IFIP Open Access Digital Library
Not a member yet
22614 research outputs found
Sort by
Employing Clustering Techniques and Association Rules for Client Segmentation and Attribute Dependency Mining in the Domain of Car Insurance
No full textPart 2: Digital Transformation, Industry 4.0, and Predictive AnalyticsInternational audienceSegmenting clients according to common characteristics and determining the needs for each group is an important objective in the domain of car insurance. We perform segmentation through specific methods, comparing multiple clustering techniques, considering both classical and deep learning algorithms. Regarding the classical methods, clustering techniques appropriate for both numerical and categorical data were adopted, such as k-means clustering, X-means clustering, respectively k-prototype clustering. Regarding the deep-learning techniques, a stacked denoising autoencoder, followed by conventional clustering techniques, was experimented, the performance being compared with that achieved after the individual application of the classical techniques. After employing the clustering methods, the relevant attributes that separate among clusters were determined, the dependencies between the policy insurance type and other attributes being also analyzed through graphical representations and association rules. The experiments were performed considering the data extracted from a relational database specific for car insurance, containing 1000 instances for the main tables
Planning and Optimising Value Chains in Production Networks of MSEs: A Lightweight Planner For Parallel Processes
No full textPart 4: Mechanism Design for Smart and Sustainable Supply ChainsInternational audienceWith increasingly automated production and global competition, pricing pressure on micro, small and medium-sized enterprises (SME) from the trade sector is increasing. Cooperation with other enterprises could be part of the solution to allow them to continue providing their services in the form of made-to-order, customised products. With new challenges and changing circumstances, applying modern Information and Communication Technology and AI (Artificial Intelligence) to local production in networks could provide valuable opportunities. The construction of value chains is a complex planning problem with partial parallelism, as companies can work independently and in parallel, but are also often dependent on precursors from previous production steps. Utilising this partial parallelism is essential for finding production plans with a short duration. While heuristically guided planners can optimise for such a criterion, selecting a value chain is a multifactorial optimisation problem. Besides total production time, aspects like cost or transport can be significant. Moreover, if this choice is up to customers, they will require a quick, interactive generation of plans according to their preferences. A graph-planning-based approach for interactive multifactorial optimisation is presented. The approach is demonstrated and evaluated on examples from the production domain
Fuzzy TOPSIS with Interval Data Based Possibility Measure Approach for Multi-criteria Group Decision Making: Application to Information System Selection
No full textPart 3: Hybrid Intelligence – Decision-Making for AI-Enabled Industry 5.0International audienceSupply chain partners increasingly make shared important decisions to achieve joint goals. Decisions include selecting partners, sites, machines, technologies, transportation modes, maintenance policies, etc. In this paper, we address the supply chain selection as a multi-criteria group decision making (MCGDM) problem. More specifically, a fuzzy TOPSIS with interval data-based possibility measure approach is developed. To bring consensus among the decision makers (DMs) regarding the preferences, a possibility measure algorithm is used. The final fuzzy decision matrix is formed by consensus of all the concerned partners. Finally, to demonstrate the applicability of the approach, a simple illustrative example dedicated to information system selection problem is presented and the obtained numerical results analysed
Mechanism Design as Collaborative Production Systems
No full textPart 4: Mechanism Design for Smart and Sustainable Supply ChainsInternational audienceThis paper discusses a platform in which customer participation shapes product development in a collaborative production system such as LEGO IDEAS. By employing ‘mechanism design’ developed in economics, our objective is to build a production system in which the platform takes into account the potential demands of the customers. In general, customers’ potential needs are private information and it is difficult to gather adequate information even through marketing surveys. Therefore, we provide a framework in which the members of the platform propose their alternatives and let customers vote based on them. The choices offered by the platforms are necessarily limited to those that can be produced by their production systems. This allows for the collection of information on highly feasible products. In addition, a scoring rule is introduced to determine how well the suitability of the proposal matches the needs of the consumer, and multiple proposals are evaluated under that rule. Finally, we also propose a method to implement platform exploration and exploitation guidelines through natural language analysis of descriptive responses from customers
From Vineyard to Smart Factory: The Case for a Digital Innovation Hub in the Atacama Desert
No full textPart 1: Smart Manufacturing Assets as Drivers for the Twin Transition Towards Green and Digital BusinessInternational audienceThis paper explores the challenges posed by the low digital maturity of Small and Medium-sized Enterprises (SMEs) in developing countries, using the example of viticulture in the northern region of Tarapacá in Chile, part of the Atacama Desert. The study proposes a concept for a Digital Innovation Hub (DIH) that considers region-specific requirements. We argue that the low digital literacy score in Chile exemplifies a broader issue in developing countries. Drawing upon previous insights from an explorative study on digital maturity in Chilean SMEs, we propose an action-oriented approach and delve into the critical role of DIHs as a facilitator for a digitally transformed business landscape for SMEs. Such hubs can offer competent and provider-neutral contact points for information, awareness-raising, and qualification of SMEs. Central to such an approach are considerations of regional and cultural characteristics that influence the uptake and sustainable implementation of digital technologies. Amongst these characteristics are, for example, the level of hierarchy, uncertainty avoidance, and the environmental challenges due to the extensive use of freshwater by the mining industry in competition with agricultural food production. Despite local specificites, the concept of DIHs considering regional and cultural characteristics may be beneficial for SMEs in other developing countries
Towards Human-Centric Digital Services: A Development Framework
No full textPart 4: Methods and Tools to Achieve the Digital and Sustainable Servitization of Manufacturing CompaniesInternational audienceThe emerging Industry 5.0 paradigm is initiating changes in different aspects of manufacturing businesses as well as in their products and services. Industry 5.0 pillars – human-centricity, sustainability, and resilience – are guiding these changes with the intent to provide a smarter, greener, and digitalized society and market. The human-centric pillar aims to bring people back to the centre of attention by using the advances of Industry 4.0 technologies. Previous studies have shown a tendency for new services development based on Industry 5.0. This paper aims to show the development from product-related services influenced by digital technologies to human-centric product-related services. Data used for this study was obtained through a Digital Servitization Survey in 2023, and the dataset represents the current state of the Republic of Serbia’s manufacturing sector. The main findings of this paper show a correlation between human-centricity and digital technologies, human-centricity and product-related services with the use of digital technologies, and their influence on firms’ annual turnover
Yard Logistics: Framework and Classification of Yard Types
No full textPart 3: Transforming Engineer-to-Order Projects, Supply Chains, and Systems in Turbulent TimesInternational audienceFor shipyards and offshore construction yards delivering highly customized and complex products via an engineer-to-order (ETO) manufacturing approach, the importance of logistics performance is increasing. This is occurring because of lower profit margins and more challenging market environments, especially in the Norwegian yard industry. However, yard logistics has not yet received adequate academic attention, and there is a lack of knowledge on how to address the current need for more cost-efficient logistics at yards. Therefore, this paper aims to develop and structure knowledge on yard logistics. Via a multiple case study of eight Norwegian yards, this paper builds on empirical evidence to establish a definition and description of yards as logistics systems in ETO manufacturing. Specifically, the paper outlines the constituents and main activities of yard logistics and describes the key characteristics of yard logistics. Furthermore, a classification model is developed to differentiate between the logistics requirements of three main types of yards: fabrication yards, outfitting yards, and service yards. This classification helps in understanding the specific logistics needs and challenges faced by different types of yards, contributing to the academic literature and providing practical insights for practitioners to enhance yard logistics performance
Comparison of Community Detection Algorithms for Reducing Variant Diversity in Production
No full textPart 6: Applications of Artificial Intelligence in ManufacturingInternational audienceIn production planning and control, discrete-event simulation (DES) is commonly used to address optimization challenges. DES using simgen generally begins with data preprocessing, parameterization, and experiment design. However, due to the complexity of manufacturing environments, DES models require careful parameterization, with empirical experiments designed to ensure efficient execution. This parameterization involves optimizing parameter settings for different materials based on routing, bill-of-materials complexity, and other production process-related features. To achieve optimized parameterization within expected timeframes, reducing variant diversity to eliminate redundant materials is necessary by using data-driven approaches. In this study, to identify representative materials, a network-based approach with five community-detection algorithms is compared for their efficiency in execution time and efficient module detection by constructing bipartite networks of material and routing features for identifying similar material groups and representative materials. The results show that communities and subcommunities identify representative materials by significantly reducing the initial number of materials with a faster approach that can be used for DES parameterization
De-politicised in Court: The Interaction of Democracy with Innovation Projects
No full textPart 1: Modelling Supply Chain and Production SystemsInternational audienceThis study explores the interaction of politics and innovation. We discuss how entrepreneurs and innovators face policies, legislation, governmental rules and public opinion when compiling innovation projects. This paper highlights the power of politics in a democracy, emphasising the principle of checks and balances. We also touch upon the concept of deliberative democracy and how it should ideally function. Since the authors argue that excessive politicisation may hinder innovation, they seek to test this theory. The aim is to provide insight for overcoming undesired political influence, thereby helping those working on innovation projects to lower or mitigate risk. This study underlines the need to understand the implications of political leadership on innovation projects and statutory amendments. Further, it discusses the potential impact of political constraints on innovation, emphasising the need for strategies to influence policymakers effectively. The authors not only acknowledge the existence and need for political leadership in a democratic society, but also are interested in understanding the implications of such leadership on innovation. A two-sample case study is conducted with mixed methods research. Literature reviews and interviews are combined with theory in an iterative process to test the following hypothesis: If governments and departments become too politicised this may impede innovation. Results from our two cases vindicate our assumption. This study encompasses the maritime and marine sectors, mainly within ports, transport and logistics
Assessing Trustworthy Artificial Intelligence of Voice-Enabled Intelligent Assistants for the Operator 5.0
No full textPart 2: Human-centred Manufacturing and Logistics Systems Design and Management for the Operator 5.0International audienceThe concept of Trustworthy Artificial Intelligence (TAI) focuses on the establishment of trust in AI systems’ development, deployment, and use. In this realm, the European Commission (EC) developed the Assessment List for Trustworthy Artificial Intelligence (ALTAI) in order to enable the assessment of trustworthiness in the AI systems under development. Since this is an emerging topic, there is little evidence on how to apply ALTAI. In this paper, we present the application of ALTAI on a Digital Intelligent Assistant (DIA) for manufacturing. In this way, we aim at contributing to the enrichment of ALTAI applications and to the drawing of remarks regarding its applicability to diverse domains. We also discuss our responses to the ALTAI questionnaire, and present the score and the recommendations derived from the ALTAI web application