Abstract
Quality inspection is a critical step in ensuring the quality and efficiency of textile production processes. With the increasing complexity and scale of modern textile manufacturing systems, the need for accurate and efficient quality inspection and defect detection techniques has become paramount. This paper compares supervised and unsupervised Machine Learning techniques for defect detection in the context of industrial textile production, in terms of their respective advantages and disadvantages, and their implementation and computational costs. We explore the use of an autoencoder for the detection of defects in textiles. The goal of this preliminary work is to find out if unsupervised methods can successfully train models with good performance without the need for defect labelled data. (c) 2023 The Authors. Published by Elsevier B.V.

Abstract
Quality inspection is crucial in the textile industry as it ensures that the final products meet the required standards. It helps detect and address defects, such as fabric flaws and stitching irregularities, enhancing customer satisfaction, and optimizing production efficiency by identifying areas of improvement, reducing waste, and minimizing rework. In the competitive textile market, it is vital for maintaining customer loyalty, brand reputation, and sustained success. Nonetheless, and despite the importance of quality inspection, it is becoming increasingly harder to hire and train people for such tedious and repetitive tasks. In this context, there is an increased interest in automated quality control techniques that can be used in the industrial domain. In this paper we describe a computer vision model for localizing and classifying different types of defects in textiles. The model developed achieved an mAP@0.5 of 0.96 on the validation dataset. While this model was trained with a publicly available dataset, we will soon use the same architecture with images collected from Jacquard looms in the context of a funded research project. This paper thus represents an initial validation of the model for the purposes of fabric defect detection.

Abstract
Considering the great challenge of implementing digital tools to improve collaboration in the value chain and promote the adoption of circularity strategies, as is the case with digital traceability tools and digital product passports. This paper presents an innovative proposal for implementing an industrial data sharing ecosystem, namely an architecture and platform for digital traceability between entities based on Data Spaces. To validate our proposal, a use case scenario was implemented as part of the BioShoes4All project.

Abstract
Legislation is a technical domain characterized by highly specialized knowledge forming a large corpus where content is interdependent in nature, but the context is poorly formalized. Typically, the legal domain involves several document types that can be related. Amendments, past judicial interpretations, or new laws can refer to other legal documents to contextualize or support legal formulation. Lengthy and complex texts are frequently unstructured or in some cases semi-structured. Therefore, several problems arise since legal documents, articles, or specific constraints can be cited and referenced differently. Based on legal annotations from a real-world scenario, an architectural approach for modeling a Knowledge Organization System for classifying legal documents and the related legal objects is presented. Data is summarized and classified using a topic modeling approach, with a view toward the improvement of browsing and retrieval of main legal topics and associated terms.

Abstract
Although the concept of Circular Economy (CE) has become popular in recent years, the transition towards a CE system requires a change in consumers' behaviour. However, there is still limited knowledge of consumers' efforts in CE initiatives. The present paper aims to analyse and compare consumers' behaviour towards circular approaches and compare the results on items like generation and demographics. 495 answers were collected through a questionnaire from 3 countries (Albania, Poland, and Portugal). Data collected was analysed mainly through a Crosstabs analysis to identify associations or different behaviours regarding nationality, gender, generation, education, and place of residence. From the paper's findings, we can emphasise that residents of EU countries seem to be more aware of the concept of circular economy. However, price is still a very important factor for EU residents when it comes to deciding on a greener purchase. Albanians (non-EU residents) tend to take a more linear approach when it comes to purchasing a new product regardless of its cost. Regarding the Digital Product Passport, a tool proposed by the European Commission through its Circular Economy Action Plan, non-EU residents have a better understanding of the concept. This tool seems to be more relevant for Millennials and Generation X. Generation Z, i.e., the tech generation, does not show an overwhelming propensity for technological options, such as online buying and digital technologies for a greener society.

Abstract
This paper discusses the Digital Product Passport (DPP) as a key tool for achieving a circular economy. An architecture of the DPP is presented built upon the principles of data spaces and W3C Decentralized Identifiers (DIDs). By leveraging data spaces, the DPP enables secure and controlled data exchange among stakeholders, fostering transparency, traceability, and collaboration throughout the product's lifecycle. The use of decentralized identifiers ensures the uniqueness and verifiability of product-related information, facilitating seamless access and sharing of data. The DPP architecture offers a promising framework for realizing the circular economy by promoting resource efficiency, sustainable practices, and informed decision-making. © 2024 The Author(s). Published by Elsevier B.V.