Search results

Assembly action recognition plays an important role in assembly process monitoring and human-robot collaborative assembly. Previous works overlook the interaction relationship between hands and operated objects and lack the modeling of subtle hand motions, which leads to a decline in accuracy for fine-grained action recognition. This paper aims to model the hand-object interactions and hand movements to realize high-accuracy assembly action recognition.

In this paper, a novel multi-stream hand-object interaction network (MHOINet) is proposed for assembly action recognition. To learn the hand-object interaction relationship in assembly sequence, an interaction modeling network (IMN) comprising both geometric and visual modeling is exploited in the interaction stream. The former captures the spatial location relation of hand and interacted parts/tools according to their detected bounding boxes, and the latter focuses on mining the visual context of hand and object at pixel level through a position attention model. To model the hand movements, a temporal enhancement module (TEM) with multiple convolution kernels is developed in the hand stream, which captures the temporal dependences of hand sequences in short and long ranges. Finally, assembly action prediction is accomplished by merging the outputs of different streams through a weighted score-level fusion. A robotic arm component assembly dataset is created to evaluate the effectiveness of the proposed method.

The method can achieve the recognition accuracy of 97.31% and 95.32% for coarse and fine assembly actions, which outperforms other comparative methods. Experiments on human-robot collaboration prove that our method can be applied to industrial production.

The author proposes a novel framework for assembly action recognition, which simultaneously leverages the features of hands, objects and hand-object interactions. The TEM enhances the representation of dynamics of hands and facilitates the recognition of assembly actions with various time spans. The IMN learns the semantic information from hand-object interactions, which is significant for distinguishing fine assembly actions.

The purpose of this research is to provide a theoretical and practical theory and application that provides understanding and means to manage complex infrastructures.

In this research, complexity, nonlinear, noncontinuous effects and aleatoric and data unknowns are bypassed by directly addressing systems' responses. Graph theory, statistics and digital signal processing (DSP) tools are applied within a theoretical framework of the theory of faults (ToF). Motivational complex infrastructure systems (CISs) are difficult to model. Data are often missing or erroneous, changes are not well documented and processes are not well understood. On top of it, under complexity, stalwart analytical tools have limited predictive power. The aleatoric risk, such as rain and risk cascading from interconnected infrastructures, is unpredictable. Mitigation, response and recovery efforts are adversely affected.

The theory and application are presented and demonstrated by a step-by-step development of an application to a municipal drainage system. A database of faults is analyzed to produce system statistics, spatio-temporal morphology, behavior and traits. The gained understanding is compared to the physical system's design and to its modus operandi. Implications for design and maintenance are inferred; DSP tools to manage the system in real time are developed.

Sociological systems are interest driven. Some events are intentionally created and directed to the benefit and detriment of the opposing parties in a project. Those events may be explained and possibly predicted by understanding power plays, not power functions. For those events, sociological game theories provide better explanatory value than mathematical gain theories.

The theory provides a thematic network for modeling and resolving aleatoric uncertainty in engineering and sociological systems. The framework may be elaborated to fields such as energy, healthcare and critical infrastructure.

ToF provides a framework for the modeling and prediction of faults generated by inherent aleatoric uncertainties in social and technological systems. Therefore, the framework and theory lay the basis for automated monitoring and control of aleatoric uncertainties such as mechanical failures and human errors and the development of mitigation systems.

The contribution of this research is in the provision of an explicatory theory and a management paradigm for complex systems. This theory is applicable to a wide variety of fields from facilities and construction project management to maintenance and from academic studies to commercial use.

This paper aims to empirically investigate the typologies of phygital (synaeresis of “physical” and “digital”) customer experiences (CXs) that can arise in high-tech retail based on the intensity of consumers' responses and reactions to the stimuli triggered by firms. Moreover, it explores how firms attempt to shape the architecture of the phygital CXs. Notably, this article identifies the flexible and agile strategies implemented by firms to enhance the several typologies of phygital CXs, with the intention of better exploiting physical and digital features to respond to the differences in customers' needs, preferences and expectations.

This study performs an in-depth exploratory single-case study based on semi-structured interviews with the customers, managers and employees of the Webidoo Store.

This study develops a framework illustrating the main typologies of ordinary (“hostile”, “controversial” and “disappointing”) and extraordinary (“passionate” and “explorative”) CXs that can arise in phygital contexts. Also, it identifies some key flexible and agile strategies (“decompressive strategy”, “mentoring strategy”, “prompting strategy” and “entertaining strategy”) that companies might follow to adjust their offerings and respond quickly to the different forms of phygital CXs to create a more compelling experience tailored to customers' needs, preferences and expectations.

Among the study's limitations are the single-case study methodology and a specific setting like the Italian one. As a result, future studies could broaden the study to include other research contexts and countries. The paper offers significant managerial insights based on the many forms of CX across ordinary and extraordinary CXs. Thus, it provides critical takeaways for businesses to meet customer demand.

This paper analyzes the different typologies of ordinary and extraordinary CXs that could occur in phygital contexts based on the intensity of consumers' responses and reactions to firms' stimuli. Also, it explores how firms attempt to shape the architecture of the phygital CXs through flexible and agile strategies. From this paper, managers and decision-makers can reflect on successful strategies they could use to affect the stimuli to which customers respond in an agile manner, thus enhancing phygital CXs.

The purpose of this paper is to present a method that addresses the data sparsity problem in points of interest (POI) recommendation by introducing spatiotemporal context features based on location-based social network (LBSN) data. The objective is to improve the accuracy and effectiveness of POI recommendations by considering both spatial and temporal aspects.

To achieve this, the paper introduces a model that integrates the spatiotemporal context of POI records and spatiotemporal transition learning. The model uses graph convolutional embedding to embed spatiotemporal context information into feature vectors. Additionally, a recurrent neural network is used to represent the transitions of spatiotemporal context, effectively capturing the user’s spatiotemporal context and its changing trends. The proposed method combines long-term user preferences modeling with spatiotemporal context modeling to achieve POI recommendations based on a joint representation and transition of spatiotemporal context.

Experimental results demonstrate that the proposed method outperforms existing methods. By incorporating spatiotemporal context features, the approach addresses the issue of incomplete modeling of spatiotemporal context features in POI recommendations. This leads to improved recommendation accuracy and alleviation of the data sparsity problem.

The research has practical implications for enhancing the recommendation systems used in various location-based applications. By incorporating spatiotemporal context, the proposed method can provide more relevant and personalized recommendations, improving the user experience and satisfaction.

The paper’s contribution lies in the incorporation of spatiotemporal context features into POI records, considering the joint representation and transition of spatiotemporal context. This novel approach fills the gap left by existing methods that typically separate spatial and temporal modeling. The research provides valuable insights into improving the effectiveness of POI recommendation systems by leveraging spatiotemporal information.

This study explores the spatial and temporal relationship between tourism activities and transportation-related carbon dioxide (CO₂) emissions in the United States (US) from 2003 to 2022 using advanced geospatial modeling techniques.

The research integrated geographic information systems (GIS) to map tourist attractions against high-resolution annual emissions data. The analysis covered 3,108 US counties, focusing on county-level attraction densities and annual on-road CO₂ emission patterns. Advanced spatial analysis techniques, including bivariate mapping and local bivariate relationship testing, were employed to assess potential correlations.

The findings reveal limited evidence of significant associations between tourism activities and transportation-based CO₂ emissions around major urban centers, with decreases observed in Eastern states and the Midwest, particularly in non-coastal areas, from 2003 to 2022. Most counties (86.03%) show no statistically significant relationship between changes in tourism density and on-road CO₂ emissions. However, 1.90% of counties show a positive linear relationship, 2.64% a negative linear relationship, 0.29% a concave relationship, 1.61% a convex relationship and 7.63% a complex, undefined relationship. Despite this, the 110% national growth in tourism output and resource consumption from 2003–2022 raises potential sustainability concerns.

To tackle sustainability issues in tourism, policymakers and stakeholders can integrate emissions accounting, climate modeling and sustainability governance. Effective interventions are vital for balancing tourism demands with climate resilience efforts promoting social equity and environmental justice.

This study’s innovative application of geospatial modeling and comprehensive spatial analysis provides new insights into the complex relationship between tourism activities and CO₂ emissions. The research highlights the challenges in isolating tourism’s specific impacts on emissions and underscores the need for more granular geographic assessments or comprehensive emission inventories to fully understand tourism’s environmental footprint.

Accurate prediction of the structural condition of urban critical infrastructure is crucial for predictive maintenance. However, the existing prediction methods lack precision due to limitations in utilizing heterogeneous sensing data and domain knowledge as well as insufficient generalizability resulting from limited data samples. This paper integrates implicit and qualitative expert knowledge into quantifiable values in tunnel condition assessment and proposes a tunnel structure prediction algorithm that augments a state-of-the-art attention-based long short-term memory (LSTM) model with expert rating knowledge to achieve robust prediction results to reasonably allocate maintenance resources.

Through formalizing domain experts' knowledge into quantitative tunnel condition index (TCI) with analytic hierarchy process (AHP), a fusion approach using sequence smoothing and sliding time window techniques is applied to the TCI and time-series sensing data. By incorporating both sensing data and expert ratings, an attention-based LSTM model is developed to improve prediction accuracy and reduce the uncertainty of structural influencing factors.

The empirical experiment in Dalian Road Tunnel in Shanghai, China showcases the effectiveness of the proposed method, which can comprehensively evaluate the tunnel structure condition and significantly improve prediction performance.

This study proposes a novel structure condition prediction algorithm that augments a state-of-the-art attention-based LSTM model with expert rating knowledge for robust prediction of structure condition of complex projects.

The study aims to enhance energy efficiency within the high-energy consuming construction industry. It explores the spatial-temporal dynamics and distribution patterns of total factor energy efficiency (TFEE) across China’s construction industry, aiming to inform targeted emission reduction policies at provincial and city levels.

Utilizing a three-stage super-efficiency SBM-DEA model that integrates carbon emissions, the TFEE in 30 Chinese provinces and cities from 2004 to 2019 is assessed. Through kernel density estimation and exploratory spatial data analysis, the dynamic evolution and spatial patterns of TFEE are examined.

Analysis reveals that environmental investments positively impact TFEE, whereas Gross Regional Product (GRP) exerts a negative influence. R&D expenditure intensity and marketization show mixed effects. Excluding environmental and random factors, TFEE averages declined, aligning more closely with actual development trends, showing a gradual decrease from east to west. TFEE exhibited fluctuating growth with a trend moving from inefficient clusters to a more even distribution. Spatially, TFEE demonstrated aggregation effects and characteristics of space-time transition.

This research employs the three-stage super-efficiency SBM-DEA model to measure the total factor energy efficiency of the construction industry, taking into account external environment, random disturbances, and multiple effective decision-making units. It also evaluates energy efficiency changes before and after removing disturbances and comprehensively examines regional and temporal differences from static and dynamic, overall and phased perspectives. Additionally, Moran scatter plots and LISA cluster maps are used to objectively analyze the spatial agglomeration and factors influencing energy efficiency.

This article aims to develop and validate a theoretical model via survey data to identify the affordances and challenges influencing metaverse adoption. We specifically examine the impact of immersion on users' adoption decisions and identify which affordances predict this immersion. Additionally, this paper assesses the importance of perceived risks in users' decision-making processes regarding future metaverse engagement.

Using regression models applied to 198 survey responses, we tested our proposed model. To deepen our insights, we also conducted a qualitative analysis.

The findings confirm that users' perceptions of immersion and perceived risks are critical determinants in adoption decisions. Social presence, influenced by factors such as ubiquity and interoperability, emerges as a key component of immersion. From the qualitative data, we identified two potential strategies to enhance metaverse immersion: technical improvements and offline device-assisted strategies.

Our study contributes to the literature on information systems (IS) adoption and provides practical insights for practitioners on crucial considerations in metaverse design.

The purpose is to provide decision support for tourists recommending scenic spots and corresponding suggestions for the management of scenic spots.

Based on the Baidu index data generated, this paper analyzes the temporal and spatial characteristics of network attention of 5A scenic spots in Sichuan Province. The online comment data are used to build the assessment model of scenic spots based on network attention, and the comment information of tourists is mined and analyzed through statistical analysis. At the same time, the key attributes of scenic spots from the perspective of network attention are evaluated and analyzed by using the probabilistic linguistic term set. Finally, this paper further constructs a recommendation model based on the key attribute set of scenic spots.

This paper uses different types of tourism network information, integrates multi-types of data and methods, fully excavates the value information of tourism network information, constructs the research framework of “scenic spot assessment + scenic spot recommendation” from the perspective of network attention, analyzes the network attention characteristics of scenic spots, evaluates the performance of scenic spots, and implements scenic spot recommendation.

This paper integrates multi-source data and multidisciplinary theoretical methods to form a scenic spot research framework of “assessment + recommendation” from the perspective of network attention.

This study aims to provide nuanced insights into the effectiveness of digital outdoor advertising in redefining urban tourism appeal. Amidst a transformative era for urban tourism and city branding strategies, this study evaluates Tecoration’s influence on city branding and tourism promotion frameworks. Using the “Wave” digital outdoor advertising campaign in Seoul as a focal point, this analysis explores how such innovative marketing efforts reshape potential tourists’ perceptions and intentions toward visiting Seoul.

The study uses a bifurcated methodological framework. The initial phase undertakes a granular topical analysis, decoding keyword patterns from YouTube video commentaries, offering an unmediated insight into viewer sentiment. This is juxtaposed with a structural equation modeling technique in the subsequent phase, which serves to validate and triangulate the findings of the primary analysis.

The study reveals that viewer reactions, imbued with a sense of surprise attributable to both the content’s novelty and the technological innovation, exhibit a strong correlation with increased media engagement. This enhanced engagement significantly influences the viewers’ overall perception of the city, culminating in a marked increase in their intentions to visit Seoul.

The findings have transformative implications for city branding strategies, accentuating the potential of digital outdoor mediums. The study advocates for a paradigm shift that underscores the indispensability of Tecoration in elevating urban brand imagery and catalyzing the broader objectives of smart city metamorphosis, urban tourism rejuvenation and commercial growth trajectories.

The results of this research highlight the transformative potential of digital outdoor media in city branding. The findings suggest a shift in strategy, emphasizing the critical role of Tecoration in enhancing urban brand imagery, driving smart city development, revitalizing urban tourism and fostering commercial growth. This study underscores the strategic importance of integrating Tecoration into the urban branding framework, showcasing its vital contribution to the growth and dynamism of modern cities.

The findings of this study highlight the social implications of integrating Tecoration media in urban environments. By enhancing city branding and tourism through innovative digital signage, cities can foster a more vibrant and attractive urban atmosphere, promoting community pride and engagement. Additionally, the increased visitor traffic can boost local economies and support cultural exchange, contributing to the overall social and economic well-being of urban areas. Strategic use of digital outdoor advertising can also bridge the gap between technological advancements and public spaces, creating more interactive and inclusive urban experiences for residents and tourists alike.

This study embraces a viewer-centric perspective, delving into the relatively uncharted realms of surprise and media engagement within the digital consumption landscape. By adopting this innovative angle, the research significantly deepens the comprehension of viewer experiences and broadens the academic boundaries concerning city branding and media effect frameworks in management literature.