Search results

Fall accidents can cause casualties and economic losses in the construction industry. Fall portents, such as loss of balance (LOB) and sudden sways, can result in fatal, nonfatal or attempted fall accidents. All of them are worthy of studying to take measures to prevent future accidents. Detecting fall portents can proactively and comprehensively help managers assess the risk to workers as well as in the construction environment and further prevent fall accidents.

This study focused on the postures of workers and aimed to directly detect fall portents using a computer vision (CV)-based noncontact approach. Firstly, a joint coordinate matrix generated from a three-dimensional pose estimation model is employed, and then the matrix is preprocessed by principal component analysis, K-means and pre-experiments. Finally, a modified fusion K-nearest neighbor-based machine learning model is built to fuse information from the x, y and z axes and output the worker's pose status into three stages.

The proposed model can output the worker's pose status into three stages (steady–unsteady–fallen) and provide corresponding confidence probabilities for each category. Experiments conducted to evaluate the approach show that the model accuracy reaches 85.02% with threshold-based postprocessing. The proposed fall-portent detection approach can extract the fall risk of workers in the both pre- and post-event phases based on noncontact approach.

First, three-dimensional (3D) pose estimation needs sufficient information, which means it may not perform well when applied in complicated environments or when the shooting distance is extremely large. Second, solely focusing on fall-related factors may not be comprehensive enough. Future studies can incorporate the results of this research as an indicator into the risk assessment system to achieve a more comprehensive and accurate evaluation of worker and site risk.

The proposed machine learning model determines whether the worker is in a status of steady, unsteady or fallen using a CV-based approach. From the perspective of construction management, when detecting fall-related actions on construction sites, the noncontact approach based on CV has irreplaceable advantages of no interruption to workers and low cost. It can make use of the surveillance cameras on construction sites to recognize both preceding events and happened accidents. The detection of fall portents can help worker risk assessment and safety management.

Existing studies using sensor-based approaches are high-cost and invasive for construction workers, and others using CV-based approaches either oversimplify by binary classification of the non-entire fall process or indirectly achieve fall-portent detection. Instead, this study aims to detect fall portents directly by worker's posture and divide the entire fall process into three stages using a CV-based noncontact approach. It can help managers carry out more comprehensive risk assessment and develop preventive measures.

The impact of digital technology in the wider travel field has been substantial and significant, changing both the competitive landscape of businesses and the behavior of travelers. However, we are now on the cusp of new digital developments encompassing cloud computing, blockchain, internet of things (IoT) and above all, artificial intelligence (AI), which are predicted to disrupt the business and consumer sides of several industries – travel included. This study aims to frame this upcoming digital transformation in travel within a human-centered approach where the critical understanding of digital humanism principles will enrich social scientists’ research agenda in the coming years.

The viewpoint follows a structure based on (i) setting the scene for the rise of digital transformation, (ii) the historical perspective on digital transformation in travel, (iii) the pandemic’s impact and (iv) future development and research agenda.

It is only by fostering a human-centered digital transformation perspective that social science researchers in travel can realize the “high-tech for high-touch” promise of fostering a human-to-human encounter empowered and possibly hampered, by digital technologies. This work proposes to start from the concepts of digital technology control, participation, education and ethics to design a research agenda with a 2050 horizon.

This work has been designed to shift the attention of researchers toward a human-centered digital transformation approach to reflect on the human-machine relationship for a better society. Due to its inner characteristics the travel field can foster a reflection on this topic by reaffirming the centrality of human beings and their authorship in the travel product creation.

数字技术在更广泛的旅游领域产生了巨大而显著的影响, 改变了企业的竞争图景和游客行为。然而, 我们现在正处于新的数字发展的风口浪尖, 包括云计算、区块链、物联网以及最重要的人工智能, 预计这些技术将颠覆包括旅游业在内的多个行业的企业端和消费端。这项研究建议将即将到来的旅行数字化转型纳入以人为本的方法, 对数字人文主义原则的批判性理解将丰富社会科学家未来几年的研究议程。

该观点遵循基于以下方面的一种结构, (i)为数字化转型的兴起设定场景, （ii）旅行数字化转型的历史视角, (iii)疫情的影响和（iv）未来发展和研究议程。

只有培养以人为中心的数字化转型视角, 旅游领域的社会科学研究人员才能实现“高科技换高品质”的承诺, 培养一种被数字技术赋能但也可能受到阻碍的人与人之间的接触。这项工作建议从数字技术控制、参与、教育和伦理的概念出发, 设计一个2050年的研究议程。

这项工作旨在将研究人员的注意力转移到以人为中心的数字化转型方法上, 以反思更美好社会的人机关系。由于旅游领域的内在特征, 它可以通过重申人在旅游产品创造中的中心地位和作者身份来促进对这一主题的反思。

El impacto de la tecnología digital en el ámbito de los viajes en general ha sido sustancial y significativo, cambiando tanto el panorama competitivo de las empresas como el comportamiento de los viajeros. Sin embargo, en la actualidad estamos en la cúspide de nuevos desarrollos digitales que abarcan la nube informática, blockchain, IoT y, sobre todo, la inteligencia artificial, que se prevé que alteren los aspectos comerciales y de consumo de varias industrias, incluidos los viajes. Esta investigación propone enmarcar esta próxima transformación digital en los viajes dentro de un enfoque centrado en el ser humano, donde la comprensión crítica de los principios del humanismo digital enriquecerá la agenda de investigación de los científicos sociales en los próximos años.

El presente trabajo presenta una estructura basada en (i) el establecimiento del escenario para el auge de la transformación digital, (ii) la perspectiva histórica de la transformación digital en los viajes, (iii) el impacto de la pandemia y (iv) el desarrollo futuro y líneas de investigación.

Únicamente si se fomenta una perspectiva de transformación digital centrada en el ser humano podrán los investigadores de las ciencias sociales en el ámbito de los viajes hacer realidad la promesa de “alta tecnología para un alto contacto”, promoviendo un encuentro entre seres humanos potenciado, y posiblemente obstaculizado, por las tecnologías digitales. Este trabajo propone partir de los conceptos de control de la tecnología digital, participación, educación y ética para diseñar una agenda de investigación con horizonte 2050.

Este trabajo ha sido diseñado para desplazar la atención de los investigadores hacia un enfoque de transformación digital centrado en el ser humano para reflexionar sobre la relación ser humano-máquina para una sociedad mejor. Por sus características internas, el ámbito de los viajes puede propiciar una reflexión sobre este tema reafirmando la centralidad del ser humano y su autoría en la creación del producto turístico.

The study aspires to enhance comprehension of the intricate interplay between supply chain management (SCM) and resilience in family businesses, thereby offering valuable insights to managers and policymakers endeavouring to foster resilience in uncertain environments.

Commencing from the premise that family businesses (FBs) prioritize the preservation of socio-emotional wealth (SEW) when formulating strategic decisions, this study endeavours to advance understanding of supply chain practices adopted by FBs and their direct impact on resilience during crisis situations or economically challenging periods. Through an exploratory case study of nine FBs, the present research reveals four pivotal strategies in SCM that contribute to their resilience: (i) reorganization of inventory management; (ii) cultivating close relationships with suppliers; (iii) emphasizing product quality and customer retention; and (iv) implementing cost reduction measures to bolster resilience. The aim of the study is to provide an in-depth understanding of the intricate interplay between SCM and resilience in FBs, thereby offering valuable insights to managers and policymakers endeavouring to foster resilience in uncertain environments.

Our approach offers a theoretical framework for SCM aligned with prior research on the interplay between characteristics of family businesses and resilience strategies. Furthermore, this paper illustrates how factors such as the emphasis on high-quality products and services by family businesses contribute to achieving non-economic objectives that owners adopt to reconcile family and business needs, creating intrinsic added value for the company. It reveals various challenges in SCM, including inventory organization changes, supplier closures and the significance of customer retention. Family businesses are implementing product and technology enhancements and leveraging digitization to enhance supply chain processes.

This paper contributes significantly to the field of FBs by highlighting the crucial role of SCM in enhancing business resilience during crises. It empirically examines how the SEW characteristics of FBs influence the reconfiguration of their supply chains to enhance resilience, presenting a theoretical model for this context. Our theoretical framework employs an SEW perspective to elucidate how FBs respond to the challenges posed by the COVID-19 pandemic by adapting their SCM processes to safeguard their social and emotional legitimacy, organizational visibility and reputation. These adaptations gain particular relevance during crises or turbulent conditions, potentially leading to alterations in how FBs formulate their supply chain strategies and manage supply chain-related processes.

Intent detection (ID) and slot filling (SF) are two important tasks in natural language understanding. ID is to identify the main intent of a paragraph of text. The goal of SF is to extract the information that is important to the intent from the input sentence. However, most of the existing methods use sentence-level intention recognition, which has the risk of error propagation, and the relationship between intention recognition and SF is not explicitly modeled. Aiming at this problem, this paper proposes a collaborative model of ID and SF for intelligent spoken language understanding called ID-SF-Fusion.

ID-SF-Fusion uses Bidirectional Encoder Representation from Transformers (BERT) and Bidirectional Long Short-Term Memory (BiLSTM) to extract effective word embedding and context vectors containing the whole sentence information respectively. Fusion layer is used to provide intent–slot fusion information for SF task. In this way, the relationship between ID and SF task is fully explicitly modeled. This layer takes the result of ID and slot context vectors as input to obtain the fusion information which contains both ID result and slot information. Meanwhile, to further reduce error propagation, we use word-level ID for the ID-SF-Fusion model. Finally, two tasks of ID and SF are realized by joint optimization training.

We conducted experiments on two public datasets, Airline Travel Information Systems (ATIS) and Snips. The results show that the Intent ACC score and Slot F1 score of ID-SF-Fusion on ATIS and Snips are 98.0 per cent and 95.8 per cent, respectively, and the two indicators on Snips dataset are 98.6 per cent and 96.7 per cent, respectively. These models are superior to slot-gated, SF-ID NetWork, stack-Prop and other models. In addition, ablation experiments were performed to further analyze and discuss the proposed model.

This paper uses word-level intent recognition and introduces intent information into the SF process, which is a significant improvement on both data sets.

This research outlines the technological structure of the entire Japanese manufacturing and service industry using the patent information from research and development (R&D) activities to set R&D goals.

By analyzing the technological development capability of individual companies, the direction of the companies' R&D activities and current state of technological fusion between them can be understood. A group of companies participating in a particular product/service market must have the same technological development capabilities. As a result, the ratio of patent applications by a company to the total number of applications in a technical field will be similar across companies. This study uses the inter-company correlation coefficient of the ratio of patent applications by technical field as an index of technological development capability. A total of 167 major companies covering the major industries of Japan were analyzed. The analysis period was 15 years from 2004 to 2018, and the technical fields were rearranged to 42 fields with reference to the International Patent Classification (IPC)-Technology Concordance used by the World Intellectual Property Organization (WIPO). Considering the fluctuation in patent application opportunities, the number of patent applications was collected for at least three years for the analysis of patent applications by technical field, company and industry.

Examining the entire Japanese industry, the research found that chemicals, ceramics, non-ferrous metals and electrical/electronic equipment act as intermediaries between the respective groups and are linked to the transportation equipment, electrical/electronic equipment and information and communication services industries that are currently driving the Japanese economy. However, the technical connections between these groups are relatively loose. Over the last 15 years, the propagation structure of technical knowledge information has not changed. The progress of technological fusion remains within the scope of commerce and is conditioned by commerce.

Studies focusing on the technological development capability between companies and the technological structure of the Japanese manufacturing and service industries are almost non-existent since 2000 when Japan's economic growth slowed. The analytical methods presented in this research can be applied to individual companies to gain an understanding of technical positions of companies and can be useful for planning a technical environment, business or R&D strategy.

Maintaining the safety of the human is a major concern in factories where humans co-exist with robots and other physical tools. Typically, the area around the robots is monitored using lasers. However, lasers cannot distinguish between human and non-human objects in the robot’s path. Stopping or slowing down the robot when non-human objects approach is unproductive. This research contribution addresses that inefficiency by showing how computer-vision techniques can be used instead of lasers which improve up-time of the robot.

A computer-vision safety system is presented. Image segmentation, 3D point clouds, face recognition, hand gesture recognition, speed and trajectory tracking and a digital twin are used. Using speed and separation, the robot’s speed is controlled based on the nearest location of humans accurate to their body shape. The computer-vision safety system is compared to a traditional laser measure. The system is evaluated in a controlled test, and in the field.

Computer-vision and lasers are shown to be equivalent by a measure of relationship and measure of agreement. R² is given as 0.999983. The two methods are systematically producing similar results, as the bias is close to zero, at 0.060 mm. Using Bland–Altman analysis, 95% of the differences lie within the limits of maximum acceptable differences.

In this paper an original model for future computer-vision safety systems is described which is equivalent to existing laser systems, identifies and adapts to particular humans and reduces the need to slow and stop systems thereby improving efficiency. The implication is that computer-vision can be used to substitute lasers and permit adaptive robotic control in human–robot collaboration systems.

With the rapid development of short videos in China, the public has become accustomed to using short videos to express their opinions. This paper aims to solve problems such as how to represent the features of different modalities and achieve effective cross-modal feature fusion when analyzing the multi-modal sentiment of Chinese short videos (CSVs).

This paper aims to propose a sentiment analysis model MSCNN-CPL-CAFF using multi-scale convolutional neural network and cross attention fusion mechanism to analyze the CSVs. The audio-visual and textual data of CSVs themed on “COVID-19, catering industry” are collected from CSV platform Douyin first, and then a comparative analysis is conducted with advanced baseline models.

The sample number of the weak negative and neutral sentiment is the largest, and the sample number of the positive and weak positive sentiment is relatively small, accounting for only about 11% of the total samples. The MSCNN-CPL-CAFF model has achieved the Acc-2, Acc-3 and F1 score of 85.01%, 74.16 and 84.84%, respectively, which outperforms the highest value of baseline methods in accuracy and achieves competitive computation speed.

This research offers some implications regarding the impact of COVID-19 on catering industry in China by focusing on multi-modal sentiment of CSVs. The methodology can be utilized to analyze the opinions of the general public on social media platform and to categorize them accordingly.

This paper presents a novel deep-learning multimodal sentiment analysis model, which provides a new perspective for public opinion research on the short video platform.

The purpose of this paper is to improve the existing paradigm of edge computing to maintain a balanced energy usage.

The new greedy algorithm is proposed to balance the energy consumption in edge computing.

The new greedy algorithm can balance energy more efficiently than the random approach by an average of 66.59 percent.

The results are shown in this paper which are better as compared to existing algorithms.

This study aims to explore a new restaurant category’s development from birth to maturity, thereby explaining the rationale for category innovation strategies.

The authors conducted a qualitative case study analysis of the New Chinese-style Fusion Restaurant category’s development from birth to maturity. Thematic analysis was conducted on data collected from semi-structured interviews and textual information.

A new restaurant category’s maturation is determined by the formation of society’s shared knowledge about the category’s crucial attributes, which is an outcome of market participants’ category-related social practices. The authors develop a novel, four-stage framework for the socialized construction of this shared knowledge: a knowledge creation (KC), knowledge diffusion (KD), knowledge integration (KI) and knowledge structuralization (KS). This knowledge evolution along this KC–KD–KI–KS sequence can holistically describe the category maturation process. This framework can help understand the rationale for a restaurant category’s maturation by analyzing the interrelationships among market participants’ social practices, knowledge-related activities and market development.

This study explains how market participants’ knowledge-related activities facilitate a new restaurant category’s maturation. This can help restaurant managers cope with increasingly homogeneous competition by applying a category-innovation strategy.

This study extends product categorization research on restaurants by articulating a product category’s maturation process from a knowledge perspective.

This paper examines and empirically validates the artificial intelligence-enabled human resource management (AI-enabled HRM) dimensions and sustainable organisational performance (SOP) relationship. It also examines the mediation and moderation of employee engagement (EE) and fusion skills (FS).

The indirect effects of AI-enabled HRM dimensions on SOP were found using structural equation modelling (SEM), bootstrapping and FS’s moderation effect by AMOS 22.

Results showed that AI-enabled HRM dimensions indirectly affected SOP through EE as a full and partial mediator with no moderation effects of FS.

This is the first study to link AI-enabled HRM dimensions, EE and SOP and determine how FS moderates EE and SOP.