded by the MHN and VPN and learn their sequence alignments.

We verify the effectiveness of the proposed approach and provide experimental results on three large-scale datasets, which show that translation accuracy is 94.96, 54.52, and 92.88 per cent, and the inference time is 18 and 1.7 times faster than listen-attend-spell network (LAS) and visual hierarchy to lexical sequence network (H2SNet) , respectively.

In this paper, we propose a novel framework that can fuse multimodal input (i.e. joint, bone and their motion stream) and align input streams with nature language. Moreover, the provided framework is improved by the different properties of MHN, VPN and JN. Experimental results on the three datasets demonstrate that our approaches outperform the state-of-the-art methods in terms of translation accuracy and speed.

This study discusses the tracking trajectory issue of the exoskeleton under the bounded disturbance and designs an useful tracking trajectory control method to solve it. By using the proposed control method, the tracking error can be successfully convergence to the assigned boundary. Meanwhile, the chattering effect caused by the actuators is already reduced, and the tracking performance of the pneumatic artificial muscles (PAMs) elbow exoskeleton is improved effectively.

A prescribed performance sliding mode control method was developed in this study to fulfill the joint position tracking trajectory task on the elbow exoskeleton driven by two PAMs. In terms of the control structure, a dynamic model was built by conforming to the adaptive law to compensate for the time variety and uncertainty exhibited by the system. Subsequently, a super-twisting algorithm-based second-order sliding mode control method was subjected to the exoskeleton under the boundedness of external disturbance. Moreover, the prescribed performance control method exhibits a smooth prescribed function with an error transformation function to ensure the tracking error can be finally convergent to the pre-designed requirement.

From the theoretical perspective, the stability of the control method was verified through Lyapunov synthesis. On that basis, the tracking performance of the proposed control method was confirmed through the simulation and the manikin model experiment.

As revealed by the results of this study, the proposed control method sufficiently applies to the PAMs elbow exoskeleton for tracking trajectory, which means it has potential application in the actual robot-assisted passive rehabilitation tasks.

Bayesian cubature (BC) has emerged to be one of most competitive approach for estimating the multi-dimensional integral especially when the integrand is expensive to evaluate, and alternative acquisition functions, such as the Posterior Variance Contribution (PVC) function, have been developed for adaptive experiment design of the integration points. However, those sequential design strategies also prevent BC from being implemented in a parallel scheme. Therefore, this paper aims at developing a parallelized adaptive BC method to further improve the computational efficiency.

By theoretically examining the multimodal behavior of the PVC function, it is concluded that the multiple local maxima all have important contribution to the integration accuracy as can be selected as design points, providing a practical way for parallelization of the adaptive BC. Inspired by the above finding, four multimodal optimization algorithms, including one newly developed in this work, are then introduced for finding multiple local maxima of the PVC function in one run, and further for parallel implementation of the adaptive BC.

The superiority of the parallel schemes and the performance of the four multimodal optimization algorithms are then demonstrated and compared with the k-means clustering method by using two numerical benchmarks and two engineering examples.

Multimodal behavior of acquisition function for BC is comprehensively investigated. All the local maxima of the acquisition function contribute to adaptive BC accuracy. Parallelization of adaptive BC is realized with four multimodal optimization methods.

This study aims to fabricate a multifunctional electromagnetic interference (EMI) shielding composite fabric with simultaneous high-efficiency photothermal conversion and Joule heating performances.

A multifunctional polypyrrole (PPy) hydrogel/multiwalled carbon nanotube (MWCNT)/cotton EMI shielding composite fabric (hereafter denoted as PHMC) was prepared by loading MWCNT onto tannin-treated cotton fabric, followed by in situ crosslinking-polymerization to synthesize three-dimensional (3D) conductive networked PPy hydrogel on the surface of MWCNT-coated cotton fabric.

Benefiting from the unique interconnected 3D networked conductive structure of PPy hydrogel, the obtained PHMC exhibited a high EMI-shielding effectiveness vale of 48 dB (the absorbing electromagnetic wave accounted for 84%) within a large frequency range (8.2–12.4 GHz). Moreover, the temperature of the laminated fabric reached 54°C within 900 s under 15 V, and it required more than 100 s to return to room temperature (28.7°C). When the light intensity was adjusted to 150 mW/cm², the PHMC temperature was about 38.2°C after lighting for 900 s, indicating high-efficiency electro-photothermal effect function.

This paper provides a novel strategy for designing a type of multifunctional EMI shielding composite fabric with great promise for wearable smart garments, EMI shielding and personal heating applications.

Corporate social responsibility (CSR) practices frequently result in increased costs for Chinese international contractors (CICs), where profitability is the primary objective; therefore, internal corporate drivers and external pressures play a crucial role in encouraging them to engage in sustainable CSR practices. This study systematically examines the dynamic impact of internal and external stakeholders on the CSR practices of CICs.

This study adopted a structural equation model (SEM) to identify and validate a correlation between stakeholders and CSR practices. Standardized causal coefficients estimated in SEM were used to construct a fuzzy cognitive map (FCM) model to illustrate the effect of stakeholders on CSR practices with linkage direction and weights. Predictive, diagnostic, and hybrid analyses were performed to dynamically model the variation in stakeholders on the evolution of CSR practices.

The empirical results demonstrate that (1) employee participation in CSR has the greatest impact on CSR practices, followed by CSR strategies, partner and customer expectations, and finally government regulations. (2) In the early stage of CSR fulfillment, CSR strategies have the greatest influence on CSR practices; in the later stage of CSR fulfillment, employee participation in CSR has the greatest influence on CSR practices. (3) In the long run, the most effective and economical integrated interventions are those that address employee participation in CSR, partner expectations and customer expectations, and intervention in CSR strategies is needed if the level of CSR practice needs to be improved in the short term.

This study contributes to the research on the influence mechanisms of CSR practices of CICs and systematically analyzes their dynamic influence on CSR practices of CICs from the perspective of stakeholders.

This study aims to assess financial development and debt status impact on energy efficiency in Nigeria as a developing economy.

This study combined the autoregressive distributed lag (ARDL), fully modified ordinary least squares and canonical cointegration regression analytical methods to estimate the parameters for energy efficiency policy recommendations. Secondary data between 1990 and 2020 were used for the analysis.

The result confirms the long-run nexus between energy efficiency, financial development and total debt stock. Furthermore, the ARDL estimates for this study’s key variables show that financial development promotes energy efficiency in the short run but hinders long-run energy efficiency. Total debt stock limits energy efficiency in Nigeria in short- and long-run periods.

The limitation of this study is that the scope is limited to Nigeria as a developing economy. The need to support energy efficiency projects is a global call requiring cross-country analysis. Despite this study’s focus on Nigeria, it provides useful insights that can guide energy efficiency policy through the financial sector and debt management.

The financial sector must ensure the availability of long-term credit facilities to clean energy investors. The government must maintain a sustainable debt profile to pave the way for capital expenditure on clean energy projects that promote energy efficiency.

The environmental consequences of energy intensity are being felt globally, with the developing countries most vulnerable. The cheapest way to curb these consequences is to promote energy efficiency to reduce the disastrous effect. Driving energy efficiency requires investment in energy-efficient technology but the challenge for developing economies, i.e. Nigeria’s funding, remains challenging amid a blotted debt profile. This becomes crucial to investigate how financial sector development and debt management can accelerate energy-efficient investments in Nigeria.

Robotic arms’ interactions with the external environment are growing more intricate, demanding higher control precision. This study aims to enhance control precision by establishing a dynamic model through the identification of the dynamic parameters of a self-designed robotic arm.

This study proposes an improved particle swarm optimization (IPSO) method for parameter identification, which comprehensively improves particle initialization diversity, dynamic adjustment of inertia weight, dynamic adjustment of local and global learning factors and global search capabilities. To reduce the number of particles and improve identification accuracy, a step-by-step dynamic parameter identification method was also proposed. Simultaneously, to fully unleash the dynamic characteristics of a robotic arm, and satisfy boundary conditions, a combination of high-order differentiable natural exponential functions and traditional Fourier series is used to develop an excitation trajectory. Finally, an arbitrary verification trajectory was planned using the IPSO to verify the accuracy of the dynamical parameter identification.

Experiments conducted on a self-designed robotic arm validate the proposed parameter identification method. By comparing it with IPSO1, IPSO2, IPSOd and least-square algorithms using the criteria of torque error and root mean square for each joint, the superiority of the IPSO algorithm in parameter identification becomes evident. In this case, the dynamic parameter results of each link are significantly improved.

A new parameter identification model was proposed and validated. Based on the experimental results, the stability of the identification results was improved, providing more accurate parameter identification for further applications.

This study investigates the influence of artificial intelligence (AI) stimuli on customer stickiness (CS), the mediation effects of social presence (SP) and the moderating impacts of customer traits in this influencing process.

Drawing on the arousal theory and social response theory, a conceptual model was established and tested by a data set of 268 customers in the catering industry.

The results indicate that AI stimuli, such as perceived personalization and perceived interactivity, positively affect CS. SP partially mediates the influence of AI stimuli on CS. Customer traits such as customers' need for interaction (NFI) and novelty seeking (NS) actively moderate the mediating effects of SP.

This study advances the interactive marketing literature from three aspects. Firstly, instead of focusing on the functional aspects of AI stimuli, it extends our understanding of AI-enabled interactive marketing by examining the effects of social and emotional aspects of AI stimuli on customer response. Secondly, it extends our understanding of social response by illuminating the mediating effects of SP between AI stimuli and CS. Finally, it provides new insights and empirical evidence for the research focus on customer traits in AI-enabled interactive marketing.

Currently, the Tang tomb mural cultural relic resources are presented in a multi-source and heterogeneous manner, with a lack of effective organization and sharing between resources. Therefore, this study aims to propose a multidimensional knowledge discovery solution for Tang tomb mural cultural relic resources.

Taking the Tang tomb murals collected by the Shaanxi History Museum as an example, based on clarifying the relevant concepts of Tang tomb mural resources and considering both dynamic and static dimensions, a top-down approach was adopted to first construct an ontology model of Tang tomb mural type cultural relics resources. Then, the actual case data was imported into the Neo4J graph database according to the defined pattern hierarchy to complete the static organization of knowledge, and presented in a multimodal form in knowledge reasoning and retrieval. In addition, geographic information system (GIS) technology is used to dynamically display the spatiotemporal distribution of Tang tomb mural resources, and the distribution trend is analysed from a digital humanistic perspective.

The multi-dimensional knowledge discovery of Tang tomb mural cultural relics resources can help establish the correlation and spatiotemporal relationship between resources, providing support for semantic retrieval and navigation, knowledge discovery and visualization and so on.

This study takes the murals in the collection of the Shaanxi History Museum as an example, revealing potential knowledge associations in a static and intelligent way, achieving knowledge discovery and management of Tang tomb murals, and dynamically presents the spatial distribution of Tang tomb murals through GIS technology, meeting the knowledge presentation needs of different users and opening up new ideas for the study of Tang tomb murals.

As an advanced manufacturing method, additive manufacturing (AM) technology provides new possibilities for efficient production and design of parts. However, with the continuous expansion of the application of AM materials, subtractive processing has become one of the necessary steps to improve the accuracy and performance of parts. In this paper, the processing process of AM materials is discussed in depth, and the surface integrity problem caused by it is discussed.

Firstly, we listed and analyzed the characterization parameters of metal surface integrity and its influence on the performance of parts and then introduced the application of integrated processing of metal adding and subtracting materials and the influence of different processing forms on the surface integrity of parts. The surface of the trial-cut material is detected and analyzed, and the surface of the integrated processing of adding and subtracting materials is compared with that of the pure processing of reducing materials, so that the corresponding conclusions are obtained.

In this process, we also found some surface integrity problems, such as knife marks, residual stress and thermal effects. These problems may have a potential negative impact on the performance of the final parts. In processing, we can try to use other integrated processing technologies of adding and subtracting materials, try to combine various integrated processing technologies of adding and subtracting materials, or consider exploring more efficient AM technology to improve processing efficiency. We can also consider adopting production process optimization measures to reduce the processing cost of adding and subtracting materials.

With the gradual improvement of the requirements for the surface quality of parts in the production process and the in-depth implementation of sustainable manufacturing, the demand for integrated processing of metal addition and subtraction materials is likely to continue to grow in the future. By deeply understanding and studying the problems of material reduction and surface integrity of AM materials, we can better meet the challenges in the manufacturing process and improve the quality and performance of parts. This research is very important for promoting the development of manufacturing technology and achieving success in practical application.