IFIP Open Access Digital Library
Not a member yet
22614 research outputs found
Sort by
A Worker-Centric Order Release Method Based on Workload Control: An Assessment by Simulation
No full textPart 6: Advances in Production Management SystemsInternational audienceThis study presents a novel paradigm of production planning and control by introducing a worker-centric workload control order release approach, which is particularly suitable for the manufacturing shops involving robots and workers, such as the human-machine collaborative production system. Specifically, a production order in the real-life production process may consist of multiple operations. Some of these operations are exclusively performed by machines and others necessitating collaboration between workers and machines. This will make it more difficult for managers to balance the workload on the shop floor, even deteriorating the available capacity of workers and machines. Therefore, this study first classifies the production orders into two kinds of tasks (i.e., independent tasks and collaborative tasks) based on their processing attributes before holding them in a pre-shop pool. Subsequently, we give priority to releasing the workload of collaborative tasks (i.e., triggered by the workers) and subsequently release independent tasks (i.e., triggered by the independent machines) to balance the workload across machines at the order release stage. The experimental results demonstrate that prioritizing worker workload balance can significantly improve the shop performance in terms of throughput time and tardiness time. Furthermore, we observe that prioritizing workers’ workload also mitigates tardiness typically associated with high load periods when expediting the processing of urgent orders. In other words, prioritizing workers’ workload to some extent diminishes the disparity between high load and low load periods due to this is conducive to avoiding premature idle or overload of small capacity resources, therefore leading to a more balanced workload on the manufacturing shops
Developing 3D Production Simulation Models in Industrial Production Systems
No full textPart 6: Advances in Production Management SystemsInternational audienceThis research presents a comprehensive framework for the development, integration, and formulation of 3D simulation models within industrial production systems. It aims to provide the required guidelines for utilizing 3D simulation technology, improving system productivity, assisting with decision-making, and furthering system optimization. The research highlights the considerable influence of 3D simulation technology on production systems, starting with developing and evaluating the system current state and its potential in manufacturing industries. The framework includes elements related to collecting data, the creation of 3D production simulation models, validation, and verification phases; setting objectives for the integration of 3D simulation; and the choice and advancement of customized simulation technologies that meets specific industry demands. The framework is developed with the help of a case study where the authors present the steps and information necessary to facilitate the modelling of the current state version within 3D production simulation model. Through the case study presented, this research illustrates the practical application of this framework, aiming to serve as an exemplary guide for academic and industrial practitioners
An Overview of Cloud-Based Services for Smart Production Plants
No full textPart 6: Advances in Production Management SystemsInternational audienceCloud computing is a game-changer model that opens new directions for modern manufacturing. It enables services and solutions that help improve the productivity and efficiency of smart production plants. The main objective of the paper is to provide a summary of the various cloud-based manufacturing services currently being offered to manufacturers or that could be offered in the future. Additionally, the paper aims to discuss the various enabling technologies used to support the integration of cloud manufacturing in the manufacturing industry. Furthermore, the paper categorizes the different services based on their functionalities and maps them to four levels of production such as plant level, production line level, machine level, and process level. The categorization of services and mapping them to appropriate levels in production can enhance efficiency and productivity in the manufacturing industry. The study advances the discussion on cloud-based manufacturing from the types of services and enabling technologies perspective
The Potential of Generative AI Chatbots as Career Advisors in Cybersecurity: Professionals’ Perspectives
No full textPart 4: Cybersecurity Programs and Career DevelopmentInternational audienceThe introduction of generative AI chatbots as career advisors in the cybersecurity domain represents a promising intersection of technology and career development. By addressing the critical skills gap, offering solutions to career progression challenges, and providing personalized, accessible guidance, AI chatbots hold the potential to significantly impact the professional landscape. This work investigates cybersecurity professionals’ perceptions of using AI chatbots for career advising. Investigations focus on professionals’ attitudes toward these chatbots, examining their trust in the advice offered, their belief in the chatbots’ capability to provide valuable career guidance, and the features they consider that can be supported by AI-powered career advisors in cybersecurity. The analysis seeks to enhance understanding of the role generative AI chatbots could play in advancing career development within the cybersecurity field, aiming to address the skills gap challenge faced by the sector. By evaluating these insights, the paper aims to highlight the potential contributions of generative AI chatbots to professional growth and development in cybersecurity
Hand Gesture Recognition Using a Multi-modal Deep Neural Network
No full textPart 2: Image UnderstandingInternational audienceAs devices around us get more intelligent, new ways of interacting with them are sought to improve user convenience and comfort. While gesture-controlled systems have existed for some time, they either use additional specialized imaging equipment, require unreasonable computing resources, or are simply not accurate enough to be a viable alternative. In this work, a reliable method of recognizing gestures is proposed. The built model correctly classifies hand gestures for keyboard typing based on the activity captured by an ordinary camera. Two models are initially developed for classifying video data and classifying time-series sequences of the skeleton data extracted from a video. The models use different strategies of classification and are built using lightweight architectures. The two models are the baseline models which are integrated to form a single multi-modal model with multiple inputs, i.e., video and time-series inputs, to improve accuracy. The performances of the baseline models are then compared to the multimodal classifier. Since the multimodal classifier is based on the initial models, it naturally inherits the benefits of both baseline architectures and provides a higher testing accuracy of 100% compared to the accuracy of 85% and 75% for the baseline models respectively
AI Applications in the Healthcare Logistics and Supply Chain Sectors
No full textPart 1: Smart and Sustainable Supply Chain Management in the Society 5.0 EraInternational audienceArtificial Intelligence (AI) has recently been established in healthcare management to support clinical activities and pharmaceutical research and development. Moreover, AI can potentially improve decision-making in healthcare supply chains (HSCs) by leveraging the information provided by various sources. However, research on the application of AI to HSCs is still in its infancy. This work presents a Systematic Literature Review to identify the main trends and future research directions. The analysis of the 23 pertinent papers suggests that more quantitative case studies on AI implementation in HSC are necessary. Additionally, the role of AI in facilitating logistics and supply chain management activities, promoting supply chain resilience, and ultimately creating integrated and agile HSCs should be investigated. Further literature reviews on AI-driven HSC management will help to keep the focus on this research field and its relevant developments
Analytical and Computational Models for In-Store Shopper Journeys
No full textPart 1: Smart and Sustainable Supply Chain Management in the Society 5.0 EraInternational audienceRetailing is an important part of the supply chain, the link at which money is transferred from the consumer and flows to upstream trading partners. However, retailing has received very little attention from researchers in terms of developing quantitative models that are used in the rest of the supply chain. This paper proposes analytical and computational models based on queuing theory and discrete-event simulation, respectively, for in-store shopper journeys. Specifically, based on empirical data from retail stores, we propose a M/G/∞ and Mt/G/c queues in tandem to model the shopping process and the checkout process to characterize key aspects of shopper journeys. Such an analytical model is probably the very first of its kind proposed to mathematically characterize retailing and offers prospects for enabling better understanding and decision-making in this multi-trillion-dollar industry. A key advantage of such analytical models is that they can provide quick answers to questions such as average customer waiting times at checkout for different levels of staffing, which is an important issue in customer service vs staffing cost. A shortcoming of such analytical models is that they are based on assumptions therefore their output has limited accuracy, and these models cannot predict variance in the output. To overcome these shortcomings, this paper presents ShopperSim, which is a stand-alone discrete-event simulation software being developed using SimPy, a Python library, to simulate shopper journeys in a variety of store formats. To ensure practical relevance of these developments, ShopperSim has been programmed to statistically reproduce empirically observed shopping time, basket size, and store area covered – key attributes for shopper journeys. Tests indicate that ShopperSim can reproduce empirically observed statistics of key attributes for shopper journeys. Data generated from ShopperSim indicates that M/G/∞ and M/G/c, a much simpler and more tractable tandem queuing model may be adequate for the tested case of a convenience store. In the future, analytical and computational models developed here can be leveraged in several ways for education, training, and operational decision-making in stores, including gamification of these decisions
Enriching Scene-Graph Generation with Prior Knowledge from Work Instruction
No full textPart 2: Human-centred Manufacturing and Logistics Systems Design and Management for the Operator 5.0International audienceWith the current focus on human resources in Industry 5.0, analysing the work movements of industrial operators is the important first step in optimising labour performance. Thanks to the popularity of camera sensors, vision-based Human Activity Recognition models have become useful engines for real-time monitoring tools, in which scene-graphs play an important role. Traditional scene-graph generation methods rely primarily on visual data for perception, neglecting a valuable source of process-oriented prior knowledge: the work instruction. Therefore, an extension of the scene-graph paradigm by integrating ground truth elaborated on elements from the work instruction is elaborated to complement and enhance the understanding of human activities in industrial environments, and improve the tracking capability with micro and repetitive movements. This conceptual paper discusses the basic design of this approach with potential applications in industrial environments, which is validated by a simulated use case of an electronic assembly process. Based on the proposed extension, the Human Activity Recognition model can be lightweight and robust. Further integration of multi-modal sensory inputs beyond visual cues, such as environmental and human-centric data, can enrich scene interpretation and provide a more comprehensive understanding of work behaviour, paving the way for more effective labour utilisation and improved productivity
Exploring the Cognitive Workload Assessment According to Human-Centric Principles in Industry 5.0
No full textPart 4: Evolving Workforce Skills and Competencies for Industry 5.0International audienceIndustry 4.0 and 5.0 paradigms have been crucial for companies in employing digital technologies as an ally for men to free them from dangerous and routine tasks in favour of higher value tasks, putting humans at the centre of the organization as the decision maker. However, on the one hand, the new industrial systems shift to new tasks requiring more ‘cognitive’ than ‘physical’ efforts; on the other hand, the approaches to assess the cognitive workload and ensure the physical well-being of the operators are far to be considered easily applicable. For this reason, this research reveals current research trajectories and explores the cognitive workload using subjective and objective indicators. The discussion highlights cognitive ergonomics and advocates for a harmonious balance between human and machine capabilities. It identifies factors contributing to cognitive overload in manufacturing and maps their interconnections. The analysis of recent research trends reveals a growing adoption of new approaches requiring the adoption of physiological measurements (e.g., electrocardiogram (ECG), electroencephalography (EEG), Electromyography (EMG), etc.). Finally, this investigation offers insights into future research directions, urging a nuanced exploration of industrial activities and addressing cognitive workload across organisational layers in the context of Industry 5.0
Sign Language Recognition System – A Review
No full textPart 2: SDG 4 Quality EducationInternational audienceSpeech is the easiest and the most basic mode of communication in our day-to-day life. Hence, speech impaired people are at a major disadvantage in this concern. The staple mode of communication for the speech impaired is Sign Language which in turn isolates them from the rest of the world in more ways than one. The Sign Language Recognition (SLR) System is an attempt to compress this isolation by recognizing the gestures of the Sign Language. The application may be used to map the sign into their corresponding text or speech in the given spoken language. In general, the system has been realized either using image processing techniques or with sensor signals employed in smart gloves. The system based on image processing captures the hand gestures made by an individual and maps it to their corresponding alphabets, words or phrases pre-defined in the existing dataset. Although this system proves to be useful, the dwindling accuracy of the image capturing process is a major drawback. The sensor-based system, on the other hand, works using a number of sensors attached to a glove which detects the hand gestures and computes it to its corresponding meaning. The performance of these systems is relatively higher but they also have a few setbacks, one of which is its high price due to the involvement of sensors making it unattainable to people of all economic strata. In addition to this, the extensive usage of wires and other electronic devices increases the weight of the glove making it inconvenient to be worn for long hours. There are a number of Sign languages existing from various parts of the world, each of which have their own recognition systems individually. This comes out as another drawback of the Sign Language Recognition Systems as they aren’t adaptable to all Sign Languages and are restricted to a specific Sign Language as per its dataset. This paper illustrates the state of art of SLR with the detailed descriptions on various Sign Languages, dataset and recognition methodology and the mode of output, accuracy and application