Archivio Istituzionale della Ricerca - Università degli Studi della Campania "Luigi Vanvitelli"
Not a member yet
116395 research outputs found
Sort by
Anomaly detection in manufacturing systems with temporal networks and unsupervised machine learning
No full textTraditional manufacturing systems face significant challenges in detecting operational anomalies due to the absence of advanced sensor networks and intelligent machinery commonly associated with Industry 4.0. Existing solutions often rely on sophisticated, interconnected infrastructures, which are not feasible in conventional settings. This paper introduces a novel methodology for anomaly detection tailored specifically for traditional manufacturing environments, addressing the gap in cost-effective monitoring solutions. The proposed approach models manufacturing systems as complex temporal networks, where each machine or process is represented as a node and job flows between machines form the network edges over time. The novelty of this method lies in the combination of dynamic network theory with unsupervised machine learning. Statistical features extracted from the temporal networks are processed through dimensionality reduction techniques, specifically Principal Component Analysis (PCA) and Deep Neural Autoencoders, to reduce feature complexity while preserving essential information. The reduced feature sets are then analysed using multiple unsupervised anomaly detection algorithms, including Isolation Forest, One-Class Support Vector Machine (OC-SVM), and Local Outlier Factor (LOF). This approach does not require significant infrastructure upgrades, making it suitable for traditional manufacturing plants while still aligning with Industry 4.0 paradigms. By using only normal job flow data, it provides a cost-effective solution where anomalous data is scarce. The results demonstrate that Local Outlier Factor and Isolation Forest, when combined with Autoencoder-based feature reduction, achieved an F1-score exceeding 84%, with precision close to 99% and recall at 74%. This strong performance underscores the methodology's potential for real-world manufacturing environments, bridging the gap between traditional settings and modern Industry 4.0 paradigms
Random Survival Forest for Censored Functional Data
No full textThis article introduces a Random Survival Forest (RSF) method for functional data. The focus is specifically on defining a new functional data structure, the Censored Functional Data (CFD), for addressing the challenge of accurately modelling time-to-event data in the presence of censoring and irregular temporal structures. Traditional survival models struggle to incorporate complex functional patterns, making the proposed approach particularly valuable for improving prediction and interpretation. This approach allows for precise modelling of functional survival trajectories, leading to improved interpretation and prediction of survival dynamics across different groups. A medical survival study on the benchmark Sequential Organ Failure Assessment (SOFA) dataset and an extensive simulation study are presented. Results show good performance of the proposed approach, particularly in ranking the importance of predicting variables
Simultaneous Medullary and Papillary Thyroid Carcinomas: Personal Experience Report and Literature Review
No full textWhile the frequency of papillary thyroid carcinoma (PTC) has increased in recent decades, both due to improvements in diagnostic procedures and a real, effective percentage increase in cases, the frequency of medullary thyroid carcinoma (MTC), however, has remained almost unchanged, representing 3–5% of thyroid cancer cases. Our experience relates to the observation of cases with the synchronous presence of PTC and MTC, also in chronic autoimmune thyroiditis, and this led us to carry out a brief review of the literature on the subject, with the aim above all of identifying the most correct postoperative therapeutic process
Insulin resistance and cancer: molecular links and clinical perspectives
No full textThe association between insulin resistance (IR), type 2 diabetes mellitus (T2DM), and cancer is increasingly recognized and poses an escalating global health challenge, as the incidence of these conditions continues to rise. Studies indicate that individuals with T2DM have a 10–20% increased risk of developing various solid tumors, including colorectal, breast, pancreatic, and liver cancers. The relative risk (RR) varies depending on cancer type, with pancreatic and liver cancers showing a particularly strong association (RR 2.0–2.5), while colorectal and breast cancers demonstrate a moderate increase (RR 1.2–1.5). Understanding these epidemiological trends is crucial for developing integrated management strategies. Given the global rise in T2DM and cancer cases, exploring the complex relationship between these conditions is critical. IR contributes to hyperglycemia, chronic inflammation, and altered lipid metabolism. Together, these factors create a pro-tumorigenic environment conducive to cancer development and progression. In individuals with IR, hyperinsulinemia triggers the insulin-insulin-like growth factor (IGF1R) signaling pathway, activating cancer-associated pathways such as mitogen-activated protein kinase (MAPK) and phosphatidylinositol 3-kinase (PIK3CA), which promote cell proliferation and survival, thereby supporting tumor growth. Both IR and T2DM are linked to increased morbidity and mortality in patients with cancer. By providing an in-depth analysis of the molecular links between insulin resistance and cancer, this review offers valuable insights into the role of metabolic dysfunction in tumor progression. Addressing insulin resistance as a co-morbidity may open new avenues for risk assessment, early intervention, and the development of integrated treatment strategies to improve patient outcomes
Towards defect-free lattice structures in additive manufacturing: A holistic review of machine learning advancements
No full textAdditive manufacturing has transformed modern production by enabling the fabrication of complex and lightweight structures, particularly lattice geometries, which are widely used in aerospace, automotive, medical, and energy industries. Renowned for their superior strength-to-weight ratios and energy absorption properties, lattice structures have unlocked new possibilities for weight-critical, high-performance applications. However, their intricate geometries and susceptibility to defects, such as surface roughness, voids, and porosity, pose significant challenges to ensuring mechanical integrity and functional reliability. Traditional methods of defect mitigation, process control and optimization, are often constrained by high computational costs and limited adaptability to complex defect mechanisms. To address these challenges, machine learning (ML) has emerged as a transformative tool, offering data-driven solutions for defect prediction, detection, and minimization. These techniques excel in optimizing designs, tuning process parameters, and enabling real-time adjustments to mitigate defects, thereby enhancing manufacturing outcomes. While numerous studies have explored ML applications in additive manufacturing, current literature lacks a specific focus on its use for defect minimization in lattice structures, which require defect-free fabrication to achieve optimal performance. This review paper fills this critical research gap by investigating the application of advanced ML techniques across key areas: design optimization, properties prediction, process parameter tuning, and defect detection and real-time monitoring for lattice structures. In doing so, it gives a comprehensive outline of lattice structures, the challenges posed by manufacturing defects, and state-of-the-art ML applications in AM. This study paves the way for defect-free lattice structures, maximizing their industrial potential
La sfera emotiva nello spazio scolastico tra percepito, concepito e vissuto
No full textLa centralità del corpo come protagonista dello spazio e come attore proteso all’apprendimento, nel campo dell’architettura dei luoghi dell’istruzione, offre una chiave di lettura che interessa le discipline della Pedagogia e degli Interni rafforzandone una intesa. Prendendo in esame il corpo umano in analogia al corpo architettonico si riscontra che en-trambi rappresentano il tempio della conoscenza in cui si consacra il sapere. Se, da un lato la sensibilità dell’individuo favorisce lo sviluppo attraverso lo spettro cognitivo arricchendo la sua sfera personale, dall’altro cerca una relazione sinergica con l’intorno, creando occasioni di dialogo intimamente connesse. Su questa prospettiva si orienta una lettura dell’istituzione scola-stica come corpo che racconta, non solo parole ma anche un benessere psicofisico dell’abitante. Non esiste oggi ancora un linguaggio che codifica e mette a sistema come me-todo il progetto degli interni delle scuole per rispondere ad ogni contesto ambientale e sociale, ma potrebbero esistere invece occasioni per operare sulla messa in scena di fenomeni atmo-sferici per creare architetture dal coinvolgimento emotivo. Nella gestione del lavoro educa-tivo, stravolgere la matrice spazio-temporale significa far tendere l’interesse verso un modello di cultura del progetto in cui lo spazio atmosferico introduce una completa libertà di azione che aiuta a far conciliare il sistema mente-corpo-ambiente favorendo l’apprendimento e la con-figurazione di identità
Hall e cortile come spazi di attesa
No full textQuesto libro è una raccolta di lavori marginali come occasioni di ricerca. Opportunità che partono dalla sovrascrittura dell’esistente e seguono le prescrizioni della Grammatica euclidea nel rapporto con la forma e lo spazio