Procedia Computer Science最新文献

The emerging concept of Industry 5.0 has led industries to design industrial environments integrating robots to support human work. The impact of implementing human-robot interaction (HRI) on humans and the work-related stress linked to it is still an open issue. In this context, measuring mental stress is crucial for designing effective HRI environments.

This study aims to experimentally test the influence of the robot's presence on mental stress by measuring humans' performance, physiological data, and workload perception.

Sixty participants were asked to perform an assembly task while coexisting with a robot. Three scenarios were tested, changing the kind of task performed by the robot and the distance from the participants' working area. Statistical analyses were performed to capture the differences between scenarios.

Results show that the robot's presence does not significantly affect the participants' stress levels. However, when the distance to the robot decreases, human performance is affected, concluding that the robot's proximity could cause more distraction to human workers.

When companies increasingly use artificial intelligence (AI), this changes the world of work and, in particular, the way people and technology work together and divide up their work. Because with the help of AI systems, even cognitively demanding activities can be automated. For example, AI can support executives in their leadership tasks and partially take over administrative coordination and control tasks. Workflows and processes must be redesigned or at least adapted accordingly. This scientific article provides an overview of the necessary changes and presents suitable tools for well-structured change management that is oriented toward human-centered work design and takes AI-specific design criteria into account. Furthermore, the article presents a qualification concept, which helps executives to develop, implement and establish AI applications in a socio-technical and human-oriented manner. With the help of this concept, executives and users of AI, for example, will be able to acquire the necessary competencies. In this context, the results of the practical evaluation of the concept will also be presented.

In order to accompany the process of work design, a systemic analysis is useful, which reveals changes in elements of the work system. Physical and psychological situations at work that can lead to adverse effects should be avoided. In processes of change, it is essential to identify developments at an early stage so that appropriate measures can be taken into account. This is also valid in the context of work design. This article presents an instrument that addresses the analysis of work system elements in the context of change. Besides content, structure and intended process, findings from the first application are presented. These experiences within the research project WIRKsam show the potentials of the instrument and allow to discuss the limitations as well as the possibilities for further development.

Manufacturing and assembly lines have become more and more complex over the years. One reason for this complexity is multistage manufacturing, where faults in one stage may carry forward downstream in the production line. Our goal is to find the production stage where reliable fault prediction will already be possible. Our approach takes an holistic view over the complete manufacturing line and performs an ablation study on product-specific data. The outcome of our approach is the analysis of a given manufacturing line that results in locating manufacturing stages where reliable prediction of faulty products is possible. Our objective is to support the implementation of an operative decision support system that allows to decide when to perform early prediction in a manufacturing process.

Missing Data is of concern in smart manufacturing. There are various reasons why data may be missing. Buffering issues, sensor failure, or protocol issues can cause missing entries or skipped captures. This missing data leads to distorted datasets, failure to train models, and either to disregard, deletion of records or typically to vast manual re-work efforts. This paper shows types of missing data and various approaches to detect them. Replacement or fill-in approaches are presented and their limitations are highlighted. A more precise imputation method beyond the state of the art is explained in detail. The implementation of this physics-informed imputation method was performed and experiments were carried out. The results of the experiments are presented in this paper and the results discussed.

In recent years, multiple crises have shown the fragility of global supply chains. In particular, climate change sheds light on the never-ending waste of resources caused by the linear economic model. In response, circular economy emerges as a promising alternative. Companies must rethink and innovate their business models, product life cycles, and underlying mindsets for a systemic transition. Cross-sectoral collaboration in networks is necessary to redesign, reuse, recycle, and remanufacture products and close the loop of material flows. First, projects and research on the concepts of open source hardware, open innovation, and open design show that openness can be a game-changer for the circular economy and circular business models. Although there has been growing interest, there is still a lack of comprehensive research examining possible synergies of openness and circularity, as well as identifying patterns for integrating these concepts into business models. This paper explores possible ways, prerequisites, and obstacles of open source concepts enabling circular value creation in industry. We combine explorative data from a literature review and more than 10 interviews with open source and circular economy experts. Furthermore, a total of 38 case studies of circular or open or open & circular business models were identified and selected for analysis. The empirical results were triangulated with existing business model patterns from the literature. The study presents a framework to describe open and circular business models and four prototypical patterns. In an exploratory approach, we identify necessary lines of future research in order to facilitate open source movements toward a circular economy. The paper provides insights for academics and practitioners from production and supply chain management. It combines interdisciplinary perspectives to unlock the potential of open source concepts and collaboration for enabling a circular economy.

Supply Chain 4.0 is characterized by various factors, including seamless integration and connectivity, the Internet of Things (IoT), Big Data, AI participation, Cyber-Physical Systems (CPSs), flexibility, adaptability, and customer-centricity across different parts of the supply chain. The application of Distributed AI (DAI) systems like Multi-Agent Systems (MAS) opens new horizons to enhance the efficiency, responsiveness, and intelligence of these supply chains. DAI facilitates advanced autonomous decision-making and real-time optimization at different stages of the agri-food supply chain, such as demand forecasting, inventory management, production planning, logistics optimization, and quality assurance and control. This article, by focusing on the case of scheduling through the entire supply chain, examines how DAI initiatives, including Multi-Agent Systems (MASs) enhanced with Case-Based Reasoning (CBR), enable the distribution of intelligence across smart, interconnected elements of the supply chain network. It is shown that through the use of DAI in SCM, the performance of the entire supply chain optimizes consistently and adaptively through the use of MAS, in which different parts of SCM collaborate as agents. Supply Chain 4.0 can gain autonomy, self-organization, self-optimization, self-adaptation, robustness, and flexibility, and its knowledge base can be enriched over time by using CBR to learn from past situations. It also discusses the opportunities and challenges associated with the adoption of DAI in Supply Chain 4.0, including operational efficiency, cost reduction, agility enhancement, and improved customer satisfaction. However, several concerns, such as data security, privacy issues, and interoperability, must be addressed.

Ophthalmic disorders represent a major global health problem leading to visual impairment and even blindness if not detected and treated early. Deep learning is a popular approach where pre-trained models are now often used to diagnose a variety of diseases from different medical images. In order to provide an accurate and reliable categorization of ophthalmic illnesses, this study suggests a fusion or ensemble technique that harnesses the power of pre-trained models like ResNet50, DenseNet and EfficientNet. The proposed ensemble model enhances the performance by incorporating the benefits of three architectural paradigms, guiding the convergence of each one's distinct strengths to achieve improved overall classification result. The ensemble architecture has undertaken inclusive validation on multiple fundus image datasets, showing improved performance over lone models. An accuracy of 92% demonstrates the potential of ensemble model in the categorization of eye diseases like cataract, diabetic retinopathy, glaucoma and normal eyes. In addition to achieving cutting-edge accuracy, the ensemble also offers an AUC-ROC score of 1.00. This technique presents a viable alternative for boosting the accuracy and reliability in identifying various eye illnesses by combining diverse model capabilities. The empirical data and conclusions show that the ensemble model has the potential to make a substantial contribution to the field of ocular medical imaging and patient care by enabling precise and timely treatments that may significantly improve the lives of millions of people worldwide who are impacted by ophthalmic diseases.

In the dynamic landscape of cloud computing, efficient task scheduling plays a pivotal role in optimizing resource utilization and enhancing overall system performance. This research introduces a groundbreaking approach to task scheduling in cloud environments through the implementation of a novel Modified Shortest Job First (SJF) algorithm within the CloudSim simulation framework. The primary objectives of this study are to address existing challenges in traditional scheduling algorithms, mitigate resource bottlenecks, reduce task completion times, and improve overall system efficiency.

Blockchain is an emerging technology penetrating various real-time and sensitive domains including financial products. Block chain can deal with complex system of financial transactions with focus to provide security and integrity to both the parties with reliable flow of transactions and asset securitization. Block chain is a distributed technology providing a lot of benefits such as cryptic transactions, smart contracts, distributed ledger system along with decentralization, authentication, authorization, and immutability to enhance the efficiency of the financial system. In this paper, the existing solutions for asset-backed securitization in blockchain are analysed and reviewed to highlight the requirements for change in design and ideas for enterprise applicability of blockchain for asset securitization. Also, the benefits of blockchain to reduce the risk.