Politecnio die Bari - Catalogo di prodotti della Ricerca
Not a member yet
36616 research outputs found
Sort by
Development of a novel prognostic risk model for pancreatic adenocarcinoma exploiting multi-omics data
No full textThis paper proposes a novel approach for developing prognostic risk models for pancreatic adenocarcinoma (PDAC) using data from multiple omics layers, including clinical data, micro-RNA (miRNA), copy number variation (CNV), proteomics, phosphoproteomics, transcriptomics, and radiomics. Through a multi-step process, a highly reduced set of prognostically significant features is selected from an initial pool of over 135,000 features. Specifically, the first step involves the selection of omics layers that produce the highest C-index for prognosis prediction when training a Cox proportional hazards model within a leave-one-out (LOO) cross-validation (CV) framework. Dimensionality reduction is performed as a preliminary step using principal component analysis (PCA) to address the high dimensionality of the data before training the Cox model. In the second step, the SelectKBest algorithm is employed to identify the most significant features within the selected layers. This procedure results in the development of a phosphoproteomics-based risk model comprising only four features, achieving a C-index of 0.65 under LOO-CV. Additionally, a transcriptomics-based risk model is derived from the phosphoproteomics model. Its performance is compared against risk models in the literature, consistently demonstrating superior C-index values across all test datasets used in this study
Assessing Soil Sealing Dynamics in the Metropolitan Area of Bari Using Sentinel-2, Sealed Surface Index, and Machine Learning Approaches
No full textSoil sealing, the irreversible covering of natural soil with impermeable material, impacts environmental sustainability by degrading ecosystems and reducing water quality and infiltration capacity. Advanced geospatial detecting and monitoring approaches are, thus, needed to face this critical environmental challenge. This study assesses the effectiveness of two advanced geomatics approaches in detecting the dynamics of sealed surfaces in the metropolitan area of Bari from 2018 to 2024 using Sentinel-2 satellite imageries processed in Google Earth Engine: the sealed surface index and the machine learning-based Classification and Regression Trees algorithm. Twenty-eight Sentinel-2 imageries, acquired during February, May, July, and October, were analyzed. When necessary, a cloud cover masking process was employed before classification. After that, the filtered maps were classified with the two above-mentioned techniques generating four land cover classes: sealed surfaces, vegetation, bare land, and water bodies. Their accuracy was assessed against the training data gathered from the land use map provided by ISPRA. The outcomes demonstrated that incorporating machine learning significantly improved classification accuracy. The sealed surface class exhibited the highest classification accuracy, with Producer’s and User’s Accuracy consistently exceeding 90% and 85%, respectively. Conversely, bare soil proved more challenging to classify, leading to slightly lower accuracy values. These findings highlight the annual variations in sealed surfaces and their correlation with seasonal land-use dynamics. A notable increase in urban sealing, exceeding 2%, was observed between February 2018 and October 2024. This study underscores the importance of continuous monitoring of soil sealing for sustainable urban planning and environmental management
Gap Analysis of Industry 5.0-Driven Product Lifecycle Management
No full textThe transition toward human-centric, resilient, and sustainable manufacturing is redefining the role of Product Lifecycle Management (PLM) systems and the competencies required to implement them effectively. At the same time, the increasing integration of digital technologies—such as digital twin, artificial intelligence, and Internet of Things—adds significant complexity to this transformation. As a result, the academic community has shown growing interest in identifying how PLM competences should evolve to support these emerging paradigms. However, clear research directions in this domain are still lacking. By applying a systematic literature review, this study proposes a strategic research agenda with six promising avenues: (1) Human-centric PLM for skill development and decision support; (2) Resilient PLM systems for disruption management; (3) Sustainable PLM and circular economy integration; (4) Digital twin and AI for intelligent PLM; (5) Interoperability and data governance in PLM; and (6) Scalability and adaptability of PLM in dynamic environments. These findings offer valuable insights to guide future academic work and support the development of PLM systems that are better aligned with the principles of Industry 5.0
Ri_abitare i luoghi di margine del paesaggio del sud Salento ‘‘Risignificazione dei comuni salentini caratterizzati da marginalizzazione e declino demografico”
No full textThe research “Re_inhabiting the marginal places of the landscape of southern Salento. Re-signification of Salento municipalities affected by marginalization and demographic decline” investigates the deep relationship between landscape, architecture, and identity within the territories of Terra di Leuca, adopting the concept of the margin as both an interpretative key and a design tool. Southern Salento, a land of boundaries and crossings, is conceived as a living laboratory where the memory of place and its regenerative capacity become central elements for a renewed territorial vision. In this context, the notion of “place” acquires a symbolic and emotional value, as a custodian of experiences, traditions, and cultural stratifications, while the “margin” transcends its role as a limit to become a threshold — an intermediate, dynamic space where nature, history, and dwelling intertwine.
The aim of the research is to restore meaning to territories often considered peripheral, recognizing within them the potential for rebirth based on an awareness of their roots and on the valorization of the landscape as a system of relationships. The study develops through three main phases: the morphological and historical analysis of the Salento territory; the critical reading of the transformations and vulnerabilities affecting the inner areas of southern Salento; and the definition of a design proposal — the Parco Meridionale Salentino — conceived as both a recompositional device and an operational tool for territorial enhancement.
The research method combines historical, geographical, and design approaches, intertwining documentary sources, cartography, GIS analysis, and fieldwork with a theoretical reflection on the relationship between landscape and architecture. The investigation demonstrates that the Salento landscape cannot be understood through isolated fragments but only within its relational continuity, where each element — natural or constructed — participates in a coherent and dynamic system. The morphology of the land, the agrarian structure, the polycentric settlements, the ancient routes, and the double coastline form the components of a single territorial organism, where memory and contemporary transformation coexist.
The identification of the southern plateau of Leuca as a critical and operational area marks the transition from analysis to design. Here, geographical marginality becomes an opportunity for renewal: the margin turns into a generative place, capable of revealing latent potential and inspiring new forms of dwelling. The Parco Meridionale Salentino emerges as the outcome of this reflection, conceived as a cultural and environmental infrastructure that connects nature and settlement, past and future, conservation and innovation. It takes shape as an open, reticular system in which each fragment of the territory — a farmhouse, an ancient road, a coastal segment — regains meaning within a unified vision.
The landscape, understood not as a mere backdrop but as the protagonist of the project, becomes a space of belonging and responsibility. The research restores to the territory its living dimension, recognizing that to design means to act with care, respecting the historical density of the soil and the fragility of its transformations. In the landscape of Terra di Leuca, finibus terrae, the threshold becomes opportunity, and the boundary turns into a place of encounter between cultures, memories, and possibilities.
The thesis reaffirms that the landscape is a collective fact — not an image to contemplate but an act of culture, a civic practice capable of generating the future. Every dry-stone wall, every ancient path, every rural architecture becomes part of a shared narrative, where the continuity between nature and artifice translates into a new balance between memory and innovation. The Parco Meridionale Salentino thus represents not an endpoint, but the beginning of a re-inhabitation process grounded in knowledge, memory, and responsibility toward the land and future generations
Seeing Through the Robot’s Eyes: Adaptive Point Cloud Streaming for Immersive Teleoperation
No full textAutonomous Mobile Robots (AMRs) are increasingly deployed in diverse scenarios to automate tedious and hazardous tasks. Nonetheless, challenges such as complex environments, sensor occlusions, and limitations of autonomous navigation systems often require human intervention. Teleoperation offers a viable solution, allowing operators to remotely control AMRs when autonomy fails, without requiring physical presence. A key requirement for effective teleoperation is the real-time delivery of rich sensory information to the operator. Head-Mounted Displays (HMDs), combined with volumetric videos, provide an immersive visualization of the robot’s surroundings, enabling natural viewpoint changes and improved spatial awareness compared to traditional 2D video streams. In this paper, we present a teleoperation framework to stream in real-time volumetric videos in the form of point clouds to an operator wearing a HMD. The system includes a distance-based sampling strategy that dynamically adapts the point cloud bitrate to the estimated time-varying network bandwidth, addressing constraints imposed by limited computational resources on both the robot and the HMD. The framework is implemented on a real mobile robot and evaluated under various network conditions, including a 5G connection, demonstrating its effectiveness and robustness in supporting immersive remote teleoperation. Code is available at our GitHub repository (https://github.com/Diane-Spirit)
Experimental and Numerical Investigation of the Acoustic Response of a Hollow-cone Fuel Spray in a Swirling Air Flow
No full textA perspective analysis of imaging-based monitoring systems in precision viticulture: Technologies, intelligent data analyses and research challenges
No full textThis paper presents a comprehensive review of recent advancements in intelligent monitoring systems within the precision viticulture sector. These systems have the potential to make agricultural production more efficient and ensure the adoption of sustainable practices to increase food production and meet growing global demand while maintaining high-quality standards. The review examines core components of non-destructive imaging-based monitoring systems in vineyards, focusing on sensors, tasks, and data processing methodologies. Particular emphasis is placed on solutions designed for practical, in-field deployment. The analysis revealed that the most commonly used sensors are RGB cameras and that the most widespread analysis focuses on grape bunches, as they provide information on both the quality and quantity of the harvest. Regarding the image processing methods, it emerged that those based on deep learning are the most adopted. In addition, a detailed analysis highlights the main technical and practical limitations in real-world scenarios, such as the management of computational resources, the need for large datasets, and the difficulties in interpreting the results. The paper concludes with an in-depth discussion of the challenges and open research questions, providing insights into potential future directions for intelligent monitoring systems in precision viticulture. These include the continued exploration of sensors to balance ease of use and accuracy, the development of generalizable methods, experimentation in real-world scenarios, and collaboration between experts for practical solutions
GIS-Based Approach to Evaluate the Photovoltaic Potential of a Territory: The Case Study of the Municipality of San Severo in the Apulia Region
No full textAbstract. This study explores a Geographic Information Systems (GIS)-based
approach to assess the photovoltaic (PV) potential of a specific territory, focus-
ing on the municipality of San Severo in the Apulia Region, Italy. The research
highlights the growing need for renewable energy sources (RES) in response to
climate change and the global energy transition. Using GIS, the study evaluates
solar radiation, land use, and technical constraints to identify suitable locations
for PV installations, including agrivoltaic systems that integrate agriculture and
solar energy production. The methodology combines spatial analysis and environ-
mental data to optimize energy planning while considering landscape and policy
constraints. The results demonstrate the effectiveness of GIS tools in supporting
sustainable energy development and local decision-making processes. This case
study provides a replicable model for assessing solar energy potential in other
regions with similar climatic and geographical characteristics
Exploring the Pairing of Circular Manufacturing Data Categories and Rebound Effect Factors
No full textThe adoption of circular economy (CE) strategies is widespread in the manufacturing industry, as it is one of the main contributors to global pollution. CE strategies within the manufacturing industry, such as remanufacturing and cleaner production, are recognised as circular manufacturing (CM). In this context, a conceptual data model has been developed to support manufacturers in their decision-making process for adopting circular strategies. The model incorporates and connects four data categories: product, process, technologies, and management. Despite the potential benefits of implementing CM strategies, these benefits could be undermined by the occurrence of rebound effect (RE). Recently, a CE-RE reference model has been developed to map the existing situation about the occurrence of negative effects during the implementation of CE strategies. However, there is still limited knowledge regarding which specific data should be collected to identify where RE occurs within the CM context. To fill this gap, this study aims to detect and categorise the links among the factors composing the CE-RE reference model with the categories of classes of the CM data model to identify the relevant data that should be collected, employing the Design Research Methodology. The resulting categorisation provides an initial framework useful to set the collection of data in this context, supporting the effective adoption of CE strategies and laying the groundwork for the development of indexes to assess the RE and the impact model
Circular Economy Upskilling: A Course on Digital Transition and Transformation
No full textThe use of Digital Technologies (DTs) combined with Circular Economy (CE) practices is becoming increasingly promising. However, there is still a gap between industry and academia in terms of education and the professionalization of individuals within this domain. Given this context, this study presents the structure of a cross-disciplinary course developed under an EU-funded project that aims to empower humans in terms of knowledge and competencies for digital and circular transition. The course encompasses four sessions: 1. Digital Technologies and Circular Economy; 2. Virtual and Augmented Reality for Circular Economy; 3. The Role of Automation in Circular Economy; and 4. Data Analysis for Circular Manufacturing. Throughout the sessions, content on digital technologies applied to developing more sustainable solutions is explored. Each session supports the development of essential skills such as automation and data management, as well as an understanding of DTs applications, which play a critical role in the current era of systemic changes, including climate change, digitalization, and business adaptation