Parthenope University of Naples
Archivio della ricerca - Università degli studi di Napoli "Parthenope"Not a member yet
29604 research outputs found
Sort by
Interpolation and Machine Learning Methods for Sub-Hourly Missing Rainfall Data Imputation in a Data-Scarce Environment: One- and Two-Step Approaches
No full textComplete sub-hourly rainfall datasets are critical for accurate flood modeling, real-time
forecasting, and understanding of short-duration rainfall extremes. However, these datasets
often contain missing values due to sensor or transmission failures. Recovering missing
values (or filling these data gaps) at high temporal resolution is challenging due to the
imbalance between rain and no-rain periods. In this study, we developed and tested two
approaches for the imputation of missing 10-min rainfall data by means of machine learning
(Multilayer Perceptron and Random Forest) and interpolation methods (Inverse Distance
Weighting and Ordinary Kriging). The (a) direct approach operates on raw data to directly
feed the imputation models, while the (b) two-step approach first classifies time steps as rain
or no-rain with a Random Forest classifier and subsequently applies an imputation model
to predicted rainfall depth instances classified as rain. Each approach was tested under
three spatial scenarios: using all nearby stations, using stations within the same cluster, and
using the three most highly correlated stations. An additional test involved the comparison
of the results obtained using data from the imputed time interval only and data from a time
window containing several time intervals before and after the imputed time interval. The
methods were evaluated with reference to two different environments, mountainous and
coastal, in Campania region (Southern Italy), under data-scarce conditions where rainfall
depth is the only available variable. With reference to the application of the two-step
approach, the Random Forest classifier shows a good performance both in the mountainous
and in the coastal area, with an average weighted F1 score of 0.961 and 0.957, and an
average Accuracy of 0.928 and 0.946, respectively. The highest performance in the regression
step is obtained by the Random Forest in the mountainous area with an R
2 of 0.541 and
an RMSE of 0.109 mm, considering a spatial configuration including all stations. The
comparison with the direct approach results shows that the two-step approach consistently
improves accuracy across all scenarios, highlighting the benefits gained from breaking
the data imputation process in stages where different physical conditions (in this case,
rain and no-rain) are separately managed. Another important finding is that the use of
time windows containing data lagged with respect to the imputed time interval allows
capturing the atmospheric dynamics by connecting rainfall instances at different time levels
and distant stations. Finally, the study confirms that machine learning models outperform
spatial interpolation methods, thanks to their ability to manage data with complicated
internal structure
Guerra giustizia giurisprudenza
No full textUna breve rimeditazione avente ad oggetto quelle che appaiono le testimonianze più significative sul rapporto tra categorie giuridiche e vicende belliche, al fine di verificare una possibile trama idonea ad 'annodare' l’antica normativa feziale alla successiva elaborazione ciceroniana ed entrambe al pensiero dei prudentes compresi fra gli Antonini, i Severi e Diocleziano
Analysing EU unemployment and underemployment in a fuzzy perspective: The comparison between fuzzy and official rates
No full textGender Is the Main Predictor of Wearing-Off and Dyskinesia in Levodopa-Naïve Patients with Parkinson's Disease
No full textBackground: Evidence suggests that female gender represents a risk factor for the development of motor/nonmotor fluctuations and dyskinesia in Parkinson's disease (PD). So far, no prospective study has analyzed this aspect in relation to the introduction of levodopa treatment. Objective: This prospective multicenter study aims to assess the development of motor/nonmotor fluctuations and dyskinesia based on gender over a 2-year observation period in PD patients starting levodopa. Methods: Two hundred and eighty-nine PD patients requiring levodopa at baseline were enrolled at 17 Movement Disorders Centers and followed for 2 years. Gender differences in the development of fluctuations, defined as a score ≥2 in the 19-item Wearing-Off Questionnaire, and dyskinesia, defined by Movement Disorders Society Unified Parkinson's Disease Rating Scale Part IV (MDS-UPDRS-IV) score >0 on item 4.1 were assessed. Baseline predictors of such complications were evaluated by stepwise multivariate logistic regression analysis. Results: Two hundred and sixteen patients (139 men, 77 women) completed the follow-up (M24). By M24, 53,2% of men and 64.9% of women had fluctuations (P = 0.048), whereas 5% of men and 14.3% of women developed dyskinesia (P = 0.0185). Multivariate analysis showed that female gender significantly predicted wearing-off (Odds ratio [OR] = 1.930; P = 0.0333), whereas older age was a significant protective factor (for 5-year increase: OR = 0.712; P < 0.0001). Multivariate analysis showed that gender (OR = 3.405; P = 0.0228) and MDS-UPDRS Part III score (for a 5-unit increase: OR = 1.281; P = 0.0239) were significant predictors of dyskinesia at M24. Conclusions: Female gender was the strongest predictor of fluctuations and dyskinesia after 2-year intake of levodopa. This finding could have important implications for the development of gender-oriented therapeutic recommendations in early PD
Advancing Circular Supplier Selection: Multi-Criteria Perspectives on Risk and Sustainability
No full textSupplier selection is a crucial factor for ensuring compliance with the circular economy’s principles. Existing approaches often overlook the integration of circularity and risk assessment in supplier evaluation, limiting their effectiveness in achieving sustainability goals. This paper addresses this gap by applying suitable criteria and proposing a structured decision-making model for circular supplier selection. The model innovatively integrates Multi-Criteria Decision Analysis (MCDA) techniques with risk evaluation, providing a comprehensive framework for assessing suppliers in circular supply chains. By advancing the theoretical understanding of circular supplier selection, this research contributes to both academia and practice, reinforcing the alignment between supply chain decision-making and the Sustainable Development Goal (SDG), particularly Target 12.5
The ALES Platform: State of the Art and Gap Analysis for an Academic LLM Chatbot
No full textThe widespread use of large language models (LLMs) in education has introduced challenges related to citation reliability, academic integrity, and factual accuracy. This study presents the Augmented LLM-Based Engagement System (ALES), a domain-specific chatbot designed for higher education. ALES incorporates retrieval-augmented generation (a method for grounding responses in verified documents), citation-aware output, and ethical usage safeguards. The system's design was informed by a structured state-of-the-art analysis of 584 articles, of which 76 peer-reviewed studies were selected for analysis based on strict inclusion criteria. The review identified critical limitations in current academic AI systems, including lack of transparency, source verifiability, and institutional integration. ALES addresses these gaps through a modular architecture and university-compatible interface. Preliminary comparison with existing academic AI tools highlights ALES's potential to support student learning while promoting responsible use. This paper outlines the platform's architecture and proposes directions for future development and evaluation
Educazione, Impegno e Ricerca in Danilo Dolci
No full textNel testo si prendono brevemente in esame alcuni degli
aspetti di cui la prospettiva educativa di Dolci si sostanzia, in primis il
legame tra educazione e azione politica, la crescita del pensare e del
fare insieme attraverso la maieutica, il ruolo e la responsabilità
dell’educatore, di liberazione dai destini, potremmo dire, di aprire alla
ricchezza e alla complessità e, al contempo, di offrire risorse e strumenti,
anche dialogici, per individuare quanto emerge come prioritario
ed essenziale
Comparison of Machine-Learning Algorithms for SPOT 7 Multispectral Image Classification
No full textPrecise and timely land-cover identification plays an important role in effective environmental monitoring and land management. This study compares the performance of five machine-learning classifiers – support vector machine (SVM), decision tree (DT), normal Bayes (NB), random forest (RF), and k-nearest neighbor (k-NN) – in the land-cover mapping of the Agro Nocerino Sarnese area (Southern Italy) using high-resolution SPOT 7 pan-sharpened multispectral images with a pixel size of 1.5 m × 1.5 m. The data set consisted of blue, green, red, and near-infrared (NIR) bands and was processed with Orfeo ToolBox (OTB) software. Two data sets were analyzed: DS-3B (which included only the visible bands [blue, green, and red]), and DS-4B (which also included the NIR band). A comparison of the classifiers’ performances across various land-cover classes was conducted in order to assess their respective classification accuracy. The results showed that SVM and k-NN achieved the highest overall accuracy levels (93% and 92%, respectively) using only the visible bands, whereas the decision tree classifier performed best when the NIR band was included. Random forest achieved excellent accuracy in vegetation classes (88–99%) but struggled with misclassifications in bare soil and man-made classes such as buildings and roads. These results emphasized the significant impact of data set characteristics on classifier performance as well as the importance of band selection and pan-sharpening techniques in high-resolution land-cover mapping
Wider effects of transportation planning: Focusing on socioeconomic dynamics and issues
No full textTransport systems have a significant impact on socioeconomic growth. However, traditional cost-benefit analysis (CBA) techniques are often insufficient to address the critical social aspects of transport planning. Our research comprehensively reviews notable social theories and their relevance to transportation. We examine the existing literature on the social impact of investments in transportation networks and services, emphasizing social justice and equity in decision-making processes. Furthermore, we list additional methods and tools to complement CBA in assessing social dimensions. Finally, this study presents a novel application based on the methodological review above, developed in order to determine the impact of introducing high-speed rail on demographic vibrancy in Italy