Giuseppe Antuono

El artículo presenta los resultados de un taller de experimentación gráfico-pedagógica desarrollado con el objetivo de formar a 35 estudiantes de ingeniería de la edificación en aproximaciones gráficas analógicas, digitales e híbridas. El taller, como primera experiencia para los estudiantes, fue realizado sobre el terreno para desarrollar conocimiento compartido de la arquitectura expositiva de la Mostra d’Oltremare de Nápoles. Este taller promovió la hibridación de representaciones y mapeos analógicos y digitales. Tras un primer momento de conocimiento de los tres pabellones escogidos, a partir de la lectura de datos historiográficos y el uso de tecnologías de levantamiento digital en el trabajo de campo. Los estudiantes se dividieron en grupos y trabajaron con sus cuadernos, produciendo dibujos a mano alzada, respondiendo así a un propósito de proyecto diferente, según el juego de rol propuesto en seis partes: patrimonio, paisaje, uso turístico, cliente, administración municipal y autoridad expositiva. La sesión crítica final del taller, llamada «Cartografía Arquitectónica», permitió a los estudiantes producir paneles técnico-explicativos, aplicando la técnica Pecha Kucha y la prefiguración de la intervención proyectual a través de la hibridación del dibujo analógico y digital.

This contribution offers a critical reinterpretation of Franciscan architecture in Campania, developed through the reuse and transformation of pre-existing structures, particularly castles, fortifications, and medieval noble residences. Rather than focusing solely on stylistic or chronological aspects, the study adopts a multidimensional approach, highlighting the processes through which these spaces acquired new meanings. The Franciscan Order has consistently demonstrated a notable ability to integrate into local contexts, often choosing sites already rich in historical, social, or strategic significance. By reinterpreting such spaces considering their spiritual and communal needs, the friars transformed fortified or noble architectures into places of prayer, retreat, and community life. Within this framework, the investigation then focuses on a significant case study: a monastic complex in Campania established on a fortified pre-existence, analysed through detailed historical and morphological reconstruction. The research relies on the systematic acquisition of data, combining digital surveys with documentary sources. This integrated approach allows for the reconstruction of the phases of use and functional transformations of the site, revealing both the original spatial layout and the successive layers of stratification that shape its present identity. By combining digital technologies with historical-critical analysis, the work aims to provide a renewed “cultural visibility”, valuable for both academic purposes and the broader dissemination and enhancement of heritage.

Today, numerous studies explore the concepts of Smart City and City Information Modeling (CIM), highlighting the need to develop methods for systematizing, analyzing, and representing data typically managed by different information systems. The shared vision is to integrate BIM outputs with those from GIS, as well as with data from various other sources (historical documents, technical reports, IoT sensors, etc.), within a single working environment, thus building a true digital twin of extensive territorial areas. The goal is to optimize decision-making processes at both building and urban scales, and a potential solution lies in the combined use of Business Intelligence (BI) tools, which allow for the reading, integration, and querying of data stored across the different information systems mentioned. In this context, the present contribution aims to frame the issue of data integration and to test a digital solution integrating BIM, GIS, and BI, developed through a collaboration between the research group at the University of Naples Federico II and the company ACCA Software, and applied to publicly owned building assets.

The study proposes an optimized approach for feature selection in the semantic segmentation of point clouds within the architectural domain of cultural heritage, with a specific focus on historical monastic architecture. The goal is to enhance the automatic recognition and classification of architectural elements using the Random Forest algorithm, by reducing classifier dependency and increasing the model’s generalization capability. The developed method is based on a multiscale statistical selection of features, through p-value analysis and the optimization of influence radii, fully automating the process within a Python environment. The method was tested on a TLS point cloud dataset specifically built for Franciscan cloisters in the Campania region, segmented into ten architectural classes. The new approach builds upon the existing but implemented RF4PCC model, against which it was compared, showing significant improvements in the classification of minority classes, thanks to the adoption of the class_weight=”balanced” parameter and the expansion of the dataset. The analysis of feature_importances_ revealed biases related to class imbalance, which were addressed through regularization strategies and complexity control of the decision trees. Experimental results show an increase in the macro F1-score and greater fairness in class classification. The proposed approach proves effective for applications in the cultural heritage field, offering an interpretable, efficient, and adaptable method for complex architectural contexts.

In recent years, automatic segmentation and classification of data from digital surveys have taken a central role in built heritage studies. However, the application of Machine and Deep Learning (ML and DL) techniques for semantic segmentation of point clouds is complex in the context of historic architecture because it is characterized by high geometric and semantic variability. Data quality, subjectivity in manual labeling, and difficulty in defining consistent categories may compromise the effectiveness and reproducibility of the results. This study analyzes the influence of three key factors—annotator specialization, point cloud density, and sensor type—in the supervised classification of architectural elements by applying the Random Forest (RF) algorithm to datasets related to the architectural typology of the Franciscan cloister. The main innovation of the study lies in the development of an advanced feature selection technique, based on multibeam statistical analysis and evaluation of the p-value of each feature with respect to the target classes. The procedure makes it possible to identify the optimal radius for each feature, maximizing separability between classes and reducing semantic ambiguities. The approach, entirely in Python, automates the process of feature extraction, selection, and application, improving semantic consistency and classification accuracy.