Search results

The 6D pose estimation is a crucial branch of robot vision. However, the authors find that due to the failure to make full use of the complementarity of the appearance and geometry information of the object, the failure to deeply explore the contributions of the features from different regions to the pose estimation, and the failure to take advantage of the invariance of the geometric structure of keypoints, the performances of the most existing methods are not satisfactory. This paper aims to design a high-precision 6D pose estimation method based on above insights.

First, a multi-scale cross-attention-based feature fusion module (MCFF) is designed to aggregate the appearance and geometry information by exploring the correlations between appearance features and geometry features in the various regions. Second, the authors build a multi-query regional-attention-based feature differentiation module (MRFD) to learn the contribution of each region to each keypoint. Finally, a geometric enhancement mechanism (GEM) is designed to use structure information to predict keypoints and optimize both pose and keypoints in the inference phase.

Experiments on several benchmarks and real robot show that the proposed method performs better than existing methods. Ablation studies illustrate the effectiveness of each module of the authors’ method.

A high-precision 6D pose estimation method is proposed by studying the relationship between the appearance and geometry from different object parts and the geometric invariance of the keypoints, which is of great significance for various robot applications.

This paper aims to investigate the suppression of end-point vibrations in industrial robot systems that exhibit joint flexibility and are subject to external disturbances.

The real-time position tracking error is effectively decomposed by using feedforward control based on a dynamic model. Various proportional-derivative controllers and adapted versions are used to compute real-time compensation torque for different position tracking errors. This approach aims to simultaneously achieve rapid response and stability in the control system, resulting in reduced end vibration in the industrial robot.

Experiments were conducted in torque compensation on a 6R industrial robot platform. Compared to the dynamic model calculate torque feedforward compensation method, the maximum reduction of the root mean square of the position error of each joint reached 77% and the minimum reduction was 36.2%. This enhancement improves the trajectory tracking accuracy and effectively suppresses the end-effector vibration.

An improved torque feedforward compensation method is proposed and verified. According to the experimental results, the method can effectively suppress vibration and further improve the trajectory tracking accuracy.

Green innovation in human-centric smart manufacturing (HSM-GI) has emerged as a new paradigm in innovation management for Industry 5.0. The evaluation analysis method is crucial for measuring the development progress and guiding continual improvements of HSM-GI. Since this process of HSM-GI can be regarded as complex and interactive, a holistic picture is often required to describe the interrelations of its antecedents and consequences. In this respect, this study aims to construct a causality network indicator system and proposes a synergy evaluation method for HSM-GI.

Firstly, based on the Driver force-State-Response (DSR) causal-effect framework, this study constructs a holistic indicator system to analyze the interactions between environmental and human concerns of HSM-GI. Secondly, owing to the imprecision of human cognition and synergy interaction in the evaluation process, a flexible hesitant fuzzy (HF) superiority-inferiority synergetic evaluation method is presented. This method quantifies the strengths of causal relationships and expresses the incentives and constraints attitudes of humans. Finally, the proposed framework is applied to six HSMs in the electronic technology industry.

The driving force and state of the HSM-GI system exhibit an upward trend, while the response continues to decline due to changing market demands. The order and synergy degree have shown an increasing trend during 2021–2023, particularly significant for BOE and Haier Smart Home. HSM-GI systems with higher scores mostly have functional coordination and a coherent synergy structure.

This study demonstrates the proposed approach’s applicability and assists policymakers in formulating targeted strategies for green innovation systems.

This study investigated what are the effective leadership styles and practices that boost employees’ work outcomes during the COVID-19 pandemic from the perspective of facilities management professionals (FMPs).

Three predominant leadership styles (transformational, transactional contingent reward and disaster management) were operationalized into 38 leadership practices (X variables) and 8 work outcomes (Y variables). The explanatory sequential research design was adopted. Online questionnaire survey was first conducted on FMPs who managed facilities during the critical periods of COVID-19 pandemic in Singapore. In-depth interviews were then carried out with subject matter experts to elaborate on the quantitative findings.

During the pandemic, FMPs were significantly stressed at work, but also experienced significant job satisfaction and satisfaction with their leaders/supervisors. Statistical results revealed a range of leadership practices that are significantly correlated with FMPs’ work outcomes. One leadership practice is critical as it affects 4 of the 8 FMPs’ work outcomes - frequently acknowledging employees’ good performance during the pandemic.

The study explored 3 leadership styles. There are other styles like laissez faire and servant leadership that might also affect work outcomes.

Based on the findings, suggestions were provided to organizations that employ FMPs on how to improve their work outcomes during a crisis such as a pandemic.

The novelty is the discovery that in the context of a global disaster such as the COVID-19 pandemic, the most relevant leadership styles to boost employees’ work outcomes are transactional contingent reward and disaster management leadership. The study adds to knowledge by showing that not one leadership style is superior – all 3 styles are complementary, but distinct, forms of leadership that need to work in tandem to boost FMPs’ work outcomes during a crisis such as a pandemic.

This study delves into the nuanced relationship between financial constraints, ownership structures (state-owned and foreign) and innovation engagement within China’s A-share market, aiming to uncover how these dynamics vary across different industries and regional contexts.

By retrieving data from various datasets in China (2010–2022), this study analyzed the effectiveness of each variable, employing various dimensions to reflect innovation engagement among Chinese listed companies. Meanwhile, for the measurement of financial constraints, this study tested all four typical ones and opted for the KZ Index, as it is the most suitable for China’s A-share market. Then, by fixing the industry and year effects, the study examined the main and moderating effects. At last, in order to address endogeneity issues and capture the dynamic nature of innovation activities, this study follow the suggestion of Khatib (2024) and employed the two-step system Generalized Method of Moments (GMM) estimation.

The results demonstrate that while the government has introduced many policies to promote innovation, state-owned ownership does not consistently enhance innovation engagement as expected, especially when firms are in financial dilemma. Particularly, in Hi-tech industries, foreign ownership demonstrates greater interest and confidence in the innovation capabilities of China’s A-share market. Findings also reveal significant regional heterogeneity in the moderating role of ownership structures. While state-owned and foreign ownerships have a buffering effect against financial constraints in the eastern and western regions, but this effect is notably different in the middle part, even though it is China’s political heartland.

The findings offer a different insight for policymakers and corporate strategists, suggesting that targeted financial and regulatory policies that leverage specific ownership structures can foster innovation in different ways, particularly in financially constrained environments. However, how to stimulate innovation vitality in the middle part of China still requires further research.

This study aims to assess the mediating and driving roles of knowledge cooperation in the effectiveness of G60 Sci-tech Innovation Corridor (G60 STIC) for regional collaborative innovation within the knowledge economy context. Furthermore, it focuses on whether knowledge cooperation is more effective than resource cooperation in terms of spatial spillover and its mediating effects on collaborative innovation.

This study employs multiple statistical and econometric approaches, including social cooperation network, Super-DEA, spatial difference-in-difference model (SDID) and mediating effect model, to measure the effectiveness of knowledge cooperation and resource cooperation paths within the framework of the G60 STIC on regional collaborative innovation in the Yangtze River Delta region (YRD) from 2002 to 2022.

First, the knowledge cooperation networks validate the strengthening of collaborative innovation is primarily centred on provincial cities and leading manufacturing locales, with smaller cities radiating outwards from these centres. The knowledge cooperation network was generally stronger than the resource cooperation network. Second, the G60 STIC significantly enhances collaborative innovation efficiency by intensifying knowledge, resource and interactive cooperation networks. Third, within the context of the knowledge economy, knowledge cooperation presents a stronger spillover and mediating effect in stimulating collaborative innovation than resource cooperation.

This study clarifies the existence of a knowledge cooperation network and its mediating role in stimulating the effectiveness of strategic, innovative platforms on collaborative innovation. This further verifies the stronger role of the knowledge cooperation than the resource cooperation, which serves as a vital element in promoting strategic innovative platforms to optimise collaborative innovation.

Artificial intelligence (AI) customer service has grown rapidly in recent years due to the emergence of COVID-19 and the growth of the e-commerce industry. Therefore, this study employs the integration of the stimuli–organism–response (SOR) and the task-technology fit (TTF) frameworks to understand the factors that affect individuals’ intentions towards AI customer service adoption in Malaysia.

The study utilised a survey-based research approach to investigate the factors that affect individuals’ intentions towards AI customer service adoption in Malaysia. The data were collected by conducting an online survey targeting individuals aged 18 or above who had prior customer service interaction experience with human service agents but had not yet adopted AI customer service. A sample of 339 respondents was used to evaluate the hypotheses, adopting partial least squares structural equation modelling as a symmetric analytic technique.

The PLS-SEM analysis revealed that social influence and anthropomorphism have a positive direct relationship with emotional trust. Furthermore, communicative competence, technology characteristics and perceived intelligence were positively correlated with TTF. Moreover, emotional trust significantly impacts AI customer service adoption. In addition, AI readiness positively moderates the association between task technology fit and AI customer service adoption.

The study provides insights to individuals, organisations, the government and educational institutions to improve the features of AI customer service and its development in Malaysia.

The originality of this study is found in its adoption of the SOR theory and TTF to understand the factors affecting AI customer service adoption. Additionally, it incorporates moderating variables during the analysis, adding depth to the findings. This approach introduces a new perspective on the factors that impact the adoption of AI customer service and offers valuable insights for practitioners seeking to formulate effective strategies to promote its adoption.

Concrete-filled double skin steel tubes (CFDST) columns are taken more attention due to their ability to withstand high structural loads in structures such as high-rise buildings, bridges' piers, offshore and marine structures. This paper is intended to improve the CFDST column's capacity without the need to increase the column's size to maintain its lightweight by filling it with self-compacted concrete (SCC) containing nanoclay (NC).

First, experimental investigation is conducted to select the optimal NC percentage that improves the mechanical properties. Different mixing method, mixture ingredients, cement content, and NC percentage are considered. Then, slender and short CFDST columns are tested for axial capacity to investigate the effect of adding the optimum NC percentage on column's capacity and failure mode.

The test results show that adding 3% NC by cement weight using dry mixing method to SCC is the optimum ratio. It is concluded that adding 3% NC by cement weight increased the CFDST column's capacity, especially the specimens with higher slenderness ratio. Moreover, it is concluded that more specimens should be tested under various geometric and reinforcement details.

Recently, CFDST tube columns solve many structural and architectural problems that engineers have encountered in traditional systems. Therefore, more studies are required to design high-performance columns capable of carrying complex loads with high efficiency since the traditional design could not achieve the required performance. Since concrete contributes to a large portion in the axial capacity of the CFDST columns, it is proposed to improve the CFDST column's capacity without the need to increase the column's size to maintain its lightweight by filling it with (SCC containing NC. Previous research has affirmed the effectiveness of employing nanoclay in the concrete's workability, durability, microstructures, and mechanical properties.

This research aims to forecast the ABI as a leading indicator of U.S. construction activities, applying multivariate machine learning predictive models over different horizons and utilizing the nonlinear and long-term dependencies between the ABI and macroeconomic and construction market variables. To assess the applicability of the machine learning models, six multivariate machine learning predictive models were developed considering the relationships between the ABI and other construction market and macroeconomic variables. The forecasting performances of the developed predictive models were evaluated in different forecasting scenarios, such as short-term, medium-term, and long-term horizons comparable to the actual timelines of construction projects.

The architecture billings index (ABI) as a macroeconomic indicator is published monthly by the American Institute of Architects (AIA) to evaluate business conditions and track construction market movements. The current research developed multivariate machine learning models to forecast ABI data for different time horizons. Different macroeconomic and construction market variables, including Gross Domestic Product (GDP), Total Nonresidential Construction Spending, Project Inquiries, and Design Contracts data were considered for predicting future ABI values. The forecasting accuracies of the machine learning models were validated and compared using the short-term (one-year-ahead), medium-term (three-year-ahead), and long-term (five-year-ahead) ABI testing datasets.

The experimental results show that Long Short Term Memory (LSTM) provides the highest accuracy among the machine learning and traditional time-series forecasting models such as Vector Error Correction Model (VECM) or seasonal ARIMA in forecasting the ABIs over all the forecasting horizons. This is because of the strengths of LSTM for forecasting temporal time series by solving vanishing or exploding gradient problems and learning long-term dependencies in sequential ABI time series. The findings of this research highlight the applicability of machine learning predictive models for forecasting the ABI as a leading indicator of construction activities, business conditions, and market movements.

The architecture, engineering, and construction (AEC) industry practitioners, investment groups, media outlets, and business leaders refer to ABI as a macroeconomic indicator to evaluate business conditions and track construction market movements. It is crucial to forecast the ABI accurately for strategic planning and preemptive risk management in fluctuating AEC business cycles. For example, cost estimators and engineers who forecast the ABI to predict future demand for architectural services and construction activities can prepare and price their bids more strategically to avoid a bid loss or profit loss.

The ABI data have been forecasted and modeled using linear time series models. However, linear time series models often fail to capture nonlinear patterns, interactions, and dependencies among variables, which can be handled by machine learning models in a more flexible manner. Despite the strength of machine learning models to capture nonlinear patterns and relationships between variables, the applicability and forecasting performance of multivariate machine learning models have not been investigated for ABI forecasting problems. This research first attempted to forecast ABI data for different time horizons using multivariate machine learning predictive models using different macroeconomic and construction market variables.

In the vibrant world of social commerce (SC), where information flows freely, interactions thrive and online purchases abound, there is an escalating challenge. Users are uninstalling and disengaging due to approach and avoidance stimuli, a trend mirroring the approach-avoidance motivation model (AAMM). Our study, anchored in AAMM and the stimulus-organism-response (SOR) model, aims to dive into the complex dynamics of these factors that shape users' SC continuance intentions.

Our findings, drawn from 472 SC users in Malaysia, paint an intriguing research framework via PLS-SEM analysis by testing the proposed hypotheses. A purposive sampling technique was utilized, deliberately selecting respondents based on specific criteria. Subsequently, data were gathered through the distribution of face-to-face questionnaires at selected shopping malls, facilitating a focused and comprehensive exploration of consumer perspectives.

The empirical results demonstrate the following: (1) Users' determination to stay engaged on SC platforms hinges on approach factors, like emotional support, surveillance gratification and multisensory gratification. (2) Simultaneously, avoidance factors such as technostress and perceived deception exert their negative influence. (3) Flow experience, rooted in flow theory, emerges as the underlying mechanism connecting these duality stimuli, influencing the continuance intention.

In a departure from conventional research, our study pioneers a comprehensive approach and boldly confronts the research gap by introducing a rich tapestry of antecedents, embracing both the appeal of approach factors and the deterrence of avoidance ones, using the AAMM that sheds light on how individuals navigate between embracing opportunities and avoiding pitfalls based on perceived gains and losses. This holistic approach enables us to redefine our understanding of digital engagement dynamics, offering a captivating journey into the realm of user experience and intention that transcends the ordinary.