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.

Through the “Going Digital Initiative,” the Ghanaian government has introduced policies that aim at improving the information and communication technology (ICT) infrastructure of the country. These ICT policies have benefited numerous sectors of the Ghanaian economy. In logistics management, ICT has impacted drone medical delivery in the healthcare and maritime sectors. However, the importance of ICT is not realized in the motorcycle goods transport (MGT) industry, regardless of its popularity and high economic dependency. Second, all research on motorcycles is focused on diverse social concerns, and no study has attempted to analyze ICT implementation for MGT operations. This is a significant gap in logistics management. Hence, the study aimed to investigate the impact of ICT on Ghana's MGT industry empirically.

The study adopts a two-phase data collection approach to collect the data. The authors use partial least square structural equation modeling to analyze the study's measurement and structural assessment model.

ICT positively impacts MGT and the drivers considered. The drivers positively influence MGT. The study further analyzes novel results on the relationships between the drivers and their mediating roles in enhancing MGT performance.

The study's originality is the extension of ICT adoption and usage in MGT. The lack of literature on the importance of ICT for MGT services makes this study the primary source of literature, and the relationships investigated are unique as the research area is unexplored.

Based on the strong feature representation ability of the convolutional neural network (CNN), generous object detection methods in remote sensing (RS) have been proposed one after another. However, due to the large variation in scale and the omission of relevant relationships between objects, there are still great challenges for object detection in RS. Most object detection methods fail to take the difficulties of detecting small and medium-sized objects and global context into account. Moreover, inference time and lightness are also major pain points in the field of RS.

To alleviate the aforementioned problems, this study proposes a novel method for object detection in RS, which is called lightweight object detection with a multi-receptive field and long-range dependency in RS images (MFLD). The multi-receptive field extraction (MRFE) and long-range dependency information extraction (LDIE) modules are put forward.

To concentrate on the variability of objects in RS, MRFE effectively expands the receptive field by a combination of atrous separable convolutions with different dilated rates. Considering the shortcomings of CNN in extracting global information, LDIE is designed to capture the relationships between objects. Extensive experiments over public datasets in RS images demonstrate that our MFLD method surpasses the state-of-the-art methods. Most of all, on the NWPU VHR-10 dataset, our MFLD method achieves 94.6% mean average precision with 4.08 M model volume.

This paper proposed a method called lightweight object detection with multi-receptive field and long-range dependency in RS images.

Traditional visual simultaneous localization and mapping (SLAM) systems are primarily based on the assumption that the environment is static, which makes them struggle with the interference caused by dynamic objects in complex industrial production environments. This paper aims to improve the stability of visual SLAM in complex dynamic environments through semantic segmentation and its optimization.

This paper proposes a real-time visual SLAM system for complex dynamic environments based on YOLOv5s semantic segmentation, named YLS-SLAM. The system combines semantic segmentation results and the boundary semantic enhancement algorithm. By recognizing and completing the semantic masks of dynamic objects from coarse to fine, it effectively eliminates the interference of dynamic feature points on the pose estimation and enhances the retention and extraction of prominent features in the background, thereby achieving stable operation of the system in complex dynamic environments.

Experiments on the Technische Universität München and Bonn data sets show that, under monocular and Red, Green, Blue - Depth modes, the localization accuracy of YLS-SLAM is significantly better than existing advanced dynamic SLAM methods, effectively improving the robustness of visual SLAM. Additionally, the authors also conducted tests using a monocular camera in a real industrial production environment, successfully validating its effectiveness and application potential in complex dynamic environment.

This paper combines semantic segmentation algorithms with boundary semantic enhancement algorithms to effectively achieve precise removal of dynamic objects and their edges, while ensuring the system's real-time performance, offering significant application value.

This study aims to determine museum experiences by analyzing the TripAdvisor reviews of the museum visitors in Gaziantep and offer suggestions for improving the visitors' experiences by taking museum curators' opinions.

The case study method was used as one of the qualitative approaches in the study. The research comprises two stages. TripAdvisor reviews about five museums in Gaziantep were analyzed in the first stage, and museum curators' opinions on the visitor complaint reasons and solution suggestions were discussed in the second stage.

The study showed that satisfying or non-satisfying experience factors might differ according to visitors, museum curators and both visitors and museum curators. Therefore, each museum curator should effectively manage every component of visitor experience factors by its target audience.

Although this study has some valuable findings and contributes to the literature, it also has limitations. The study's sample consists of five museums in Gaziantep. Further studies can be carried out on a larger population and sample. The data for determining visitor experiences, the first stage of the research, were obtained only from an online platform (TripAdvisor).

The proposed model provides a holistic perspective on evaluating and managing visitor experience. There may be structural problems (small size of the museum area, lack of parking spaces and elevators, etc.) with the museum beyond the manager's control. Also, the lack of information and communication (limited concept, lack of artifacts, etc.) causes criticisms of the museum.

This paper contributes to the museum management literature with a model for enriching the quality of the museum experience and increasing the museum's attractiveness. The study showed that museums contribute to the visitor's experience in all dimensions. While visitors thought museums primarily contribute to object experience, museum curators thought museums contribute more to visitors' cognitive experience and other experience elements.

The present study analyzed the visitor comments and the opinions of museum curators from a holistic perspective, considering the internal and external factors that are effective in the visitor experience, and revealed the reasons for the visitors' negative experience and the solution suggestions toward the improvement of the visitor experience.

This study identifies a methodology to explore the issues of enterprise innovation ecosystem health (EIEH).

First, this study constructs the indicator system of EIEH based on the research objective; second, the dynamic vertical projection method (DVPM) and entropy weight method are proposed to analyze the status and influencing factors of EIEH; finally, the future development of EIEH is analyzed using GM (1,1).

In terms of methodology, the DVPM can effectively analyze EIEH, which can not only analyze the development status and potential of EIEH every year but also analyze the comprehensive state of EIEH for many years. In terms of practice, the value and grade of EIEH in China have been gradually increasing from 2016 to 2020, but the overall development is unbalanced, and five key factors affecting EIEH have been identified. The EIEH in China is predicted to steadily grow from 2021 to 2025.

The analytical method employed in this study can effectively analyze EIEH, which provides a new analytical perspective for the evaluation of EIEH and enriches the research content of the enterprise innovation ecosystem (EIE). By analyzing the results, we can gain a comprehensive understanding of the state of different EIEs, enabling each EIE to design tailored remedial measures to enhance EIEH and achieve sustainable development.

Effective use of data across public health organisations (PHOs) is essential for the provision of health services. While health technology and data use in clinical practice have been investigated, interactions with data in non-clinical practice have been largely neglected. The purpose of this paper is to consider what constitutes data, and how people in non-clinical roles in a PHO interact with data in their practice.

This mixed methods study involved a qualitative exploration of how employees of a large PHO interact with data in their non-clinical work roles. A quantitative survey was administered to complement insights gained through qualitative investigation.

Organisational boundaries emerged as a defining issue in interactions with data. The results explain how data work happens through observing, spanning and shifting of boundaries. The paper identifies five key issues that shape data work in relation to boundaries. Boundary objects and processes are considered, as well as the roles of boundary spanners and shifters.

The study was conducted in a large Australian PHO, which is not completely representative of the unique contexts of similar organisations. The study has implications for research in information and organisational studies, opening fields of inquiry for further investigation.

Effective systems-wide data use can improve health service efficiencies and outcomes. There are also implications for the provision of services by other health and public sectors.

The study contributes to closing a significant research gap in understanding interactions with data in the workplace, particularly in non-clinical roles in health. Research analysis connects concepts of knowledge boundaries, boundary spanning and boundary objects with insights into information behaviours in the health workplace. Boundary processes emerge as an important concept to understand interactions with data. The result is a novel typology of interactions with data in relation to organisational boundaries.

This paper proposes a self-supervised monocular depth estimation algorithm under multiple constraints, which can generate the corresponding depth map end-to-end based on RGB images. On this basis, based on the traditional visual simultaneous localisation and mapping (VSLAM) framework, a dynamic object detection framework based on deep learning is introduced, and dynamic objects in the scene are culled during mapping.

Typical SLAM algorithms or data sets assume a static environment and do not consider the potential consequences of accidentally adding dynamic objects to a 3D map. This shortcoming limits the applicability of VSLAM in many practical cases, such as long-term mapping. In light of the aforementioned considerations, this paper presents a self-supervised monocular depth estimation algorithm based on deep learning. Furthermore, this paper introduces the YOLOv5 dynamic detection framework into the traditional ORBSLAM2 algorithm for the purpose of removing dynamic objects.

Compared with Dyna-SLAM, the algorithm proposed in this paper reduces the error by about 13%, and compared with ORB-SLAM2 by about 54.9%. In addition, the algorithm in this paper can process a single frame of image at a speed of 15–20 FPS on GeForce RTX 2080s, far exceeding Dyna-SLAM in real-time performance.

This paper proposes a VSLAM algorithm that can be applied to dynamic environments. The algorithm consists of a self-supervised monocular depth estimation part under multiple constraints and the introduction of a dynamic object detection framework based on YOLOv5.

The research focuses on determining the prospects for improving the practice of accounting, reflecting in International Financial Reporting Standards (IFRS), and managing intellectual property objects in Uzbekistan based on international experience. Using data from the World Bank's 2022 statistics and regression analysis, the authors model the impact of a set of managerial measures on the manifestations of creating and applying intellectual property objects. The authors conclude that nonfinancial measures are preferable, with human resource management (HRM) in research and development (R&D) being a prospective choice for managing the creation and application of intellectual property objects. The theoretical significance lies in justifying the need to reflect an expanded list of intellectual property objects in IFRS. The research also justifies the conditions for effective management of intellectual property objects, that are a rejection of financial measures and reliance on and active use of nonfinancial management measures. The managerial significance is reflected in the newly developed nonfinancial approach to accounting, reflecting in IFRS and managing intellectual property objects. This approach can enhance the efficiency of such management in knowledge-intensive and high-tech industries, unlocking the potential of IFRS to support the development of the knowledge economy. The practical significance lies in offering author recommendations for improving the practice of accounting, reflecting in IFRS, and managing intellectual property objects in Uzbekistan. Implementing these recommendations in the practice of IFRS and corporate accounting in Uzbekistan could propel the country toward a leading model in the knowledge economy and strengthen its position in global high-tech markets.

Master information delivery plan (MIDP) is a key requirement for building information modelling (BIM) execution plan (BEP) that enlists all information deliverables in BIM-based project, containing information about what would be prepared, when, by who, as well as the procedures and protocols to be used. In a well-conceived BEP, the MIDP facilitates collaboration among stakeholders. However, current approaches to generating MIDP are manual, making it tedious, error-prone and inconsistent, thereby limiting some expected benefits of BIM implementation. The purpose of this study is to automate the MIDP and demonstrate a collaborative BIM system that overcomes the problems associated with the traditional approach.

A BIM cloud-based system (named Auto-BIMApp) involving naming that automated MIDP generation is presented. A participatory action research methodology involving academia and industry stakeholders is followed to design and validate the Auto-BIMApp.

A mixed-method experiment is conducted to compare the proposed automated generation of MIDP using Auto-BIMApp with the traditional practice of using spreadsheets. The quantitative results show over 500% increased work efficiency, with improved and error-free collaboration among team members through Auto-BIMApp. Moreover, the responses from the participants using Auto-BIMApp during the experiment shows positive feedback in term of ease of use and automated functionalities of the Auto-BIMApp.

The replacement of traditional practices to a complete automated collaborative system for the generation of MIDP, with substantial productivity improvement, brings novelty to the present research. The Auto-BIMApp involve multidimensional information, multiple platforms, multiple types and levels of users, and generates three different representations of MIDP.