The advent of Industry 5.0 represents a paradigm shift towards a more human-centric approach in manufacturing, focusing on integrating human operators with advanced technological systems. Despite significant progress in predictive maintenance for machinery, there is a notable gap in predictive assessment technologies to safeguard human operators.
This thesis introduces a novel conceptual framework designed to fill this gap by leveraging predictive technologies and methodologies to monitor human operators in Industry 5.0 paradigm settings proactively. Our framework emphasizes the importance of human well-being and safety by integrating data collection, advanced analytics, and targeted intervention techniques. Through a literature review of related works, a formulation of a taxonomy of the human factors to be considered, and a detailed exposition of our framework, we highlight its potential to enhance operational efficiency, environmental sustainability, and, importantly, the overall welfare of the workforce. This research underlines the critical need for a balanced focus on both technological advancement and the well-being of human operators, proposing a preemptive approach that aligns with the pillars of Industry 5.0. We discuss the implications of our findings for future research, particularly the need for ethical data collection practices, real-time data processing techniques, and personalized interventions. The proposed framework categorizes conceptual approaches and introduces recent innovations in predictive assessment technologies, outlining the way for more sustainable, efficient, and human-centric industrial environments. The proposed framework categorizes conceptual approaches and introduces recent innovations in predictive assessment technologies, outlining the way for more sustainable, efficient, and human-centric industrial environments.
The advent of Industry 5.0 represents a paradigm shift towards a more human-centric approach in manufacturing, focusing on integrating human operators with advanced technological systems. Despite significant progress in predictive maintenance for machinery, there is a notable gap in predictive assessment technologies to safeguard human operators.
This paper introduces a novel conceptual framework designed to fill this gap by leveraging predictive technologies and methodologies to proactively monitor human operators in Industry 5.0 paradigm settings. Our framework emphasizes the importance of human well-being and safety by integrating data collection, advanced analytics, and targeted intervention techniques. Through a literature review of related works and a detailed exposition of our framework, we highlight its potential to enhance operational efficiency, environmental sustainability, and, importantly, the overall welfare of the workforce. This research underlines the critical need for a balanced focus on both technological advancement and the well-being of human operators, proposing a preemptive approach that aligns with the pillars of Industry 5.0. We discuss the implications of our findings for future research, particularly the need for ethical data collection practices, real-time data processing techniques, and personalized interventions. The proposed framework categorizes conceptual approaches and introduces recent innovations in predictive assessment technologies, outlining the way for more sustainable, efficient, and human-centric industrial environments.
The transition to Industry 5.0 underscores a critical shift toward human-centric manufacturing, motivating the need to bridge the gap in systems for the proactive assessment of human operators.
To address that, this paper introduces a conceptual framework that integrates data collection, analytics, and targeted interventions to enhance the safety and well-being of operators in Industry 5.0 settings. The proposed framework categorizes conceptual approaches and introduces recent innovations in predictive assessment technologies, outlining the way for more sustainable, efficient, and human-centric industrial environments.
This paper presents the work of the CLOSE group, a team of students from the University of Padua, Italy, for the Conference and Labs of the Evaluation Forum (CLEF) LongEval LAB 2023 Task 1.
Our work involved developing an Information Retrieval (IR) system that can handle changes in data over time while maintaining high performance. We first introduce the problem as stated by CLEF and then describe our system, explaining the different methodologies we implemented. We provide the results of our experiments and analyze them based on the choices we made regarding various techniques. Finally, we propose potential avenues for future improvement of our system.
In questa tesi viene affrontato il tema della compressione dati con perdite, effettuata attraverso l’algoritmo di Linde-Buzo-Gray (LBG) e l’autoencoder (AE). I due metodi sono prima stati analizzati analiticamente in termini di efficienza di compressione, complessità computazionale e occupazione di memoria. In seguito, i due metodi sono stati testati su due dataset, per andare a valutare la qualità della compressione e le regioni di decisione create.
È emerso che, a parità di bit usati per la compressione, l’autoencoder effettua una ricostruzione equivalente o migliore dell’algoritmo LBG, risultando vantaggioso anche in termini di occupazione di memoria e complessità computazionale. Si nota inoltre che, nonostante la componente di non linearità introdotta dal quantizzatore, in generale un autoencoder lineare riesce ad ottenere una qualità di compressione equivalente a quella di autoencoder non lineari.