Abstract
This communication explores an optical extreme learning architecture to unravel the impact of using a nonlinear optical media as an activation layer. Our analysis encloses the evaluation of multiple parameters, with special emphasis on the efficiency of the training process, the dimensionality of the output space, and computing performance across tasks associated with the classification in low-dimensionality input feature spaces. The results enclosed provide evidence of the importance of the nonlinear media as a building block of an optical extreme learning machine, effectively increasing the size of the output space, the accuracy, and the generalization performances. These findings may constitute a step to support future research on the field, specifically targeting the development of robust general-purpose all-optical hardware to a full-stack integration with optical sensing devices toward edge computing solutions.

Abstract
The European Project Semester (EPS) at Instituto Superior de Engenharia do Porto (ISEP) is a capstone engineering design programme in which students, organised in multidisciplinary and multicultural teams, develop a solution for a proposed problem, taking into account sustainability, ethical and market concerns. This paper describes a research project aimed at raising awareness and changing behaviour in relation to waste disposal, carried out by a team of EPS@ISEP students during spring 2023. BinIt, as the project is named, targets young adults who want to live in a cleaner city. Unlike other campaigns, it simplifies and stimulates proper waste disposal and recycling, tackling the root of the problem and creating a new social norm. BinIt includes a campaign, a web app and the Garbage Gladiator bin. The app consists of a city map where users can pin and check bin locations, and an educational platform with information on waste disposal and recycling issues. Gamification is incorporated through a ranking system. The Garbage Gladiator is a physical container for urban public spaces specially designed to encourage people to dispose of their waste correctly. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

Abstract
The footwear industry is known for its longstanding traditional production methods that require intense manual labor. Roughing, for example, is regarded as one of the significant and critical operations in shoe manufacturing and consists of using abrasive tools to remove a thin layer of the shoe's surface, creating a slightly roughened texture that provides a better surface area for adhesion. As such, workers are typically subjected to hazardous substances (i.e., dust, chromium), repetitive strain injuries, and ergonomic challenges. Although robots can automate repetitive tasks and perform with high precision and consistency, the footwear industry is usually reluctant to employ industrial robots due to the need for restructuring. This paper addresses the challenge of re-designing the lateral roughing of uppers to allow robot-assisted manufacturing with minimal modifications in the manufacturing process. The proposed innovative system employs a robotic manipulator to perform roughing based on data collected from preceding manufacturing steps. Workers marking the mesh line of each sole-upper pair can simultaneously teach the manipulator path for that same pair, using a programming-by-demonstration approach. Multiple paths were collected by outlining a piece of footwear, converted into robot instructions, and deployed on a simulated and real industrial manipulator. The key findings of this research showcase the capability of the proposed solution to replicate collected paths accurately, indicating potential applications not only in roughing processes but also in similar tasks like primer and adhesive application.

Abstract
This paper examines the concept of learning factories and their role in addressing contemporary challenges in the production sector. Learning factories integrate learning and production environments, offering hands-on experiences to develop essential competencies for modern manufacturing. Originating from initiatives like the Germany's "Lernfabriken" in the late 1980s and the National Science Foundation's funding in the 1990s, learning factories have gained global prominence. They serve as platforms for research, education, and workforce development, attracting students and workers from diverse sectors. Examples from Europe, the United States, and China illustrate various approaches to leveraging learning factories for industrial advancement and skill development. Overall, learning factories play a vital role in fostering innovation, enhancing competitiveness, and driving economic growth in the manufacturing sector. © 2024 The Authors.

Abstract
Lately, the field of optical computing resurfaced with the demonstration of a series of novel photonic neuromorphic schemes for autonomous and inline data processing promising parallel and light-speed computing. We emphasize the Photonic Extreme Learning Machine (PELM) as a versatile configuration exploring the randomness of optical media and device production to bypass the training of the hidden layer. Nevertheless, the implementation of this framework is limited to having the output layer performed digitally. In this work, we extend the general PELM implementation to an all-optical configuration by exploring the amplitude modulation from a spatial light modulator (SLM) as an output linear layer with the main challenge residing in the training of the output weights. The proposed solution explores the package pyTorch to train a digital twin using gradient descent back-propagation. The trained model is then transposed to the SLM performing the linear output layer. We showcase this methodology by solving a two-class classification problem where the total intensity reaching the camera predicts the class of the input sample.

Abstract
Image segmentation for detecting illegal landfill waste in aerial images is essential for environmental crime monitoring. Despite advancements in segmentation models, the primary challenge in this domain is the lack of annotated data due to the unknown locations of illegal waste disposals. This work mainly focuses on evaluating segmentation models for identifying individual illegal landfill waste segments using limited annotations. This research seeks to lay the groundwork for a comprehensive model evaluation to contribute to environmental crime monitoring and sustainability efforts by proposing to harness the combination of agnostic segmentation and supervised classification approaches. We mainly explore different metrics and combinations to better understand how to measure the quality of this applied segmentation problem.